ac99b14fc67a6843f6751148bd97358b1f93fddd
angie
  Sat Sep 9 12:06:12 2017 -0700
New script to build ncbiRefSeqOther BED with extra columns sourced from an attributes file generated by gff3ToGenePred -attrsOut.
Refining attributes for ncbiRefSeqOther:
* Split Dbxref into separate columns GeneID, MIM, HGNC, miRBase for linking out
* Remove Name2 column which is now redundant with gene column
* Remove ncrna_class column which doesn't appear in p11 GFF
* Reorder columns to flow a bit better
* Reword some column descriptions that appear in hgc table display

diff --git src/hg/inc/ncbiRefSeqOther.as src/hg/inc/ncbiRefSeqOther.as
index 32f6549..cbea67e 100644
--- src/hg/inc/ncbiRefSeqOther.as
+++ src/hg/inc/ncbiRefSeqOther.as
@@ -1,36 +1,37 @@
 table ncbiRefSeqOtherBb
 "Additional information for NCBI 'Other' annotation"
     (
     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 reserved;     "Used as itemRgb as of 2004-11-22"
-    int blockCount;    "Number of blocks"
+    uint   score;      "Placeholder for BED format (score 0-1000)"
+    char[1] strand;    "+ or -"
+    uint thickStart;   "CDS start/end in chromosome if coding"
+    uint thickEnd;     "CDS start/end in chromosome if coding"
+    uint reserved;     "Placeholder for BED format (itemRgb)"
+    int blockCount;    "Number of alignment blocks"
     int[blockCount] blockSizes; "Comma separated list of block sizes"
-    int[blockCount] chromStarts; "Start positions relative to chromStart"
+    int[blockCount] chromStarts; "Block start positions relative to chromStart"
 
-    string gene;        "gene name"
-    string gbkey;       "genbank key type: CDS, Gene, V_segment, ncRNA, rRNA, tRNA"
-    string ID;          "genbank ID"
-    string Dbxref;      "DB cross reference"
+    string gene;        "Gene name"
+    string GeneID;      "Entrez Gene"
+    string MIM;         "OMIM"
+    string HGNC;        "HGNC"
+    string miRBase;     "miRBase"
+    string description; "Description"
+    string Note;        "Note"
+    string exception;   "Exceptional properties"
+    string product;     "Gene product"
+    string geneSynonym; "Gene synonyms"
+    string modelEvidence;  "Supporting evidence for gene model"
+    string gbkey;       "Feature type"
+    string geneBiotype; "Gene biotype"
     string pseudo;      "'true' if pseudogene"
-    string geneBiotype; "gene biotype: C_region, J_segment_pseudogene, pseudogene or other"
-    string Name2;        "additional gene name"
-    string description; "annotation description"
-    string geneSynonym; "additional gene name"
-    string product;     "gene product"
-    string ncrnaClass;  "ncRNA class: miRNA or empty"
-    string exception;   "exception note"
     string partial;     "'true' if partial"
-    string Note;        "additional note"
-    string anticodon;   "anti-codon"
-    string startRange;  "start range"
-    string endRange;    "end range"
-    string codons;      "codons"
-    string modelEvidence;  "evidence notes"
+    string anticodon;   "Anticodon position within tRNA"
+    string codons;      "Number of codons in anticodon range"
+    string startRange;  "Start range on genome"
+    string endRange;    "End range on genome"
+    string ID;          "Unique ID in RefSeq GFF3"
 )