def main(
otu_file: str,
rm_sparse_samples: str,
rm_sparse_obs: str,
axis: str,
count_thres: int,
prevalence_thres: float,
abundance_thres: float,
obssum_thres: float,
) -> Otu:
otu = Otu.load_data(otu_file)
if rm_sparse_samples == "true":
otu = otu.rm_sparse_samples(count_thres=count_thres)
if rm_sparse_obs == "true":
otu = otu.rm_sparse_obs(
prevalence_thres=prevalence_thres,
abundance_thres=abundance_thres,
obssum_thres=obssum_thres,
)
else:
n_samples = otu.otu_data.shape[1]
otu = otu.rm_sparse_obs(
prevalence_thres=2 / n_samples, abundance_thres=0.001, obssum_thres=10
)
if axis != "None":
otu_norm = otu.normalize(axis=axis)
else:
otu_norm = otu
return otu_norm
def main(otu_file: str, axis: str, column: str):
otu = Otu.load_data(otu_file)
if axis != "sample":
raise NotImplementedError(
"Axis other than sample are not currently supported")
if not column:
warn("No column supplied for splitting")
split_results = [("", otu)]
else:
func = lambda id_, md: md[column]
split_results = otu.partition(axis, func)
return split_results
def main(
otu_file: str,
rm_sparse_samples: bool,
rm_sparse_obs: bool,
axis: str,
count_thres: int,
prevalence_thres: float,
abundance_thres: float,
) -> Otu:
otu = Otu.load_data(otu_file)
if rm_sparse_samples:
otu = otu.rm_sparse_samples(count_thres=count_thres)
if rm_sparse_obs:
otu = otu.rm_sparse_obs(
prevalence_thres=prevalence_thres, abundance_thres=abundance_thres
)
return otu.normalize(axis=axis)
def main(otu_file, count_thres, prevalence_thres, abundance_thres):
otu_data = Otu.load_data(otu_file)
filtered_otu_data = otu_data.rm_sparse_obs(
prevalence_thres, abundance_thres).rm_sparse_samples(count_thres)
fname, _ = os.path.splitext(otu_file)
filtered_otu_data.write(f"{fname}_filtered", file_type="biom")
def grp_otu_data(otu_data: Otu, tax_level: str) -> Tuple[Otu, dict]:
child_otu, child_groups = otu_data.collapse_taxa(tax_level)
return child_otu, child_groups
#!/usr/bin/env python3
# Script that groups OTU data on different taxa levels
import json
from typing import Tuple
from micone import Otu
# Group the otu_data on all the tax_levels
def grp_otu_data(otu_data: Otu, tax_level: str) -> Tuple[Otu, dict]:
child_otu, child_groups = otu_data.collapse_taxa(tax_level)
return child_otu, child_groups
if __name__ == "__main__":
TAX_LEVEL: str = "${tax_level}" # ['Family', 'Genus', 'Species']
OTU_FILE = "${otu_file}" # "otu.biom"
OTU_DATA = Otu.load_data(OTU_FILE)
child_otu, child_groups = grp_otu_data(OTU_DATA, TAX_LEVEL)
fname = "${new_meta.id}"
child_otu.write(fname, file_type="biom")
with open(fname + "_children.json", "w") as fid:
json.dump(child_groups, fid, indent=2, sort_keys=True)
#!/usr/bin/env python3
# Script that groups OTU data on different taxa levels
import json
from typing import List, Iterable, Tuple
from micone import Otu, Lineage
# Group the otu_data on all the tax_levels
def grp_otu_data(otu_data: Otu, tax_levels: List[str]) -> Iterable[Tuple[Otu, dict]]:
sorted_tax_levels = list(reversed(tax_levels))
child_otu = otu_data
for tax_level in sorted_tax_levels:
child_otu, child_groups = child_otu.collapse_taxa(tax_level)
yield child_otu, child_groups
if __name__ == "__main__":
TAX_LEVELS: List[str] = ${params.group.tax_levels} # ['Family', 'Genus', 'Species']
OTU_FILE = "$otu_file" # "otu.biom"
otu_data = Otu.load_data(OTU_FILE)
for child_otu, child_groups in grp_otu_data(otu_data, TAX_LEVELS):
fname = child_otu.tax_level + "_level"
child_otu.write(fname, file_type="biom")
with open(fname + "_children.json", "w") as fid:
json.dump(child_groups, fid, indent=2, sort_keys=True)
def main(biom_file, base_name):
otu_biom = Otu.load_data(biom_file)
otu_biom.write(base_name=base_name, file_type="tsv")