a77bab60dc03de789c241d97692ba1f672dfddab max Mon Sep 14 07:30:12 2026 -0700 uniprot otto: use the miniprot in /cluster/bin/x86_64 max built the current miniprot into /cluster/bin/x86_64/miniprot, which is the right home for it: shared, on the PATH the cluster nodes already use, and maintained with the rest of the kent binaries rather than by this pipeline. Dropped the copy I had built under the otto directory, so there is only one. Both were 0.18-r281; checked that otto can run the system one. refs #38300 diff --git src/hg/utils/otto/uniprot/doUniprot src/hg/utils/otto/uniprot/doUniprot index 8676593dab5..34cfc56281f 100755 --- src/hg/utils/otto/uniprot/doUniprot +++ src/hg/utils/otto/uniprot/doUniprot @@ -1011,31 +1011,31 @@ # augustus - ab initio prediction, present almost everywhere, so it is the last resort. # Each entry is (name, glob relative to the hub directory). Globs, not constructed names, # because the files under bbi/ carry the full asmId with its assembly-name suffix while the # hub directory is named with the short accession. # Several globs per source, because the layouts differ: a GenArk assembly keeps its gene # models under bbi/ and its CAT genes in a contrib collection, while hs1 is a hub assembly # that keeps them in /gbdb/hs1// like a classic assembly does. genArkGeneSources = [ ("catGenes", ["contrib/*/catGenes.bb", "catLiftOffGenesV1/*.bb"]), ("ncbiRefSeq", ["bbi/*.ncbiRefSeq.bb", "ncbiRefSeq/ncbiRefSeq.bb"]), ("ncbiGene", ["bbi/*.ncbiGene.bb"]), ] # Augustus is deliberately not in that list. It is an ab initio prediction, so mapping # UniProt through it stacks its errors on top of ours; aligning the proteins straight to # the genome with miniprot is better and much faster than the old BLAT protein search. -miniprotBin = "/hive/data/outside/otto/uniprot/bin/miniprot" +miniprotBin = "/cluster/bin/x86_64/miniprot" miniprotThreads = 16 def miniprotVersion(): " version string of the miniprot binary we are using " proc = subprocess.Popen([miniprotBin, "--version"], stdout=PIPE, encoding="utf8") return proc.communicate()[0].strip() dbIsHubCache = {} def genArkHubDir(db): """ return the hub directory of a hub assembly, or None for a classic db. dbDb.nibPath is "hub:" for these, e.g. hub:/gbdb/genark/GCF/029/289/425/GCF_029289425.2 for a GenArk assembly. """ if db not in dbIsHubCache: