In [ ]:
# Import Libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.impute import KNNImputer
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, TargetEncoder
In [337]:
# load data
final_data = pd.read_csv('gdsc_dataset.csv')
In [338]:
# Overview data
print(final_data.info())
<class 'pandas.core.frame.DataFrame'> RangeIndex: 242036 entries, 0 to 242035 Data columns (total 22 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 COSMIC_ID 242036 non-null int64 1 CELL_LINE_NAME 242036 non-null object 2 TCGA_DESC 240969 non-null object 3 DRUG_ID 242036 non-null int64 4 DRUG_NAME 242036 non-null object 5 PATHWAY_NAME 242036 non-null object 6 MIN_CONC 242036 non-null float64 7 MAX_CONC 242036 non-null float64 8 LN_IC50 242036 non-null float64 9 AUC 242036 non-null float64 10 RMSE 242036 non-null float64 11 Z_SCORE 242036 non-null float64 12 Whole Exome Sequencing (WES) 232670 non-null object 13 Gene Expression 232670 non-null object 14 Methylation 232670 non-null object 15 Drug Response 232670 non-null object 16 GDSC Tissue descriptor 1 232670 non-null object 17 GDSC Tissue descriptor 2 232670 non-null object 18 CANCER_TYPE 190589 non-null object 19 MSI 229683 non-null object 20 Growth Properties 232670 non-null object 21 TARGET 214881 non-null object dtypes: float64(6), int64(2), object(14) memory usage: 40.6+ MB None
In [339]:
# Statistical information of numeric features
numeric_cols = ['MIN_CONC','MAX_CONC','LN_IC50', 'AUC', 'RMSE', 'Z_SCORE']
final_data[numeric_cols].describe()
Out[339]:
| MIN_CONC | MAX_CONC | LN_IC50 | AUC | RMSE | Z_SCORE | |
|---|---|---|---|---|---|---|
| count | 242036.000000 | 242036.000000 | 242036.000000 | 242036.000000 | 242036.000000 | 2.420360e+05 |
| mean | 0.023143 | 23.462279 | 2.817079 | 0.882592 | 0.082779 | 7.312962e-10 |
| std | 0.158738 | 158.622810 | 2.762229 | 0.146998 | 0.042695 | 9.993925e-01 |
| min | 0.000010 | 0.010000 | -8.747724 | 0.006282 | 0.003274 | -8.254501e+00 |
| 25% | 0.003002 | 3.000000 | 1.508018 | 0.849449 | 0.051107 | -6.568485e-01 |
| 50% | 0.010005 | 10.000000 | 3.236731 | 0.944196 | 0.076083 | 1.058000e-02 |
| 75% | 0.010005 | 10.000000 | 4.700110 | 0.974934 | 0.106105 | 6.560362e-01 |
| max | 2.001054 | 2000.000000 | 13.820189 | 0.998904 | 0.299984 | 7.978776e+00 |
In [340]:
# Check for outliers through graphs
for column in numeric_cols:
plt.figure(figsize=(5, 5))
sns.histplot(x=column, data=final_data, alpha=0.2, bins = 50)
plt.title(column)
plt.show()
In [341]:
# MAX and MIN concentration top lining: check 2000 for MAX and 2 for MIN
print(final_data['MAX_CONC'].value_counts())
print(final_data['MIN_CONC'].value_counts())
# No outliers to drop
MAX_CONC 10.000000 142075 1.000000 22188 2.000000 13576 3.000000 13575 5.000000 10618 20.000000 7077 30.000000 6874 0.100000 5013 4.000000 3129 0.010000 2800 100.000000 1788 0.020000 1686 2000.000000 1467 0.500000 1383 0.250000 1185 0.012500 967 2.500000 962 0.800000 942 32.000000 743 121.000000 735 640.000000 732 40.000000 731 6.000000 715 8.000000 468 50.000000 370 0.200000 225 0.316256 12 Name: count, dtype: int64 MIN_CONC 0.010005 128564 0.001001 23120 0.002001 14619 0.003002 14198 0.005003 12855 0.020011 7684 0.030016 6825 0.000100 5499 0.004002 5396 0.000010 2918 0.000250 2572 0.100053 1788 0.000020 1693 0.009766 1548 2.001054 1467 0.000500 1395 0.008004 1036 0.007813 972 0.000800 942 0.000013 916 0.002501 892 0.015625 744 0.121064 735 0.640337 732 0.040021 731 0.000977 389 0.050026 370 0.004883 315 0.003906 306 0.000200 225 0.000098 219 0.019531 126 0.009491 94 0.000012 51 0.029297 49 0.001953 48 0.006003 1 0.005859 1 0.000195 1 Name: count, dtype: int64
In [342]:
# Statistical information and unique values of categorical features
# Check need of one - hot encoding; especially for cell line name and drug name
final_data.select_dtypes(include= 'object').describe().transpose()
Out[342]:
| count | unique | top | freq | |
|---|---|---|---|---|
| CELL_LINE_NAME | 242036 | 969 | PC-14 | 295 |
| TCGA_DESC | 240969 | 32 | UNCLASSIFIED | 45691 |
| DRUG_NAME | 242036 | 286 | Ulixertinib | 1698 |
| PATHWAY_NAME | 242036 | 24 | Unclassified | 24979 |
| Whole Exome Sequencing (WES) | 232670 | 1 | Y | 232670 |
| Gene Expression | 232670 | 2 | Y | 227886 |
| Methylation | 232670 | 2 | Y | 225082 |
| Drug Response | 232670 | 2 | Y | 231244 |
| GDSC Tissue descriptor 1 | 232670 | 19 | lung_NSCLC | 26977 |
| GDSC Tissue descriptor 2 | 232670 | 54 | lung_NSCLC_adenocarcinoma | 16112 |
| CANCER_TYPE | 190589 | 31 | LUAD | 15483 |
| MSI | 229683 | 2 | MSS/MSI-L | 214105 |
| Growth Properties | 232670 | 3 | Adherent | 168431 |
| TARGET | 214881 | 185 | PARP1, PARP2 | 4714 |
In [343]:
# Overview unique values of categorical columns
cat_cols = final_data.select_dtypes(include='object').columns
for col in cat_cols:
print(f"\nTop values for '{col}':")
print(final_data[col].value_counts().head(10))
Top values for 'CELL_LINE_NAME': CELL_LINE_NAME PC-14 295 SW620 295 HT-29 295 U-2-OS 294 MHH-ES-1 294 C32 294 A375 294 HCC70 284 MDA-MB-157 284 EFM-19 284 Name: count, dtype: int64 Top values for 'TCGA_DESC': TCGA_DESC UNCLASSIFIED 45691 LUAD 15653 SCLC 13570 BRCA 13106 SKCM 12637 COREAD 12538 HNSC 9358 ESCA 9126 GBM 8384 OV 8166 Name: count, dtype: int64 Top values for 'DRUG_NAME': DRUG_NAME Ulixertinib 1698 Oxaliplatin 1684 Fulvestrant 1680 Selumetinib 1666 Dactinomycin 1659 Docetaxel 1637 GSK343 1634 Uprosertib 1634 Acetalax 1434 MG-132 969 Name: count, dtype: int64 Top values for 'PATHWAY_NAME': PATHWAY_NAME Unclassified 24979 PI3K/MTOR signaling 22724 Other 21402 DNA replication 17650 Other, kinases 17277 ERK MAPK signaling 13350 Genome integrity 12221 Cell cycle 11620 Apoptosis regulation 10828 Chromatin histone methylation 10612 Name: count, dtype: int64 Top values for 'Whole Exome Sequencing (WES)': Whole Exome Sequencing (WES) Y 232670 Name: count, dtype: int64 Top values for 'Gene Expression': Gene Expression Y 227886 N 4784 Name: count, dtype: int64 Top values for 'Methylation': Methylation Y 225082 N 7588 Name: count, dtype: int64 Top values for 'Drug Response': Drug Response Y 231244 N 1426 Name: count, dtype: int64 Top values for 'GDSC Tissue descriptor 1': GDSC Tissue descriptor 1 lung_NSCLC 26977 urogenital_system 25707 leukemia 20484 aero_dig_tract 18583 lymphoma 16747 lung_SCLC 13750 breast 13388 nervous_system 12894 skin 12636 large_intestine 12438 Name: count, dtype: int64 Top values for 'GDSC Tissue descriptor 2': GDSC Tissue descriptor 2 lung_NSCLC_adenocarcinoma 16112 lung_small_cell_carcinoma 13750 breast 13388 large_intestine 12438 melanoma 12097 glioma 11822 ovary 10434 head and neck 9457 oesophagus 9126 B_cell_lymphoma 7978 Name: count, dtype: int64 Top values for 'CANCER_TYPE': CANCER_TYPE LUAD 15483 SCLC 13750 BRCA 13106 COAD/READ 12438 SKCM 12097 HNSC 9178 ESCA 9126 GBM 8384 OV 8166 DLBC 7978 Name: count, dtype: int64 Top values for 'MSI': MSI MSS/MSI-L 214105 MSI-H 15578 Name: count, dtype: int64 Top values for 'Growth Properties': Growth Properties Adherent 168431 Suspension 56814 Semi-Adherent 7425 Name: count, dtype: int64 Top values for 'TARGET': TARGET PARP1, PARP2 4714 MEK1, MEK2 4547 TOP1 4325 EGFR 3836 TNKS1, TNKS2 3699 AKT1, AKT2, AKT3 3308 DOT1L 2873 IGF1R, IR 2872 BRAF 2859 ATR 2803 Name: count, dtype: int64
In [344]:
# Check if Drug Id and drug name values match
print(final_data['DRUG_ID'].nunique())
# Numbers are not same
# Check if COSMIC ID and cell line name values match
print(final_data['COSMIC_ID'].nunique())
# unique values are same: 979
295 969
In [345]:
# Figuring out which drug names have multiple IDs
drug_map = final_data[['DRUG_ID','DRUG_NAME']]
id_per_name = final_data.groupby('DRUG_NAME')['DRUG_ID'].nunique()
duplicates = id_per_name[id_per_name > 1]
print(f"Drug names linked to multiple IDs: {len(duplicates)}")
print(duplicates)
print()
# Get the pairs that aren't 1-to-1
conflicting_pairs = drug_map.drop_duplicates()
conflicting = conflicting_pairs[conflicting_pairs['DRUG_NAME'].isin(duplicates.index)]
conflicting_sorted = conflicting.sort_values('DRUG_NAME')
print(conflicting_sorted)
print()
Drug names linked to multiple IDs: 9
DRUG_NAME
Acetalax 2
Dactinomycin 2
Docetaxel 2
Fulvestrant 2
GSK343 2
Oxaliplatin 2
Selumetinib 2
Ulixertinib 2
Uprosertib 2
Name: DRUG_ID, dtype: int64
DRUG_ID DRUG_NAME
145052 1804 Acetalax
144335 1803 Acetalax
180104 1911 Dactinomycin
148637 1811 Dactinomycin
153655 1819 Docetaxel
3212 1007 Docetaxel
69109 1200 Fulvestrant
152221 1816 Fulvestrant
207847 2037 GSK343
117542 1627 GSK343
145769 1806 Oxaliplatin
55178 1089 Oxaliplatin
133166 1736 Selumetinib
42959 1062 Selumetinib
215011 2047 Ulixertinib
177231 1908 Ulixertinib
90529 1553 Uprosertib
218768 2106 Uprosertib
In [346]:
# Keep one DRUG_ID per DRUG_NAME (e.g., the smallest)
remapping_dict = { 1804:1803, 1911:1811, 1819:1007, 1200:1816, 2037:1627, 1806:1089, 1736:1062, 2047:1908, 1553:2106 }
final_data['DRUG_ID'] = final_data['DRUG_ID'].replace(remapping_dict)
# Check if Drug Id and drug name values match
print(final_data['DRUG_ID'].nunique())
# Numbers are same
# Will be using Drug ID instead of Drug Name
final_data.drop(columns = 'DRUG_ID')
286
Out[346]:
| COSMIC_ID | CELL_LINE_NAME | TCGA_DESC | DRUG_NAME | PATHWAY_NAME | MIN_CONC | MAX_CONC | LN_IC50 | AUC | RMSE | ... | Whole Exome Sequencing (WES) | Gene Expression | Methylation | Drug Response | GDSC Tissue descriptor 1 | GDSC Tissue descriptor 2 | CANCER_TYPE | MSI | Growth Properties | TARGET | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 683667 | PFSK-1 | MB | Camptothecin | DNA replication | 0.000100 | 0.1 | -1.463887 | 0.930220 | 0.089052 | ... | Y | Y | Y | Y | nervous_system | medulloblastoma | MB | MSS/MSI-L | Adherent | TOP1 |
| 1 | 684052 | A673 | UNCLASSIFIED | Camptothecin | DNA replication | 0.000100 | 0.1 | -4.869455 | 0.614970 | 0.111351 | ... | Y | Y | Y | Y | soft_tissue | rhabdomyosarcoma | NaN | MSS/MSI-L | Adherent | TOP1 |
| 2 | 684057 | ES5 | UNCLASSIFIED | Camptothecin | DNA replication | 0.000100 | 0.1 | -3.360586 | 0.791072 | 0.142855 | ... | Y | Y | Y | Y | bone | ewings_sarcoma | NaN | MSS/MSI-L | Adherent | TOP1 |
| 3 | 684059 | ES7 | UNCLASSIFIED | Camptothecin | DNA replication | 0.000100 | 0.1 | -5.044940 | 0.592660 | 0.135539 | ... | Y | Y | Y | Y | bone | ewings_sarcoma | NaN | MSS/MSI-L | Adherent | TOP1 |
| 4 | 684062 | EW-11 | UNCLASSIFIED | Camptothecin | DNA replication | 0.000100 | 0.1 | -3.741991 | 0.734047 | 0.128059 | ... | Y | Y | Y | Y | bone | ewings_sarcoma | NaN | MSS/MSI-L | Adherent | TOP1 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 242031 | 1659928 | SNU-175 | COREAD | N-acetyl cysteine | Metabolism | 2.001054 | 2000.0 | 10.127082 | 0.976746 | 0.074498 | ... | Y | Y | Y | Y | large_intestine | large_intestine | COAD/READ | MSI-H | Suspension | Metabolism |
| 242032 | 1660034 | SNU-407 | COREAD | N-acetyl cysteine | Metabolism | 2.001054 | 2000.0 | 8.576377 | 0.913378 | 0.057821 | ... | Y | Y | Y | Y | large_intestine | large_intestine | COAD/READ | MSI-H | Adherent | Metabolism |
| 242033 | 1660035 | SNU-61 | COREAD | N-acetyl cysteine | Metabolism | 2.001054 | 2000.0 | 10.519636 | 0.975001 | 0.058090 | ... | Y | Y | Y | Y | large_intestine | large_intestine | COAD/READ | MSS/MSI-L | Adherent | Metabolism |
| 242034 | 1674021 | SNU-C5 | COREAD | N-acetyl cysteine | Metabolism | 2.001054 | 2000.0 | 10.694579 | 0.969969 | 0.101013 | ... | Y | Y | Y | Y | large_intestine | large_intestine | COAD/READ | MSI-H | Adherent | Metabolism |
| 242035 | 1789883 | DiFi | COREAD | N-acetyl cysteine | Metabolism | 2.001054 | 2000.0 | 10.034825 | 0.966988 | 0.089057 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | Metabolism |
242036 rows × 21 columns
In [347]:
# Check for missing values
print(final_data.isnull().sum())
COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1067 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 9366 Gene Expression 9366 Methylation 9366 Drug Response 9366 GDSC Tissue descriptor 1 9366 GDSC Tissue descriptor 2 9366 CANCER_TYPE 51447 MSI 12353 Growth Properties 9366 TARGET 27155 dtype: int64
In [348]:
# Check for missing values
def check_missing_values_by_drug(df):
missing_values = {}
for drug in df['DRUG_NAME'].unique():
drug_data = df[df['DRUG_NAME'] == drug]
missing_values[drug] =drug_data.isnull().sum()
return missing_values
drug_missing_values = check_missing_values_by_drug(final_data)
for drug, missing_counts in drug_missing_values.items():
print(f"\nMissing values for {drug}:")
print(missing_counts)
print(f"Total missing values: {missing_counts.sum()}")
print("-" * 50)
Missing values for Camptothecin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 205 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 537 -------------------------------------------------- Missing values for Vinblastine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 158 MSI 28 Growth Properties 24 TARGET 0 dtype: int64 Total missing values: 355 -------------------------------------------------- Missing values for Cisplatin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for Cytarabine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for Docetaxel: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 65 Gene Expression 65 Methylation 65 Drug Response 65 GDSC Tissue descriptor 1 65 GDSC Tissue descriptor 2 65 CANCER_TYPE 352 MSI 84 Growth Properties 65 TARGET 0 dtype: int64 Total missing values: 897 -------------------------------------------------- Missing values for Methotrexate: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 36 Gene Expression 36 Methylation 36 Drug Response 36 GDSC Tissue descriptor 1 36 GDSC Tissue descriptor 2 36 CANCER_TYPE 176 MSI 49 Growth Properties 36 TARGET 0 dtype: int64 Total missing values: 483 -------------------------------------------------- Missing values for Tretinoin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for Gefitinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Navitoclax: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Vorinostat: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Nilotinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Refametinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Temsirolimus: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 193 MSI 50 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 515 -------------------------------------------------- Missing values for Olaparib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Veliparib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Bosutinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Lenalidomide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Axitinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for AZD7762: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for GW441756: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Lestaurtinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for SB216763: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Tanespimycin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Motesanib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for KU-55933: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Elesclomol: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for Afatinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Vismodegib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Staurosporine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 205 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 537 -------------------------------------------------- Missing values for PLX-4720: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for BX795: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for NU7441: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for SL0101: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for Doramapimod: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for JNK Inhibitor VIII: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Wee1 Inhibitor: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Nutlin-3a (-): COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Mirin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for PD173074: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for ZM447439: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Alisertib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 201 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 533 -------------------------------------------------- Missing values for RO-3306: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for MK-2206: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Palbociclib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Dactolisib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Pictilisib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for AZD8055: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 157 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 362 -------------------------------------------------- Missing values for PD0325901: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 205 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 537 -------------------------------------------------- Missing values for SB590885: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Selumetinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 64 Gene Expression 64 Methylation 64 Drug Response 64 GDSC Tissue descriptor 1 64 GDSC Tissue descriptor 2 64 CANCER_TYPE 355 MSI 83 Growth Properties 64 TARGET 0 dtype: int64 Total missing values: 892 -------------------------------------------------- Missing values for CCT007093: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 200 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 532 -------------------------------------------------- Missing values for Obatoclax Mesylate: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 30 Gene Expression 30 Methylation 30 Drug Response 30 GDSC Tissue descriptor 1 30 GDSC Tissue descriptor 2 30 CANCER_TYPE 170 MSI 35 Growth Properties 30 TARGET 0 dtype: int64 Total missing values: 416 -------------------------------------------------- Missing values for EHT-1864: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 52 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 533 -------------------------------------------------- Missing values for Avagacestat: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for 5-Fluorouracil: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Dasatinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Paclitaxel: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Crizotinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Rapamycin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Sorafenib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for BI-2536: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 196 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 520 -------------------------------------------------- Missing values for Irinotecan: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Oxaliplatin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 65 Gene Expression 65 Methylation 65 Drug Response 65 GDSC Tissue descriptor 1 65 GDSC Tissue descriptor 2 65 CANCER_TYPE 359 MSI 84 Growth Properties 65 TARGET 0 dtype: int64 Total missing values: 904 -------------------------------------------------- Missing values for BMS-536924: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for GSK1904529A: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Tozasertib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 48 MSI 25 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 176 -------------------------------------------------- Missing values for PF-4708671: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 48 MSI 25 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 176 -------------------------------------------------- Missing values for PRIMA-1MET: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for Serdemetan: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 199 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 523 -------------------------------------------------- Missing values for TW 37: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 12 Gene Expression 12 Methylation 12 Drug Response 12 GDSC Tissue descriptor 1 12 GDSC Tissue descriptor 2 12 CANCER_TYPE 81 MSI 13 Growth Properties 12 TARGET 0 dtype: int64 Total missing values: 179 -------------------------------------------------- Missing values for Erlotinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for CCT-018159: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for Rucaparib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for Niraparib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for MK-1775: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Dinaciclib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for Gemcitabine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Bortezomib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for GSK269962A: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 48 MSI 25 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 176 -------------------------------------------------- Missing values for SB505124: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 15 Gene Expression 15 Methylation 15 Drug Response 15 GDSC Tissue descriptor 1 15 GDSC Tissue descriptor 2 15 CANCER_TYPE 48 MSI 25 Growth Properties 15 TARGET 0 dtype: int64 Total missing values: 183 -------------------------------------------------- Missing values for Tamoxifen: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Fulvestrant: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 65 Gene Expression 65 Methylation 65 Drug Response 65 GDSC Tissue descriptor 1 65 GDSC Tissue descriptor 2 65 CANCER_TYPE 359 MSI 84 Growth Properties 65 TARGET 0 dtype: int64 Total missing values: 904 -------------------------------------------------- Missing values for EPZ004777: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for YK-4-279: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Piperlongumine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for Daporinad: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 127 MSI 37 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 352 -------------------------------------------------- Missing values for BMS-345541: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 187 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 478 -------------------------------------------------- Missing values for AZ960: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 186 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 477 -------------------------------------------------- Missing values for Talazoparib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for XAV939: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 187 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 478 -------------------------------------------------- Missing values for Trametinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Dabrafenib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Temozolomide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Bleomycin (50 uM): COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 155 MSI 28 Growth Properties 24 TARGET 0 dtype: int64 Total missing values: 352 -------------------------------------------------- Missing values for AZD5438: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for IAP_5620: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for AZD2014: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for AZD1208: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for AZD1332: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for SN-38: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Bicalutamide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for Ruxolitinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 35 Gene Expression 35 Methylation 35 Drug Response 35 GDSC Tissue descriptor 1 35 GDSC Tissue descriptor 2 35 CANCER_TYPE 189 MSI 49 Growth Properties 35 TARGET 0 dtype: int64 Total missing values: 488 -------------------------------------------------- Missing values for Linsitinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Epirubicin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Cyclophosphamide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Pevonedistat: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Sapitinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Uprosertib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 58 Gene Expression 58 Methylation 58 Drug Response 58 GDSC Tissue descriptor 1 58 GDSC Tissue descriptor 2 58 CANCER_TYPE 344 MSI 76 Growth Properties 58 TARGET 0 dtype: int64 Total missing values: 832 -------------------------------------------------- Missing values for LCL161: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 187 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 478 -------------------------------------------------- Missing values for Lapatinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Luminespib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 52 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Alpelisib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Taselisib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 52 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for EPZ5676: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for SCH772984: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for IWP-2: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for Leflunomide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for GSK2801: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Bromosporine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for SGC-CBP30: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for GSK-LSD1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for BDOCA000347a: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for BDF00022089a: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for BDILV000379a: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for Entinostat: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for OSI-027: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for LGK974: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for VE-822: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for WZ4003: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for CZC24832: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for AZD5582: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 33 Gene Expression 33 Methylation 33 Drug Response 33 GDSC Tissue descriptor 1 33 GDSC Tissue descriptor 2 33 CANCER_TYPE 185 MSI 47 Growth Properties 33 TARGET 0 dtype: int64 Total missing values: 468 -------------------------------------------------- Missing values for GSK2606414: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 185 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 476 -------------------------------------------------- Missing values for PFI3: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for PCI-34051: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for Wnt-C59: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for I-BET-762: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for RVX-208: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for OTX015: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for GSK343: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 59 Gene Expression 59 Methylation 59 Drug Response 59 GDSC Tissue descriptor 1 59 GDSC Tissue descriptor 2 59 CANCER_TYPE 346 MSI 77 Growth Properties 59 TARGET 0 dtype: int64 Total missing values: 842 -------------------------------------------------- Missing values for ML323: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for Entospletinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for PRT062607: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for Ribociclib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for AGI-6780: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for Picolinici-acid: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for AZD5153: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for CDK9_5576: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for CDK9_5038: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for Eg5_9814: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 153 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 366 -------------------------------------------------- Missing values for ERK_2440: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for ERK_6604: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for IRAK4_4710: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for JAK1_8709: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for AZD5991: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 152 MSI 30 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 357 -------------------------------------------------- Missing values for PAK_5339: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for TAF1_5496: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for ULK1_4989: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 367 -------------------------------------------------- Missing values for VSP34_8731: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for IGF1R_3801: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for JAK_8517: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for GSK2256098C: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for GSK2276186C: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for GSK2110183B: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for GSK626616AC: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for GSK3337463A: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for GSK2830371A: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for LMB_AB1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for LMB_AB2: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for LMB_AB3: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for AZD4547: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Ibrutinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for Zoledronate: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for Acetalax: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 52 Gene Expression 52 Methylation 52 Drug Response 52 GDSC Tissue descriptor 1 52 GDSC Tissue descriptor 2 52 CANCER_TYPE 310 MSI 62 Growth Properties 52 TARGET 1434 dtype: int64 Total missing values: 2170 -------------------------------------------------- Missing values for Topotecan: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for Teniposide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Mitoxantrone: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for Dactinomycin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 65 Gene Expression 65 Methylation 65 Drug Response 65 GDSC Tissue descriptor 1 65 GDSC Tissue descriptor 2 65 CANCER_TYPE 357 MSI 84 Growth Properties 65 TARGET 0 dtype: int64 Total missing values: 902 -------------------------------------------------- Missing values for Bleomycin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for Fludarabine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for Nelarabine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 716 dtype: int64 Total missing values: 1084 -------------------------------------------------- Missing values for Dacarbazine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for Romidepsin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for 123829: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 765771: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 123138: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Podophyllotoxin bromide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 50869: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Dihydrorotenone: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 715 dtype: int64 Total missing values: 1083 -------------------------------------------------- Missing values for 720427: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 667880: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Gallibiscoquinazole: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for L-Oxonoreleagnine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 729189: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 741909: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 743380: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Elephantin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 150412: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Sinularin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 615590: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for 630600: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for LMP744: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 0 dtype: int64 Total missing values: 368 -------------------------------------------------- Missing values for 776928: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 154 MSI 31 Growth Properties 26 TARGET 716 dtype: int64 Total missing values: 1083 -------------------------------------------------- Missing values for Schweinfurthin A: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 716 dtype: int64 Total missing values: 1084 -------------------------------------------------- Missing values for BEN: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 26 Gene Expression 26 Methylation 26 Drug Response 26 GDSC Tissue descriptor 1 26 GDSC Tissue descriptor 2 26 CANCER_TYPE 155 MSI 31 Growth Properties 26 TARGET 717 dtype: int64 Total missing values: 1085 -------------------------------------------------- Missing values for Sabutoclax: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for LY2109761: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 188 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 479 -------------------------------------------------- Missing values for OF-1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for MN-64: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for KRAS (G12C) Inhibitor-12: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 34 Gene Expression 34 Methylation 34 Drug Response 34 GDSC Tissue descriptor 1 34 GDSC Tissue descriptor 2 34 CANCER_TYPE 189 MSI 48 Growth Properties 34 TARGET 0 dtype: int64 Total missing values: 480 -------------------------------------------------- Missing values for MG-132: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 205 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 537 -------------------------------------------------- Missing values for BDP-00009066: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for Buparlisib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Ulixertinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 7 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 64 Gene Expression 64 Methylation 64 Drug Response 64 GDSC Tissue descriptor 1 64 GDSC Tissue descriptor 2 64 CANCER_TYPE 361 MSI 82 Growth Properties 64 TARGET 0 dtype: int64 Total missing values: 898 -------------------------------------------------- Missing values for Venetoclax: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for ABT737: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Afuresertib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for AGI-5198: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for AZD3759: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for AZD5363: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for AZD6738: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for AZD8186: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Osimertinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 203 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 535 -------------------------------------------------- Missing values for Cediranib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Ipatasertib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for GDC0810: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for GNE-317: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 202 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 526 -------------------------------------------------- Missing values for GSK2578215A: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for I-BRD9: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Telomerase Inhibitor IX: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for MIRA-1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for NVP-ADW742: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for P22077: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Savolitinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for UMI-77: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for WIKI4: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for Sepantronium bromide: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for MIM1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for WEHI-539: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 204 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 536 -------------------------------------------------- Missing values for BPD-00008900: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 743 dtype: int64 Total missing values: 1107 -------------------------------------------------- Missing values for N25720-51-A1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 742 dtype: int64 Total missing values: 1106 -------------------------------------------------- Missing values for N27922-53-1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 743 dtype: int64 Total missing values: 1107 -------------------------------------------------- Missing values for N30652-18-1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 743 dtype: int64 Total missing values: 1107 -------------------------------------------------- Missing values for N29087-69-1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 743 dtype: int64 Total missing values: 1107 -------------------------------------------------- Missing values for HKMTI-1-005: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 157 MSI 29 Growth Properties 25 TARGET 741 dtype: int64 Total missing values: 1103 -------------------------------------------------- Missing values for ICL-SIRT078: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 157 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 362 -------------------------------------------------- Missing values for UNC0638: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 157 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 362 -------------------------------------------------- Missing values for AGK2: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 3 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 37 Gene Expression 37 Methylation 37 Drug Response 37 GDSC Tissue descriptor 1 37 GDSC Tissue descriptor 2 37 CANCER_TYPE 197 MSI 48 Growth Properties 37 TARGET 0 dtype: int64 Total missing values: 507 -------------------------------------------------- Missing values for Foretinib: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for BIBR-1532: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Pyridostatin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for AMG-319: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 200 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 532 -------------------------------------------------- Missing values for MK-8776: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 202 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 534 -------------------------------------------------- Missing values for Vinorelbine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 201 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 525 -------------------------------------------------- Missing values for Mycophenolic acid: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 156 MSI 28 Growth Properties 24 TARGET 737 dtype: int64 Total missing values: 1090 -------------------------------------------------- Missing values for Remodelin: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 12 Gene Expression 12 Methylation 12 Drug Response 12 GDSC Tissue descriptor 1 12 GDSC Tissue descriptor 2 12 CANCER_TYPE 76 MSI 15 Growth Properties 12 TARGET 370 dtype: int64 Total missing values: 545 -------------------------------------------------- Missing values for VX-11e: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 201 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 525 -------------------------------------------------- Missing values for LJI308: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 201 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 525 -------------------------------------------------- Missing values for AZ6102: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 201 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 525 -------------------------------------------------- Missing values for GSK591: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 201 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 525 -------------------------------------------------- Missing values for VE821: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 199 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 523 -------------------------------------------------- Missing values for VTP-A: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 156 MSI 28 Growth Properties 24 TARGET 737 dtype: int64 Total missing values: 1090 -------------------------------------------------- Missing values for VTP-B: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 156 MSI 28 Growth Properties 24 TARGET 737 dtype: int64 Total missing values: 1090 -------------------------------------------------- Missing values for PBD-288: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 741 dtype: int64 Total missing values: 1105 -------------------------------------------------- Missing values for POMHEX: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 741 dtype: int64 Total missing values: 1105 -------------------------------------------------- Missing values for CT7033-2: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for GSK-LSD1-2HCl : COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 157 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 362 -------------------------------------------------- Missing values for 5-azacytidine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 158 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 363 -------------------------------------------------- Missing values for A-366: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for CPI-637: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for UNC0379: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 159 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 364 -------------------------------------------------- Missing values for AZD6482: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 48 MSI 25 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 176 -------------------------------------------------- Missing values for AT13148: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for BMS-754807: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for JQ1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 38 Gene Expression 38 Methylation 38 Drug Response 38 GDSC Tissue descriptor 1 38 GDSC Tissue descriptor 2 38 CANCER_TYPE 200 MSI 52 Growth Properties 38 TARGET 0 dtype: int64 Total missing values: 524 -------------------------------------------------- Missing values for PFI-1: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 200 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 532 -------------------------------------------------- Missing values for IOX2: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for CHIR-99021: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 5 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 14 Gene Expression 14 Methylation 14 Drug Response 14 GDSC Tissue descriptor 1 14 GDSC Tissue descriptor 2 14 CANCER_TYPE 47 MSI 24 Growth Properties 14 TARGET 0 dtype: int64 Total missing values: 174 -------------------------------------------------- Missing values for SGC0946: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 6 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 39 Gene Expression 39 Methylation 39 Drug Response 39 GDSC Tissue descriptor 1 39 GDSC Tissue descriptor 2 39 CANCER_TYPE 200 MSI 53 Growth Properties 39 TARGET 0 dtype: int64 Total missing values: 532 -------------------------------------------------- Missing values for GSK2830371: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 155 MSI 28 Growth Properties 24 TARGET 0 dtype: int64 Total missing values: 352 -------------------------------------------------- Missing values for THR-101: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 155 MSI 28 Growth Properties 24 TARGET 0 dtype: int64 Total missing values: 352 -------------------------------------------------- Missing values for THR-102: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 155 MSI 28 Growth Properties 24 TARGET 0 dtype: int64 Total missing values: 352 -------------------------------------------------- Missing values for THR-103: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 24 Gene Expression 24 Methylation 24 Drug Response 24 GDSC Tissue descriptor 1 24 GDSC Tissue descriptor 2 24 CANCER_TYPE 155 MSI 28 Growth Properties 24 TARGET 0 dtype: int64 Total missing values: 352 -------------------------------------------------- Missing values for ascorbate (vitamin C): COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 157 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 362 -------------------------------------------------- Missing values for glutathione: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 157 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 362 -------------------------------------------------- Missing values for alpha-lipoic acid: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 155 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 360 -------------------------------------------------- Missing values for N-acetyl cysteine: COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 1 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 25 Gene Expression 25 Methylation 25 Drug Response 25 GDSC Tissue descriptor 1 25 GDSC Tissue descriptor 2 25 CANCER_TYPE 155 MSI 29 Growth Properties 25 TARGET 0 dtype: int64 Total missing values: 360 --------------------------------------------------
Different drugs have different patterns of null data Will be approaching missing values by drugs and by categories
GDSC tissue descriptor / Cancer type / TGCA desc: use related tissue information (mode) within each drug subset
TARGET / PATHWAY_NAME : fill in with unknown
WES / Gene Expression / Methylation: will attempt to impute based on tissue type, then use KNN imputer
MSI, Growth Properties : use mode within each drug subset also
Use KNN imputer, which fills in missing values utilizing KNN algorithm
In [349]:
def handling_null(df):
knn_imputer = KNNImputer(n_neighbors = 5) # Instantiate object
for drug in df['DRUG_NAME'].unique():
drug_data = df[df['DRUG_NAME'] == drug].copy() # Since creating multiple seperate drug datasets use .copy()
# Descriptor information filling
desc_cols = ['TCGA_DESC', 'GDSC Tissue descriptor 1', 'GDSC Tissue descriptor 2', 'CANCER_TYPE']
for col in desc_cols:
if drug_data[col].isnull().any(): # if there are any null values
for other_col in [c for c in desc_cols if c != col]: # Other columns in desc_cols
grouped = drug_data.groupby(other_col)[col] # Group by other columns
modes = grouped.transform(lambda x: x.mode()[0] if not x.mode().empty else 'Unknown') # Return the first mode value if mode is not empty
drug_data[col] = drug_data[col].fillna(modes)
# If still null, use overall mode
drug_data[col] = drug_data[col].fillna(drug_data[col].mode()[0] if not drug_data[col].mode().empty else 'Unknown')
# Target and pathway filling
tp_cols = ['TARGET', 'PATHWAY_NAME']
for col in tp_cols:
if drug_data[col].isnull().all():
drug_data[col] = 'Unknown for this drug'
#else:
#known_target = drug_data[col].dropna().iloc[0]
#drug_data[col] = drug_data[col].fillna(known_target)
# MSI and Growth properties
msi_gp_cols = ['MSI', 'Growth Properties']
for col in msi_gp_cols:
if drug_data[col].isnull().any():
# Group by primary tissue description
drug_data[col] = drug_data.groupby('GDSC Tissue descriptor 1')[col].transform(
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else 'Unknown')
)
# Genomic Features
genomic_cols = ['Whole Exome Sequencing (WES)', 'Gene Expression', 'Methylation', 'Drug Response']
for col in genomic_cols:
if drug_data[col].isnull().any():
# Group by primary tissue description
drug_data[col] = drug_data.groupby('GDSC Tissue descriptor 1')[col].transform(
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
)
# If still null use knn imputer
if drug_data[col].isnull().any():
feature_data = pd.get_dummies(drug_data[col], prefix=col) # One hot encoding
imputed_data = knn_imputer.fit_transform(feature_data)
imputed_df = pd.DataFrame(imputed_data, columns=feature_data.columns, index=feature_data.index)
drug_data[col] = imputed_df.idxmax(axis=1).str.split('_').str[1]
df.loc[df['DRUG_NAME'] == drug] = drug_data
return df
cleaned_data = handling_null(final_data)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
/var/folders/gn/8692wbbn2jqbdbljkddblglm0000gn/T/ipykernel_77083/1356287288.py:47: FutureWarning: Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`
lambda x: x.fillna(x.mode()[0] if not x.mode().empty else np.nan)
In [350]:
# Check for missing values again
print(cleaned_data.isnull().sum())
COSMIC_ID 0 CELL_LINE_NAME 0 TCGA_DESC 0 DRUG_ID 0 DRUG_NAME 0 PATHWAY_NAME 0 MIN_CONC 0 MAX_CONC 0 LN_IC50 0 AUC 0 RMSE 0 Z_SCORE 0 Whole Exome Sequencing (WES) 0 Gene Expression 0 Methylation 0 Drug Response 0 GDSC Tissue descriptor 1 0 GDSC Tissue descriptor 2 0 CANCER_TYPE 0 MSI 0 Growth Properties 0 TARGET 0 dtype: int64
In [351]:
# Check unique values of features
print(cleaned_data.info())
print(cleaned_data.nunique())
<class 'pandas.core.frame.DataFrame'> RangeIndex: 242036 entries, 0 to 242035 Data columns (total 22 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 COSMIC_ID 242036 non-null int64 1 CELL_LINE_NAME 242036 non-null object 2 TCGA_DESC 242036 non-null object 3 DRUG_ID 242036 non-null int64 4 DRUG_NAME 242036 non-null object 5 PATHWAY_NAME 242036 non-null object 6 MIN_CONC 242036 non-null float64 7 MAX_CONC 242036 non-null float64 8 LN_IC50 242036 non-null float64 9 AUC 242036 non-null float64 10 RMSE 242036 non-null float64 11 Z_SCORE 242036 non-null float64 12 Whole Exome Sequencing (WES) 242036 non-null object 13 Gene Expression 242036 non-null object 14 Methylation 242036 non-null object 15 Drug Response 242036 non-null object 16 GDSC Tissue descriptor 1 242036 non-null object 17 GDSC Tissue descriptor 2 242036 non-null object 18 CANCER_TYPE 242036 non-null object 19 MSI 242036 non-null object 20 Growth Properties 242036 non-null object 21 TARGET 242036 non-null object dtypes: float64(6), int64(2), object(14) memory usage: 40.6+ MB None COSMIC_ID 969 CELL_LINE_NAME 969 TCGA_DESC 32 DRUG_ID 286 DRUG_NAME 286 PATHWAY_NAME 24 MIN_CONC 39 MAX_CONC 27 LN_IC50 237097 AUC 142587 RMSE 118662 Z_SCORE 233614 Whole Exome Sequencing (WES) 1 Gene Expression 2 Methylation 2 Drug Response 2 GDSC Tissue descriptor 1 20 GDSC Tissue descriptor 2 55 CANCER_TYPE 32 MSI 3 Growth Properties 4 TARGET 186 dtype: int64
In [366]:
# Encode categorical features
def encoding_features(df, target = 'LN_IC50'):
# For binary features
binary = [col for col in df.columns if df[col].nunique() == 2]
for feature in binary:
df[feature] = (df[feature] == df[feature].unique()[0]).astype(int) # Creates boolean series consisting of 1 and 0
# For features with small counts of unique value (low-cardinality), use one hot encoder
onehot_encoder = OneHotEncoder(sparse_output=False, handle_unknown='ignore') # sparse=False returns as np array
msi_encoded = onehot_encoder.fit_transform(df[['MSI']])
msi_columns = onehot_encoder.get_feature_names_out(['MSI']) # renames the columns
msi_onehot = pd.DataFrame(msi_encoded, columns=msi_columns, index=df.index)
gp_encoded = onehot_encoder.fit_transform(df[['Growth Properties']])
gp_columns = onehot_encoder.get_feature_names_out(['Growth Properties'])
gp_onehot = pd.DataFrame(gp_encoded, columns=gp_columns, index=df.index)
# For high cardinality features
high_feature = ['TCGA_DESC', 'DRUG_NAME', 'GDSC Tissue descriptor 1', 'GDSC Tissue descriptor 2',
'CANCER_TYPE', 'TARGET', 'PATHWAY_NAME']
target_encoder = TargetEncoder()
df_high_encoded = target_encoder.fit_transform(df[high_feature], df[target])
df_high_encoded = pd.DataFrame(df_high_encoded, columns=high_feature, index=df.index)
# Label encoding for drug ID, cosmic id, and cell line name
label_feature = ['DRUG_ID','COSMIC_ID','CELL_LINE_NAME']
df_label_encoded = pd.DataFrame(index=df.index)
for col in label_feature:
le = LabelEncoder()
df_label_encoded[col] = le.fit_transform(df[col])
# Combine all encoded features
df_encoded = pd.concat([df[binary],msi_onehot, gp_onehot, df_high_encoded, df_label_encoded], axis = 1)
return df_encoded
encoded = encoding_features(cleaned_data)
In [371]:
encoded['LN_IC50']=cleaned_data['LN_IC50']
encoded['AUC']=cleaned_data['AUC']
encoded['Z_SCORE']=cleaned_data['Z_SCORE']
print(encoded.columns)
print(len(encoded.columns))
print()
print(cleaned_data.columns)
print(len(cleaned_data.columns))
Index(['Gene Expression', 'Methylation', 'Drug Response', 'MSI_MSI-H',
'MSI_MSS/MSI-L', 'MSI_Unknown', 'Growth Properties_Adherent',
'Growth Properties_Semi-Adherent', 'Growth Properties_Suspension',
'Growth Properties_Unknown', 'TCGA_DESC', 'DRUG_NAME',
'GDSC Tissue descriptor 1', 'GDSC Tissue descriptor 2', 'CANCER_TYPE',
'TARGET', 'PATHWAY_NAME', 'DRUG_ID', 'COSMIC_ID', 'CELL_LINE_NAME',
'LN_IC50', 'AUC', 'Z_SCORE'],
dtype='object')
23
Index(['COSMIC_ID', 'CELL_LINE_NAME', 'TCGA_DESC', 'DRUG_ID', 'DRUG_NAME',
'PATHWAY_NAME', 'MIN_CONC', 'MAX_CONC', 'LN_IC50', 'AUC', 'RMSE',
'Z_SCORE', 'Whole Exome Sequencing (WES)', 'Gene Expression',
'Methylation', 'Drug Response', 'GDSC Tissue descriptor 1',
'GDSC Tissue descriptor 2', 'CANCER_TYPE', 'MSI', 'Growth Properties',
'TARGET'],
dtype='object')
22
In [375]:
# Correlation Analysis of encoded
plt.figure(figsize=(20, 16))
correlation_matrix = encoded.corr()
sns.heatmap(correlation_matrix, annot=True)
plt.title('Correlation Heatmap of Encoded Features')
plt.tight_layout()
plt.show()
In [373]:
# Features to select with correlation
features = ['Z_SCORE', 'AUC', 'PATHWAY_NAME', 'TARGET', 'DRUG_NAME', 'GDSC Tissue descriptor 1',
'GDSC Tissue descriptor 2', 'CANCER_TYPE', 'TCGA_DESC', 'Growth Properties_Adherent']
In [374]:
# Dataframe to csv
encoded.to_csv('modeling_data.csv', index=False)