aca6a4d166404c0129cb07116dde6a1f0927085e
angie
  Fri Dec 17 14:41:15 2010 -0800
Track #1684 (SNPs 132 (dbSNP)): Added new columns to SNP table(snp132Ext.as) in doDbSnp.pl and snpNcbiToUcsc.  It now runs
successfully on hg19 snp132; I have verified that the first 17
columns match the old snp132.bed and that the pre-existing
exceptions match the old snp132Exceptions.bed.  The snp125 code
in hgTracks/hgTrackUi/hgc works find on the new snp132 -- new
columns are ignored.  There is still some polishing to do before
doDbSnp.pl is ready for general use -- more consistency checks,
and much more info for the developer about what they need to
follow through on.  But next I plan to enhance the CGIs to make
use of the new columns so we can get snp132 out the door.

diff --git src/hg/lib/snp132Ext.as src/hg/lib/snp132Ext.as
new file mode 100644
index 0000000..a988158
--- /dev/null
+++ src/hg/lib/snp132Ext.as
@@ -0,0 +1,30 @@
+table snp132Ext
+"Polymorphism data from dbSNP"
+    (
+    string   chrom;      "Reference sequence chromosome or scaffold"
+    uint     chromStart; "Start position in chrom"
+    uint     chromEnd;   "End position in chrom"
+    string   name;       "dbSNP Reference SNP (rs) identifier"
+    uint     score;      "Not used"
+    string   strand;     "Which DNA strand contains the observed alleles"
+    lstring  refNCBI;  	 "Reference genomic sequence from dbSNP"
+    lstring  refUCSC;    "Reference genomic sequence from UCSC lookup of chrom,chromStart,chromEnd"
+    string   observed;   "The sequences of the observed alleles from rs-fasta files"
+    string   molType;    "Sample type from exemplar submitted SNPs (ss)"
+    string   class;      "Class of variant (single, in-del, named, mixed, etc.)"
+    string   valid;      "Validation status of the SNP"
+    float    avHet;      "Average heterozygosity from all observations.  Note: may be computed on small number of samples."
+    float    avHetSE;    "Standard Error for the average heterozygosity"
+    string   func;       "Functional category of the SNP (coding-synon, coding-nonsynon, intron, etc.)"
+    string   locType;    "Type of mapping inferred from size on reference; may not agree with class"
+    uint     weight;     "The quality of the alignment: 1 = unique mapping, 2 = non-unique, 3 = many matches"
+    
+    lstring  exceptions; "Unusual conditions noted by UCSC that may indicate a problem with the data"
+    int      submitterCount; "Number of distinct submitter handles for submitted SNPs for this ref SNP"
+    string[submitterCount] submitters; "List of submitter handles"
+    int      alleleFreqCount; "Number of observed alleles with frequency data"
+    string[alleleFreqCount] alleles; "Observed alleles for which frequency data are available"
+    float[alleleFreqCount] alleleNs; "Count of chromosomes (2N) on which each allele was observed. Note: this is extrapolated by dbSNP from submitted frequencies and total sample 2N, and is not always an integer."
+    float[alleleFreqCount] alleleFreqs; "Allele frequencies"
+    string    bitfields; "SNP attributes extracted from dbSNP's SNP_bitfield table"
+    )