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/rare/encode_2024/K562_bias/encode_2024.LV.lymphocyte.H.mean.variant_scores.tsv', out_prefix='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_annotations/rare/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/rare/encode_2024/K562_bias/encode_2024.LV.lymphocyte.H.mean.variant_scores.tsv', out_prefix='/oak/stanford/groups/akundaje/projects/neuro-variants/variant_annotations/rare/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 3230544 chr1 10126 10127 A T chr1:10127:A:T 3230545 chr1 10127 10128 A G chr1:10128:A:G 3230546 chr1 10133 10134 A G chr1:10134:A:G 3230547 chr1 10451 10452 A G chr1:10452:A:G 3230548 chr1 10452 10453 C A chr1:10453:C:A Variants table shape: (9126367, 6) annotating with closest genes 0 1 2 3 4 5 6 7 8 9 10 \ 0 chr1 10126 10127 A T chr1:10127:A:T chr1 65419 65420 OR4F5 0 1 chr1 10126 10127 A T chr1:10127:A:T chr1 451677 451678 OR4F29 0 2 chr1 10126 10127 A T chr1:10127:A:T chr1 686653 686654 OR4F16 0 3 chr1 10127 10128 A G chr1:10128:A:G chr1 65419 65420 OR4F5 0 4 chr1 10127 10128 A G chr1:10128:A:G chr1 451677 451678 OR4F29 0 11 12 13 14 0 + ENSG00000186092.7 protein_coding 55293 1 - ENSG00000284733.2 protein_coding 441551 2 - ENSG00000284662.2 protein_coding 676527 3 + ENSG00000186092.7 protein_coding 55292 4 - ENSG00000284733.2 protein_coding 441550 Closest genes table shape: (27379101, 15) annotating with peak overlap chr pos end allele1 allele2 variant_id 0 chr1 180980 180981 A C chr1:180981:A:C 1 chr1 181007 181008 C G chr1:181008:C:G 2 chr1 181014 181015 G A chr1:181015:G:A 3 chr1 181128 181129 C G chr1:181129:C:G 4 chr1 181140 181141 C G chr1:181141:C:G Peak overlap table shape: (58451, 6) chr pos allele1 allele2 variant_id logfc.mean logfc.mean.pval \ 0 chr10 10394 A T chr10:10394:A:T -0.002737 0.735931 1 chr10 10418 A C chr10:10418:A:C -0.000798 0.700724 2 chr10 10532 G A chr10:10532:G:A 0.006232 0.587037 3 chr10 10573 G A chr10:10573:G:A -0.017746 0.335201 4 chr10 10663 G C chr10:10663:G:C 0.011473 0.414606 abs_logfc.mean abs_logfc.mean.pval jsd.mean ... \ 0 0.005127 0.705550 0.003354 ... 1 0.005683 0.678835 0.007329 ... 2 0.006232 0.638133 0.005919 ... 3 0.017746 0.300153 0.008333 ... 4 0.011473 0.459262 0.010182 ... logfc_x_jsd_x_active_allele_quantile.mean.pval \ 0 0.605152 1 0.462900 2 0.354978 3 0.182124 4 0.169644 abs_logfc_x_jsd_x_active_allele_quantile.mean \ 0 0.000011 1 0.000029 2 0.000025 3 0.000104 4 0.000092 abs_logfc_x_jsd_x_active_allele_quantile.mean.pval closest_gene_1 \ 0 0.576510 TUBB8 1 0.441870 TUBB8 2 0.398290 TUBB8 3 0.159634 TUBB8 4 0.196176 TUBB8 gene_distance_1 closest_gene_2 gene_distance_2 closest_gene_3 \ 0 63769 ZMYND11 119695 DIP2C 1 63745 ZMYND11 119671 DIP2C 2 63631 ZMYND11 119557 DIP2C 3 63590 ZMYND11 119516 DIP2C 4 63500 ZMYND11 119426 DIP2C gene_distance_3 peak_overlap 0 679274 False 1 679250 False 2 679136 False 3 679095 False 4 679005 False [5 rows x 34 columns] Annotation table shape: (9126367, 34) DONE Done Annotating