def vsearch(percent_id, genes, num_threads=num_vcpu):
centroids = f"centroids.{percent_id}.ffn"
uclust = f"uclust.{percent_id}.txt"
# log = f"uclust.{percent_id}.log"
if find_files(centroids) and find_files(uclust):
tsprint(
f"Found vsearch results at percent identity {percent_id} from prior run."
)
else:
try:
command(
f"vsearch --quiet --cluster_fast {genes} --id {percent_id/100.0} --threads {num_threads} --centroids {centroids} --uc {uclust}"
)
except:
# Do not keep bogus zero-length files; those are harmful if we rerun in place.
command(f"mv {centroids} {centroids}.bogus", check=False)
command(f"mv {uclust} {uclust}.bogus", check=False)
raise
return centroids, uclust #, log
def init(args):
"""
Input spec: https://github.com/czbiohub/iggtools/wiki#inputs
Output spec: https://github.com/czbiohub/iggtools/wiki#target-layout-in-s3
"""
msg = f"Building {outputs.genomes}."
if find_files(outputs.genomes):
if not args.force:
tsprint(
f"Destination {outputs.genomes} already exists. Specify --force to overwrite."
)
return
msg = f"Rebuilding {outputs.genomes}."
tsprint(msg)
id_remap = {}
with InputStream(inputs.alt_species_ids) as ids:
for row in select_from_tsv(
ids, selected_columns=["alt_species_id", "species_id"]):
new_id, old_id = row
id_remap[old_id] = new_id
seen_genomes, seen_species = set(), set()
with OutputStream(outputs.genomes) as out:
target_columns = [
"genome", "species", "representative", "genome_is_representative"
]
out.write("\t".join(target_columns) + "\n")
with InputStream(inputs.genomes2species) as g2s:
for row in select_from_tsv(
g2s, selected_columns=["MAG_code", "Species_id"]):
genome, representative = row
species = id_remap[representative]
genome_is_representative = str(int(genome == representative))
target_row = [
genome, species, representative, genome_is_representative
]
out.write("\t".join(target_row) + "\n")
seen_genomes.add(genome)
seen_species.add(species)
tsprint(
f"Emitted {len(seen_genomes)} genomes and {len(seen_species)} species to {outputs.genomes}."
)
def hmmsearch(genome_id, species_id, marker_genes_hmm, num_threads=1):
# Input
annotated_genes_s3_path = input_annotations_file(genome_id, species_id, f"{genome_id}.faa.lz4")
annotated_genes = download_reference(annotated_genes_s3_path)
# Output
hmmsearch_file = f"{genome_id}.hmmsearch"
# Command
if find_files(hmmsearch_file):
# This only happens in debug mode, where we can use pre-existing file.
tsprint(f"Found hmmsearch results for genome {genome_id} from prior run.")
else:
try:
command(f"hmmsearch --noali --cpu {num_threads} --domtblout {hmmsearch_file} {marker_genes_hmm} {annotated_genes}")
except:
# Do not keep bogus zero-length files; those are harmful if we rerun in place.
command(f"mv {hmmsearch_file} {hmmsearch_file}.bogus", check=False)
raise
return hmmsearch_file
def find_files_with_retry(f):
return find_files(f)