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.lymphocyte.H.mean.variant_scores.tsv', out_prefix='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_annotations/asd/encode_2024/K562_bias/encode_2024.LV.lymphocyte.H', peaks='/oak/stanford/groups/akundaje/projects/neuro-variants/data/processed/encode_2024/peaks/overlap/encode_2024.LV.lymphocyte.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.lymphocyte.H.mean.variant_scores.tsv', out_prefix='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_annotations/asd/encode_2024/K562_bias/encode_2024.LV.lymphocyte.H', peaks='/oak/stanford/groups/akundaje/projects/neuro-variants/data/processed/encode_2024/peaks/overlap/encode_2024.LV.lymphocyte.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 1616194 1616195 G A chr1:1616195:G:A 1 chr1 2049922 2049923 G T chr1:2049923:G:T 2 chr1 3384558 3384559 A C chr1:3384559:A:C 3 chr1 10210431 10210432 C G chr1:10210432:C:G 4 chr1 10677083 10677084 C T chr1:10677084:C:T Peak overlap table shape: (891, 6) chr pos allele1 allele2 variant_id logfc.mean \ 0 chr1 3747728 T C chr1:3747728:T:C 0.002271 1 chr1 117942118 T G chr1:117942118:T:G 0.005915 2 chr1 163337297 C A chr1:163337297:C:A -0.007140 3 chr1 32951474 G C chr1:32951474:G:C 0.016367 4 chr1 214496189 G C chr1:214496189:G:C 0.005256 logfc.mean.pval abs_logfc.mean abs_logfc.mean.pval jsd.mean ... \ 0 0.485390 0.011269 0.486602 0.010422 ... 1 0.668542 0.005915 0.668859 0.007682 ... 2 0.610987 0.007140 0.609460 0.006864 ... 3 0.341742 0.016725 0.347895 0.012014 ... 4 0.689913 0.005625 0.690654 0.008191 ... logfc_x_jsd_x_active_allele_quantile.mean.pval \ 0 0.251429 1 0.823930 2 0.797967 3 0.324646 4 0.583560 abs_logfc_x_jsd_x_active_allele_quantile.mean \ 0 0.000089 1 0.000002 2 0.000002 3 0.000048 4 0.000011 abs_logfc_x_jsd_x_active_allele_quantile.mean.pval closest_gene_1 \ 0 0.255236 CCDC27 1 0.826796 WDR3 2 0.793727 RGS5 3 0.335856 RNF19B 4 0.591738 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 False [5 rows x 34 columns] Annotation table shape: (84980, 34) DONE Done Annotating