9d63cc04f4da43dc2f454a55c1144b1604c29ab1
hiram
  Thu Feb 6 15:23:56 2020 -0800
add .as file and ftp location script refs #24818

diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt
index 5d8d8ad..bf70be9 100644
--- src/hg/makeDb/doc/hg19.txt
+++ src/hg/makeDb/doc/hg19.txt
@@ -34007,36 +34007,46 @@
 ##############################################################################
 2020-01-21: manually update GENCODE V19 to include chrMT (markd)
 
   cd /hive/data/genomes/hg19/bed/gencodeV19/chrMT
   # convert chrM annotation in gff3 to chrMT
   zcat ../data/release_19/gencode.v19.annotation.gff3.gz | tawk 'NR==1{print;next} $1=="chrM"{$1="chrMT"; print}' >chrMT.gff3
   # comprensive and basic are the same on chrM and there are no pseudogenes, so this is
   # easy
   cat ../tables/wgEncodeGencodeCompV19.gp chrMT.gp >wgEncodeGencodeCompV19.gp
   cat ../tables/wgEncodeGencodeBasicV19.gp chrMT.gp >wgEncodeGencodeBasicV19.gp
   
   hgLoadGenePred -genePredExt hg19  wgEncodeGencodeCompV19 wgEncodeGencodeCompV19.gp
   hgLoadGenePred -genePredExt hg19  wgEncodeGencodeBasicV19 wgEncodeGencodeBasicV19.gp
 
 ##############################################################################
-# doseSensitivity (WORKING - 2020-02-06)
+# doseSensitivity (WORKING - 2020-02-06, Ana, Hiram)
 
   mkdir /hive/data/genomes/hg19/bed/doseSensitivity
   cd /hive/data/genomes/hg19/bed/doseSensitivity
 
-  ftp original files from ClinGen
+  ftp original files from ClinGen:
+
+  ftp://ftp.ncbi.nlm.nih.giv/pub/dbVar/clingen/
+
+  wget --timestamping \
+ftp://ftp.ncbi.nlm.nih.gov/pub/dbVar/clingen/ClinGen_haploinsufficiency_gene_GRCh37.bed
+
+  wget --timestamping \
+ftp://ftp.ncbi.nlm.nih.gov/pub/dbVar/clingen/ClinGen_triplosensitivity_gene_GRCh37.bed
+
+
 -rw-rw-rw- 1 202784 Jan 28 16:21 ClinGen_gene_curation_list_GRCh37.tsv
 -rw-rw-rw- 1  45142 Jan 28 16:21 ClinGen_haploinsufficiency_gene_GRCh37.bed
 -rw-rw-rw- 1  48750 Jan 28 16:22 ClinGen_triplosensitivity_gene_GRCh37.bed
 
   # create perl script for processing: toUcsc.pl
 
 ###########################################################################
 #!/usr/bin/env perl
 
 use strict;
 use warnings;
 
 my $argc = scalar(@ARGV);
 
 if ($argc != 1) {
@@ -34092,30 +34102,48 @@
   }
   printf "%s\t%d\t%d\t%s\t%d\t+\t%d\t%d\t%s\t%s\t%d - %s\n",
     $a[0], $a[1], $a[2], $a[3], $score, $a[1], $a[2], $color, $a[4], $score, $mouseOver[$selectMouseOver];
 }
 close (FH);
 ###########################################################################
 
   # convert the original 'bed 5' data to bed 9+2 with perl script:
 
   ./toUcsc.pl ClinGen_haploinsufficiency_gene_GRCh37.bed \
          | sort -k1,1 -k2,2n > haploInsufficiency.bed
   ./toUcsc.pl ClinGen_triplosensitivity_gene_GRCh37.bed \
          | sort -k1,1 -k2,2n > triploSensitivity.bed
 
   # convert bed to bigBed:
+  # using the dosSensitivity.as file:
+
+table doseSensitivity
+"ClinGen dosage sensitivity bed 9 plus original dosageScore"
+    (
+    string chrom;      "Chromosome (or contig, scaffold, etc.)"
+    uint   chromStart; "Start position in chromosome"
+    uint   chromEnd;   "End position in chromosome"
+    string name;       "Name of item"
+    uint   score;      "Score from 0-1000"
+    char[1] strand;    "+ or -"
+    uint thickStart;   "Start of where display should be thick (start codon)"
+    uint thickEnd;     "End of where display should be thick (stop codon)"
+    uint itemRgb;      "color indicates dosage score"
+    string dosageScore; "dosage score from ClinGen"
+    string mouseOver;  "description for the score meaning"
+    )
+
 
   bedToBigBed -tab -type=bed9+2 -as=doseSensitivity.as \
      haploInsufficiency.bed ../../chrom.sizes haploInsufficiency.bb
   bedToBigBed -tab -type=bed9+2 -as=doseSensitivity.as \
      triploSensitivity.bed ../../chrom.sizes triploSensitivity.bb
 
   # measure data in bigBed files:
   bigBedInfo haploInsufficiency.bb | sed -e 's/^/# /;'
 # version: 4
 # fieldCount: 11
 # hasHeaderExtension: yes
 # isCompressed: yes
 # isSwapped: 0
 # extraIndexCount: 0
 # itemCount: 1,396