Mercurial > repos > artbio > small_rna_signatures

comparison overlapping_reads.py @ 13:124f404b0fe7 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_signatures commit bc672cf9d5fe9c1f7eaf02abdc906cf2c1763668
author artbio
date Sat, 25 Feb 2023 09:54:28 +0000
parents 8d3ca9652a5b
children
comparison
equal deleted inserted replaced
12:aa5e2c64dff8 13:124f404b0fe7
88 def countpairs(self, uppers, lowers): 88 def countpairs(self, uppers, lowers):
89 query_range = self.query_range 89 query_range = self.query_range
90 target_range = self.target_range 90 target_range = self.target_range
91 uppers = [seq for seq in uppers if (len(seq) in query_range or len(seq) 91 uppers = [seq for seq in uppers if (len(seq) in query_range or len(seq)
92 in target_range)] 92 in target_range)]
93 print(uppers)
94 uppers_expanded = [] 93 uppers_expanded = []
95 for seq in uppers: 94 for seq in uppers:
96 expand = [seq for i in range(self.readdic[seq])] 95 expand = [seq for i in range(self.readdic[seq])]
97 uppers_expanded.extend(expand) 96 uppers_expanded.extend(expand)
98 print(uppers_expanded)
99 uppers = uppers_expanded 97 uppers = uppers_expanded
100 lowers = [seq for seq in lowers if (len(seq) in query_range or len(seq) 98 lowers = [seq for seq in lowers if (len(seq) in query_range or len(seq)
101 in target_range)] 99 in target_range)]
102 lowers_expanded = [] 100 lowers_expanded = []
103 for seq in lowers: 101 for seq in lowers:
121 target_range = self.target_range 119 target_range = self.target_range
122 overlap = self.overlap 120 overlap = self.overlap
123 stringresult = [] 121 stringresult = []
124 header_template = '>%s|coord=%s|strand %s|size=%s|nreads=%s\n%s\n' 122 header_template = '>%s|coord=%s|strand %s|size=%s|nreads=%s\n%s\n'
125 total_pairs = 0 123 total_pairs = 0
126 print('Chromosome\tNbre of pairs')
127 for chrom in sorted(self.chromosomes): 124 for chrom in sorted(self.chromosomes):
128 number_pairs = 0 125 number_pairs = 0
129 for pos in self.all_query_positions[chrom]: 126 for pos in self.all_query_positions[chrom]:
130 stringbuffer = [] 127 stringbuffer = []
131 uppers = self.alignement_dic[chrom, pos, 'F'] 128 uppers = self.alignement_dic[chrom, pos, 'F']
147 header_template % 144 header_template %
148 (chrom, pos+overlap-len(downread)+1, '-', 145 (chrom, pos+overlap-len(downread)+1, '-',
149 len(downread), self.readdic[downread], 146 len(downread), self.readdic[downread],
150 self.revcomp(downread))) 147 self.revcomp(downread)))
151 stringresult.extend(sorted(set(stringbuffer))) 148 stringresult.extend(sorted(set(stringbuffer)))
152 print('%s\t%s' % (chrom, number_pairs))
153 print('Total nbre of pairs that can be simultaneously formed\t%s'
154 % total_pairs)
155 F.write(''.join(stringresult)) 149 F.write(''.join(stringresult))
156 150
157 def revcomp(self, sequence): 151 def revcomp(self, sequence):
158 antidict = {"A": "T", "T": "A", "G": "C", "C": "G", "N": "N"} 152 antidict = {"A": "T", "T": "A", "G": "C", "C": "G", "N": "N"}
159 revseq = sequence[::-1] 153 revseq = sequence[::-1]