def test_gtex_geno_lines_generator(self):
data = []
for i, line in enumerate(
GTExGenotype.gtex_geno_lines(
"tests/_td/genotype/gtex_like.txt.gz",
"tests/_td/genotype/gtex_snp.txt.gz")):
data.append(line)
header = GTExGenotype.gtex_geno_header(
"tests/_td/genotype/gtex_like.txt.gz")
gtex_ids = header[1:]
header = [
"rsid", "chromosome", "position", "ref_allele", "alt_allele",
"frequency"
] + gtex_ids
dataframe = Utilities.to_dataframe(data, header, to_numeric="ignore")
gtex_snp = pandas.read_table("tests/_td/genotype/gtex_snp.txt.gz")
dataframe_2 = pandas.read_table("tests/_td/genotype/gtex_like.txt.gz")
dataframe_2 = pandas.merge(dataframe_2,
gtex_snp,
left_on="Id",
right_on="VariantID")
compare_data_frames(dataframe, dataframe_2, gtex_ids)
def torture_dosage(metadata, dosage, gtex_ids):
d = [dosage[x] for x in metadata.rsid]
d = Utilities.to_dataframe(d, gtex_ids, to_numeric="ignore")
d["rsid"] = list(metadata.rsid)
d = pandas.merge(metadata, d, on="rsid")
d["number"] = list(range(0, len(d)))
d = d.set_index("number")
return d
def torture_dosage(metadata, dosage, gtex_ids):
d = [dosage[x] for x in metadata.rsid]
d = Utilities.to_dataframe(d, gtex_ids, to_numeric="ignore")
d["rsid"] = list(metadata.rsid)
d = pandas.merge(metadata, d, on="rsid")
d["number"] = range(0, len(d))
d = d.set_index("number")
return d
def test_gtex_geno_lines_generator(self):
data = []
for i, line in enumerate(GTExGenotype.gtex_geno_lines("tests/_td/genotype/gtex_like.txt.gz", "tests/_td/genotype/gtex_snp.txt.gz")):
data.append(line)
header = GTExGenotype.gtex_geno_header("tests/_td/genotype/gtex_like.txt.gz")
gtex_ids = header[1:]
header = ["rsid", "chromosome", "position", "ref_allele", "alt_allele", "frequency"]+gtex_ids
dataframe = Utilities.to_dataframe(data, header, to_numeric="ignore")
gtex_snp = pandas.read_table("tests/_td/genotype/gtex_snp.txt.gz")
dataframe_2 = pandas.read_table("tests/_td/genotype/gtex_like.txt.gz")
dataframe_2 = pandas.merge(dataframe_2,gtex_snp, left_on="Id", right_on="VariantID")
compare_data_frames(dataframe, dataframe_2, gtex_ids)
def run(args):
if os.path.exists(args.snp_covariance_output):
logging.info("%s already exists, you have to move it or delete it if you want it done again", args.snp_covariance_output)
return
start = timer()
logging.info("Loading models...")
model_manager = PredictionModel.load_model_manager(args.models_folder, name_pattern=args.models_pattern)
all_snps = model_manager.get_rsids()
logging.info("processing genotype")
for chromosome, metadata, dosage in GenotypeUtilities.genotype_by_chromosome_from_args(args, all_snps):
logging.log(9, "Processing chromosome %s", str(chromosome))
covariance_results = pandas.DataFrame()
context = GenotypeAnalysis.GenotypeAnalysisContext(metadata, dosage, model_manager)
genes = context.get_genes()
reporter = Utilities.PercentReporter(9, len(genes))
reporter.update(0, "%d %% of genes processed so far in chromosome " + str(chromosome))
for i,gene in enumerate(genes):
logging.log(6, "%d/%d:%s", i+1, len(genes), gene)
cov_data = GenotypeAnalysis.get_prediction_covariance(context, gene)
cov_data = MatrixManager._flatten_matrix_data([cov_data])
cov_data = Utilities.to_dataframe(cov_data, GenotypeAnalysis.COVARIANCE_COLUMNS, to_numeric="ignore", fill_na="NA")
covariance_results = pandas.concat([covariance_results, cov_data])
reporter.update(i, "%d %% of genes processed so far in chromosome "+str(chromosome))
reporter.update(len(genes), "%d %% of genes processed so far in chromosome " + str(chromosome))
logging.log(9, "writing chromosome results")
Utilities.save_dataframe(covariance_results, args.snp_covariance_output,
mode="w" if chromosome ==1 else "a",
header=chromosome==1)
end = timer()
logging.info("Ran covariance builder in %s seconds" % (str(end - start)))