def process(w, s, c, data, data_annotation_, features, features_metadata, x_weights, summary_fields, train, postfix=None, nested_folds=10, use_individuals=None):
gene_id_ = data_annotation_.gene_id if postfix is None else "{}-{}".format(data_annotation_.gene_id, postfix)
logging.log(8, "loading data")
d_ = Parquet._read(data, [data_annotation_.gene_id], specific_individuals=use_individuals)
features_ = Genomics.entries_for_gene_annotation(data_annotation_, args.window, features_metadata)
if x_weights is not None:
x_w = features_[["id"]].merge(x_weights[x_weights.gene_id == data_annotation_.gene_id], on="id")
features_ = features_[features_.id.isin(x_w.id)]
x_w = robjects.FloatVector(x_w.w.values)
else:
x_w = None
if features_.shape[0] == 0:
logging.log(9, "No features available")
return
features_data_ = Parquet._read(features, [x for x in features_.id.values],
specific_individuals=[x for x in d_["individual"]])
logging.log(8, "training")
weights, summary = train(features_data_, features_, d_, data_annotation_, x_w, not args.dont_prune, nested_folds)
if weights.shape[0] == 0:
logging.log(9, "no weights, skipping")
return
logging.log(8, "saving")
weights = weights.assign(gene=data_annotation_.gene_id). \
merge(features_.rename(columns={"id": "feature", "allele_0": "ref_allele", "allele_1": "eff_allele"}), on="feature"). \
rename(columns={"feature": "varID"}). \
assign(gene=gene_id_)
weights = weights[["gene", "rsid", "varID", "ref_allele", "eff_allele", "weight"]]
if args.output_rsids:
weights.loc[weights.rsid == "NA", "rsid"] = weights.loc[weights.rsid == "NA", "varID"]
w.write(weights.to_csv(sep="\t", index=False, header=False, na_rep="NA").encode())
summary = summary. \
assign(gene=gene_id_, genename=data_annotation_.gene_name,
gene_type=data_annotation_.gene_type). \
rename(columns={"n_features": "n_snps_in_window", "n_features_in_model": "n.snps.in.model",
"zscore_pval": "pred.perf.pval", "rho_avg_squared": "pred.perf.R2",
"cv_converged":"nested_cv_converged"})
summary["pred.perf.qval"] = None
summary = summary[summary_fields]
s.write(summary.to_csv(sep="\t", index=False, header=False, na_rep="NA").encode())
var_ids = [x for x in weights.varID.values]
cov = numpy.cov([features_data_[k] for k in var_ids], ddof=1)
ids = [x for x in weights.rsid.values] if args.output_rsids else var_ids
cov = matrices._flatten_matrix_data([(gene_id_, ids, cov)])
for cov_ in cov:
l = "{} {} {} {}\n".format(cov_[0], cov_[1], cov_[2], cov_[3]).encode()
c.write(l)
def run(args):
Utilities.maybe_create_folder(args.intermediate_folder)
Utilities.ensure_requisite_folders(args.output_prefix)
logging.info("Opening data")
p_ = re.compile(args.data_name_pattern)
f = [x for x in sorted(os.listdir(args.data_folder)) if p_.search(x)]
tissue_names = [p_.search(x).group(1) for x in f]
data = []
for i in range(0, len(tissue_names)):
logging.info("Loading %s", tissue_names[i])
data.append((tissue_names[i],
pq.ParquetFile(os.path.join(args.data_folder, f[i]))))
data = collections.OrderedDict(data)
available_data = {
x
for p in data.values() for x in p.metadata.schema.names
}
logging.info("Preparing output")
WEIGHTS_FIELDS = [
"gene", "rsid", "varID", "ref_allele", "eff_allele", "weight"
]
SUMMARY_FIELDS = [
"gene", "genename", "gene_type", "alpha", "n_snps_in_window",
"n.snps.in.model", "rho_avg", "pred.perf.R2", "pred.perf.pval"
]
Utilities.ensure_requisite_folders(args.output_prefix)
if args.skip_regression:
weights, summaries, covariances = None, None, None
else:
weights, summaries, covariances = setup_output(args.output_prefix,
tissue_names,
WEIGHTS_FIELDS,
SUMMARY_FIELDS)
logging.info("Loading data annotation")
data_annotation = StudyUtilities._load_gene_annotation(
args.data_annotation)
data_annotation = data_annotation[data_annotation.gene_id.isin(
available_data)]
if args.chromosome or (args.sub_batches and args.sub_batch):
data_annotation = StudyUtilities._filter_gene_annotation(
data_annotation, args.chromosome, args.sub_batches, args.sub_batch)
logging.info("Kept %i entries", data_annotation.shape[0])
logging.info("Opening features annotation")
if not args.chromosome:
features_metadata = pq.read_table(args.features_annotation).to_pandas()
else:
features_metadata = pq.ParquetFile(
args.features_annotation).read_row_group(args.chromosome -
1).to_pandas()
if args.chromosome and args.sub_batches:
logging.info("Trimming variants")
features_metadata = StudyUtilities.trim_variant_metadata_on_gene_annotation(
features_metadata, data_annotation, args.window)
if args.rsid_whitelist:
logging.info("Filtering features annotation")
whitelist = TextFileTools.load_list(args.rsid_whitelist)
whitelist = set(whitelist)
features_metadata = features_metadata[features_metadata.rsid.isin(
whitelist)]
logging.info("Opening features")
features = pq.ParquetFile(args.features)
logging.info("Setting R seed")
seed = numpy.random.randint(1e8)
if args.run_tag:
d = pandas.DataFrame({
"run": [args.run_tag],
"cv_seed": [seed]
})[["run", "cv_seed"]]
for t in tissue_names:
Utilities.save_dataframe(
d, "{}_{}_runs.txt.gz".format(args.output_prefix, t))
failed_run = False
try:
for i, data_annotation_ in enumerate(data_annotation.itertuples()):
logging.log(9, "processing %i/%i:%s", i + 1,
data_annotation.shape[0], data_annotation_.gene_id)
logging.log(8, "loading data")
d_ = {}
for k, v in data.items():
d_[k] = Parquet._read(v, [data_annotation_.gene_id],
to_pandas=True)
features_ = Genomics.entries_for_gene_annotation(
data_annotation_, args.window, features_metadata)
if features_.shape[0] == 0:
logging.log(9, "No features available")
continue
features_data_ = Parquet._read(features,
[x for x in features_.id.values],
to_pandas=True)
features_data_["id"] = range(1, features_data_.shape[0] + 1)
features_data_ = features_data_[["individual", "id"] +
[x for x in features_.id.values]]
logging.log(8, "training")
prepare_ctimp(args.script_path, seed, args.intermediate_folder,
data_annotation_, features_, features_data_, d_)
del (features_data_)
del (d_)
if args.skip_regression:
continue
subprocess.call([
"bash",
_execution_script(args.intermediate_folder,
data_annotation_.gene_id)
])
w = pandas.read_table(_weights(args.intermediate_folder,
data_annotation_.gene_id),
sep="\s+")
s = pandas.read_table(_summary(args.intermediate_folder,
data_annotation_.gene_id),
sep="\s+")
for e_, entry in enumerate(s.itertuples()):
entry_weights = w[["SNP", "REF.0.", "ALT.1.",
entry.tissue]].rename(
columns={
"SNP": "varID",
"REF.0.": "ref_allele",
"ALT.1.": "eff_allele",
entry.tissue: "weight"
})
entry_weights = entry_weights[entry_weights.weight != 0]
entry_weights = entry_weights.assign(
gene=data_annotation_.gene_id)
entry_weights = entry_weights.merge(features_,
left_on="varID",
right_on="id",
how="left")
entry_weights = entry_weights[WEIGHTS_FIELDS]
if args.output_rsids:
entry_weights.loc[entry_weights.rsid == "NA",
"rsid"] = entry_weights.loc[
entry_weights.rsid == "NA", "varID"]
weights[entry.tissue].write(
entry_weights.to_csv(sep="\t",
index=False,
header=False,
na_rep="NA").encode())
entry_summary = s[s.tissue == entry.tissue].rename(
columns={
"zscore_pval": "pred.perf.pval",
"rho_avg_squared": "pred.perf.R2"
})
entry_summary = entry_summary.assign(
gene=data_annotation_.gene_id,
alpha=0.5,
genename=data_annotation_.gene_name,
gene_type=data_annotation_.gene_type,
n_snps_in_window=features_.shape[0])
entry_summary["n.snps.in.model"] = entry_weights.shape[0]
#must repeat strings beause of weird pandas indexing issue
entry_summary = entry_summary.drop(
["R2", "n", "tissue"], axis=1)[[
"gene", "genename", "gene_type", "alpha",
"n_snps_in_window", "n.snps.in.model", "rho_avg",
"pred.perf.R2", "pred.perf.pval"
]]
summaries[entry.tissue].write(
entry_summary.to_csv(sep="\t",
index=False,
header=False,
na_rep="NA").encode())
features_data_ = Parquet._read(
features, [x for x in entry_weights.varID.values],
to_pandas=True)
var_ids = [x for x in entry_weights.varID.values]
cov = numpy.cov([features_data_[k] for k in var_ids], ddof=1)
ids = [x for x in entry_weights.rsid.values
] if args.output_rsids else var_ids
cov = matrices._flatten_matrix_data([(data_annotation_.gene_id,
ids, cov)])
for cov_ in cov:
l = "{} {} {} {}\n".format(cov_[0], cov_[1], cov_[2],
cov_[3]).encode()
covariances[entry.tissue].write(l)
if not args.keep_intermediate_folder:
logging.info("Cleaning up")
shutil.rmtree(
_intermediate_folder(args.intermediate_folder,
data_annotation_.gene_id))
if args.MAX_M and i >= args.MAX_M:
logging.info("Early abort")
break
except Exception as e:
logging.info("Exception running model training:\n%s",
traceback.format_exc())
failed_run = True
finally:
pass
# if not args.keep_intermediate_folder:
# shutil.rmtree(args.intermediate_folder)
if not args.skip_regression:
set_down(weights, summaries, covariances, tissue_names, failed_run)
logging.info("Finished")
