Commit 217b76ca authored by Martin Larralde's avatar Martin Larralde
Browse files

Sort annotation tables before performing CRF predictions

parent 34aabf42
Pipeline #16444 passed with stages
in 3 minutes and 31 seconds
......@@ -186,6 +186,10 @@ class Run(Command): # noqa: D101
feats_df = feats_df[feats_df["i_Evalue"] < self.args["--e-filter"]]
self.logger.debug("Using remaining {} domains", len(feats_df))
# Sort by location
self.logger.debug("Sorting annotations by protein coordinates")
feats_df.sort_values(by=["sequence_id", "protein_id", "start", "domain_start"], inplace=True)
# Write feature table to file
feat_out = os.path.join(out_dir, f"{base}.features.tsv")
self.logger.debug("Writing feature table to {!r}", feat_out)
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment