99764ad55bb121d285e9734de955bba41802ad06
max
  Wed Jul 15 23:35:19 2026 -0700
varFreqs: add gnomAD-Canada HostSeq SNV frequencies and fold into combined tracks, refs #36642

#Preview2 week - bugs introduced now will need a build patch to fix
New "hostseq" vcfTabix subtrack of the SNV Frequencies container:
gnomAD-Canada v1.0 / HostSeq, 10,487 Canadian COVID-19 WGS genomes on hg38.
The release ships only as a ~104 GB Hail table, so hostseqHtToVcf.py reads it
with Hail and flattens the freq array into a sites-only VCF with overall +
9 gnomAD ancestry-group AC/AN/AF, nhomalt, grpmax, dbSNP rsID and the variant
filter status. 232,028,491 release rows -> 213,382,086 written (18,646,405 AC0
sites dropped).

Registered HostSeq (is_disease=0) in databases.tsv and its 9 ancestry groups
in populations.tsv, and rebuilt varFreqsAffected/varFreqsBackground so HostSeq
feeds the background side (29 cohorts, 185 fields; merged set 1,374,129,993
variants). Added HostSeq to filterValues.backgroundSources.

diff --git src/hg/makeDb/trackDb/human/varFreqs.ra src/hg/makeDb/trackDb/human/varFreqs.ra
index c9d117642e9..62b6832f96e 100644
--- src/hg/makeDb/trackDb/human/varFreqs.ra
+++ src/hg/makeDb/trackDb/human/varFreqs.ra
@@ -10,31 +10,31 @@
         track varFreqsAffected
         shortLabel Disease cohorts
         longLabel SNV Frequencies: variants in ~130,000 affected or case individuals (autism, schizophrenia, rare disease cohorts)
         type bigBed 9 +
         parent varFreqs on
         bigDataUrl /gbdb/$D/varFreqs/_affected/varFreqsAffected.bb
         tableBrowser off
         visibility pack
         itemRgb on
         maxWindowToDraw 5000000
         priority 0.11
         mouseOver <b>Var:</b> ${name}<br><b>AA change:</b> ${aaChange}<br><b>Var type:</b> ${varType}<br><b>Conseq:</b> ${consequence}<br><b>Affected AF:</b> ${affectedAF}<br><b>Affected AC/AN:</b> ${affectedAC} / ${affectedAN}<br><b>Affected cohorts:</b> ${affectedCohorts}<br><b>Top affected by AF:</b> ${topAffectedSources}<br><b>Background AF:</b> ${backgroundAF}
         filterValues.affectedCohorts SPARK|SFARI SPARK WES,SFARI_WGS|SFARI SPARK WGS,GREGoR|GREGoR,SCHEMA|SCHEMA,GA4K|GA4K PacBio LR
         filterType.affectedCohorts multipleListOr
         filterLabel.affectedCohorts Affected/case cohort
-        filterValues.backgroundSources AllOfUs|AllOfUs,SPARK|SFARI SPARK WES,SFARI_WGS|SFARI SPARK WGS,GenomeAsia|GenomeAsia SNVs,GenomeAsiaIndel|GenomeAsia Indels,NPM|NPM Singapore,KOVA|KOVA Korea,ToMMo|ToMMo Japan,FinnGen|FinnGen Finland,Saudi|Saudi,SweGen|SweGen Sweden,TOPMed|TOPMed,ABraOM|ABraOM Brazil,ALFA|ALFA,MGRB|MGRB Australia,HRC|HRC,SGDP|SGDP,HGDP1kG|gnomAD HGDP+1kG,GREGoR|GREGoR,SCHEMA|SCHEMA,CoLoRSdb|CoLoRSdb PacBio LR,SVatalog|SVatalog 101 10XG SR,Tishkoff180|Tishkoff 180 African WGS,WBBC|WBBC China,ChinaMAP|China ChinaMAP,GenomeIndia|GenomeIndia 9.7k WGS,GoNL|GoNL Netherlands ~13x SR
+        filterValues.backgroundSources AllOfUs|AllOfUs,SPARK|SFARI SPARK WES,SFARI_WGS|SFARI SPARK WGS,GenomeAsia|GenomeAsia SNVs,GenomeAsiaIndel|GenomeAsia Indels,NPM|NPM Singapore,KOVA|KOVA Korea,ToMMo|ToMMo Japan,FinnGen|FinnGen Finland,Saudi|Saudi,SweGen|SweGen Sweden,TOPMed|TOPMed,ABraOM|ABraOM Brazil,ALFA|ALFA,MGRB|MGRB Australia,HRC|HRC,SGDP|SGDP,HGDP1kG|gnomAD HGDP+1kG,GREGoR|GREGoR,SCHEMA|SCHEMA,CoLoRSdb|CoLoRSdb PacBio LR,SVatalog|SVatalog 101 10XG SR,Tishkoff180|Tishkoff 180 African WGS,WBBC|WBBC China,ChinaMAP|China ChinaMAP,GenomeIndia|GenomeIndia 9.7k WGS,GoNL|GoNL Netherlands ~13x SR,HostSeq|HostSeq Canada
         filterType.backgroundSources multipleListOr
         filterLabel.backgroundSources Background source (population or unaffected)
         # Variant type and consequence filters
         filterValues.varType SNV|SNV,INS|Insertion,DEL|Deletion,MNV|MNV
         filterLabel.varType Variant Type
         filterValues.consequence missense|Missense,synonymous|Synonymous,stop_gained|Stop Gained,frameshift|Frameshift,splice_donor|Splice Donor,splice_acceptor|Splice Acceptor,intron|Intron,3_prime_utr|3' UTR,5_prime_utr|5' UTR,non_coding|Non-coding,.|Intergenic,others|Other
         filterType.consequence multipleListOr
         filterLabel.consequence Consequence
         # Length filters
         filterByRange.refLen on
         filterLabel.refLen Reference Length
         filter.refLen 1:28037
         filterLimits.refLen 1:28037
         filterByRange.altLen on
         filterLabel.altLen Alternate Length
@@ -176,30 +176,34 @@
         # filterLabel.WBBCAF WBBC China AF
         # filter.WBBCAF 0:1
         # filterLimits.WBBCAF 0:1
         # filterByRange.ChinaMAPAF on
         # filterLabel.ChinaMAPAF China ChinaMAP AF
         # filter.ChinaMAPAF 0:1
         # filterLimits.ChinaMAPAF 0:1
         # filterByRange.GenomeIndiaAF on
         # filterLabel.GenomeIndiaAF GenomeIndia 9.7k WGS AF
         # filter.GenomeIndiaAF 0:1
         # filterLimits.GenomeIndiaAF 0:1
         # filterByRange.GoNLAF on
         # filterLabel.GoNLAF GoNL Netherlands ~13x SR AF
         # filter.GoNLAF 0:1
         # filterLimits.GoNLAF 0:1
+        # filterByRange.HostSeqAF on
+        # filterLabel.HostSeqAF HostSeq Canada AF
+        # filter.HostSeqAF 0:1
+        # filterLimits.HostSeqAF 0:1
         # Per-database AC filters (commented out: re-enable as needed)
         # filterByRange.AllOfUsAC on
         # filterLabel.AllOfUsAC AllOfUs AC
         # filter.AllOfUsAC 0:2000000
         # filterLimits.AllOfUsAC 0:2000000
         # filterByRange.SPARKAC on
         # filterLabel.SPARKAC SFARI SPARK WES AC
         # filter.SPARKAC 0:2000000
         # filterLimits.SPARKAC 0:2000000
         # filterByRange.SFARI_WGSAC on
         # filterLabel.SFARI_WGSAC SFARI SPARK WGS AC
         # filter.SFARI_WGSAC 0:2000000
         # filterLimits.SFARI_WGSAC 0:2000000
         # filterByRange.GenomeAsiaAC on
         # filterLabel.GenomeAsiaAC GenomeAsia SNVs AC
@@ -289,30 +293,34 @@
         # filterLabel.WBBCAC WBBC China AC
         # filter.WBBCAC 0:2000000
         # filterLimits.WBBCAC 0:2000000
         # filterByRange.ChinaMAPAC on
         # filterLabel.ChinaMAPAC China ChinaMAP AC
         # filter.ChinaMAPAC 0:2000000
         # filterLimits.ChinaMAPAC 0:2000000
         # filterByRange.GenomeIndiaAC on
         # filterLabel.GenomeIndiaAC GenomeIndia 9.7k WGS AC
         # filter.GenomeIndiaAC 0:2000000
         # filterLimits.GenomeIndiaAC 0:2000000
         # filterByRange.GoNLAC on
         # filterLabel.GoNLAC GoNL Netherlands ~13x SR AC
         # filter.GoNLAC 0:2000000
         # filterLimits.GoNLAC 0:2000000
+        # filterByRange.HostSeqAC on
+        # filterLabel.HostSeqAC HostSeq Canada AC
+        # filter.HostSeqAC 0:2000000
+        # filterLimits.HostSeqAC 0:2000000
         # Population-specific AF/AC filters (commented out: re-enable as needed)
         # AllOfUs populations
         # filterByRange.AllOfUsAF_AFR on
         # filterLabel.AllOfUsAF_AFR AllOfUs African AF
         # filter.AllOfUsAF_AFR 0:1
         # filterLimits.AllOfUsAF_AFR 0:1
         # filterByRange.AllOfUsAF_AMR on
         # filterLabel.AllOfUsAF_AMR AllOfUs Indigenous American AF
         # filter.AllOfUsAF_AMR 0:1
         # filterLimits.AllOfUsAF_AMR 0:1
         # filterByRange.AllOfUsAF_EAS on
         # filterLabel.AllOfUsAF_EAS AllOfUs East Asian AF
         # filter.AllOfUsAF_EAS 0:1
         # filterLimits.AllOfUsAF_EAS 0:1
         # filterByRange.AllOfUsAF_EUR on
@@ -628,31 +636,31 @@
         track varFreqsBackground
         shortLabel Population reference
         longLabel SNV Frequencies: variants in ~1.5 million individuals from population cohorts and unaffected or control arms
         type bigBed 9 +
         parent varFreqs on
         bigDataUrl /gbdb/$D/varFreqs/_background/varFreqsBackground.bb
         tableBrowser off
         visibility pack
         itemRgb on
         maxWindowToDraw 5000000
         priority 0.1
         mouseOver <b>Var:</b> ${name}<br><b>AA change:</b> ${aaChange}<br><b>Var type:</b> ${varType}<br><b>Conseq:</b> ${consequence}<br><b>Background AF:</b> ${backgroundAF}<br><b>Background AC/AN:</b> ${backgroundAC} / ${backgroundAN}<br><b>Sources:</b> ${backgroundSources}<br><b>Top population sources by AF:</b> ${topBackgroundSources}<br><b>Affected AF:</b> ${affectedAF}
         filterValues.affectedCohorts SPARK|SFARI SPARK WES,SFARI_WGS|SFARI SPARK WGS,GREGoR|GREGoR,SCHEMA|SCHEMA,GA4K|GA4K PacBio LR
         filterType.affectedCohorts multipleListOr
         filterLabel.affectedCohorts Affected/case cohort
-        filterValues.backgroundSources AllOfUs|AllOfUs,SPARK|SFARI SPARK WES,SFARI_WGS|SFARI SPARK WGS,GenomeAsia|GenomeAsia SNVs,GenomeAsiaIndel|GenomeAsia Indels,NPM|NPM Singapore,KOVA|KOVA Korea,ToMMo|ToMMo Japan,FinnGen|FinnGen Finland,Saudi|Saudi,SweGen|SweGen Sweden,TOPMed|TOPMed,ABraOM|ABraOM Brazil,ALFA|ALFA,MGRB|MGRB Australia,HRC|HRC,SGDP|SGDP,HGDP1kG|gnomAD HGDP+1kG,GREGoR|GREGoR,SCHEMA|SCHEMA,CoLoRSdb|CoLoRSdb PacBio LR,SVatalog|SVatalog 101 10XG SR,Tishkoff180|Tishkoff 180 African WGS,WBBC|WBBC China,ChinaMAP|China ChinaMAP,GenomeIndia|GenomeIndia 9.7k WGS,GoNL|GoNL Netherlands ~13x SR
+        filterValues.backgroundSources AllOfUs|AllOfUs,SPARK|SFARI SPARK WES,SFARI_WGS|SFARI SPARK WGS,GenomeAsia|GenomeAsia SNVs,GenomeAsiaIndel|GenomeAsia Indels,NPM|NPM Singapore,KOVA|KOVA Korea,ToMMo|ToMMo Japan,FinnGen|FinnGen Finland,Saudi|Saudi,SweGen|SweGen Sweden,TOPMed|TOPMed,ABraOM|ABraOM Brazil,ALFA|ALFA,MGRB|MGRB Australia,HRC|HRC,SGDP|SGDP,HGDP1kG|gnomAD HGDP+1kG,GREGoR|GREGoR,SCHEMA|SCHEMA,CoLoRSdb|CoLoRSdb PacBio LR,SVatalog|SVatalog 101 10XG SR,Tishkoff180|Tishkoff 180 African WGS,WBBC|WBBC China,ChinaMAP|China ChinaMAP,GenomeIndia|GenomeIndia 9.7k WGS,GoNL|GoNL Netherlands ~13x SR,HostSeq|HostSeq Canada
         filterType.backgroundSources multipleListOr
         filterLabel.backgroundSources Background source (population or unaffected)
         # Variant type and consequence filters
         filterValues.varType SNV|SNV,INS|Insertion,DEL|Deletion,MNV|MNV
         filterLabel.varType Variant Type
         filterValues.consequence missense|Missense,synonymous|Synonymous,stop_gained|Stop Gained,frameshift|Frameshift,splice_donor|Splice Donor,splice_acceptor|Splice Acceptor,intron|Intron,3_prime_utr|3' UTR,5_prime_utr|5' UTR,non_coding|Non-coding,.|Intergenic,others|Other
         filterType.consequence multipleListOr
         filterLabel.consequence Consequence
         # Length filters
         filterByRange.refLen on
         filterLabel.refLen Reference Length
         filter.refLen 1:28037
         filterLimits.refLen 1:28037
         filterByRange.altLen on
         filterLabel.altLen Alternate Length
@@ -794,30 +802,34 @@
         # filterLabel.WBBCAF WBBC China AF
         # filter.WBBCAF 0:1
         # filterLimits.WBBCAF 0:1
         # filterByRange.ChinaMAPAF on
         # filterLabel.ChinaMAPAF China ChinaMAP AF
         # filter.ChinaMAPAF 0:1
         # filterLimits.ChinaMAPAF 0:1
         # filterByRange.GenomeIndiaAF on
         # filterLabel.GenomeIndiaAF GenomeIndia 9.7k WGS AF
         # filter.GenomeIndiaAF 0:1
         # filterLimits.GenomeIndiaAF 0:1
         # filterByRange.GoNLAF on
         # filterLabel.GoNLAF GoNL Netherlands ~13x SR AF
         # filter.GoNLAF 0:1
         # filterLimits.GoNLAF 0:1
+        # filterByRange.HostSeqAF on
+        # filterLabel.HostSeqAF HostSeq Canada AF
+        # filter.HostSeqAF 0:1
+        # filterLimits.HostSeqAF 0:1
         # Per-database AC filters (commented out: re-enable as needed)
         # filterByRange.AllOfUsAC on
         # filterLabel.AllOfUsAC AllOfUs AC
         # filter.AllOfUsAC 0:2000000
         # filterLimits.AllOfUsAC 0:2000000
         # filterByRange.SPARKAC on
         # filterLabel.SPARKAC SFARI SPARK WES AC
         # filter.SPARKAC 0:2000000
         # filterLimits.SPARKAC 0:2000000
         # filterByRange.SFARI_WGSAC on
         # filterLabel.SFARI_WGSAC SFARI SPARK WGS AC
         # filter.SFARI_WGSAC 0:2000000
         # filterLimits.SFARI_WGSAC 0:2000000
         # filterByRange.GenomeAsiaAC on
         # filterLabel.GenomeAsiaAC GenomeAsia SNVs AC
@@ -907,30 +919,34 @@
         # filterLabel.WBBCAC WBBC China AC
         # filter.WBBCAC 0:2000000
         # filterLimits.WBBCAC 0:2000000
         # filterByRange.ChinaMAPAC on
         # filterLabel.ChinaMAPAC China ChinaMAP AC
         # filter.ChinaMAPAC 0:2000000
         # filterLimits.ChinaMAPAC 0:2000000
         # filterByRange.GenomeIndiaAC on
         # filterLabel.GenomeIndiaAC GenomeIndia 9.7k WGS AC
         # filter.GenomeIndiaAC 0:2000000
         # filterLimits.GenomeIndiaAC 0:2000000
         # filterByRange.GoNLAC on
         # filterLabel.GoNLAC GoNL Netherlands ~13x SR AC
         # filter.GoNLAC 0:2000000
         # filterLimits.GoNLAC 0:2000000
+        # filterByRange.HostSeqAC on
+        # filterLabel.HostSeqAC HostSeq Canada AC
+        # filter.HostSeqAC 0:2000000
+        # filterLimits.HostSeqAC 0:2000000
         # Population-specific AF/AC filters (commented out: re-enable as needed)
         # AllOfUs populations
         # filterByRange.AllOfUsAF_AFR on
         # filterLabel.AllOfUsAF_AFR AllOfUs African AF
         # filter.AllOfUsAF_AFR 0:1
         # filterLimits.AllOfUsAF_AFR 0:1
         # filterByRange.AllOfUsAF_AMR on
         # filterLabel.AllOfUsAF_AMR AllOfUs Indigenous American AF
         # filter.AllOfUsAF_AMR 0:1
         # filterLimits.AllOfUsAF_AMR 0:1
         # filterByRange.AllOfUsAF_EAS on
         # filterLabel.AllOfUsAF_EAS AllOfUs East Asian AF
         # filter.AllOfUsAF_EAS 0:1
         # filterLimits.AllOfUsAF_EAS 0:1
         # filterByRange.AllOfUsAF_EUR on
@@ -1640,15 +1656,25 @@
         visibility hide
         dataVersion Chirmade 2025 release
         priority 29
 
         track tishkoff180
         shortLabel 12 Afr Pops 180 WGS
         longLabel SNV Frequencies: 180 WGS from 12 Indigenous African Populations (Fan 2023)
         type vcfTabix
         parent varFreqs on
         bigDataUrl /gbdb/$D/varFreqs/_tishkoff/tishkoff180.vcf.gz
         visibility hide
         dataVersion Cell 2023 (hg19 lift)
         tableBrowser off
         priority 1
 
+        track hostseq
+        shortLabel Canada HostSeq 10.5k WGS
+        longLabel SNV Frequencies: gnomAD-Canada HostSeq - 10,487 WGS, Canadian COVID-19 cohort
+        type vcfTabix
+        parent varFreqs on
+        bigDataUrl /gbdb/$D/varFreqs/hostseq/hostseq.vcf.gz
+        visibility hide
+        dataVersion gnomAD-Canada v1.0
+        priority 2
+