Python GEOparse.parse_GSM Examples

Example #1

File: expr_converter.py Project: cmdoret/case_studies

import GEOparse
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

probes_conv = GEOparse.parse_GSM( \
    "/home/cyril/Documents/Master/sem_1/Case_study/module1/data/GPL6457_old_annotations.txt.gz")

gse = GEOparse.get_GEO("GSE24616", destdir="./")
# gse = GEOparse.get_GEO(filepath="./GSM606890.TXT.GZ.soft")

char = {"stage": [], "time": [], "sex": [], "sample_name": []}
for gsm_name, gsm in sorted(gse.gsms.iteritems()):
    char["stage"].append(gsm.metadata['characteristics_ch1'][1].split(": ")[1])
    char["time"].append(gsm.metadata['characteristics_ch1'][2].split(": ")[1])
    char["sex"].append(gsm.metadata['characteristics_ch1'][3].split(": ")[1])
    char["sample_name"].append(gsm.name)

print(char["stage"][3], char["time"][3], char["sex"][3],
      char["sample_name"][3])

GPL = gse.gpls.values()[0]
pivoted_samples = gse.pivot_samples('VALUE')
pivoted_samples.set_index(GPL.table.SPOT_ID, inplace=True)

# pivoted_samples.hist()

strata = pd.read_csv("../phylostrata.txt", sep="\t", header=None)
strata.columns = ["GeneID", "ProbeID", "age"]
strata.set_index("ProbeID", inplace=True)