PDB Drug Bank Mapping — MMTF-PySpark 0.3.6 documentation

Imports and variables¶

In [1]:

from pyspark import SparkConf, SparkContext
from mmtfPyspark.datasets import customReportService, drugBankDataset, pdbjMineDataset
from mmtfPyspark import structureViewer

# Create variables
APP_NAME = "MMTF_Spark"
path = "../../resources/mmtf_full_sample/"

# Configure Spark
conf = SparkConf().setAppName(APP_NAME).setMaster("local[*]")
sc = SparkContext(conf=conf)

Download open DrugBank dataset¶

In [2]:

drugBank = drugBankDataset.get_open_drug_links()
drugBank.toPandas().head(10)

Out[2]:

	DrugBankID	AccessionNumbers	Commonname	CAS	UNII	Synonyms	StandardInChIKey
0	DB00001	BTD00024 \| BIOD00024	Lepirudin	138068-37-8	Y43GF64R34	Hirudin variant-1 \| Lepirudin recombinant	None
1	DB00002	BTD00071 \| BIOD00071	Cetuximab	205923-56-4	PQX0D8J21J	Cetuximab \| Cétuximab \| Cetuximabum \| Immunogl...	None
2	DB00003	BTD00001 \| BIOD00001	Dornase alfa	143831-71-4	953A26OA1Y	Deoxyribonuclease (human clone 18-1 protein mo...	None
3	DB00004	BTD00084 \| BIOD00084	Denileukin diftitox	173146-27-5	25E79B5CTM	Diphtheria toxin precursor \| DT \| NAD(+--dipht...	None
4	DB00005	BTD00052 \| BIOD00052	Etanercept	185243-69-0	OP401G7OJC	Etanercept-szzs \| RHU TNFR:FC \| RHU-TNFR:FC \| ...	None
5	DB00006	BTD00076 \| EXPT03302 \| BIOD00076 \| DB02351	Bivalirudin	128270-60-0	TN9BEX005G	Bivalirudina \| Bivalirudinum \| Hirulog	OIRCOABEOLEUMC-GEJPAHFPSA-N
6	DB00007	BTD00009 \| BIOD00009	Leuprolide	53714-56-0	EFY6W0M8TG	(D-Leu(6),des-gly-NH2(10),pro-ethylamide(9))-g...	None
7	DB00008	BTD00043 \| BIOD00043	Peginterferon alfa-2a	198153-51-4	Q46947FE7K	Pegylated interferon alfa-2a \| Pegylated inter...	None
8	DB00009	BTD00050 \| BIOD00050	Alteplase	105857-23-6	1RXS4UE564	Alteplase (genetical recombination) \| Alteplas...	None
9	DB00010	BTD00033 \| BIOD00033	Sermorelin	86168-78-7	89243S03TE	None	None

Filter out DrugBank entries without StandardInChIKey¶

In [3]:

drugBank = drugBank.filter(drugBank.StandardInChIKey.isNotNull())
drugBank.toPandas().head(5)

Out[3]:

	DrugBankID	AccessionNumbers	Commonname	CAS	UNII	Synonyms	StandardInChIKey
0	DB00006	BTD00076 \| EXPT03302 \| BIOD00076 \| DB02351	Bivalirudin	128270-60-0	TN9BEX005G	Bivalirudina \| Bivalirudinum \| Hirulog	OIRCOABEOLEUMC-GEJPAHFPSA-N
1	DB00014	BTD00113 \| BIOD00113	Goserelin	65807-02-5	0F65R8P09N	None	BLCLNMBMMGCOAS-URPVMXJPSA-N
2	DB00027	BTD00036 \| BIOD00036	Gramicidin D	1405-97-6	5IE62321P4	Bacillus brevis gramicidin D \| Gramicidin \| Gr...	NDAYQJDHGXTBJL-MWWSRJDJSA-N
3	DB00035	BTD00112 \| BTD00061 \| BIOD00112 \| BIOD00061	Desmopressin	16679-58-6	ENR1LLB0FP	1-(3-mercaptopropionic acid)-8-D-arginine-vaso...	NFLWUMRGJYTJIN-NXBWRCJVSA-N
4	DB00050	BTD00115 \| APRD00686 \| BIOD00115	Cetrorelix	120287-85-6	OON1HFZ4BA	Cetrorelixum	SBNPWPIBESPSIF-MHWMIDJBSA-N

Get PDB ligand annotations¶

In [4]:

ligands = customReportService.get_dataset(["ligandId","ligandMolecularWeight","ligandFormula","ligandSmiles","InChIKey"])
ligands.toPandas().head(10)

Out[4]:

	structureChainId	structureId	chainId	ligandId	ligandMolecularWeight	ligandFormula	ligandSmiles	InChIKey
0	100D.A	100D	A	SPM	202.34	C10 H26 N4	C(CCNCCCN)CNCCCN	PFNFFQXMRSDOHW-UHFFFAOYSA-N
1	100D.B	100D	B	None	NaN	None	None	None
2	101D.A	101D	A	CBR	386.09	C9 H13 Br N3 O7 P	C1[C@@H]([C@H](O[C@H]1N2C=C(C(=NC2=O)N)Br)COP(...	PLDRCXOBLRYJSZ-RRKCRQDMSA-N
3	101D.A	101D	A	MG	24.31	Mg 2	[Mg+2]	JLVVSXFLKOJNIY-UHFFFAOYSA-N
4	101D.B	101D	B	CBR	386.09	C9 H13 Br N3 O7 P	C1[C@@H]([C@H](O[C@H]1N2C=C(C(=NC2=O)N)Br)COP(...	PLDRCXOBLRYJSZ-RRKCRQDMSA-N
5	101D.B	101D	B	NT	430.46	C18 H26 N10 O3	Cn1cc(cc1C(=O)Nc2cc(n(c2)C)C(=O)NCCC(=N)N)NC(=...	IDBIFFKSXLYUOT-UHFFFAOYSA-N
6	101M.A	101M	A	HEM	616.49	C34 H32 Fe N4 O4	Cc1c2n3c(c1CCC(=O)O)C=C4C(=C(C5=[N]4[Fe]36[N]7...	KABFMIBPWCXCRK-RGGAHWMASA-L
7	101M.A	101M	A	NBN	83.13	C5 H9 N	CCCC[N+]#[C-]	FSBLVBBRXSCOKU-UHFFFAOYSA-N
8	101M.A	101M	A	SO4	96.06	O4 S -2	[O-]S(=O)(=O)[O-]	QAOWNCQODCNURD-UHFFFAOYSA-L
9	102D.A	102D	A	None	NaN	None	None	None

Filter out DrugBank entries without InChIKey¶

In [5]:

ligands = ligands.filter(ligands.InChIKey.isNotNull())
ligands.toPandas().head(5)

Out[5]:

	structureChainId	structureId	chainId	ligandId	ligandMolecularWeight	ligandFormula	ligandSmiles	InChIKey
0	100D.A	100D	A	SPM	202.34	C10 H26 N4	C(CCNCCCN)CNCCCN	PFNFFQXMRSDOHW-UHFFFAOYSA-N
1	101D.A	101D	A	CBR	386.09	C9 H13 Br N3 O7 P	C1[C@@H]([C@H](O[C@H]1N2C=C(C(=NC2=O)N)Br)COP(...	PLDRCXOBLRYJSZ-RRKCRQDMSA-N
2	101D.A	101D	A	MG	24.31	Mg 2	[Mg+2]	JLVVSXFLKOJNIY-UHFFFAOYSA-N
3	101D.B	101D	B	CBR	386.09	C9 H13 Br N3 O7 P	C1[C@@H]([C@H](O[C@H]1N2C=C(C(=NC2=O)N)Br)COP(...	PLDRCXOBLRYJSZ-RRKCRQDMSA-N
4	101D.B	101D	B	NT	430.46	C18 H26 N10 O3	Cn1cc(cc1C(=O)Nc2cc(n(c2)C)C(=O)NCCC(=N)N)NC(=...	IDBIFFKSXLYUOT-UHFFFAOYSA-N

Join ligand dataset with DrugBank info by InChIKey¶

In [6]:

ligands = ligands.join(drugBank, ligands.InChIKey == drugBank.StandardInChIKey)
ligands.toPandas().head(10)

Out[6]:

	structureChainId	structureId	chainId	ligandId	ligandMolecularWeight	ligandFormula	ligandSmiles	InChIKey	DrugBankID	AccessionNumbers	Commonname	CAS	UNII	Synonyms	StandardInChIKey
0	100D.A	100D	A	SPM	202.34	C10 H26 N4	C(CCNCCCN)CNCCCN	PFNFFQXMRSDOHW-UHFFFAOYSA-N	DB00127	NUTR00055 \| EXPT02947 \| DB02564	Spermine	71-44-3	2FZ7Y3VOQX	4,9-Diaza-1,12-dodecanediamine \| 4,9-Diazadode...	PFNFFQXMRSDOHW-UHFFFAOYSA-N
1	101D.A	101D	A	MG	24.31	Mg 2	[Mg+2]	JLVVSXFLKOJNIY-UHFFFAOYSA-N	DB01378	None	Magnesium	7439-95-4	T6V3LHY838	None	JLVVSXFLKOJNIY-UHFFFAOYSA-N
2	101M.A	101M	A	NBN	83.13	C5 H9 N	CCCC[N+]#[C-]	FSBLVBBRXSCOKU-UHFFFAOYSA-N	DB01826	EXPT02302	N-Butyl Isocyanide	2769-64-4	None	None	FSBLVBBRXSCOKU-UHFFFAOYSA-N
3	102D.B	102D	B	TNT	312.37	C17 H20 N4 O2	c1cc(ccc1C(=N)N)OCCCOc2ccc(cc2)C(=N)N	WTFXJFJYEJZMFO-UHFFFAOYSA-N	DB13296	None	Propamidine	104-32-5	G20G12V769	None	WTFXJFJYEJZMFO-UHFFFAOYSA-N
4	102L.A	102L	A	BME	78.13	C2 H6 O S	C(CS)O	DGVVWUTYPXICAM-UHFFFAOYSA-N	DB03345	EXPT02882 \| DB03131	Beta-Mercaptoethanol	60-24-2	14R9K67URN	2-Sulfhydryl-Ethanol	DGVVWUTYPXICAM-UHFFFAOYSA-N
5	103L.A	103L	A	BME	78.13	C2 H6 O S	C(CS)O	DGVVWUTYPXICAM-UHFFFAOYSA-N	DB03345	EXPT02882 \| DB03131	Beta-Mercaptoethanol	60-24-2	14R9K67URN	2-Sulfhydryl-Ethanol	DGVVWUTYPXICAM-UHFFFAOYSA-N
6	103M.A	103M	A	NBN	83.13	C5 H9 N	CCCC[N+]#[C-]	FSBLVBBRXSCOKU-UHFFFAOYSA-N	DB01826	EXPT02302	N-Butyl Isocyanide	2769-64-4	None	None	FSBLVBBRXSCOKU-UHFFFAOYSA-N
7	104M.A	104M	A	NBN	83.13	C5 H9 N	CCCC[N+]#[C-]	FSBLVBBRXSCOKU-UHFFFAOYSA-N	DB01826	EXPT02302	N-Butyl Isocyanide	2769-64-4	None	None	FSBLVBBRXSCOKU-UHFFFAOYSA-N
8	105M.A	105M	A	NBN	83.13	C5 H9 N	CCCC[N+]#[C-]	FSBLVBBRXSCOKU-UHFFFAOYSA-N	DB01826	EXPT02302	N-Butyl Isocyanide	2769-64-4	None	None	FSBLVBBRXSCOKU-UHFFFAOYSA-N
9	106M.A	106M	A	ENC	56.09	C3 H6 N 1	CC[N+]#C	JEGVKBYNUPNGJU-UHFFFAOYSA-N	DB03399	EXPT01344	Ethyl Isocyanide	None	None	None	JEGVKBYNUPNGJU-UHFFFAOYSA-N

Show one example per drug molecule¶

In [7]:

ligands = ligands.dropDuplicates(["Commonname"])
ligands = ligands.select("structureChainId", "ligandId", "DrugBankID", "Commonname", "ligandMolecularWeight","ligandFormula", "InChIKey", "ligandSmiles")
ligands.sort("Commonname").toPandas().head(10)

Out[7]:

	structureChainId	ligandId	DrugBankID	Commonname	ligandMolecularWeight	ligandFormula	InChIKey	ligandSmiles
0	1NJ6.A	A5A	DB03376	'5'-O-(N-(L-Alanyl)-Sulfamoyl)Adenosine	417.40	C13 H19 N7 O7 S	CWWYMWDIYBJVLP-YTMOPEAISA-N	C[C@@H](C(=O)NS(=O)(=O)OC[C@@H]1[C@H]([C@H]([C...
1	1NJ5.A	P5A	DB02510	'5'-O-(N-(L-Prolyl)-Sulfamoyl)Adenosine	443.43	C15 H21 N7 O7 S	LKVJEMXWEODCAY-JVEUSOJLSA-N	c1nc(c2c(n1)n(cn2)[C@H]3[C@@H]([C@@H]([C@H](O3...
2	1VQ2.A	DDN	DB04280	((2r,3s,5r)-3-Hydroxy-5-(4-Hydroxy-2-Oxo-3,4-D...	310.20	C9 H15 N2 O8 P	ILSIYJVILUIVPM-LXGUWJNJSA-N	C1[C@@H]([C@H](O[C@H]1N2C=C[C@H](NC2=O)O)COP(=...
3	1A7A.A	ADC	DB03216	(1'r,2's)-9-(2-Hydroxy-3'-Keto-Cyclopenten-1-Y...	233.23	C10 H11 N5 O2	RQPALADHFYHEHK-CHKWXVPMSA-N	c1nc(c2c(n1)n(cn2)[C@@H]3C=CC([C@H]3O)O)N
4	1DCY.A	I3N	DB03121	(1-Benzyl-5-methoxy-2-methyl-1H-indol-3-yl)ace...	309.36	C19 H19 N O3	ZEKCBTQHDTUHRJ-UHFFFAOYSA-N	Cc1c(c2cc(ccc2n1Cc3ccccc3)OC)CC(=O)O
5	2E99.A	B08	DB07404	(1-HYDROXY-1-PHOSPHONO-2-[1,1';3',1'']TERPHENY...	434.32	C20 H20 O7 P2	YXQQNSYZOQHKHD-UHFFFAOYSA-N	c1ccc(cc1)c2cccc(c2)c3cccc(c3)CC(O)(P(=O)(O)O)...
6	2E9A.A	B28	DB07409	(1-HYDROXY-1-PHOSPHONO-2-[1,1';4',1'']TERPHENY...	434.32	C20 H20 O7 P2	MPBUFKZCEBTBSK-UHFFFAOYSA-N	c1ccc(cc1)c2ccc(cc2)c3cccc(c3)CC(O)(P(=O)(O)O)...
7	2Z52.A	H23	DB07873	(1-HYDROXYDODECANE-1,1-DIYL)BIS(PHOSPHONIC ACID)	346.29	C12 H28 O7 P2	KKVZONPEMODBBG-UHFFFAOYSA-N	CCCCCCCCCCCC(O)(P(=O)(O)O)P(=O)(O)O
8	2Z50.A	028	DB06830	(1-HYDROXYHEPTANE-1,1-DIYL)BIS(PHOSPHONIC ACID)	276.16	C7 H18 O7 P2	IJEGNOYPWRBKAE-UHFFFAOYSA-N	CCCCCCC(O)(P(=O)(O)O)P(=O)(O)O
9	2Z4X.A	252	DB06931	(1-HYDROXYNONANE-1,1-DIYL)BIS(PHOSPHONIC ACID)	304.21	C9 H22 O7 P2	COHUUYPEYRMWTH-UHFFFAOYSA-N	CCCCCCCCC(O)(P(=O)(O)O)P(=O)(O)O

Query structures with 2.7.11.1 EC number using PDBjMine¶

In [8]:

enzymeQuery = "SELECT * FROM sifts.pdb_chain_enzyme WHERE ec_number = '2.7.11.1'"
enzyme = pdbjMineDataset.get_dataset(enzymeQuery)

print(f"First 10 results for query: {enzymeQuery}")
enzyme.show(10)

First 10 results for query: SELECT * FROM sifts.pdb_chain_enzyme WHERE ec_number = '2.7.11.1'
+-----+-----+---------+---------+----------------+
|pdbid|chain|accession|ec_number|structureChainId|
+-----+-----+---------+---------+----------------+
| 1AUE|    A|   P42345| 2.7.11.1|          1AUE.A|
| 1AUE|    B|   P42345| 2.7.11.1|          1AUE.B|
| 1BPV|    A|   Q8WZ42| 2.7.11.1|          1BPV.A|
| 1C1Y|    B|   P04049| 2.7.11.1|          1C1Y.B|
| 1CF4|    B|   Q07912| 2.7.11.1|          1CF4.B|
| 1CJA|    A|   P80197| 2.7.11.1|          1CJA.A|
| 1CJA|    B|   P80197| 2.7.11.1|          1CJA.B|
| 1CKI|    A|   Q06486| 2.7.11.1|          1CKI.A|
| 1CKI|    B|   Q06486| 2.7.11.1|          1CKI.B|
| 1CKJ|    A|   Q06486| 2.7.11.1|          1CKJ.A|
+-----+-----+---------+---------+----------------+
only showing top 10 rows

Join ligand dataset with PDBjMine dataset with structureChainId¶

In [9]:

ligands = ligands.join(enzyme, ligands.structureChainId == enzyme.structureChainId)
print(f"Total number of structures: {ligands.count()}")

df = ligands.toPandas()
df.head()

Total number of structures: 172

Out[9]:

	structureChainId	ligandId	DrugBankID	Commonname	ligandMolecularWeight	ligandFormula	InChIKey	ligandSmiles	pdbid	chain	accession	ec_number	structureChainId
0	1UVR.A	BI8	DB01946	3-[1-(3-Aminopropyl)-1h-Indol-3-Yl]-4-(1-Methy...	398.46	C24 H22 N4 O2	UQHKJRCFSLMWIA-UHFFFAOYSA-N	Cn1cc(c2c1cccc2)C3=C(C(=O)NC3=O)c4cn(c5c4cccc5...	1UVR	A	O15530	2.7.11.1	1UVR.A
1	4EKL.A	0RF	DB11743	Ipatasertib	458.00	C24 H32 Cl N5 O2	GRZXWCHAXNAUHY-NSISKUIASA-N	C[C@@H]1C[C@H](c2c1c(ncn2)N3CCN(CC3)C(=O)[C@H]...	4EKL	A	P31749	2.7.11.1	4EKL.A
2	2NP8.A	CC3	DB07545	N-{3-[(4-{[3-(TRIFLUOROMETHYL)PHENYL]AMINO}PYR...	413.40	C21 H18 F3 N5 O	RDTDWGQDFJPTPD-UHFFFAOYSA-N	c1cc(cc(c1)Nc2ccnc(n2)Nc3cccc(c3)NC(=O)C4CC4)C...	2NP8	A	O14965	2.7.11.1	2NP8.A
3	2C3L.A	IDZ	DB07959	3-(1H-BENZIMIDAZOL-2-YL)-1H-INDAZOLE	234.26	C14 H10 N4	JTKFRFMSUBOCIQ-UHFFFAOYSA-N	c1ccc2c(c1)c(n[nH]2)c3[nH]c4ccccc4n3	2C3L	A	O14757	2.7.11.1	2C3L.A
4	3BQR.A	4RB	DB07125	4-(6-{[(1R)-1-(hydroxymethyl)propyl]amino}imid...	326.35	C17 H18 N4 O3	KKZYGUVAFJCULH-CYBMUJFWSA-N	CC[C@H](CO)Nc1ccc2ncc(n2n1)c3ccc(cc3)C(=O)O	3BQR	A	O43293	2.7.11.1	3BQR.A

Visualize protein kinase interaction¶

In [11]:

structureViewer.view_binding_site(df.pdbid, df.ligandId, df.chain, 4.0)

Out[11]:

<function mmtfPyspark.structureViewer.view_binding_site.<locals>.view3d(i=0)>

Terminate Spark¶

In [12]:

sc.stop()

PDB Drug Bank Mapping¶

Imports and variables¶

Download open DrugBank dataset¶

Filter out DrugBank entries without StandardInChIKey¶

Get PDB ligand annotations¶

Filter out DrugBank entries without InChIKey¶

Join ligand dataset with DrugBank info by InChIKey¶

Show one example per drug molecule¶

Query structures with 2.7.11.1 EC number using PDBjMine¶

Join ligand dataset with PDBjMine dataset with structureChainId¶

Visualize protein kinase interaction¶

Terminate Spark¶