combine bindome and greatpy

[1]:

%load_ext autoreload
%autoreload 2

[9]:

import greatpy as great
import bindome as bd
import warnings
warnings.filterwarnings('ignore')

Import data with bindome

[10]:

annpath = '/storage/groups/ml01/datasets/annotations'
bd.bindome.constants.ANNOTATIONS_DIRECTORY = annpath
df1 = bd.bindome.datasets.REMAP2020.get_remap_peaks('SRF')
df1

[10]:

	chr	start	end	3	4	5	6	7	8	coordinate	summit.start	summit.end	k.summit
0	chr1	629831	629954	SRF:K-562	1	.	629938	629939	140,112,224	chr1:629831-629954	629838	630038	chr1:629838-630038
1	chr1	778597	778779	SRF:Ishikawa,GM12878,A-673-clone-Asp114,K-562,...	8	.	778671	778672	140,112,224	chr1:778597-778779	778571	778771	chr1:778571-778771
2	chr1	869817	870104	SRF:A-673-clone-Asp114	1	.	870004	870005	140,112,224	chr1:869817-870104	869904	870104	chr1:869904-870104
3	chr1	904714	904924	SRF:GM12878,A-673-clone-Asp114	2	.	904795	904796	140,112,224	chr1:904714-904924	904695	904895	chr1:904695-904895
4	chr1	905143	905666	SRF:A-673-clone-Asp114	1	.	905393	905394	140,112,224	chr1:905143-905666	905293	905493	chr1:905293-905493
...	...	...	...	...	...	...	...	...	...	...	...	...	...
130753	chrY	19567211	19567311	SRF:Hep-G2	1	.	19567231	19567232	140,112,224	chrY:19567211-19567311	19567131	19567331	chrY:19567131-19567331
130754	chrY	19744932	19745043	SRF:Hep-G2	1	.	19744983	19744984	140,112,224	chrY:19744932-19745043	19744883	19745083	chrY:19744883-19745083
130755	chrY	20575583	20575822	SRF:WA01,Hep-G2	2	.	20575707	20575708	140,112,224	chrY:20575583-20575822	20575607	20575807	chrY:20575607-20575807
130756	chrY	20575934	20576114	SRF:WA01,Hep-G2	2	.	20576046	20576047	140,112,224	chrY:20575934-20576114	20575946	20576146	chrY:20575946-20576146
130757	chrY	21021882	21022040	SRF:Hep-G2	1	.	21021946	21021947	140,112,224	chrY:21021882-21022040	21021846	21022046	chrY:21021846-21022046

130758 rows × 13 columns

[12]:

df1 = df1[df1[3] == "SRF:Ishikawa,MCF-7"].iloc[:,0:3]
df1 = df1.rename(columns = {"chr":'Chr','start':"Chr_start",'end':"Chr_end"})
df1

[12]:

	Chr	Chr_start	Chr_end
47	chr1	1157504	1157660
178	chr1	2586482	2586614
241	chr1	3900438	3900894
371	chr1	6785102	6785311
708	chr1	10796590	10796818
...	...	...	...
130119	chrX	132023226	132023393
130187	chrX	133418786	133418958
130266	chrX	135344596	135344830
130562	chrX	152830686	152830951
130645	chrX	154000071	154000286

578 rows × 3 columns

Compute the data with greatpy

[16]:

enrichment = great.tl.enrichment(
    test_file = df1,
    regdom_file = "../data/human/hg38/regulatory_domain.bed",
    chr_size_file = "../data/human/hg38/chr_size.bed",
    annotation_file = "../data/human/ontologies.csv",
    binom = True,
    hypergeom = True,
    )
enrichment = great.tl.set_fdr(enrichment)
enrichment = great.tl.set_bonferroni(enrichment)
enrichment

[16]:

	go_term	binom_p_value	binom_fold_enrichment	hypergeom_p_value	hypergeometric_fold_enrichment	binom_fdr	hypergeom_fdr	binom_bonferroni	hypergeom_bonferroni
GO:0003887	DNA-directed DNA polymerase activity	5.58223e-07	6.86070e+03	6.78765e-03	2.83705e+00	2.52484e-03	4.24967e-01	2.52484e-03	1.00000e+00
GO:0005654	nucleoplasm	2.37389e-06	7.76641e+02	1.00000e+00	2.46288e-01	5.36856e-03	1.00000e+00	1.07371e-02	1.00000e+00
GO:0051271	negative regulation of cellular component move...	9.61747e-06	7.40429e+03	2.99533e-03	9.27107e+00	1.02085e-02	4.24967e-01	4.34998e-02	1.00000e+00
GO:0045095	keratin filament	1.06729e-05	5.59057e+03	2.05747e-01	1.45603e+00	1.02085e-02	5.39459e-01	4.82736e-02	1.00000e+00
GO:0044317	rod spherule	1.12851e-05	2.42732e+05	4.62268e-02	2.16325e+01	1.02085e-02	4.24967e-01	5.10424e-02	1.00000e+00
...	...	...	...	...	...	...	...	...	...
GO:0042391	regulation of membrane potential	9.99684e-01	7.22182e+01	9.98196e-01	1.62650e-01	1.00000e+00	1.00000e+00	1.00000e+00	1.00000e+00
GO:0045211	postsynaptic membrane	9.99729e-01	1.92339e+02	9.14369e-01	6.36250e-01	1.00000e+00	9.60393e-01	1.00000e+00	1.00000e+00
GO:0004930	G protein-coupled receptor activity	9.99972e-01	1.78522e+02	1.00000e+00	2.21872e-01	1.00000e+00	1.00000e+00	1.00000e+00	1.00000e+00
GO:0005886	plasma membrane	9.99999e-01	4.37347e+02	1.00000e+00	2.62943e-01	1.00000e+00	1.00000e+00	1.00000e+00	1.00000e+00
GO:0007186	G protein-coupled receptor signaling pathway	1.00000e+00	2.02047e+02	1.00000e+00	3.01381e-01	1.00000e+00	1.00000e+00	1.00000e+00	1.00000e+00

4523 rows × 9 columns