775f8e290daefbb3312fd1d8962344690550c887
angie
  Mon Jun 8 16:20:24 2020 -0700
Extending and updating tree manipulation & SARS-CoV-2 lineage coloring python scripts and modules that I've been working on for David et al.  sorta refs #25278, #25382

diff --git src/hg/utils/otto/nextstrainNcov/sampleLineage.py src/hg/utils/otto/nextstrainNcov/sampleLineage.py
new file mode 100755
index 0000000..dbf43c3
--- /dev/null
+++ src/hg/utils/otto/nextstrainNcov/sampleLineage.py
@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+
+import logging, argparse, sys
+import lineageColors, nextstrainVcf, utils, virusNames
+
+def main():
+    parser = argparse.ArgumentParser(description="""
+Read sample names from sampleFile.
+Read sample IDs that are a concatenation of EPI ID, sample name and approximate date,
+for resolving sampleFile IDs and lineageFile IDs, from a Nextstrain VCF file.
+Read lineage assignments from lineageFile.
+Write out 3 tab-sep columns:
+sample, lineage, lineageColor.
+"""
+    )
+    parser.add_argument('sampleFile', help='File containing sample IDs')
+    parser.add_argument('vcfFile', help='VCF file derived from Nextstrain data')
+    parser.add_argument('lineageFile', help='Two-column tab-sep file mapping sample to lineage')
+    args = parser.parse_args()
+
+    samples = utils.listFromFile(args.sampleFile)
+    (vcfSamples, vcfSampleClades) = nextstrainVcf.readVcfSamples(args.vcfFile)
+    idLookup = virusNames.makeIdLookup(vcfSamples)
+    lineages = utils.dictFromFile(args.lineageFile)
+    nsLineages = dict([ (virusNames.maybeLookupSeqName(name, idLookup), lin)
+                        for name, lin in lineages.items() ])
+    for sample in samples:
+        nsSample = virusNames.maybeLookupSeqName(sample, idLookup)
+        lineage = nsLineages.get(nsSample)
+        if (not lineage):
+            lineage = ''
+        color = "#%06x" % (lineageColors.lineageToColor(lineage))
+        print('\t'.join([sample, lineage, color]))
+
+main()