# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import argparse
import pandas as pd
import numpy as np
import entrez
import rnaseq_atlas
from load_rna_data import load_rsem
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--filename",
"-f",
required=True,
help="""File with two tab separated columns: Entrez gene IDs and RSEM expression values""")
parser.add_argument(
"pattern",
help="Gene name, part of a gene name, or regular expression ")
args = parser.parse_args()
df = load_rsem(args.filename, translate_entrez_ids = True)
mask = df.Hugo.str.contains(args.pattern)
subset = df[mask]
if len(subset) == 0:
print "Pattern %s not found" % args.pattern
else:
print subset
help="Which column to select from the reference")
parser.add_argument(
"--percentile",
help="Which rank percentile do we consider 'low'?",
type = float,
default = 0.25)
parser.add_argument(
"--compare-rsem",
default = False,
action = "store_true",
help = "Compare RSEM values directly instead of rank (default: False)")
args = parser.parse_args()
if not args.sample_uses_hugo_ids:
hugo_df = load_rsem(args.sample, translate_entrez_ids = True)
else:
hugo_df = load_rsem(args.sample, translate_entrez_ids = False)
group_rank_method = 'average'
if args.normal is None:
if args.compare_rsem:
normal_df = rnaseq_atlas.hugo_to_rpkm()
else:
normal_df = rnaseq_atlas.hugo_to_rank(group_rank_method)
tissue_cols = rnaseq_atlas.TISSUE_COLUMNS
else:
normal_df = pd.read_csv(args.normal)
normal_df = hugo_mapping.merge(normal_df, on = "Entrez")
normal_df = normal_df.drop("Entrez", axis=1)
tissue_cols = normal_df.columns[1:]
