3640a4d6b3303a6bebc7c5b2fc5abcf7f4fae0b2
angie
  Wed Sep 28 11:56:00 2016 -0700
Partial support for changes in VCF4.2 and latest samtools mpileup output:
- Tolerate 'Number=R' and new INFO attributes Source and Version
- Tolerate mpileup's '<X>' alt (no alternate allele was observed)
- The 4.3 spec includes '<*>' from gVCF, also meaning no alt al obsvd.
- GT is no longer required; user's example has PL instead, so parse that
into genotypes.
- hgVai now annotates "variants" with <X> and <*> as no_sequence_alteration
- annoFormatVep now uses html encoding for html output in various places so
that "<X>" is displayed properly (custom track labels and various item
names could also have undesirable characters).  I am not encoding the
extras' descriptions because those are internal and some have <a>'s.
refs #15625

diff --git src/hg/inc/soTerm.h src/hg/inc/soTerm.h
index 3818e5d..27eed1b 100644
--- src/hg/inc/soTerm.h
+++ src/hg/inc/soTerm.h
@@ -1,59 +1,60 @@
 /* soTerm.h --- a subset of locally used Sequence Ontology terms */
 
 /* Copyright (C) 2013 The Regents of the University of California 
  * See README in this or parent directory for licensing information. */
 
 // To explore the full tree of SO terms and their relationships, try the MISO browser:
 // http://www.sequenceontology.org/browser/obob.cgi
 
 // would be nice to more closely match Ensembl's subset of SO:
 // http://uswest.ensembl.org/info/docs/variation/predicted_data.html#consequences
 
 #ifndef SOTERM_H
 #define SOTERM_H
 
 enum soTerm	// the various variant effects
     {
     regulatory_region_variant=1566,
     stop_retained_variant=1567,
     exon_loss=1572,
     splice_acceptor_variant=1574,
     splice_donor_variant=1575,
     complex_transcript_variant=1577,
     stop_lost=1578,
     coding_sequence_variant=1580,
     initiator_codon_variant=1582,
     missense_variant=1583,
     stop_gained=1587,
     frameshift_variant=1589,
     nc_transcript_variant=1619,
     mature_miRNA_variant=1620,
     NMD_transcript_variant=1621,
     UTR_variant=1622,
     _5_prime_UTR_variant=1623,
     _3_prime_UTR_variant=1624,
     incomplete_terminal_codon_variant=1626,
     intron_variant=1627,
     intergenic_variant=1628,
     splice_site_variant=1629,
     splice_region_variant=1630,
     upstream_gene_variant=1631,
     downstream_gene_variant=1632,
     TF_binding_site_variant=1782,
     non_coding_transcript_exon_variant=1792,
     protein_altering_variant=1818,
     synonymous_variant=1819,
     inframe_indel=1820,
     inframe_insertion=1821,
     inframe_deletion=1822,
     feature_variant=1878,
+    no_sequence_alteration=2073,
     };
 
 char *soTermToString(enum soTerm termNumber);
 /* Translate termNumber to its string equivalent; errAbort if not found.
  * Do not modify or free result. */
 
 int soTermStringToId(char *soTermStr);
 /* Translate soTermStr into its numeric ID.  Return -1 if soTermStr is not recognized. */
 
 #endif /* SOTERM_H */