890098d958d7df3a643b6a0b3589b1bfe4b7f6a0
markd
  Sun Apr 17 22:37:36 2022 -0700
added microsatellites

diff --git src/hg/makeDb/doc/chm13v2.0userData/build.txt src/hg/makeDb/doc/chm13v2.0userData/build.txt
index 912718c..fe44bcc 100644
--- src/hg/makeDb/doc/chm13v2.0userData/build.txt
+++ src/hg/makeDb/doc/chm13v2.0userData/build.txt
@@ -231,68 +231,85 @@
 ----------------------------------------------------------------
 from Nick Altemose <nickaltemose@gmail.com> via Slack:
    t2t_censat_CHM13v2.0_trackv2.0.10col.bed
    t2t_censat_CHM13v2.0_trackv2.0_description.html
 
    cd censat/
 
    # drop track header
    tawk 'NR>1' t2t_censat_CHM13v2.0_trackv2.0.10col.bed | csort -k1,1 -k2,2n  >tmp.bed
    bedToBigBed -type=bed9+1 -as=${HOME}/compbio/t2t/projs/chm13-v2.0/makeDir/schema/cenSat.as -tab tmp.bed ../chromAlias/ucsc.sizes.txt censat.bb
 
 ================================================================
 * dbSNP155 (2022-03-29 markd)
 ----------------------------------------------------------------
 
-# dbSNP Variants	Lifted+Recovered	TBD	Dylan Taylor
+# dbSNP Variants	Lifted+Recovered	Dylan Taylor
 https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/liftover/chm13v2.0_dbSNPv155.vcf.gz
 dbSNP_lifted-recovered.html
 
 
 # need to use NCBI names until supported by chromAlias
    zcat chm13v2.0_dbSNPv155.vcf.gz  | chromToUcsc --chromAlias=../chromAlias/GCA_009914755.4_T2T-CHM13v2.0.chromAlias.txt /dev/stdin | bgzip -c >chm13v2.0_dbSNPv155.ncbi-names.vcf.gz
 
 tabix -p vcf chm13v2.0_dbSNPv155.vcf.gz &
 tabix -p vcf chm13v2.0_dbSNPv155.ncbi-names.vcf.gz &
 
 
 ================================================================
 * clinVar20220313 (2022-03-29 markd)
 ----------------------------------------------------------------
-ClinVar	Lifted+Recovered	TBD	Dylan Taylor
+ClinVar	Lifted+Recovered	Dylan Taylor
 https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/liftover/chm13v2.0_ClinVar20220313.vcf.gz
 
    zcat chm13v2.0_ClinVar20220313.vcf.gz | chromToUcsc --chromAlias=../chromAlias/GCA_009914755.4_T2T-CHM13v2.0.chromAlias.txt /dev/stdin | bgzip -c >chm13v2.0_ClinVar20220313.ncbi-names.vcf.gz
 
 tabix -p vcf chm13v2.0_ClinVar20220313.vcf.gz &
 tabix -p vcf chm13v2.0_ClinVar20220313.ncbi-names.vcf.gz &
 
 
 ================================================================
-* gwasSNPs2022-03-08 (2022-03-29 markd
+* gwasSNPs2022-03-08 (2022-03-29 markd)
 ----------------------------------------------------------------
 GWAS SNPs	Lifted+Recovered	TBD	Dylan Taylor
 
 https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/liftover/chm13v2.0_GWASv1.0rsids_e100_r2022-03-08.vcf.gz
 gwas_catalog_lifted-recovered.html											
 
 # need to use NCBI names until supported by chromAlias
    zcat chm13v2.0_GWASv1.0rsids_e100_r2022-03-08.vcf.gz  | chromToUcsc --chromAlias=../chromAlias/GCA_009914755.4_T2T-CHM13v2.0.chromAlias.txt /dev/stdin | bgzip -c >chm13v2.0_GWASv1.0rsids_e100_r2022-03-08.ncbi-names.vcf.gz
 
 tabix -p vcf  chm13v2.0_GWASv1.0rsids_e100_r2022-03-08.ncbi-names.vcf.gz&
 tabix -p vcf  chm13v2.0_GWASv1.0rsids_e100_r2022-03-08.vcf.gz&
 
+
+================================================================
+* microsatellites (2022-04-17 markd)
+----------------------------------------------------------------
+Arang Rhie
+
+doc https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/pattern/microsatellite.html
+
+GA https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/pattern/chm13v2.0.microsatellite.GA.128.wig
+TC https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/pattern/chm13v2.0.microsatellite.TC.128.wig
+GC https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/pattern/chm13v2.0.microsatellite.GC.128.wig
+AT https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/annotation/pattern/chm13v2.0.microsatellite.AT.128.wig
+
+# convert to bigWi
+for f in *.wig ; do wigToBigWig -clip $f ../ucscChromNames/t2t-chm13-v2.0.sizes  $(basename $f .wig).bw ; done
+pigz *.wig
+
 ================================================================
 pending:
 
 - ensembl:
   http://ftp.ebi.ac.uk/pub/databases/ensembl/hprc/y1_freeze/ contains all Y1 assemblies;
   http://ftp.ebi.ac.uk/pub/databases/ensembl/hprc/y1_freeze/GCA_009914755.4/ is CHM13v2
 
 - isoseq BAMs
   http://courtyard.gi.ucsc.edu/~mhauknes/T2T/t2t_Y/out-t2t-chrY-augPB/assemblyHub/CHM13/
   @PG   ID:minimap2   PN:minimap2   VN:2.22-r1105-dirty   CL:minimap2 -ax splice -f 1000 --sam-hit-only --secondary=no --eqx -K 100M -t 8 --cap-sw-mem=3g chm13v2.0.chrY.fasta HG002-NA24385-LCL-polished_isoforms_hq.fasta
   globus /HG002-IsoSeq
 
 - isoseq
     Fritz Sedlazeck  1 minute ago
     STUDY: PRJNA754107