def test_writeFASTA(self): read_fasta_data = bioio.readFASTA(['sample1.fasta'])['sample1'] read_fasta_data_seqids = bioio.splitFASTA(read_fasta_data)['output_seq_ids'] read_fasta_data_seqs = bioio.splitFASTA(read_fasta_data)['output_seqs'] bioio.writeFASTA('rewritten_sample1.fasta',read_fasta_data_seqids,read_fasta_data_seqs) self.assertEqual(bioio.readFASTA(['rewritten_sample1.fasta'])['rewritten_sample1'],read_fasta_data) os.remove('rewritten_sample1.fasta')
def test_writeFASTA(self): read_fasta_data = bioio.readFASTA(['sample1.fasta'])['sample1'] read_fasta_data_seqids = bioio.splitFASTA( read_fasta_data)['output_seq_ids'] read_fasta_data_seqs = bioio.splitFASTA(read_fasta_data)['output_seqs'] bioio.writeFASTA('rewritten_sample1.fasta', read_fasta_data_seqids, read_fasta_data_seqs) self.assertEqual( bioio.readFASTA(['rewritten_sample1.fasta'])['rewritten_sample1'], read_fasta_data) os.remove('rewritten_sample1.fasta')
@author: thatbudakguy """ import sys import os sys.path.append(os.path.join(sys.path[0],'lib')) sys.path.append(os.path.join(sys.path[0],'test')) import bioio import biomath # strip file extension and read file read_csv = bioio.readCSV([sys.argv[-1]]) input_csv_name = sys.argv[-1][:-4] input_csv_data = read_csv[input_csv_name] # find longest sequences and get their corresponding ids output_csv_data = biomath.findLongestSeq(input_csv_data) output_seq_ids = bioio.splitCSV(output_csv_data)['output_seq_ids'] output_seqs = bioio.splitCSV(output_csv_data)['output_seqs'] output_seq_ids_txt = bioio.addGreaterThans(output_seq_ids) # define names of the resulting files output_csv_name = input_csv_name+"_trimmed.csv" output_txt_name = input_csv_name+"_names_only.txt" output_fasta_name = input_csv_name+".fasta" # write the resulting data to files bioio.writeCSV(output_csv_name,output_csv_data) bioio.writeTXT(output_txt_name,output_seq_ids_txt) bioio.writeFASTA(output_fasta_name,output_seq_ids,output_seqs)
""" @author: thatbudakguy """ import sys import os sys.path.append(os.path.join(sys.path[0],'lib')) sys.path.append(os.path.join(sys.path[0],'test')) import bioio import biomath # strip file extensions,'>' and read files read_fasta = bioio.readFASTA([sys.argv[-2]]) input_fasta_name = sys.argv[-2][:-6] input_fasta_data = read_fasta[input_fasta_name] input_fasta_splitdata = bioio.splitFASTA(input_fasta_data) input_fasta_seq_ids = input_fasta_splitdata['output_seq_ids'] input_fasta_seqs = input_fasta_splitdata['output_seqs'] read_txt = bioio.readTXT([sys.argv[-1]]) input_txt_name = sys.argv[-1][:-4] input_txt_data = read_txt[input_txt_name] # find seqs from database using seqids list output_fasta_data = biomath.reduceNames(input_txt_data,input_fasta_seq_ids,input_fasta_seqs) output_seq_ids = output_fasta_data['output_seq_ids'] output_seqs = output_fasta_data['output_seqs'] # write the seqs to the file output_fasta_name = input_fasta_name+"_concatenated.fasta" bioio.writeFASTA(output_fasta_name,output_seq_ids,output_seqs)