Namespace(genes='/oak/stanford/groups/akundaje/soumyak/refs/gencode/hg38/hg38.gencode.protein_coding.tss.bed', list='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_summary/asd/encode_2024/K562_bias/encode_2024.LV.endothelial_cell.H.mean.variant_scores.tsv', out_prefix='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_annotations/asd/encode_2024/K562_bias/encode_2024.LV.endothelial_cell.H', peaks='/oak/stanford/groups/akundaje/projects/neuro-variants/data/processed/encode_2024/peaks/overlap/encode_2024.LV.endothelial_cell.H.overlap.peaks.bed.gz', schema='chrombpnet') Namespace(genes='/oak/stanford/groups/akundaje/soumyak/refs/gencode/hg38/hg38.gencode.protein_coding.tss.bed', list='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_summary/asd/encode_2024/K562_bias/encode_2024.LV.endothelial_cell.H.mean.variant_scores.tsv', out_prefix='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_annotations/asd/encode_2024/K562_bias/encode_2024.LV.endothelial_cell.H', peaks='/oak/stanford/groups/akundaje/projects/neuro-variants/data/processed/encode_2024/peaks/overlap/encode_2024.LV.endothelial_cell.H.overlap.peaks.bed.gz', schema='chrombpnet') chr pos end allele1 allele2 variant_id 44909 chr1 843979 843980 A G chr1:843980:A:G 1968 chr1 848166 848167 A G chr1:848167:A:G 1969 chr1 894776 894777 A G chr1:894777:A:G 44237 chr1 915678 915679 G A chr1:915679:G:A 1544 chr1 932169 932170 C G chr1:932170:C:G Variants table shape: (84980, 6) annotating with closest genes 0 1 2 3 4 5 6 7 8 9 \ 0 chr1 843979 843980 A G chr1:843980:A:G chr1 923923 923924 SAMD11 1 chr1 843979 843980 A G chr1:843980:A:G chr1 959308 959309 NOC2L 2 chr1 843979 843980 A G chr1:843980:A:G chr1 960584 960585 KLHL17 3 chr1 848166 848167 A G chr1:848167:A:G chr1 923923 923924 SAMD11 4 chr1 848166 848167 A G chr1:848167:A:G chr1 959308 959309 NOC2L 10 11 12 13 14 0 0 + ENSG00000187634.13 protein_coding 79944 1 0 - ENSG00000188976.11 protein_coding 115329 2 0 + ENSG00000187961.15 protein_coding 116605 3 0 + ENSG00000187634.13 protein_coding 75757 4 0 - ENSG00000188976.11 protein_coding 111142 Closest genes table shape: (254940, 15) annotating with peak overlap chr pos end allele1 allele2 variant_id 0 chr1 1133328 1133329 A G chr1:1133329:A:G 1 chr1 1201166 1201167 C A chr1:1201167:C:A 2 chr1 1574250 1574251 C A chr1:1574251:C:A 3 chr1 1616194 1616195 G A chr1:1616195:G:A 4 chr1 1906277 1906278 A G chr1:1906278:A:G Peak overlap table shape: (2735, 6) chr pos allele1 allele2 variant_id logfc.mean \ 0 chr1 3747728 T C chr1:3747728:T:C 0.012420 1 chr1 117942118 T G chr1:117942118:T:G 0.004460 2 chr1 163337297 C A chr1:163337297:C:A -0.011338 3 chr1 32951474 G C chr1:32951474:G:C 0.007524 4 chr1 214496189 G C chr1:214496189:G:C 0.053786 logfc.mean.pval abs_logfc.mean abs_logfc.mean.pval jsd.mean ... \ 0 0.589591 0.014773 0.591132 0.008628 ... 1 0.757761 0.008313 0.757744 0.010450 ... 2 0.591916 0.018278 0.591027 0.010765 ... 3 0.636812 0.013623 0.636600 0.017929 ... 4 0.205753 0.053786 0.207749 0.013929 ... logfc_x_jsd_x_active_allele_quantile.mean.pval \ 0 0.148879 1 0.575141 2 0.835580 3 0.852914 4 0.151530 abs_logfc_x_jsd_x_active_allele_quantile.mean \ 0 8.030406e-05 1 3.270358e-06 2 4.438925e-07 3 2.201515e-07 4 9.601129e-05 abs_logfc_x_jsd_x_active_allele_quantile.mean.pval closest_gene_1 \ 0 0.151491 CCDC27 1 0.574145 WDR3 2 0.834719 RGS5 3 0.851611 RNF19B 4 0.155615 PTPN14 gene_distance_1 closest_gene_2 gene_distance_2 closest_gene_3 \ 0 1267 SMIM1 25022 LRRC47 1 12397 GDAP2 12497 SPAG17 2 15506 NUF2 70720 RGS4 3 13335 TMEM54 50036 HPCA 4 56260 CENPF 106997 SMYD2 gene_distance_3 peak_overlap 0 48770 False 1 243110 False 2 268521 False 3 65479 False 4 215086 True [5 rows x 34 columns] Annotation table shape: (84980, 34) DONE Done Annotating