def minimal_medium(models: CommunityModelDirectory,
min_growth: float = 0.1,
threads: int = 1) -> pd.DataFrame:
"""Calculate the minimal medium for a set of community models."""
samples = models.manifest.view(pd.DataFrame).sample_id.unique()
paths = [models.model_files.path_maker(model_id=s) for s in samples]
args = [[p, min_growth] for p in paths]
results = workflow(_medium, args, threads)
results = pd.concat(results, axis=0)
medium = results.groupby("reaction").flux.max().reset_index()
medium["metabolite"] = medium.reaction.str.replace("EX_", "")
return medium
def fix_community_medium(
tax,
medium,
min_growth=0.1,
max_import=1,
minimize_components=True,
n_jobs=4,
):
"""Augment a growth medium so all community members can grow in it.
Arguments
---------
tax : pandas.Dataframe
A taxonomy specification as passed to `micom.Community`.
medium : pandas.Series
A growth medium with exchange reaction IDs as index and positive
import fluxes as values.
min_growth : positive float
The minimum biomass production required for growth.
max_import : positive float
The maximum import rate for added imports.
minimize_components : boolean
Whether to minimize the number of media components rather than the
total flux.
n_jobs: int
The number of processes to use.
Returns
-------
pandas.Series
A new growth medium with the smallest amount of augmentations such
that all members of the community can grow in it.
"""
if medium[medium < 1e-6].any():
medium[medium < 1e-6] = 1e-6
logger.info(
"Some import rates were to small and were adjusted to 1e-6.")
args = [(row.id, row.file, medium, min_growth, max_import,
minimize_components) for _, row in tax.iterrows()]
res = workflow(_fix_medium, args, n_jobs=n_jobs, unit="model(s)")
return pd.concat(res, axis=1).max(axis=1)
def tradeoff(
models: CommunityModelDirectory,
medium: MicomMediumFile,
tradeoff_min: float = 0.1,
tradeoff_max: float = 1.0,
step: float = 0.1,
threads: int = 1,
) -> pd.DataFrame:
"""Run tradeoff analysis."""
samples = models.manifest.view(pd.DataFrame).sample_id.unique()
paths = {s: models.model_files.path_maker(model_id=s) for s in samples}
if tradeoff_min >= tradeoff_max:
raise ValueError(
"`tradeoff_min` must be smaller than `tradeoff_max` :(")
tradeoffs = np.arange(tradeoff_min, tradeoff_max + 1e-6, step)
medium = process_medium(medium, samples)
args = [[p, tradeoffs, medium.flux[medium.sample_id == s]]
for s, p in paths.items()]
results = workflow(_tradeoff, args, threads)
results = pd.concat(results)
return results
from micom.workflows import workflow
micom.logger.file_logger("micom.log")
max_procs = 16
taxonomy = pd.read_csv("species.csv").dropna(subset=["agora_id"])
taxonomy["file"] = taxonomy.agora_id.apply(
lambda ids: ["agora/" + i + ".xml" for i in ids.split("|")])
taxonomy.name = taxonomy.name.replace(r"[^A-Za-z0-9_\s]", "", regex=True)
taxonomy.name = taxonomy.name.replace(r"\s+", "_", regex=True)
assert not taxonomy.name.str.contains(" ").any()
taxonomy = taxonomy.rename(columns={
"id": "samples",
"name": "id",
"reads": "abundance"
})
def build_and_save(args):
s, tax = args
filename = "models/" + s + ".pickle"
if isfile(filename):
return
com = Community(tax, id=s, progress=False)
com.to_pickle(filename)
samples = taxonomy.samples.unique()
args = [(s, taxonomy[taxonomy.samples == s]) for s in samples]
workflow(build_and_save, args, max_procs)
def growth_rates(sam):
com = load_pickle("data/models/" + sam + ".pickle")
sol = com.optimize()
rates = sol.members
rates["tradeoff"] = np.nan
rates["sample"] = sam
df = [rates]
# Get growth rates
try:
sol = com.cooperative_tradeoff(fraction=tradeoffs)
except Exception as e:
logger.warning("Sample %s could not be optimized\n %s" % (sam, str(e)))
return pd.DataFrame(
{"tradeoff": tradeoffs, "growth_rate": np.nan, "sample": sam}
)
for i, s in enumerate(sol.solution):
rates = s.members
rates["tradeoff"] = sol.tradeoff[i]
rates["sample"] = sam
df.append(rates)
df = pd.concat(df)
return df
samples = pd.read_csv("data/recent.csv")
rates = workflow(growth_rates, samples.run_accession, max_procs)
rates = pd.concat(rates)
rates.to_csv("data/tradeoff.csv")
"""Calculate the elasticities for a set of built models."""
from os.path import isfile
import micom
from micom import load_pickle
from micom.elasticity import elasticities
from micom.workflows import workflow
micom.logger.file_logger("micom.log")
logger = micom.logger.logger
try:
max_procs = snakemake.threads
except NameError:
max_procs = 20
def elasticity_worker(sam):
"""Get the exchange elasticities for a sample."""
model_file = "data/models/" + sam + ".pickle"
out_file = "data/elasticities_" + sam + ".csv"
if isfile(out_file):
return
com = load_pickle(model_file)
elast = elasticities(com, fraction=0.5)
elast.to_csv(out_file, index=False)
samples = ["ERR260275", "ERR260214", "ERR260174"]
workflow(elasticity_worker, samples, max_procs)
"""Perform taxa knockouts."""
import pandas as pd
import micom
from micom import load_pickle
from micom.media import minimal_medium
from micom.workflows import workflow
logger = micom.logger.logger
logger.add("micom.log")
try:
max_procs = snakemake.threads
except NameError:
max_procs = 20
def knockout(sam):
com = load_pickle("data/models/" + sam + ".pickle")
ko = com.knockout_species(fraction=0.5)
ko["sample"] = sam
return ko
samples = pd.read_csv("data/recent.csv")
kos = workflow(knockout, samples.run_accession, max_procs)
pd.concat(kos).to_csv("data/knockouts.csv")
lambda ids: ["data/agora/" + i for i in ids.split("|")]
)
taxonomy["name"] = taxonomy.genus
assert not taxonomy.name.str.contains(" ").any()
taxonomy = taxonomy.rename(columns={"name": "id", "reads": "abundance"})
diet = pd.read_csv("data/western_diet.csv")
diet.index = diet.reaction = diet.reaction.str.replace("_e", "_m")
diet = diet.flux * diet.dilution
def build_and_save(args):
s, tax = args
filename = "data/models/" + s + ".pickle"
if isfile(filename):
return
com = Community(tax, id=s, progress=False)
ex_ids = [r.id for r in com.exchanges]
logger.info(
"%d/%d import reactions found in model.",
diet.index.isin(ex_ids).sum(),
len(diet),
)
com.medium = diet[diet.index.isin(ex_ids)]
com.to_pickle(filename)
samples = taxonomy.samples.unique()
args = [(s, taxonomy[taxonomy.samples == s]) for s in samples]
workflow(build_and_save, args, max_procs)
"""Calculate the elasticities for a set of built models."""
from os.path import isfile
from micom import load_pickle
from micom.elasticity import exchange_elasticities
from micom.workflows import workflow
max_procs = 24
def elasticities(sam):
"""Get the exchange elasticities for a sample."""
model_file = "models/" + sam + ".pickle"
out_file = "intervention/" + sam + ".csv"
if isfile(out_file):
return
com = load_pickle(model_file)
elast = exchange_elasticities(com, fraction=0.5, progress=False)
elast.to_csv(out_file, index=False)
samples = ["ERR260275", "ERR260214", "ERR260174"]
workflow(elasticities, samples, max_procs)
