dc1e0e76dbe49861bd0ebe8db64e27f587737794 max Mon Mar 30 15:40:03 2026 -0700 adding two more phased variants tracks, refs #37306 diff --git src/hg/makeDb/doc/hg38/varFreqs.txt src/hg/makeDb/doc/hg38/varFreqs.txt index e7f35b77bcc..7de0e6a41e4 100644 --- src/hg/makeDb/doc/hg38/varFreqs.txt +++ src/hg/makeDb/doc/hg38/varFreqs.txt @@ -1,217 +1,227 @@ # Mexico Biobank, Max, Nov 8 2025 CrossMap.py vcf /gbdb/hg19/liftOver/hg19ToHg38.over.chain.gz /hive /data/genomes/hg19/bed/varFreqs/mexbb/MXBv2.vcf.gz /hive/data/genomes/hg38/p14Clean/hg38.p14.fa MXBv2.lift.hg19ToHg38.vcf && bgzip MXBv2.lift.hg19ToHg38.vcf && bcftools sort MXBv2.lift.hg19ToHg38.vcf -Oz -m 200G -T /data/tmp/ -o MXBv2.lift.hg19ToHg38.vcf.gz && tabix -p vcf MXBv2.lift.hg19ToHg38.vcf.gz # Mexico City Prospective study, Max Oct 28 2025 cd /hive/data/genomes/hg38/bed/varFreqs/mcps/ for i in `seq 1 22` X; do wget https://rgc-mcps.regeneron.com/downloads/20230130/chr$i.freq.vcf.gz; done for i in `seq 1 22` X; do wget https://rgc-mcps.regeneron.com/downloads/20230130/chr$i.freq.vcf.gz.tbi; done mv *vcf* vcf/ bcftools concat --threads 16 -Oz -o mcps.freq.vcf.gz vcf/chr{1..22}.freq.vcf.gz vcf/chrX.freq.vcf.gz # make normal AC and AF and AN fields for mouseovers zcat mcps.freq.vcf.gz | sed -e 's/_RAW//g' > mcps.fix.freq.vcf mv -f mcps.fix.freq.vcf mcps.freq.vcf bgzip mcps.freq.vcf tabix -p vcf mcps.freq.vcf.gz # Regeneron million exomes, Max, Nov 3 2025 cd /hive/data/genomes/hg38/bed/varFreqs/me for i in `seq 1 22` X Y; do wget https://rgc-research.regeneron.com/me/downloads/20231004/rgc_me_variant_frequencies_chr${i}_20231004.vcf.gz.tbi; done bcftools concat --threads 10 -Oz -o rgc_me_freqs_20231004.vcf.gz rgc_me_variant_frequencies_chr{1..22}_20231004.vcf.gz rgc_me_variant_frequencies_chrX_20231004.vcf.gz rgc_me_variant_frequencies_chrY_20231004.vcf.gz zcat rgc_me_freqs_20231004.vcf.gz | sed -e 's/ALL_//g' > rgc_me_freqs_20231004.fix.vcf tabix -p vcf rgc_me_freqs_20231004.vcf.gz # GA south asia 100k pilot cd /hive/data/genomes/hg38/bed/varFreqs/ga100k/ parallel -j 8 wget -q --no-check-certificate https://browser.genomeasia100k.org/service/web/download_files/{}.substitutions.annot.cont_withmaf.vcf.gz ::: {1..22} X Y # fix the header line, remove "FORMAT" for i in *.vcf.gz; do echo "zcat $i | awk 'BEGIN{OFS=\"\\t\"} /^#CHROM/{NF=8; print; next} /^#/ {print; next} {NF=8; print}' | bgzip -c > fixed/$i" >> cmds.txt; done parallel -j 8 < cmds.txt bcftools concat --threads 16 -Oz -o ../ga100k.subst.vcf.gz fixed/{1..22}.substitutions.annot.cont_withmaf.vcf.gz # add indels wget -q --no-check-certificate https://browser.genomeasia100k.org/service/web/download_files/All.indels.annot.cont_withmaf.vcf.gz # index tabix -p vcf ../ga100k*.vcf.gz tabix -p vcf All*.vcf.gz # TOPMED Freeze 10 cd /hive/data/genomes/hg38/bed/varFreqs/topmed/ # need to download the VCFs manually, 22 VCFs, with one time links from https://bravo.sph.umich.edu/vcfs.html # grrrr... bcftools concat --threads 10 -Oz -o topmed10.vcf.gz {1..22}.vcf.gz X.vcf.gz tabix -p vcf topmed10.vcf.gz # Abraom brazil # get unique download link from https://abraom.ib.usp.br/download/index.php cd /hive/data/genomes/hg38/bed/varFreqs/abraom/ wget 'https://abraom.ib.usp.br/download/download-files.php?fid=RklEMTIzNDU2&key=1762266466-key690a0d62348de0.22872232' -O abraom.tar tar xvfz abraom.tar ln -s /hive/data/genomes/hg38/p14Clean/hg38.p14.fa samtools faidx hg38.p14.fa python ~/kent/src/hg/makeDb/scripts/varFreqs/abraomToVcf.py SABE1171.Abraom.clean.tsv abraom.vcf hg38.p14.fa tabix -p vcf abraom.vcf.gz # SGDP cd /hive/data/genomes/hg38/bed/varFreqs/sgp/ CrossMap.py vcf /gbdb/hg19/liftOver/hg19ToHg38.over.chain.gz /hive/data/genomes/hg19/bed/varFreqs/sgdp/SGDP.nh2.vcf.gz hg38.p14.fa sgdp.hg38.nh2.vcf bgzip sgdp.hg38.nh2.vcf bcftools sort sgdp.hg38.nh2.vcf.gz -Oz -m 200G -T /data/tmp/ -o sgdp.hg38.nh2.sort.vcf.gz mv sgdp.hg38.nh2.sort.vcf.gz SGDP.nh2.vcf.gz tabix -p vcf SGDP.nh2.vcf.gz # KOVA cd /hive/data/genomes/hg38/bed/varFreqs/sgp/ # got tsv file via google drive link from 장인수 <insoo078@kribb.re.kr> # VCF converter, written by Claude Opus 4.1 using 2 lines of example input python ~/kent/src/hg/makeDb/scripts/varFreqs/kovaToVcf.py 1_KOVA.v7.tsv.gz kova.v7.vcf bgzip kova.v7.vcf tabix -p vcf kova.v7.vcf.gz # NPM Singapore cd /hive/data/genomes/hg38/bed/varFreqs/npm/ # downloaded data manually from chorus website, https://chorus.grids-platform.io/vcfdl bcftools concat --threads 10 -Oz -o SG10K_Health_r5.3.2.sites.vcf.bgz SG10K_Health_r5.3.2.sites.chr{1..22}.vcf.bgz SG10K_Health_r5.3.2.sites.chrX.vcf.bgz SG10K_Health_r5.3.2.sites.chrY.vcf.bgz tabiv -p vcf SG10K_Health_r5.3.2.sites.vcf.bgz # Saudi 300 genomes cd /hive/data/genomes/hg38/bed/varFreqs/saudi wget https://figshare.com/ndownloader/files/51297884 -O 51297884.tsv.gz python3 ~/kent/src/hg/makeDb/scripts/varFreqs/saudiToVcf.py bgzip saudi.vcf tabix -p vcf saudi.vcf.gz # SFARI SPARK cd /hive/data/genomes/hg38/bed/varFreqs/sparkExomes/ # used globus to download into vcf/ sh ~/kent/src/hg/makeDb/scripts/varFreqs/sparkMergeVcfAddCounts.sh vcf/SPARK.iWES_v3.2024_08.deepvariant 8 bcftools norm -m- SPARK.iWES_v3.2024_08.deepvariant.sites.vcf.gz -Oz > SPARK.iWES_v3.2024_08.deepvariant.norm.vcf.gz && tabix -p vcf SPARK.iWES_v3.2024_08.deepvariant.norm.vcf.gz cd /hive/data/genomes/hg38/bed/varFreqs/sparkWgs/ # used globus to download into vcf/ sh ~/kent/src/hg/makeDb/scripts/varFreqs/sparkMergeVcfAddCounts.sh vcf/wgs_12519_genome.deepvariant 8 bcftools norm -m- wgs_12519_genome.deepvariant.sites.vcf.gz -Oz > wgs_12519_genome.deepvariant.norm.vcf.gz tabix -p vcf wgs_12519_genome.deepvariant.norm.vcf.gz # NCBI ALFA bigBed to VCF, Max Jan 26 2026 # Source: ALFA R4 bigBed files, 904M variants, output 163M with non-zero AF cd /hive/data/genomes/hg38/bed/varFreqs/alfa python3 ~/kent/src/hg/makeDb/scripts/varFreqs/alfa_to_vcf.py --out ALFA.vcf --zero-af-file ALFA_zero.txt # Compress and index bgzip ALFA.vcf tabix -p vcf ALFA.vcf.gz # Final: 2.7GB, 163M variants (146M SNPs, 17M indels), ALFA_zero.txt has 26GB of zero-AF variants # HRC (Haplotype Reference Consortium), Claude max, Mar 17 2026 # Source: HRC.r1-1.GRCh37.wgs.mac5.sites.tab.gz # 40M variants from 32,488 WGS samples, originally on GRCh37 cd /hive/data/genomes/hg38/bed/varFreqs/hrc/ # download HRC.r1-1.GRCh37.wgs.mac5.sites.tab.gz from http://www.haplotype-reference-consortium.org/site python3 ~/kent/src/hg/makeDb/scripts/varFreqs/hrcToVcf.py # 40,405,505 variants read, 8,052 unmapped, 40,397,453 lifted to hg38 # sort, compress, index bcftools sort hrc.vcf -Oz -o hrc.vcf.gz tabix -p vcf hrc.vcf.gz rm hrc.vcf ln -s /hive/data/genomes/hg38/bed/varFreqs/hrc/hrc.vcf.gz /gbdb/hg38/varFreqs/hrc/hrc.vcf.gz ln -s /hive/data/genomes/hg38/bed/varFreqs/hrc/hrc.vcf.gz.tbi /gbdb/hg38/varFreqs/hrc/hrc.vcf.gz.tbi # Australia, Max, Jan 2026 # received files from m.hobbs@garvan.org.au cd /hive/data/genomes/hg38/bed/varFreqs/mgrb/ bcftools norm -f hg38.fa -m-any MGRB.phase3.GRCh38.vcf.gz -o MGRB.phase3.GRCh38.norm.vcf.gz tabix MGRB.phase3.GRCh38.norm.vcf.gz # SCHEMA Schizophrenia Exome Meta-Analysis track for hg38, Max, Jan 22 2026 # source: https://schema.broadinstitute.org/ # Original is in hg19/GRCh37 coordinates cd /hive/data/genomes/hg38/bed/varFreqs/schema # SCHEMA_variant_results.vcf.bgz (384M, hg19 coordinates) # Step 1: Add AC, AN, AF fields by summing case+control counts ~/kent/src/hg/makeDb/scripts/varFreqs/schema_addAcAnAf.py bgzip SCHEMA_variant_results_withAF.vcf tabix -p vcf SCHEMA_variant_results_withAF.vcf.gz # Step 2: Liftover from hg19 to hg38 # prep hg38 reference FASTA zcat /usr/local/apache/htdocs-hgdownload/goldenPath/hg38/bigZips/hg38.fa.gz > hg38.fa samtools faidx hg38.fa CrossMap.py vcf /gbdb/hg19/liftOver/hg19ToHg38.over.chain.gz \ SCHEMA_variant_results_withAF.vcf.gz \ hg38.fa \ SCHEMA_variant_results_hg38.vcf # Output stats: Total entries: 8865268, Failed to map: 780 # Sort grep "^#" SCHEMA_variant_results_hg38.vcf > SCHEMA_variant_results_hg38_sorted.vcf grep -v "^#" SCHEMA_variant_results_hg38.vcf | sort -k1,1V -k2,2n >> SCHEMA_variant_results_hg38_sorted.vcf # Compress and index bgzip SCHEMA_variant_results_hg38_sorted.vcf tabix -p vcf SCHEMA_variant_results_hg38_sorted.vcf.gz # Clean up temporary files rm -f SCHEMA_variant_results_hg38.vcf SCHEMA_variant_results_hg38.vcf.unmap hg38.fa hg38.fa.fai # Gregor rare disease project, Max, Mar 2026 cd /hive/data/genomes/hg38/bed/varFreqs/gregor/ # Downloaded from G Drive, pointed to by Jon Bernstein, Stanford # https://drive.google.com/drive/folders/1v-BnW7nKcEjF-NyLqU1Up3YJuP5KJJAg # created symlink into my UCSC G Drive, then used rclone rclone copy mhaeussldrive:RO4 ./ bcftools concat --threads 16 -Oz -o gregor.vcf.gz chr{1..22}.vcf.gz chrX.vcf.gz chrY.vcf.gz tabix -p vcf gregor.vcf.gz # output ~20 GB, took 10 minutes. # HGDP1k data from the phased Vars track, Max/Claude, Mar 18 2026 # Just flattening what we have and reducing details # Source: 3.2TB VCF with 4094 genomes and per-population INFO fields for 80 populations # Strip genotypes and keep only overall + continental group fields (drop per-population-per-sex) # Already has chr prefix, no rename needed # Note: first attempt kept all fields -> 169GB, too large. This version keeps only continental groups. cd /hive/data/genomes/hg38/bed/varFreqs/hgdp1kFreq/ KEEP="INFO/AC,INFO/AF,INFO/AN,INFO/nhomalt,INFO/gnomad_AC,INFO/gnomad_AF,INFO/gnomad_AN,INFO/gnomad_AC_afr,INFO/gnomad_AF_a fr,INFO/gnomad_AN_afr,INFO/gnomad_AC_ami,INFO/gnomad_AF_ami,INFO/gnomad_AN_ami,INFO/gnomad_AC_amr,INFO/gnomad_AF_amr,INFO/g nomad_AN_amr,INFO/gnomad_AC_asj,INFO/gnomad_AF_asj,INFO/gnomad_AN_asj,INFO/gnomad_AC_eas,INFO/gnomad_AF_eas,INFO/gnomad_AN_ eas,INFO/gnomad_AC_fin,INFO/gnomad_AF_fin,INFO/gnomad_AN_fin,INFO/gnomad_AC_mid,INFO/gnomad_AF_mid,INFO/gnomad_AN_mid,INFO/ gnomad_AC_nfe,INFO/gnomad_AF_nfe,INFO/gnomad_AN_nfe,INFO/gnomad_AC_oth,INFO/gnomad_AF_oth,INFO/gnomad_AN_oth,INFO/gnomad_AC _sas,INFO/gnomad_AF_sas,INFO/gnomad_AN_sas,INFO/gnomad_popmax,INFO/gnomad_faf95_popmax" # This took days to complete, so asked Claude to make it parallel #bcftools view -G /gbdb/hg38/phasedVars/hgdp1k/gnomad.genomes.v3.1.2.hgdp_tgp.vcf.gz --threads 8 \ #| bcftools annotate -x "^${KEEP}" -Oz --threads 4 -o hgdp1k.freq.vcf.gz # use 30 threads, and chunks of 50 Mbp sh ~/kent/src/hg/makeDb/scripts/varFreqs/vcfFilterParallel.sh /gbdb/hg38/phasedVars/hgdp1k/gnomad.genomes.v3.1.2.hgdp_tgp.vcf.gz hgdp1k.freq.parallel.vcf.gz "$KEEP" 30 50 & tabix -p vcf hgdp1k.freq.vcf.gz # Swefreq, Max, Feb 2026 # downloaded files from https://swefreq.nbis.se/dataset/SweGen/download # Access was approved through the website, but I emailed swefreq@scilifelab.se, it needed a reminder email # Also got email from adam.ameur@igp.uu.se with followup info and do-no-allow-downloads instruction cd /hive/data/genomes/hg38/bed/varFreqs/swefreq # Indigenomes, Max Jan 2026 # downloaded from https://clingen.igib.res.in/indigen/, used as-is cd /hive/data/genomes/hg38/bed/varFreqs/indigenomes/ # Japan Tommo 60k, Max Jan 2026 # downloaded from https://jmorp.megabank.tohoku.ac.jp/downloads cd /hive/data/genomes/hg38/bed/varFreqs/tommo61kjpn/ # copied urls from website wget -i urls.txt bcftools concat --threads 16 -Oz -o tommo-61kjpn-20250616-GRCh38-snvindel-af-autosome.vcf.gz \ tommo-61kjpn-20250616-GRCh38-snvindel-af-autosome-chr{1..22}.vcf.gz tabix -p vcf tommo-61kjpn-20250616-GRCh38-snvindel-af-autosome.vcf.gz # FinnGen, Max/Claude, Jan 2026 cd /hive/data/genomes/hg38/bed/varFreqs/finngen/ # Source TSV was downloaded from FinnGen (via email link from Google Cloud bucket) # finnge_R12_annotated_variants_v1.gz (32 GB TSV) # Convert TSV to VCF using custom Python script (written by Claude Opus 4.5) python ~/kent/src/hg/makeDb/scripts/varFreqs/finngen_to_vcf.py \ finnge_R12_annotated_variants_v1.gz \ finnge_R12_annotated_variants_v1.vcf # Compress and index bgzip finnge_R12_annotated_variants_v1.vcf -@8 tabix -p vcf finnge_R12_annotated_variants_v1.vcf.gz # All of Us, Max Feb 2026 # Received from Qudsi at UCSC in the Ioannidis group via phoenix # only concated and ran tabix on it cd /hive/data/genomes/hg38/bed/varFreqs/allofus/ bcftools concat --threads 16 -Oz -o allOfUs.locAncFreq.vcf.gz clean/allele_freq_chr{1..22}.NW.clean.conf90.oneline.vcf.gz tabix allOfUs.locAncFreq.vcf.gz + +########## +# 2026-03-27 Claude max + +# Two phased SV VCF tracks moved into phasedVars superTrack from lrSv: +# - han945SvVcf: Per-sample genotypes for 945 Han Chinese SVs +# - lrSv1kgOntPhased: Phased SVs from 1,019 diverse humans (1KG ONT) +# Data files remain in /hive/data/genomes/hg38/bed/lrSv/ +# Symlinks moved from /gbdb/{hg38,hs1}/lrSv/ to /gbdb/{hg38,hs1}/phasedVars/ +# Build documentation for these tracks is in lrSv.txt