Cancer Cell Lines and Drug Dose Response Curves

import pandas as pd
import numpy as np

CCLE_all = pd.read_csv(r"C:\Users\QBPAM\Downloads\'25 summer BigData AI Cancer class by Yongmei Wang\Model.csv")
CCLE_all    #has 2116 rows, which means 2116 cancer cell lines

	ModelID	PatientID	CellLineName	StrippedCellLineName	DepmapModelType	OncotreeLineage	OncotreePrimaryDisease	OncotreeSubtype	OncotreeCode	PatientSubtypeFeatures	...	PublicComments	CCLEName	HCMIID	PediatricModelType	ModelAvailableInDbgap	ModelSubtypeFeatures	WTSIMasterCellID	SangerModelID	COSMICID	ModelIDAlias
0	ACH-000001	PT-gj46wT	NIH:OVCAR-3	NIHOVCAR3	HGSOC	Ovary/Fallopian Tube	Ovarian Epithelial Tumor	High-Grade Serous Ovarian Cancer	HGSOC	NaN	...	NaN	NIHOVCAR3_OVARY	NaN	False	Approved for public sharing - CCLE	NaN	2201.0	SIDM00105	905933.0	NaN
1	ACH-000002	PT-5qa3uk	HL-60	HL60	AMLMRC	Myeloid	Acute Myeloid Leukemia	AML with Myelodysplasia-Related Changes	AMLMRC	TP53(del), CDKN2A and NRAS mutations [PubMed=2...	...	NaN	HL60_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	NRAS, BCOR and CDKN2A	55.0	SIDM00829	905938.0	NaN
2	ACH-000003	PT-puKIyc	CACO2	CACO2	COAD	Bowel	Colorectal Adenocarcinoma	Colon Adenocarcinoma	COAD	NaN	...	NaN	CACO2_LARGE_INTESTINE	NaN	False	Approved for public sharing - CCLE	NaN	NaN	SIDM00891	NaN	NaN
3	ACH-000004	PT-q4K2cp	HEL	HEL	AMLNOS	Myeloid	Acute Myeloid Leukemia	AML, NOS	AMLNOS	JAK2 and TP53 mutations	...	NaN	HEL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	JAK2 and TP53	783.0	SIDM00594	907053.0	NaN
4	ACH-000005	PT-q4K2cp	HEL 92.1.7	HEL9217	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	JAK2 and TP53 mutations	...	NaN	HEL9217_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	NaN	NaN	SIDM00593	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2111	ACH-003473	PT-fG5tCh	CCLF_PEDS_0013_T	CCLFPEDS0013T	ERMS	Soft Tissue	Rhabdomyosarcoma	Embryonal Rhabdomyosarcoma	ERMS	NaN	...	NaN	NaN	HCM-BROD-0006-C49	True	NaN	NaN	NaN	NaN	NaN	NaN
2112	ACH-003474	PT-WxfjG3	CCLF_HNSC_0001_T	CCLFHNSC0001T	HNSC	Head and Neck	Head and Neck Squamous Cell Carcinoma	Head and Neck Squamous Cell Carcinoma	HNSC	NaN	...	NaN	NaN	HCM-BROD-1131-C06	False	NaN	NaN	NaN	NaN	NaN	NaN
2113	ACH-003475	PT-ce6oqw	CCLF_HNSC_0003_T	CCLFHNSC0003T	HNSC	Head and Neck	Head and Neck Squamous Cell Carcinoma	Head and Neck Squamous Cell Carcinoma	HNSC	NaN	...	NaN	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	NaN
2114	ACH-003476	PT-ce6oqw	CCLF_HNSC_0002_T	CCLFHNSC0002T	ESCC	Esophagus/Stomach	Esophageal Squamous Cell Carcinoma	Esophageal Squamous Cell Carcinoma	ESCC	NaN	...	NaN	NaN	HCM-BROD-1130-C06	False	NaN	NaN	NaN	NaN	NaN	NaN
2115	ACH-003480	PT-D6v5Dz	CCLF_THYR_0001_T	CCLFTHYR0001T	THAP	Thyroid	Anaplastic Thyroid Cancer	Anaplastic Thyroid Cancer	THAP	NaN	...	NaN	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	NaN

2116 rows × 49 columns

CCLE_breast = CCLE_all[CCLE_all['OncotreeLineage'].isin(['Breast'])]
CCLE_breast

	ModelID	PatientID	CellLineName	StrippedCellLineName	DepmapModelType	OncotreeLineage	OncotreePrimaryDisease	OncotreeSubtype	OncotreeCode	PatientSubtypeFeatures	...	PublicComments	CCLEName	HCMIID	PediatricModelType	ModelAvailableInDbgap	ModelSubtypeFeatures	WTSIMasterCellID	SangerModelID	COSMICID	ModelIDAlias
15	ACH-000017	PT-8CE6ah	SK-BR-3	SKBR3	BRCA	Breast	Invasive Breast Carcinoma	Invasive Breast Carcinoma	BRCA	NaN	...	NaN	SKBR3_BREAST	NaN	False	Approved for public sharing - CCLE	HER2+	NaN	SIDM00897	NaN	NaN
17	ACH-000019	PT-viJKnw	MCF7	MCF7	BRCA	Breast	Invasive Breast Carcinoma	Invasive Breast Carcinoma	BRCA	NaN	...	NaN	MCF7_BREAST	NaN	False	Approved for public sharing - CCLE	ER+	588.0	SIDM00148	905946.0	NaN
26	ACH-000028	PT-viJKnw	KPL-1	KPL1	BRCA	Breast	Invasive Breast Carcinoma	Invasive Breast Carcinoma	BRCA	NaN	...	SNP fingerprinting confirms that this line is ...	KPL1_BREAST	NaN	False	Approved for public sharing - CCLE	ER+	NaN	SIDM00147	NaN	NaN
42	ACH-000044	PT-HMBfbj	MDA-MB-134-VI	MDAMB134VI	ILC	Breast	Invasive Breast Carcinoma	Breast Invasive Lobular Carcinoma	ILC	NaN	...	NaN	MDAMB134VI_BREAST	NaN	False	Approved for public sharing - CCLE	luminal ER+	NaN	SIDM00005	NaN	NaN
95	ACH-000097	PT-k1TO7o	ZR-75-1	ZR751	IDC	Breast	Invasive Breast Carcinoma	Breast Invasive Ductal Carcinoma	IDC	NaN	...	NaN	ZR751_BREAST	NaN	False	Approved for public sharing - CCLE	luminal ER, PR+	NaN	SIDM00314	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2003	ACH-002884	PT-N65Hvq	IPM-BO-053R	IPMBO053R	ILC	Breast	Invasive Breast Carcinoma	Breast Invasive Lobular Carcinoma	ILC	NaN	...	NaN	NaN	NaN	False	NaN	HER2+	NaN	NaN	NaN	NaN
2004	ACH-002885	PT-pPJgGC	IPM-BO-056	IPMBO056	IDC	Breast	Invasive Breast Carcinoma	Breast Invasive Ductal Carcinoma	IDC	NaN	...	NaN	NaN	NaN	False	NaN	ER, PR+	NaN	NaN	NaN	NaN
2006	ACH-002921	PT-NvrCXN	BCK4	BCK4	ILC	Breast	Invasive Breast Carcinoma	Breast Invasive Lobular Carcinoma	ILC	NaN	...	NaN	NaN	NaN	False	In Progress	NaN	NaN	NaN	NaN	NaN
2018	ACH-002950	PT-hxORJf	NH93T	NH93T	BRCA	Breast	Invasive Breast Carcinoma	Invasive Breast Carcinoma	BRCA	NaN	...	NaN	NaN	NaN	False	NaN	TNBC	NaN	NaN	NaN	NaN
2019	ACH-002951	PT-URKT9Y	NH84T	NH84T	BRCA	Breast	Invasive Breast Carcinoma	Invasive Breast Carcinoma	BRCA	NaN	...	NaN	NaN	NaN	False	NaN	TNBC	NaN	NaN	NaN	NaN

96 rows × 49 columns

CCLE_AML = CCLE_all[CCLE_all['OncotreeLineage'].isin(['Myeloid'])]
CCLE_AML

	ModelID	PatientID	CellLineName	StrippedCellLineName	DepmapModelType	OncotreeLineage	OncotreePrimaryDisease	OncotreeSubtype	OncotreeCode	PatientSubtypeFeatures	...	PublicComments	CCLEName	HCMIID	PediatricModelType	ModelAvailableInDbgap	ModelSubtypeFeatures	WTSIMasterCellID	SangerModelID	COSMICID	ModelIDAlias
1	ACH-000002	PT-5qa3uk	HL-60	HL60	AMLMRC	Myeloid	Acute Myeloid Leukemia	AML with Myelodysplasia-Related Changes	AMLMRC	TP53(del), CDKN2A and NRAS mutations [PubMed=2...	...	NaN	HL60_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	NRAS, BCOR and CDKN2A	55.0	SIDM00829	905938.0	NaN
3	ACH-000004	PT-q4K2cp	HEL	HEL	AMLNOS	Myeloid	Acute Myeloid Leukemia	AML, NOS	AMLNOS	JAK2 and TP53 mutations	...	NaN	HEL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	JAK2 and TP53	783.0	SIDM00594	907053.0	NaN
4	ACH-000005	PT-q4K2cp	HEL 92.1.7	HEL9217	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	JAK2 and TP53 mutations	...	NaN	HEL9217_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	NaN	NaN	SIDM00593	NaN	NaN
5	ACH-000006	PT-ej13Dz	MONO-MAC-6	MONOMAC6	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	KMT2A-MLLT3, TP53 Arg273His	...	NaN	MONOMAC6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	KMT2A::MLLT3, TP53, ASXL1 and U2AF1	2167.0	SIDM01023	908148.0	NaN
32	ACH-000034	PT-5qa3uk	PLB-985	PLB985	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	TP53(del), CDKN2A and NRAS mutations	...	SNP fingerprinting confirms that this line is ...	PLB985_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	Approved for public sharing - CCLE	NaN	NaN	SIDM00811	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1961	ACH-002709	PT-92FgnG	CMS	CMS	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	NaN	...	NaN	CMS_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE	NaN	True	NaN	CBFA2T3::GLIS2 and TP53	NaN	NaN	NaN	NaN
1964	ACH-002716	PT-93dDAU	MO-91	MO91	AMLMD	Myeloid	Acute Myeloid Leukemia	AML with Minimal Differentiation	AMLMD	NaN	...	NaN	MO91_AML	NaN	True	NaN	NaN	NaN	NaN	NaN	NaN
2017	ACH-002946	PT-HryOAg	UKE-1	UKE1	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	JAK2 Val617Phe	...	NaN	NaN	NaN	True	Approved for dbGaP - HMB MDS	NaN	NaN	NaN	NaN	NaN
2026	ACH-002994	PT-JpUzYa	WSU-AML	WSUAML	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	CBFA2T3-GLIS2 [PubMed:28109323]	...	NaN	WSU-AML_PROSTATE	NaN	True	In Progress	CBFA2T3::GLIS2	NaN	NaN	NaN	NaN
2085	ACH-003273	PT-44yhk7	CHRF-288-11	CHRF28811	AML	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	AML	NUP98-KDM5A [PMID: 32381579], JAK2 T875N [PMID...	...	NaN	NaN	NaN	True	NaN	NUP98::KDM5A, TP53 and CREBBP	NaN	NaN	NaN	NaN

87 rows × 49 columns

CCLE_AML['ModelSubtypeFeatures'].value_counts()

ModelSubtypeFeatures
BCR-ABL1 positive                                      11
CBFA2T3::GLIS2 and TP53                                 2
JAK2 and TP53                                           1
NRAS, BCOR and CDKN2A                                   1
KMT2A::AFF1, FLT3-ITD, TP53, STAG2 and MGA              1
KMT2A::MLLT3, TP53, ASXL1 and U2AF1                     1
ETV6::AL133456.1 (ETV6::MN1), SF3B1, KRAS and GATA2     1
KMT2A::MLLT3, NRAS and TP53                             1
KMT2A-PTD and FLT3                                      1
MNX1 SV and PTPN11                                      1
FIP1L1::PDGFRA, KMT2A-PTD, PHF6                         1
TP53, KRAS, ASXL1 and MYC                               1
RUNX1::RUNX1T1, TP53, RAD21 and KIT                     1
PML::RARA; TP53; KRAS                                   1
BCR::ABL1;GATA2::MECOM, PTPN11, SF3B1 and RAD21         1
NPM1c, DNMT3A, NRAS                                     1
KMT2A::MLLT3; FLT3-ITD                                  1
DNMT3A, JAK2 and TP53                                   1
CBFA2T3::ABHD12 and TP53                                1
PICALM::MLLT10, TP53, PTPN11, JAK3 and CCND3            1
RAD21                                                   1
CBFB::MYH11, NRAS, GATA2 and SF3B1                      1
SFPQ::ZFP36L1, NRAS, EZH2, PHF6                         1
BCR::ABL1; TCR::MYB                                     1
KMT2A::AFDN, PTPN11, KRAS                               1
RUNX1::RUNX1T1, TP53, MYC and KIT                       1
ETV6::MN1, PTPN11, KIT and CCND3                        1
KMT2A::AFDN                                             1
DEK::NUP214, ETV6::ABL1, GATA2 and EZH2                 1
ZNF384                                                  1
MECOM SV, ETV6 and TP53                                 1
BCR::ABL1, TCR::MYB, TCR::NIPBL                         1
CBFA2T3::GLIS2                                          1
NUP98::KDM5A, TP53 and CREBBP                           1
Name: count, dtype: int64

drug_screen = pd.read_csv(r"C:\Users\QBPAM\Downloads\'25 summer BigData AI Cancer class by Yongmei Wang\Drug_sensitivity_replicate-level_dose_(Sanger_GDSC2)_subsetted.csv", low_memory = False)
drug_screen

	depmap_id	cell_line_display_name	lineage_1	lineage_2	lineage_3	lineage_6	lineage_4	(+)-CAMPTOTHECIN (GDSC2:1003) 0.1μM rep1	PD 0325901 (GDSC2:1060) 0.25μM rep1	ENTINOSTAT (GDSC2:1593) 10.0μM rep1	...	KU-57788 (GDSC2:1038) 5.0μM rep35	KU-57788 (GDSC2:1038) 10.0μM rep35	KU-57788 (GDSC2:1038) 2.5μM rep36	KU-57788 (GDSC2:1038) 5.0μM rep36	KU-57788 (GDSC2:1038) 10.0μM rep36	GSK 269962A (GDSC2:1192) 0.0390625μM rep5	GSK 269962A (GDSC2:1192) 0.0390625μM rep6	ENTINOSTAT (GDSC2:1593) 0.03125μM rep8	ENTINOSTAT (GDSC2:1593) 0.5μM rep8	RO-3306 (GDSC2:1052) 0.0390625μM rep7
0	ACH-000973	639V	Bladder/Urinary Tract	Urethral Cancer	Urethral Urothelial Carcinoma	NaN	NaN	0.083677	0.919947	0.848779	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	ACH-000757	A427	Lung	Non-Small Cell Lung Cancer	Lung Adenocarcinoma	NaN	NaN	0.664791	0.637017	0.861281	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	ACH-002209	ALLPO	Lymphoid	B-Cell Acute Lymphoblastic Leukemia	B-Cell Acute Lymphoblastic Leukemia	KMT2A	NaN	0.145044	0.748603	0.014993	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	ACH-002210	ARH77	Myeloid	Non-Cancerous	Immortalized Blood	NaN	NaN	0.074499	0.626689	0.145854	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	ACH-000248	AU565	Breast	Invasive Breast Carcinoma	Invasive Breast Carcinoma	HER2+	NaN	0.292193	0.986368	0.107727	...	0.629204	0.379062	0.844173	0.664378	0.300903	NaN	NaN	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
784	ACH-000452	TE8	Esophagus/Stomach	Esophageal Squamous Cell Carcinoma	Esophageal Squamous Cell Carcinoma	NaN	NaN	0.440621	0.843134	0.335483	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
785	ACH-000030	PC14	Lung	Non-Small Cell Lung Cancer	Lung Adenocarcinoma	NaN	NaN	0.508382	0.860545	0.421495	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
786	ACH-000626	U266B1	Lymphoid	Mature B-Cell Neoplasms	Plasma Cell Myeloma	NaN	NaN	0.671349	0.595165	0.176174	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
787	ACH-000835	GCT	Soft Tissue	Undifferentiated Pleomorphic Sarcoma/Malignant...	Undifferentiated Pleomorphic Sarcoma/Malignant...	NaN	NaN	0.406913	0.768039	0.334517	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
788	ACH-000579	UACC257	Skin	Melanoma	Melanoma	NaN	NaN	0.999540	0.369727	0.290306	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

789 rows × 30261 columns

drug_screen_AML = drug_screen[drug_screen['lineage_1'] == 'Myeloid']
drug_screen_AML

	depmap_id	cell_line_display_name	lineage_1	lineage_2	lineage_3	lineage_6	lineage_4	(+)-CAMPTOTHECIN (GDSC2:1003) 0.1μM rep1	PD 0325901 (GDSC2:1060) 0.25μM rep1	ENTINOSTAT (GDSC2:1593) 10.0μM rep1	...	KU-57788 (GDSC2:1038) 5.0μM rep35	KU-57788 (GDSC2:1038) 10.0μM rep35	KU-57788 (GDSC2:1038) 2.5μM rep36	KU-57788 (GDSC2:1038) 5.0μM rep36	KU-57788 (GDSC2:1038) 10.0μM rep36	GSK 269962A (GDSC2:1192) 0.0390625μM rep5	GSK 269962A (GDSC2:1192) 0.0390625μM rep6	ENTINOSTAT (GDSC2:1593) 0.03125μM rep8	ENTINOSTAT (GDSC2:1593) 0.5μM rep8	RO-3306 (GDSC2:1052) 0.0390625μM rep7
3	ACH-002210	ARH77	Myeloid	Non-Cancerous	Immortalized Blood	NaN	NaN	0.074499	0.626689	0.145854	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
23	ACH-002218	CESS	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.127404	0.745224	0.111212	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
123	ACH-002247	IM9	Myeloid	Non-Cancerous	Immortalized Blood	NaN	NaN	0.048018	0.205475	0.044806	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
137	ACH-002258	KMOE2	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.516539	0.129840	0.066219	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
169	ACH-000439	ME1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	CBFB::MYH11, NRAS, GATA2 and SF3B1	NaN	0.620186	0.736987	0.339090	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
174	ACH-002273	ML2	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	KMT2A::AFDN	NaN	0.035792	0.214482	0.047821	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
202	ACH-002290	NKM1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.088198	0.455089	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
215	ACH-000770	P31FUJ	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.045234	0.787680	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
228	ACH-002302	RPMI8866	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	BCR-ABL1 positive	NaN	0.287915	0.808903	0.180591	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
258	ACH-002314	TUR	Myeloid	Acute Myeloid Leukemia	Acute Monoblastic/Monocytic Leukemia	NaN	NaN	0.153453	0.884143	0.394355	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
263	ACH-002316	WIL2NS	Myeloid	Hereditary Spherocytosis	Spherocytosis	NaN	NaN	0.035805	0.914805	0.045246	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
272	ACH-002262	KY821	Myeloid	Acute Myeloid Leukemia	Acute Myelomonocytic Leukemia	NaN	NaN	0.063442	0.309299	0.035446	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
301	ACH-000920	CMLT1	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	BCR::ABL1; TCR::MYB	NaN	0.073786	0.549783	0.073457	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
324	ACH-000004	HEL	Myeloid	Acute Myeloid Leukemia	AML, NOS	JAK2 and TP53	NaN	0.068901	0.958312	0.085466	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
325	ACH-000006	MONOMAC6	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	KMT2A::MLLT3, TP53, ASXL1 and U2AF1	NaN	0.016069	0.936632	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
327	ACH-000295	EM2	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	NaN	NaN	0.092259	0.634823	0.047049	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
332	ACH-000301	LAMA84	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	BCR-ABL1 positive	NaN	0.066904	0.326717	0.031917	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
344	ACH-000113	OCIAML2	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.080551	0.011523	0.007210	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
345	ACH-000065	OCIAML5	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.140074	0.637822	0.065946	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
356	ACH-000190	HDMYZ	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.882623	0.912756	0.848188	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
372	ACH-000198	EOL1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	FIP1L1::PDGFRA, KMT2A-PTD, PHF6	NaN	0.095446	0.434144	0.041979	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
392	ACH-000983	KCL22	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	BCR-ABL1 positive	NaN	0.436350	0.473219	0.055107	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
394	ACH-000751	OCIM1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.086389	0.549817	0.077968	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
395	ACH-000326	JURLMK1	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	BCR-ABL1 positive	NaN	0.084028	0.132027	0.073368	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
401	ACH-000362	MOLM13	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	KMT2A::MLLT3; FLT3-ITD	NaN	0.088841	0.505942	0.028031	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
407	ACH-000336	OCIAML3	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NPM1c, DNMT3A, NRAS	NaN	0.127354	0.217878	0.026207	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
435	ACH-000002	HL60	Myeloid	Acute Myeloid Leukemia	AML with Myelodysplasia-Related Changes	NRAS, BCOR and CDKN2A	NaN	0.092201	0.326975	0.038654	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
436	ACH-000551	K562	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	NaN	NaN	0.487043	0.848782	0.495266	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
437	ACH-000386	KG1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.272359	0.814012	0.107154	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
497	ACH-000072	MEG01	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	NaN	NaN	0.518017	0.418615	0.054622	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
506	ACH-000074	KU812	Myeloid	Myeloproliferative Neoplasms	Chronic Myeloid Leukemia, BCR-ABL1+	BCR-ABL1 positive	NaN	0.229392	0.073405	0.024598	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
540	ACH-000081	GDM1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	MNX1 SV and PTPN11	NaN	0.181332	0.792789	0.115995	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
543	ACH-000263	KASUMI1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	RUNX1::RUNX1T1, TP53, RAD21 and KIT	NaN	0.551611	0.548271	0.067059	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
616	ACH-000045	MV411	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	KMT2A::AFF1, FLT3-ITD, TP53, STAG2 and MGA	NaN	0.013245	0.193469	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
698	ACH-000168	NOMO1	Myeloid	Acute Myeloid Leukemia	Acute Monoblastic/Monocytic Leukemia	NaN	NaN	0.147914	0.394173	0.366025	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
707	ACH-000373	SKM1	Myeloid	Acute Myeloid Leukemia	Acute Myeloid Leukemia	NaN	NaN	0.061619	0.210921	0.027169	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

36 rows × 30261 columns

Drug Dose Response Curve

#all drugs tested
#look for strings like "(+)-CAMPTOTHECIN (GDSC2:1003)", "PD 0325901 (GDSC2:1060)" etc.
#extract just the drug name: "(+)-CAMPTOTHECIN", "PD 0325901", etc.
#store unique names in a set to avoid duplicates.

import re

#get all column names (excluding metadata columns if any)
columns = drug_screen.columns

#use regex to extract drug names from column headers
drug_names = set()
for col in columns:
    match = re.match(r"(.+?)\s+\(GDSC2:\d+\)", col)
    if match:
        drug_names.add(match.group(1).strip())

#convert to sorted list and count
drug_list = sorted(drug_names)
print(f"Number of unique drugs: {len(drug_list)}")
print("Drugs studied:")
for drug in drug_list:
    print(drug)

Number of unique drugs: 169
Drugs studied:
(+)-CAMPTOTHECIN
(+)-JQ-1
1035270-39-3
1044870-39-4
284461-73-0
5XE
681640
A-1065-5
ABT737
ACETALAX
ADAVOSERTIB
AFATINIB
AFURESERTIB
AG-13736
AGI-5198
AGI-6780
AK-55409
AK175551
AK175558
AK298746
ALISERTIB
ALPELISIB
AMG-319
AOB2221
AOB2313
AOB5560
APO866
APR-246
ARAVA
ASP-7487
AT13148
AUY
AZ 960
AZ6102
AZD 2171
AZD 8186
AZD-8055
AZD3759
AZD7762
AZD8931
BDP-00009066
BERZOSERTIB
BEZ235
BI-2536
BI-97C1
BIBR-1532
BIIB-057
BIRABRESIB
BIRB 796
BKM120
BMS 536924
BMS-345541
BMS-754807
BORTEZOMIB
BPD-00008900
BVD-523
CAPIVASERTIB
CARMUSTINE
CERALASERTIB
CIS-DDP
CRA-032765
CRIZOTINIB
CYCLOPHOSPHAMIDE
CYTARABINE
CZC24832
DABRAFENIB
DACTINOMYCIN
DASATINIB
DIHYDROROTENONE
DINACICLIB
DOCETAXEL
ELEPHANTIN
ELOXATIN
ENTINOSTAT
ENTOSPLETINIB
EPIRUBICIN
EPZ-004777
EPZ015866
ERLOTINIB
EXEL-2880
EXELBINE
FLUDARA
FLUOROURACIL
FULVESTRANT
GALLIBISCOQUINAZOLE
GDC 0810
GEFITINIB
GEMCITABINE
GNE 317
GSK 1904529A
GSK 2578215A
GSK 269962A
GSK 602
GSK-2141795
GTPL8020
GX15-070
ICI-46474
IPATASERTIB
IRINOTECAN
IWP-2
KU-55933
KU-57788
LAPATINIB
LCL161
LGK-974
LJI308
M-39831
MIM 1
MIRA 1
MIRIN
MITOXANTRONE
MK 0457
MK 2206
MK-8776
MN-64
MOLIBRESIB
MST 312
NAVITOCLAX
NELARABINE
NILOTINIB
NIRAPARIB
NVP ADW742
OF-1
OLAPARIB
OSIMERTINIB
P 22077
PACLITAXEL
PALBOCICLIB
PD 0325901
PD 173074
PEVONEDISTAT
PF 4708671
PICOLINATE
PICTILISIB
PINOMETOSTAT
PLX 4720
PODOPHYLLOTOXIN BROMIDE
PYRIDOSTATIN
RAPAMYCIN
REBEMADLIN
RECLAST
RIBOCICLIB
RO-3306
RUXOLITINIB
SAVOLITINIB
SB 216763
SB 505124
SCH772984
SEPANTRONIUM BROMIDE
SINULARIN
TALAZOPARIB
TASELISIB
TENIPOSIDE
TOPOTECAN
TRAMETINIB
UMI 77
VE 821
VELBAN
VENETOCLAX
VINCRISTINE
VORINOSTAT
VX-11E
WEHI-539
WIKI 4
WNT-C59
WZ 4003
XAV-939
YK 4-279
ZM 447439

#drugs tested on Myeloid samples only

import re

#get all column names from Myeloid data (excluding metadata columns if any)
columns = drug_screen_AML.columns
drug_names = set()

#extract drug names from column headers
for col in columns:
    match = re.match(r"(.+?)\s+\(GDSC2:\d+\)", col)
    if match:
        if not drug_screen_AML[col].dropna().empty:   #keep column if at least one non-NaN value exists
            drug_names.add(match.group(1).strip())

drug_list = sorted(drug_names)
print(f"Number of unique drugs tested on Myeloid samples: {len(drug_list)}")
print("Drugs studied:")
for drug in drug_list:
    print(drug)

Number of unique drugs tested on Myeloid samples: 152
Drugs studied:
(+)-CAMPTOTHECIN
1035270-39-3
1044870-39-4
284461-73-0
5XE
681640
A-1065-5
ABT737
ACETALAX
ADAVOSERTIB
AFATINIB
AFURESERTIB
AGI-5198
AGI-6780
AK175551
AK175558
AK298746
ALISERTIB
ALPELISIB
AMG-319
AOB2221
AOB2313
AOB5560
APO866
APR-246
ARAVA
ASP-7487
AT13148
AUY
AZ 960
AZ6102
AZD 2171
AZD 8186
AZD3759
AZD7762
AZD8931
BDP-00009066
BERZOSERTIB
BEZ235
BI-97C1
BIBR-1532
BIIB-057
BIRABRESIB
BKM120
BMS 536924
BMS-345541
BORTEZOMIB
BPD-00008900
BVD-523
CAPIVASERTIB
CARMUSTINE
CERALASERTIB
CIS-DDP
CRA-032765
CRIZOTINIB
CYCLOPHOSPHAMIDE
CYTARABINE
CZC24832
DABRAFENIB
DACTINOMYCIN
DASATINIB
DIHYDROROTENONE
DINACICLIB
DOCETAXEL
ELEPHANTIN
ELOXATIN
ENTINOSTAT
ENTOSPLETINIB
EPIRUBICIN
EPZ-004777
EPZ015866
ERLOTINIB
EXEL-2880
EXELBINE
FLUDARA
FLUOROURACIL
FULVESTRANT
GALLIBISCOQUINAZOLE
GDC 0810
GEFITINIB
GEMCITABINE
GNE 317
GSK 1904529A
GSK 2578215A
GSK 602
GSK-2141795
GTPL8020
GX15-070
ICI-46474
IPATASERTIB
IRINOTECAN
IWP-2
LAPATINIB
LCL161
LGK-974
LJI308
M-39831
MIM 1
MIRA 1
MIRIN
MITOXANTRONE
MK 2206
MK-8776
MN-64
MOLIBRESIB
MST 312
NAVITOCLAX
NELARABINE
NILOTINIB
NIRAPARIB
NVP ADW742
OF-1
OLAPARIB
OSIMERTINIB
P 22077
PACLITAXEL
PALBOCICLIB
PD 0325901
PD 173074
PEVONEDISTAT
PICOLINATE
PICTILISIB
PINOMETOSTAT
PLX 4720
PODOPHYLLOTOXIN BROMIDE
PYRIDOSTATIN
RAPAMYCIN
REBEMADLIN
RECLAST
RUXOLITINIB
SAVOLITINIB
SCH772984
SEPANTRONIUM BROMIDE
SINULARIN
TALAZOPARIB
TASELISIB
TENIPOSIDE
TOPOTECAN
TRAMETINIB
UMI 77
VE 821
VELBAN
VENETOCLAX
VINCRISTINE
VORINOSTAT
VX-11E
WEHI-539
WIKI 4
WNT-C59
WZ 4003
XAV-939
YK 4-279

#to take the top 50 drugs most-tested on myeloid cell lines

columns = drug_screen_AML.columns
drug_to_non_nan_count = defaultdict(int)

#count non-NaN values per drug across all relevant columns
for col in columns:
    match = re.match(r"(.+?)\s+\(GDSC2:\d+\)", col)
    if match:
        drug_name = match.group(1).strip()
        non_nan_count = drug_screen_AML[col].count()    #count non-NaN values in the column
        if non_nan_count > 0:
            drug_to_non_nan_count[drug_name] += non_nan_count   #if a drug has multiple doses/reps, sum all non-NaN counts in a total count per drug

#sort drugs by total non-NaN count descending
sorted_drugs = sorted(drug_to_non_nan_count.items(), key = lambda x: x[1], reverse = True)

#take top 50
top_50_drugs = sorted_drugs[:50]

top_50_df = pd.DataFrame(top_50_drugs, columns = ['Drug', 'Data Points'])
top_50_df.index = range(1, len(top_50_df) + 1)      #make index number (left) of first row say 1 (instead of 0), so last row has 50 (instead of 49)
top_50_df

	Drug	Data Points
1	ASP-7487	904
2	PD 0325901	877
3	AFATINIB	861
4	(+)-CAMPTOTHECIN	758
5	TASELISIB	708
6	LGK-974	700
7	TRAMETINIB	699
8	DOCETAXEL	685
9	ELOXATIN	684
10	FLUOROURACIL	682
11	REBEMADLIN	663
12	CIS-DDP	656
13	FULVESTRANT	641
14	GSK-2141795	484
15	IRINOTECAN	479
16	AUY	477
17	AZD8931	470
18	GEMCITABINE	468
19	DACTINOMYCIN	467
20	BVD-523	466
21	PALBOCICLIB	466
22	PICTILISIB	465
23	SCH772984	459
24	DASATINIB	456
25	GSK 1904529A	453
26	ADAVOSERTIB	448
27	MK 2206	432
28	EPZ-004777	423
29	AZD3759	413
30	PINOMETOSTAT	401
31	ALPELISIB	396
32	PLX 4720	388
33	ARAVA	252
34	APR-246	252
35	NIRAPARIB	252
36	AZ 960	252
37	RUXOLITINIB	252
38	XAV-939	251
39	ALISERTIB	250
40	IWP-2	250
41	GX15-070	250
42	BMS-345541	250
43	CRIZOTINIB	247
44	MITOXANTRONE	245
45	VINCRISTINE	245
46	MIRIN	245
47	AOB5560	244
48	TENIPOSIDE	244
49	DIHYDROROTENONE	244
50	DINACICLIB	243

import matplotlib.pyplot as plt

drug_of_interest = "ASP-7487"
second_drug_of_interest = "PD 0325901"

#filter columns for each drug
drug_cols = [col for col in drug_screen_AML.columns if drug_of_interest in col]
second_drug_cols = [col for col in drug_screen_AML.columns if second_drug_of_interest in col]


# ----First Drug----
dose_response_1 = []     #empty list to store (dose, mean_response) pairs.
for col in drug_cols:
    dose_match = re.search(r"([\d.]+)μM", col)     #extract the number from strings like "5.0μM"
    if dose_match:
        dose = float(dose_match.group(1))
        try:
            mean_response = pd.to_numeric(drug_screen_AML[col], errors = 'coerce').mean()  #convert the column to numbers, treat all non-numeric as NaN, average viability response across all cell lines for that dose
            dose_response_1.append((dose, mean_response))     #append each dose–response pair to the list
        except:
            continue

dose_response_1.sort()
doses_1, responses_1 = zip(*dose_response_1)


# ----Second Drug----
dose_response_2 = []
for col in second_drug_cols:
    dose_match = re.search(r"([\d.]+)μM", col)
    if dose_match:
        dose = float(dose_match.group(1))
        try:
            mean_response = pd.to_numeric(drug_screen_AML[col], errors = 'coerce').mean()
            dose_response_2.append((dose, mean_response))
        except:
            continue

dose_response_2.sort()
doses_2, responses_2 = zip(*dose_response_2)

# --- Plot ---
plt.figure(figsize = (8,6))
plt.plot(doses_1, responses_1, marker = 'o', label = drug_of_interest)
plt.plot(doses_2, responses_2, marker = 's', label = second_drug_of_interest, color='orange')
plt.xscale('log')
plt.xlabel("Dose Concentration (μM)")
plt.ylabel("Cell Viability")
plt.title(f"Dose-Response Curves in Myeloid Cell Lines: {drug_of_interest} vs {second_drug_of_interest}")
plt.grid(True)
plt.legend()
plt.tight_layout()
plt.show()

from collections import defaultdict
import re
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

# --- drug names ---
drug_of_interest = "ASP-7487"
second_drug_of_interest = "PD 0325901"

# --- get drug columns ---
drug_cols = [col for col in drug_screen_AML.columns if drug_of_interest in col]
second_drug_cols = [col for col in drug_screen_AML.columns if second_drug_of_interest in col]

# ---- for first drug ----
dose_to_values = defaultdict(list)

for col in drug_cols:
    dose_match = re.search(r"([\d.]+)μM", col)
    if dose_match:
        dose = float(dose_match.group(1))
        responses = pd.to_numeric(drug_screen_AML[col], errors='coerce')
        dose_to_values[dose].extend(responses.dropna().tolist())

dose_response_1 = []
for dose, values in dose_to_values.items():
    if len(values) > 0:
        mean_val = np.mean(values)
        if not np.isnan(mean_val):
            dose_response_1.append((dose, mean_val))

dose_response_1.sort()
doses_1, responses_1 = zip(*dose_response_1)

# ---- for second drug ----
second_dose_to_values = defaultdict(list)

for col in second_drug_cols:
    dose_match = re.search(r"([\d.]+)μM", col)
    if dose_match:
        dose = float(dose_match.group(1))
        responses = pd.to_numeric(drug_screen_AML[col], errors='coerce')
        second_dose_to_values[dose].extend(responses.dropna().tolist())

dose_response_2 = []
for dose, values in second_dose_to_values.items():
    if len(values) > 0:
        mean_val = np.mean(values)
        if not np.isnan(mean_val):
            dose_response_2.append((dose, mean_val))

dose_response_2.sort()
doses_2, responses_2 = zip(*dose_response_2)

# --- plot ---
plt.figure(figsize = (8, 6))
plt.plot(doses_1, responses_1, marker='o', label=drug_of_interest)
plt.plot(doses_2, responses_2, marker='s', label=second_drug_of_interest)
plt.xscale('log')
plt.xlabel("Dose Concentration (μM)")
plt.ylabel("Mean Cell Viability")
plt.title(f"Average Dose-Response Curves in Myeloid Cell Lines: {drug_of_interest} vs {second_drug_of_interest}")
plt.grid(True)
plt.legend()
plt.tight_layout()
plt.show()

import numpy as np
from scipy.optimize import curve_fit
import matplotlib.pyplot as plt

#define a 4-parameter logistic function
def logistic4(x, A, B, C, D):
    # A = min asymptote, D = max asymptote
    # B = slope, C = inflection point (EC50)
    return A + (D - A) / (1.0 + (x / C)**B)

#fit logistic curve to drug 1
popt1, pcov1 = curve_fit(logistic4, doses_1, responses_1, 
                         bounds=([0, 0, 0, 0], [1, 10, max(doses_1)*10, 1]),
                         maxfev=10000)

#generate smooth x values for plotting
x_smooth = np.logspace(np.log10(min(doses_1)), np.log10(max(doses_1)), 200)

#calculate fitted y values
y_fit_1 = logistic4(x_smooth, *popt1)

#again drug 2
popt2, pcov2 = curve_fit(logistic4, doses_2, responses_2, 
                         bounds=([0, 0, 0, 0], [1, 10, max(doses_2)*10, 1]),
                         maxfev=10000)

y_fit_2 = logistic4(x_smooth, *popt2)

#plot raw data and fitted curves
plt.figure(figsize = (8,6))
plt.scatter(doses_1, responses_1, color = 'blue', label = f'{drug_of_interest} data')
plt.plot(x_smooth, y_fit_1, color = 'blue', linestyle = '-', label = f'{drug_of_interest} fit')

plt.scatter(doses_2, responses_2, color='orange', label=f'{second_drug_of_interest} data')
plt.plot(x_smooth, y_fit_2, color = 'orange', linestyle = '-', label = f'{second_drug_of_interest} fit')

plt.xscale('log')
plt.xlabel('Dose Concentration (μM)')
plt.ylabel('Mean Cell Viability')
plt.title(f"Fitted Average Dose-Response Curves in Myeloid Cell Lines: {drug_of_interest} vs {second_drug_of_interest}")
plt.legend()
plt.grid(True)
plt.show()