# Transcription start sites: ProCapNet predictions, #35528, Claude
Thu Sep 17 2026 (Claude/markd)

# hs1 has the ProCapNet predictions only.  There is no PRO-cap experiment and no
# sequence-contribution score set on this assembly.  See
# makeDb/doc/hg38/transcriptionStart.txt for the hg38 build, which carries all
# three.  Scripts are in ~/kent/src/hg/makeDb/outside/proCapNet.

mkdir -p /hive/data/outside/proCapNet/hs1 /hive/data/genomes/hs1/bed/proCapNet
cd /hive/data/genomes/hs1/bed/proCapNet
~/kent/src/hg/makeDb/outside/proCapNet/proCapNetDownload hs1 \
    ~/kent/src/hg/makeDb/outside/proCapNet/proCapNetExperiments.tsv \
    /hive/data/outside/proCapNet/hs1/pred
# 300 GB, about 30 minutes at six parallel streams

# Re-encode from one bedGraph interval per base into fixedStep sections.  Unlike
# hg38 these files hold no NaN, so every base is kept.
~/kent/src/hg/makeDb/outside/proCapNet/proCapNetPredBuild \
    /hive/data/genomes/hs1/chrom.sizes /hive/data/outside/proCapNet/hs1/pred pred 6
# all 12 files report:
#   24 chroms, 3117275501 bases, 3117275501 with data, 0 dropped
# about 25 GB in, 16.7 to 17.0 GB out per file

# the mean matches the published file exactly, so nothing was altered
bigWigInfo pred/K562.proCapNet.pos.bw | egrep 'basesCovered|mean'
#   basesCovered: 3,117,275,501
#   mean: 0.019773

cd ~/kent/src/hg/makeDb/outside/proCapNet
./proCapNetTrackDb hs1 proCapNetExperiments.tsv \
    ~/kent/src/hg/makeDb/trackDb/human/hs1/transcriptionStart.ra /gbdb/hs1

# transcriptionStart.ra is generated; the include line in human/hs1/trackDb.ra
# is added by hand:
#   include transcriptionStart.ra alpha

# hs1 is a curated hub assembly, so the stanzas reach the browser through the
# hub built under /gbdb/hs1/hubs/$USER by the trackDb make, and are visible only
# when curatedHubPrefix in the sandbox hg.conf names that directory.

# the downloads are only needed for the re-encoding
rm -rf /hive/data/outside/proCapNet/hs1/pred
