In [ ]:
Copied!
from grnndata import GRNAnnData
from grnndata import utils
from grnndata import GRNAnnData
from grnndata import utils
In [ ]:
Copied!
subdata
subdata
View of AnnData object with n_obs × n_vars = 142 × 2000
obs: 'n_genes', 'n_counts', 'percent_mito', 'donor_id', 'assay_ontology_term_id', 'cell_type_ontology_term_id', 'development_stage_ontology_term_id', 'disease_ontology_term_id', 'self_reported_ethnicity_ontology_term_id', 'is_primary_data', 'organism_ontology_term_id', 'sex_ontology_term_id', 'tissue_ontology_term_id', 'author_cell_type', 'suspension_type', 'cell_type', 'assay', 'disease', 'organism', 'sex', 'tissue', 'self_reported_ethnicity', 'development_stage', 'batch_id'
var: 'chromosome', 'featureend', 'featurestart', 'n_cells', 'percent_cells', 'robust', 'highly_variable_features', 'mean', 'var', 'hvf_loess', 'hvf_rank', 'gene_symbols', 'feature_is_filtered', 'feature_name', 'feature_reference', 'feature_biotype', 'id_in_vocab', 'gene_ids', 'n_counts', 'highly_variable', 'highly_variable_rank', 'means', 'variances', 'variances_norm'
uns: 'cell_type_ontology_term_id_colors', 'default_embedding', 'schema_version', 'title', 'log1p', 'hvg'
obsm: 'X_diffmap', 'X_diffmap_pca', 'X_fitsne', 'X_fle', 'X_pca', 'X_phi', 'X_umap', 'bin_edges'
layers: 'X_normed', 'X_log1p', 'X_binned'
In [ ]:
Copied!
grn
grn
array([[0. , 0. , 0.00184461, ..., 0.00069608, 0. ,
0.00147827],
[0. , 0. , 0.00195379, ..., 0.00608598, 0. ,
0.00054822],
[0. , 0. , 0.00406754, ..., 0.01028988, 0. ,
0.00044465],
...,
[0. , 0. , 0.00234615, ..., 0.00053798, 0. ,
0. ],
[0. , 0. , 0.00029704, ..., 0.00185636, 0.00043659,
0.00055524],
[0. , 0. , 0.00134493, ..., 0.01271029, 0. ,
0. ]], dtype=float32)
In [ ]:
Copied!
# if create a view of an AnnData, need to call copy()
# the first value in this array is the cell embedding, not a gene.
grn = GRNAnnData(subdata.copy(), grn=grn[1:,1:])
# if create a view of an AnnData, need to call copy()
# the first value in this array is the cell embedding, not a gene.
grn = GRNAnnData(subdata.copy(), grn=grn[1:,1:])
ask basic questions to the GRN¶
In [ ]:
Copied!
# microglia
top_central_genes = utils.get_centrality(grn)
grn.var.loc[[i[0] for i in top_central_genes],'feature_name']
# microglia
top_central_genes = utils.get_centrality(grn)
grn.var.loc[[i[0] for i in top_central_genes],'feature_name']
Top central genes: [('ENSG00000002933', 0.02610535850416804), ('ENSG00000007168', 0.02610535850416804), ('ENSG00000010278', 0.02610535850416804), ('ENSG00000014641', 0.02610535850416804), ('ENSG00000018280', 0.02610535850416804), ('ENSG00000026025', 0.02610535850416804), ('ENSG00000026297', 0.02610535850416804), ('ENSG00000046653', 0.02610535850416804), ('ENSG00000051523', 0.02610535850416804), ('ENSG00000059804', 0.02610535850416804), ('ENSG00000065135', 0.02610535850416804), ('ENSG00000067064', 0.02610535850416804), ('ENSG00000067225', 0.02610535850416804), ('ENSG00000067560', 0.02610535850416804), ('ENSG00000068697', 0.02610535850416804), ('ENSG00000074800', 0.02610535850416804), ('ENSG00000075142', 0.02610535850416804), ('ENSG00000075415', 0.02610535850416804), ('ENSG00000075624', 0.02610535850416804), ('ENSG00000078668', 0.02610535850416804), ('ENSG00000081237', 0.02610535850416804), ('ENSG00000082074', 0.02610535850416804), ('ENSG00000085063', 0.02610535850416804), ('ENSG00000086300', 0.02610535850416804), ('ENSG00000086730', 0.02610535850416804), ('ENSG00000087460', 0.02610535850416804), ('ENSG00000089220', 0.02610535850416804), ('ENSG00000089327', 0.02610535850416804), ('ENSG00000090104', 0.02610535850416804), ('ENSG00000090238', 0.02610535850416804)]
gene_ids ENSG00000002933 TMEM176A ENSG00000007168 PAFAH1B1 ENSG00000010278 CD9 ENSG00000014641 MDH1 ENSG00000018280 SLC11A1 ENSG00000026025 VIM ENSG00000026297 RNASET2 ENSG00000046653 GPM6B ENSG00000051523 CYBA ENSG00000059804 SLC2A3 ENSG00000065135 GNAI3 ENSG00000067064 IDI1 ENSG00000067225 PKM ENSG00000067560 RHOA ENSG00000068697 LAPTM4A ENSG00000074800 ENO1 ENSG00000075142 SRI ENSG00000075415 SLC25A3 ENSG00000075624 ACTB ENSG00000078668 VDAC3 ENSG00000081237 PTPRC ENSG00000082074 FYB1 ENSG00000085063 CD59 ENSG00000086300 SNX10 ENSG00000086730 LAT2 ENSG00000087460 GNAS ENSG00000089220 PEBP1 ENSG00000089327 FXYD5 ENSG00000090104 RGS1 ENSG00000090238 YPEL3 Name: feature_name, dtype: category Categories (2000, object): ['A2M', 'AACS', 'AANAT', 'ABCB1', ..., 'ZMAT4', 'ZNF804A', 'ZNF812P', 'ZNRF1']
In [ ]:
Copied!
top_central_genes = utils.get_centrality(grn)
grn.var.loc[[i[0] for i in top_central_genes],'feature_name']
top_central_genes = utils.get_centrality(grn)
grn.var.loc[[i[0] for i in top_central_genes],'feature_name']
Top central genes: [('ENSG00000001461', 0.030758883171933152), ('ENSG00000010404', 0.030758883171933152), ('ENSG00000014641', 0.030758883171933152), ('ENSG00000022267', 0.030758883171933152), ('ENSG00000042753', 0.030758883171933152), ('ENSG00000046653', 0.030758883171933152), ('ENSG00000047849', 0.030758883171933152), ('ENSG00000051620', 0.030758883171933152), ('ENSG00000052802', 0.030758883171933152), ('ENSG00000057757', 0.030758883171933152), ('ENSG00000059804', 0.030758883171933152), ('ENSG00000060138', 0.030758883171933152), ('ENSG00000067064', 0.030758883171933152), ('ENSG00000067225', 0.030758883171933152), ('ENSG00000067560', 0.030758883171933152), ('ENSG00000067606', 0.030758883171933152), ('ENSG00000068697', 0.030758883171933152), ('ENSG00000068971', 0.030758883171933152), ('ENSG00000069849', 0.030758883171933152), ('ENSG00000074317', 0.030758883171933152), ('ENSG00000074800', 0.030758883171933152), ('ENSG00000075142', 0.030758883171933152), ('ENSG00000075415', 0.030758883171933152), ('ENSG00000075624', 0.030758883171933152), ('ENSG00000075785', 0.030758883171933152), ('ENSG00000075945', 0.030758883171933152), ('ENSG00000076043', 0.030758883171933152), ('ENSG00000078668', 0.030758883171933152), ('ENSG00000078902', 0.030758883171933152), ('ENSG00000079459', 0.030758883171933152)]
gene_ids ENSG00000001461 NIPAL3 ENSG00000010404 IDS ENSG00000014641 MDH1 ENSG00000022267 FHL1 ENSG00000042753 AP2S1 ENSG00000046653 GPM6B ENSG00000047849 MAP4 ENSG00000051620 HEBP2 ENSG00000052802 MSMO1 ENSG00000057757 PITHD1 ENSG00000059804 SLC2A3 ENSG00000060138 YBX3 ENSG00000067064 IDI1 ENSG00000067225 PKM ENSG00000067560 RHOA ENSG00000067606 PRKCZ ENSG00000068697 LAPTM4A ENSG00000068971 PPP2R5B ENSG00000069849 ATP1B3 ENSG00000074317 SNCB ENSG00000074800 ENO1 ENSG00000075142 SRI ENSG00000075415 SLC25A3 ENSG00000075624 ACTB ENSG00000075785 RAB7A ENSG00000075945 KIFAP3 ENSG00000076043 REXO2 ENSG00000078668 VDAC3 ENSG00000078902 TOLLIP ENSG00000079459 FDFT1 Name: feature_name, dtype: category Categories (2000, object): ['A2M', 'AACS', 'AANAT', 'ABCB1', ..., 'ZMAT4', 'ZNF804A', 'ZNF812P', 'ZNRF1']
In [ ]:
Copied!
grn.var_names = grn.var['feature_name']
grn.var['TFs'] = [True if i in utils.TF else False for i in grn.var_names]
grn.var_names = grn.var['feature_name']
grn.var['TFs'] = [True if i in utils.TF else False for i in grn.var_names]
/home/ml4ig1/miniconda3/envs/training-gpt/lib/python3.10/site-packages/anndata/_core/anndata.py:949: UserWarning:
AnnData expects .var.index to contain strings, but got values like:
['CFH', 'NIPAL3', 'WNT16', 'MAD1L1', 'TMEM176A']
Inferred to be: categorical
names = self._prep_dim_index(names, "var")
In [ ]:
Copied!
#microglia
grn.grn.sum(1).sort_values(ascending=False).head(20)
#microglia
grn.grn.sum(1).sort_values(ascending=False).head(20)
feature_name MT-CO1 3.971675 IFI27 3.719180 MT-CO3 3.642034 CYP17A1 3.640886 MT-RNR2 3.578026 SERPING1 3.559206 CD74 3.540354 IFIT2 3.535392 TF 3.524321 NR4A3 3.513894 B2M 3.493739 HLA-DPB1 3.457864 TYROBP 3.434500 TMSB4X 3.430675 HLA-DRA 3.387647 HLA-DRB1 3.360535 CLU 3.353451 S100A9 3.321588 C1QTNF3 3.308875 QPCT 3.290879 dtype: float32
In [ ]:
Copied!
#cones
grn.grn.sum(1).sort_values(ascending=False).head(20)
#cones
grn.grn.sum(1).sort_values(ascending=False).head(20)
feature_name CHST8 4.046652 RSPO3 3.987358 CA14 3.946459 CCNA1 3.943601 COL21A1 3.925835 LYVE1 3.911230 NOS1 3.910461 SCD 3.900852 QPCT 3.894938 CSRP1 3.882580 OR7E115P 3.877537 KCNK1 3.863492 NGFR 3.852417 NEUROD2 3.843404 ZCCHC12 3.827054 PARM1 3.822857 CDH7 3.822110 SLC15A3 3.821029 ANXA8L1 3.811610 KCNH5 3.808449 dtype: float32
In [ ]:
Copied!
grn.write('grn.h5ad')
grn.write('grn.h5ad')
... storing 'batch_id' as categorical
In [ ]:
Copied!
grn
grn
AnnData object with n_obs × n_vars = 12239 × 2000
obs: 'n_genes', 'n_counts', 'percent_mito', 'donor_id', 'assay_ontology_term_id', 'cell_type_ontology_term_id', 'development_stage_ontology_term_id', 'disease_ontology_term_id', 'self_reported_ethnicity_ontology_term_id', 'is_primary_data', 'organism_ontology_term_id', 'sex_ontology_term_id', 'tissue_ontology_term_id', 'author_cell_type', 'suspension_type', 'cell_type', 'assay', 'disease', 'organism', 'sex', 'tissue', 'self_reported_ethnicity', 'development_stage', 'batch_id'
var: 'chromosome', 'featureend', 'featurestart', 'n_cells', 'percent_cells', 'robust', 'highly_variable_features', 'mean', 'var', 'hvf_loess', 'hvf_rank', 'gene_symbols', 'feature_is_filtered', 'feature_name', 'feature_reference', 'feature_biotype', 'id_in_vocab', 'gene_ids', 'n_counts', 'highly_variable', 'highly_variable_rank', 'means', 'variances', 'variances_norm', 'centrality', 'TFs'
uns: 'cell_type_ontology_term_id_colors', 'default_embedding', 'schema_version', 'title', 'log1p', 'hvg'
obsm: 'X_diffmap', 'X_diffmap_pca', 'X_fitsne', 'X_fle', 'X_pca', 'X_phi', 'X_umap', 'bin_edges'
layers: 'X_normed', 'X_log1p', 'X_binned'
varp: 'GRN'
In [ ]:
Copied!
utils.enrichment(grn, of='Regulators')
utils.enrichment(grn, of='Regulators')
2024-01-11 14:36:36,661 [WARNING] Duplicated values found in preranked stats: 5.50% of genes The order of those genes will be arbitrary, which may produce unexpected results. 2024-01-11 14:36:36,663 [INFO] Parsing data files for GSEA............................. 2024-01-11 14:36:36,665 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:36,676 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:37,185 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:37,238 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:37,241 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:37,251 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:37,876 [ERROR] No supported gene_sets: GTEx_Tissue_Sample_Gene_Expression_Profiles_up 2024-01-11 14:36:37,879 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:37,905 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:37,929 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:36:38,560 [INFO] 1941 gene_sets have been filtered out when max_size=1000 and min_size=5 2024-01-11 14:36:38,563 [INFO] 2148 gene_sets used for further statistical testing..... 2024-01-11 14:36:38,565 [INFO] Start to run GSEA...Might take a while.................. 2024-01-11 14:36:49,816 [INFO] Congratulations. GSEApy runs successfully................
[]
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) /home/ml4ig1/Documents code/scGPT/mytests/cleanup_run.ipynb Cell 37 line 1 ----> <a href='vscode-notebook-cell://ssh-remote%2Bperso/home/ml4ig1/Documents%20code/scGPT/mytests/cleanup_run.ipynb#Y151sdnNjb2RlLXJlbW90ZQ%3D%3D?line=0'>1</a> utils.enrichment(grn, of='Regulators') File ~/Documents code/GRnnData/grnndata/utils.py:92, in enrichment(grn, of, doplot, top_k, **kwargs) 90 # plot results 91 if doplot: ---> 92 ax = dotplot( 93 pre_res.res2d[ 94 (pre_res.res2d["FDR q-val"] < 0.1) & (pre_res.res2d["NES"] > 1) 95 ].sort_values(by=["NES"], ascending=False), 96 column="FDR q-val", 97 title="enrichment of " + of + " in the grn", 98 size=6, # adjust dot size 99 figsize=(4, 5), 100 cutoff=0.25, 101 show_ring=False, 102 ) 104 return val File ~/miniconda3/envs/training-gpt/lib/python3.10/site-packages/gseapy/plot.py:1150, in dotplot(df, column, x, y, x_order, y_order, title, cutoff, top_term, size, figsize, cmap, ofname, xticklabels_rot, yticklabels_rot, marker, show_ring, **kwargs) 1147 warnings.warn("group is deprecated; use x instead", DeprecationWarning, 2) 1148 return -> 1150 dot = DotPlot( 1151 df=df, 1152 x=x, 1153 y=y, 1154 x_order=x_order, 1155 y_order=y_order, 1156 hue=column, 1157 title=title, 1158 thresh=cutoff, 1159 n_terms=int(top_term), 1160 dot_scale=size, 1161 figsize=figsize, 1162 cmap=cmap, 1163 ofname=ofname, 1164 marker=marker, 1165 ) 1166 ax = dot.scatter(outer_ring=show_ring) 1168 if xticklabels_rot: File ~/miniconda3/envs/training-gpt/lib/python3.10/site-packages/gseapy/plot.py:649, in DotPlot.__init__(self, df, x, y, hue, dot_scale, x_order, y_order, thresh, n_terms, title, figsize, cmap, ofname, **kwargs) 647 self.n_terms = n_terms 648 self.thresh = thresh --> 649 self.data = self.process(df) 650 plt.rcParams.update({"pdf.fonttype": 42, "ps.fonttype": 42}) File ~/miniconda3/envs/training-gpt/lib/python3.10/site-packages/gseapy/plot.py:674, in DotPlot.process(self, df) 672 if len(df) < 1: 673 msg = "Warning: No enrich terms when cutoff = %s" % self.thresh --> 674 raise ValueError(msg) 675 self.cbar_title = self.colname 676 # clip GSEA lower bounds 677 # if self.colname in ["NOM p-val", "FDR q-val"]: 678 # df[self.colname].clip(1e-5, 1.0, inplace=True) 679 # sorting the dataframe for better visualization ValueError: Warning: No enrich terms when cutoff = 0.25
In [ ]:
Copied!
utils.enrichment(grn, of='Targets')
utils.enrichment(grn, of='Targets')
2024-01-11 14:37:43,492 [INFO] Parsing data files for GSEA............................. 2024-01-11 14:37:43,495 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:43,504 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:44,017 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:44,074 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:44,077 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:44,086 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:44,711 [ERROR] No supported gene_sets: GTEx_Tissue_Sample_Gene_Expression_Profiles_up 2024-01-11 14:37:44,714 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:44,741 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:44,764 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:37:45,383 [INFO] 1941 gene_sets have been filtered out when max_size=1000 and min_size=5 2024-01-11 14:37:45,386 [INFO] 2148 gene_sets used for further statistical testing..... 2024-01-11 14:37:45,388 [INFO] Start to run GSEA...Might take a while.................. 2024-01-11 14:37:55,976 [INFO] Congratulations. GSEApy runs successfully................
['KEGG_2016__Neuroactive ligand-receptor interaction Homo sapiens hsa04080', 'KEGG_2016__Staphylococcus aureus infection Homo sapiens hsa05150', 'GO_Cellular_Component_2015__integral component of plasma membrane (GO:0005887)', 'GO_Molecular_Function_2015__extracellular ligand-gated ion channel activity (GO:0005230)', 'Chromosome_Location__chr5p15', 'GO_Molecular_Function_2015__ligand-gated channel activity (GO:0022834)', 'GO_Molecular_Function_2015__ligand-gated ion channel activity (GO:0015276)', 'KEGG_2016__Systemic lupus erythematosus Homo sapiens hsa05322', 'GO_Cellular_Component_2015__chloride channel complex (GO:0034707)', 'GO_Cellular_Component_2015__extracellular region (GO:0005576)']
| Term | ES | NES | NOM p-val | FDR q-val | FWER p-val | Tag % | Gene % | Lead_genes | |
|---|---|---|---|---|---|---|---|---|---|
| 264 | KEGG_2016__Neuroactive ligand-receptor interac... | 0.390721 | 2.965037 | 0.0 | 0.000531 | 0.001 | 39/57 | 34.25% | P2RX5;P2RY1;S1PR3;HTR5A;CHRNA2;GRIN2B;OPRK1;CY... |
| 315 | KEGG_2016__Staphylococcus aureus infection Hom... | 0.487666 | 2.538607 | 0.0 | 0.011416 | 0.039 | 19/23 | 36.40% | FCGR1A;CFI;HLA-DPB1;HLA-DMB;FPR1;C1QC;FCGR2B;C... |
| 341 | GO_Cellular_Component_2015__integral component... | 0.213427 | 2.412604 | 0.0 | 0.029735 | 0.137 | 117/192 | 45.30% | LYVE1;NGFR;KCNH5;TPBG;P2RX5;P2RY1;GPR37;S1PR3;... |
| 354 | GO_Molecular_Function_2015__extracellular liga... | 0.441347 | 2.29744 | 0.001427 | 0.069558 | 0.351 | 16/23 | 29.25% | P2RX5;CHRNA2;GRIN2B;GABRG1;GABRR1;GRIA4;GABRA1... |
| 361 | Chromosome_Location__chr5p15 | 0.774824 | 2.274557 | 0.0 | 0.06754 | 0.41 | 6/6 | 22.75% | IRX2;MYO10;IRX4;IRX1;SEMA5A;CTNND2 |
| 365 | GO_Molecular_Function_2015__ligand-gated chann... | 0.356361 | 2.266412 | 0.0 | 0.051884 | 0.431 | 23/37 | 31.20% | KCNK1;P2RX5;KCNJ10;KCNJ6;CHRNA2;GRIN2B;GABRG1;... |
| 366 | GO_Molecular_Function_2015__ligand-gated ion c... | 0.356361 | 2.266412 | 0.0 | 0.051884 | 0.431 | 23/37 | 31.20% | KCNK1;P2RX5;KCNJ10;KCNJ6;CHRNA2;GRIN2B;GABRG1;... |
| 372 | KEGG_2016__Systemic lupus erythematosus Homo s... | 0.418975 | 2.225912 | 0.001387 | 0.062125 | 0.526 | 18/24 | 36.40% | FCGR1A;GRIN2B;HLA-DPB1;HLA-DMB;C1QC;HLA-DPA1;H... |
| 376 | GO_Cellular_Component_2015__chloride channel c... | 0.53178 | 2.214056 | 0.001541 | 0.060709 | 0.554 | 10/13 | 26.90% | GABRG1;GABRR1;GABRA1;GABRA2;GLRA3;GABRG3;FXYD3... |
| 387 | GO_Cellular_Component_2015__extracellular regi... | 0.183872 | 2.160125 | 0.0 | 0.085328 | 0.704 | 130/219 | 46.95% | RSPO3;COL21A1;NGFR;EFEMP1;TENM1;LY96;LPL;LUZP2... |
In [ ]:
Copied!
res = utils.enrichment(grn, of='Central')
res = utils.enrichment(grn, of='Central')
Top central genes: []
2024-01-11 14:52:38,615 [WARNING] Duplicated values found in preranked stats: 13.55% of genes The order of those genes will be arbitrary, which may produce unexpected results. 2024-01-11 14:52:38,617 [INFO] Parsing data files for GSEA............................. 2024-01-11 14:52:38,619 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:38,626 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:38,960 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:38,977 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:38,979 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:38,985 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:39,601 [ERROR] No supported gene_sets: GTEx_Tissue_Sample_Gene_Expression_Profiles_up 2024-01-11 14:52:39,604 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:39,628 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:39,651 [INFO] Enrichr library gene sets already downloaded in: /home/ml4ig1/.cache/gseapy, use local file 2024-01-11 14:52:40,318 [INFO] 1941 gene_sets have been filtered out when max_size=1000 and min_size=5 2024-01-11 14:52:40,321 [INFO] 2148 gene_sets used for further statistical testing..... 2024-01-11 14:52:40,322 [INFO] Start to run GSEA...Might take a while.................. 2024-01-11 14:52:51,020 [INFO] Congratulations. GSEApy runs successfully................
['ENCODE_TF_ChIP-seq_2014__NRF1 HELA-S3', 'ENCODE_TF_ChIP-seq_2014__ETS1 A549', 'PPI_Hub_Proteins__SLC2A4', 'ENCODE_TF_ChIP-seq_2014__SIX5 A549', 'ENCODE_TF_ChIP-seq_2014__NRF1 K562', 'ENCODE_TF_ChIP-seq_2014__PML K562', 'ENCODE_TF_ChIP-seq_2014__GABP H3LA3', 'ENCODE_TF_ChIP-seq_2014__ZBTB33 A549', 'ENCODE_TF_ChIP-seq_2014__ELF1 A549', 'ENCODE_TF_ChIP-seq_2014__TRIM28 K562', 'ENCODE_TF_ChIP-seq_2014__GTF2B K562', 'ENCODE_TF_ChIP-seq_2014__MYBL2 HEPG2', 'ENCODE_TF_ChIP-seq_2014__TAF1 GM12892', 'ENCODE_TF_ChIP-seq_2014__GABP HEPG2', 'ENCODE_TF_ChIP-seq_2014__SP2 K562', 'ENCODE_TF_ChIP-seq_2014__NRF1 HEPG2', 'ENCODE_TF_ChIP-seq_2014__POL2 GM12891', 'ENCODE_TF_ChIP-seq_2014__TAF1 PFSK1', 'ENCODE_TF_ChIP-seq_2014__GABP GM12878', 'PPI_Hub_Proteins__IKBKE', 'ENCODE_TF_ChIP-seq_2014__SP1 K562', 'ENCODE_TF_ChIP-seq_2014__CREB1 K562', 'ENCODE_TF_ChIP-seq_2014__GABP HELA-S3', 'ENCODE_TF_ChIP-seq_2014__BCLAF1 K562', 'ENCODE_TF_ChIP-seq_2014__PML GM12878', 'ENCODE_TF_ChIP-seq_2014__SIX5 GM12878', 'ENCODE_TF_ChIP-seq_2014__BRCA1 GM12878', 'ENCODE_TF_ChIP-seq_2014__ELK1 K562', 'ENCODE_TF_ChIP-seq_2014__MBD4 HEPG2', 'ENCODE_TF_ChIP-seq_2014__NFIC HEPG2']
