summaryrefslogtreecommitdiff
path: root/src/python/multifasta_to_otu
diff options
context:
space:
mode:
authorCalvin <calvin@EESI>2013-05-14 19:50:28 -0400
committerCalvin <calvin@EESI>2013-05-14 19:50:28 -0400
commit3631a0c9d47d8ff72085bcc534bd24bfad4f73da (patch)
treea259116534e6b5522d065e7dd46a414d54d57075 /src/python/multifasta_to_otu
parent7ab43937c81ad5af1b7d6b5b1d3c317b58881e84 (diff)
use sensing matrix
Diffstat (limited to 'src/python/multifasta_to_otu')
-rwxr-xr-xsrc/python/multifasta_to_otu34
1 files changed, 17 insertions, 17 deletions
diff --git a/src/python/multifasta_to_otu b/src/python/multifasta_to_otu
index 3cc8f3e..431cc74 100755
--- a/src/python/multifasta_to_otu
+++ b/src/python/multifasta_to_otu
@@ -26,14 +26,14 @@ def main():
global input_directory
global output_directory
global lamb
- global trained_matrix
+ global sensing_matrix
parser = argparse.ArgumentParser(description="MultifastaOTU")
parser.add_argument("-i", "--input-directory", help="directory containing fasta files", required=True)
parser.add_argument("-o", "--otu-table", help="otu_table", required=True)
- parser.add_argument("-t", "--trained-matrix", help="your trained matrix ", required=True)
- parser.add_argument("-f", "--trained-fasta", help="the fasta file used to train your matrix", required=True)
+ parser.add_argument("-s", "--sensing-matrix", help="your sensing matrix ", required=True)
+ parser.add_argument("-f", "--sensing-fasta", help="the fasta file used to train your matrix", required=True)
parser.add_argument("-l", "--lamb", type=int, help="the default lambda value is 10,000")
parser.add_argument("-k", "--kmer", type=int, help="specifies which kmer to use, default=6")
parser.add_argument("-j", "--jobs", type=int, help="specifies how many jobs to run at once, default=number of CPUs")
@@ -41,18 +41,18 @@ def main():
# our defaults
jobs = multiprocessing.cpu_count()
- trained_matrix = args.trained_matrix
+ sensing_matrix = args.sensing_matrix
input_directory = args.input_directory
# Make sure our input exist
if not os.path.isdir(args.input_directory):
parser.error("Input directory not found")
- if not os.path.isfile(args.trained_matrix):
- parser.error("Custom trained matrix not found")
+ if not os.path.isfile(args.sensing_matrix):
+ parser.error("Custom sensing matrix not found")
- if not os.path.isfile(args.trained_fasta):
- parser.error("Fasta file of trained matrix not found")
+ if not os.path.isfile(args.sensing_fasta):
+ parser.error("Fasta file of sensing matrix not found")
# use alternative lambda
if args.lamb is not None:
@@ -64,13 +64,13 @@ def main():
if args.kmer is not None:
kmer = args.kmer
- # Load trained matrix
- if q.is_compressed(args.trained_matrix):
- trained_matrix_file = gzip.open(args.trained_matrix, "rb")
+ # Load sensing matrix
+ if q.is_compressed(args.sensing_matrix):
+ sensing_matrix_file = gzip.open(args.sensing_matrix, "rb")
else:
- trained_matrix_file = open(args.trained_matrix, "rb")
+ sensing_matrix_file = open(args.sensing_matrix, "rb")
- trained_matrix = np.load(trained_matrix_file)
+ sensing_matrix = np.load(sensing_matrix_file)
fasta_list = []
@@ -89,10 +89,10 @@ def main():
# Create an array of headers
headers = []
- trained_matrix_headers = open(args.trained_fasta, "rU")
- for header in SeqIO.parse(trained_matrix_headers, "fasta"):
+ sensing_matrix_headers = open(args.sensing_fasta, "rU")
+ for header in SeqIO.parse(sensing_matrix_headers, "fasta"):
headers.append(header.id)
- trained_matrix_headers.close()
+ sensing_matrix_headers.close()
# create our number of reads matrix
number_of_reads = np.zeros((len(headers), len(fasta_list)))
@@ -148,7 +148,7 @@ def main():
def quikr_call(fasta_file):
print os.path.basename(fasta_file)
- xstar = q.calculate_estimated_frequencies(fasta_file, trained_matrix, kmer, lamb)
+ xstar = q.calculate_estimated_frequencies(fasta_file, sensing_matrix, kmer, lamb)
return xstar
if __name__ == "__main__":