| Previous changeset 4:20d28cfdeefe (2017-09-08) Next changeset 6:4da23f009c9e (2017-09-10) |
|
Commit message:
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_signatures commit 24d44a9b7ec9db4dce3d839b597eea2b1be34adb |
|
modified:
overlapping_reads.py overlapping_reads.xml test-data/paired.fa test-data/paired_2.fa |
|
added:
test-data/paired_3.fa test-data/paired_4.fa |
| b |
| diff -r 20d28cfdeefe -r a7fd04208764 overlapping_reads.py --- a/overlapping_reads.py Fri Sep 08 04:44:22 2017 -0400 +++ b/overlapping_reads.py Sat Sep 09 11:57:39 2017 -0400 |
| [ |
| b"@@ -32,12 +32,20 @@\n \n class Map:\n \n- def __init__(self, bam_file):\n+ def __init__(self, bam_file, output, minquery=23, maxquery=29,\n+ mintarget=23, maxtarget=29, overlap=10):\n self.bam_object = pysam.AlignmentFile(bam_file, 'rb')\n+ self.output = output\n+ self.query_range = range(minquery, maxquery + 1)\n+ self.target_range = range(mintarget, maxtarget + 1)\n+ self.overlap = overlap\n self.chromosomes = dict(zip(self.bam_object.references,\n self.bam_object.lengths))\n- self.all_query_positions = self.query_positions(self.bam_object)\n+ self.alignement_dic = self.index_alignments(self.bam_object)\n+ self.all_query_positions = self.query_positions(self.bam_object,\n+ overlap=self.overlap)\n self.readdic = self.make_readdic(self.bam_object)\n+ self.pairing()\n \n def make_readdic(self, bam_object):\n readdic = defaultdict(int)\n@@ -45,90 +53,67 @@\n readdic[read.query_sequence] += 1\n return readdic\n \n- def query_positions(self, bam_object):\n- all_query_positions = defaultdict(list)\n+ def index_alignments(self, bam_object):\n+ '''\n+ dic[(chrom, pos, polarity)]: [readseq1, readseq2, ...]\n+ the list value is further converted in set\n+ '''\n+ dic = defaultdict(list)\n for chrom in self.chromosomes:\n for read in bam_object.fetch(chrom):\n- if not read.is_reverse:\n- all_query_positions[chrom].append(\n- read.reference_start)\n+ if read.is_reverse:\n+ coord = read.reference_end-1\n+ pol = 'R'\n else:\n- all_query_positions[chrom].append(\n- read.reference_end)\n+ coord = read.reference_start\n+ pol = 'F'\n+ dic[(chrom, coord, pol)].append(read.query_sequence)\n+ for key in dic:\n+ dic[key] = set(dic[key])\n+ return dic\n+\n+ def query_positions(self, bam_object, overlap):\n+ all_query_positions = defaultdict(list)\n+ for genomicKey in self.alignement_dic.keys():\n+ chrom, coord, pol = genomicKey\n+ if pol == 'F' and len(self.alignement_dic[(chrom,\n+ coord+overlap-1,\n+ 'R')]) > 0:\n+ all_query_positions[chrom].append(coord)\n+ for chrom in all_query_positions:\n all_query_positions[chrom] = sorted(\n list(set(all_query_positions[chrom])))\n return all_query_positions\n \n- def direct_pairing(self, minquery, maxquery, mintarget, maxtarget,\n- file, overlap=10):\n- F = open(file, 'w')\n- query_range = range(minquery, maxquery + 1)\n- target_range = range(mintarget, maxtarget + 1)\n+ def pairing(self):\n+ F = open(self.output, 'w')\n+ query_range = self.query_range\n+ target_range = self.target_range\n+ overlap = self.overlap\n stringresult = []\n+ header_template = '>%s|coord=%s|strand %s|size=%s|nreads=%s\\n%s\\n'\n for chrom in sorted(self.chromosomes):\n- for pos in (self.all_query_positions[chrom]):\n- iterreads_1 = self.bam_object.fetch(chrom,\n- start=pos, end=pos+overlap-1)\n- iterreads_2 = self.bam_object.fetch(chrom,\n- start=pos, end=pos+overlap-1)\n- iterreads_3 = self.bam_object.fetch(chrom,\n- start=pos, end=pos+overlap-1)\n- iterreads_4 = self.bam_object.fetch(chrom,\n- start=pos, end=pos+overlap-1)"..b' (chrom, targetread.reference_start+1,\n- \'R\', targetread.query_alignment_length,\n- self.readdic[targetread.query_sequence],\n- targetreadseq))\n- # 2\n- for queryread in iterreads_3:\n- if queryread.reference_end-1 == pos+overlap-1 and \\\n- queryread.query_alignment_length in query_range \\\n- and queryread.is_reverse:\n- for targetread in iterreads_4:\n- if (targetread.\n- reference_start\n- == pos and targetread.query_alignment_length\n- in target_range and not\n- targetread.is_reverse):\n- queryreadseq = self.revcomp(\n- queryread.query_sequence)\n- targetreadseq = targetread.query_sequence\n- stringresult.append(\n- \'>%s|%s|%s|%s|n=%s\\n%s\\n\' %\n- (chrom, queryread.reference_start+1, \'R\',\n- queryread.query_alignment_length,\n- self.readdic[queryread.query_sequence],\n- queryreadseq))\n- stringresult.append(\n- \'>%s|%s|%s|%s|n=%s\\n%s\\n\' %\n- (chrom, targetread.reference_start+1,\n- \'F\', targetread.query_alignment_length,\n- self.readdic[targetread.query_sequence],\n- targetreadseq))\n- stringresult = sorted(set(stringresult),\n- key=lambda x: stringresult.index(x))\n+ for pos in self.all_query_positions[chrom]:\n+ stringbuffer = []\n+ uppers = self.alignement_dic[chrom, pos, \'F\']\n+ lowers = self.alignement_dic[chrom, pos+overlap-1, \'R\']\n+ if uppers and lowers:\n+ for upread in uppers:\n+ for downread in lowers:\n+ if (len(upread) in query_range and len(downread) in\n+ target_range) or (len(upread) in target_range\n+ and len(downread) in\n+ query_range):\n+ stringbuffer.append(\n+ header_template %\n+ (chrom, pos+1, \'+\', len(upread),\n+ self.readdic[upread], upread))\n+ stringbuffer.append(\n+ header_template %\n+ (chrom, pos+overlap-len(downread)+1, \'-\',\n+ len(downread), self.readdic[downread],\n+ self.revcomp(downread)))\n+ stringresult.extend(sorted(set(stringbuffer)))\n F.write(\'\'.join(stringresult))\n \n def revcomp(self, sequence):\n@@ -137,13 +122,7 @@\n return "".join([antidict[i] for i in revseq])\n \n \n-def main(input, minquery, maxquery, mintarget, maxtarget, output, overlap=10):\n- mapobj = Map(input)\n- mapobj.direct_pairing(minquery, maxquery, mintarget, maxtarget,\n- output, overlap)\n-\n-\n if __name__ == "__main__":\n args = Parser()\n- main(args.input, args.minquery, args.maxquery, args.mintarget,\n- args.maxtarget, args.output, args.overlap)\n+ mapobj = Map(args.input, args.output, args.minquery, args.maxquery,\n+ args.mintarget, args.maxtarget, args.overlap)\n' |
| b |
| diff -r 20d28cfdeefe -r a7fd04208764 overlapping_reads.xml --- a/overlapping_reads.xml Fri Sep 08 04:44:22 2017 -0400 +++ b/overlapping_reads.xml Sat Sep 09 11:57:39 2017 -0400 |
| b |
| @@ -1,4 +1,4 @@ -<tool id="overlapping_reads" name="Get overlapping reads" version="0.9.3"> +<tool id="overlapping_reads" name="Get overlapping reads" version="0.9.4"> <description /> <requirements> <requirement type="package" version="0.11.2.1=py27_0">pysam</requirement> @@ -47,6 +47,24 @@ <param name="overlap" value="10" /> <output file="paired_2.fa" ftype="fasta" name="output" /> </test> + <test> + <param ftype="bam" name="input" value="sr_bowtie.bam" /> + <param name="minquery" value="23" /> + <param name="maxquery" value="29" /> + <param name="mintarget" value="20" /> + <param name="maxtarget" value="22" /> + <param name="overlap" value="10" /> + <output file="paired_3.fa" ftype="fasta" name="output" /> + </test> + <test> + <param ftype="bam" name="input" value="sr_bowtie.bam" /> + <param name="minquery" value="20" /> + <param name="maxquery" value="22" /> + <param name="mintarget" value="20" /> + <param name="maxtarget" value="22" /> + <param name="overlap" value="10" /> + <output file="paired_4.fa" ftype="fasta" name="output" /> + </test> </tests> <help> @@ -70,10 +88,12 @@ overlap. Searching query reads of 20-22 nt that overlap by 10 nt with target -reads of 23-29 nt is different from searching query reads of 23-29 nt that overlap by 10 nt -with target reads of 20-22 nt. i.e, searching for siRNAs that pair with piRNAs is distinct -from searching for siRNAs that pairs with piRNAs, although of course the number of possibly -formed piRNA/siRNA pairs is the same as the number of possibly formed siRNA/piRNA pairs. +reads of 23-29 nt is equivalent to searching query reads of 23-29 nt that overlap by 10 nt +with target reads of 20-22 nt. i.e, searching for siRNAs that pair with piRNAs is equivalent +to searching for siRNAs that pairs with piRNAs. In contrast, searching query reads of 20-22 nt +that overlap by 10 nt with target reads of 23-29 nt is different from searching query reads of +23-29 nt that overlap by 10 nt with target reads of 23-29 nt, since the number of "heterotypic" +pairs of reads is likely to be different from the number of "homotypic" pairs of reads. *Overlap* The number of nucleotides by which the pairs of sequences will overlap @@ -84,17 +104,18 @@ a fasta file of pairable reads such as : ->FBgn0000004_17.6|5855|F|23|n=1 +>FBgn0000004_17.6|coord=5839|strand -|size=26|nreads=1 + +TTTTCGTCAATTGTGCCAAATAGGTA + +>FBgn0000004_17.6|coord=5855|strand +|size=23|nreads=1 TTGACGAAAATGATCGAGTGGAT ->FBgn0000004_17.6|5839|R|26|n=1 - -TTTTCGTCAATTGTGCCAAATAGGTA where FBgn0000004_17.6 stands for the chromosome, 5839 stands for the 1-based read position, -R stand for reverse strand (F forward strand), 26 stands for the size of the sequence and -n=1 stands for the number of reads of the sequence in the dataset. +'strand -' stands for lower strand of chromosome, 26 stands for the size of the sequence and +nreads=1 stands for the number of reads of the sequence in the dataset. the second sequence in this example corresponds to 1 read that overlap by 10 nt with 1 read of the first sequence. |
| b |
| diff -r 20d28cfdeefe -r a7fd04208764 test-data/paired.fa --- a/test-data/paired.fa Fri Sep 08 04:44:22 2017 -0400 +++ b/test-data/paired.fa Sat Sep 09 11:57:39 2017 -0400 |
| b |
| b'@@ -1,668 +1,668 @@\n->FBgn0000004_17.6|5855|F|23|n=1\n-TTGACGAAAATGATCGAGTGGAT\n->FBgn0000004_17.6|5839|R|26|n=1\n+>FBgn0000004_17.6|coord=5839|strand -|size=26|nreads=1\n TTTTCGTCAATTGTGCCAAATAGGTA\n->FBgn0000006_412|759|F|24|n=3\n-TTTGGTCGAAAGCTCTAAAGCTAC\n->FBgn0000006_412|742|R|27|n=1\n+>FBgn0000004_17.6|coord=5855|strand +|size=23|nreads=1\n+TTGACGAAAATGATCGAGTGGAT\n+>FBgn0000006_412|coord=742|strand -|size=27|nreads=1\n TTCGACCAAACCGGTGGCGTTTGCTGA\n->FBgn0000006_412|744|R|25|n=2\n+>FBgn0000006_412|coord=744|strand -|size=25|nreads=2\n TTCGACCAAACCGGTGGCGTTTGCT\n->FBgn0000006_412|745|R|24|n=2\n+>FBgn0000006_412|coord=745|strand -|size=24|nreads=2\n TTCGACCAAACCGGTGGCGTTTGC\n->FBgn0000006_412|759|F|25|n=1\n+>FBgn0000006_412|coord=759|strand +|size=24|nreads=3\n+TTTGGTCGAAAGCTCTAAAGCTAC\n+>FBgn0000006_412|coord=759|strand +|size=25|nreads=1\n TTTGGTCGAAAGCTCTAAAGCTACA\n->FBgn0000006_412|759|F|27|n=3\n+>FBgn0000006_412|coord=759|strand +|size=27|nreads=3\n TTTGGTCGAAAGCTCTAAAGCTACATG\n->FBgn0000006_412|760|F|26|n=6\n-TTGGTCGAAAGCTCTAAAGCTACATG\n->FBgn0000006_412|744|R|26|n=2\n+>FBgn0000006_412|coord=744|strand -|size=26|nreads=2\n TTTCGACCAAACCGGTGGCGTTTGCT\n->FBgn0000006_412|745|R|25|n=1\n+>FBgn0000006_412|coord=745|strand -|size=25|nreads=1\n TTTCGACCAAACCGGTGGCGTTTGC\n->FBgn0000007_1731|4555|F|24|n=1\n+>FBgn0000006_412|coord=760|strand +|size=26|nreads=6\n+TTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000007_1731|coord=4539|strand -|size=26|nreads=1\n+TTGAGAGCAAAGGCCGAATGAGTAAA\n+>FBgn0000007_1731|coord=4555|strand +|size=24|nreads=1\n TTGCTCTCAATGCGCTGAGTTTGG\n->FBgn0000007_1731|4539|R|26|n=1\n-TTGAGAGCAAAGGCCGAATGAGTAAA\n->FBgn0000155_roo|2176|F|24|n=1\n-TTTTGACCAAGCGGTATGAGAATA\n->FBgn0000155_roo|2159|R|27|n=1\n+>FBgn0000155_roo|coord=2159|strand -|size=27|nreads=1\n TTGGTCAAAAACTCCCAAGTGGCTTCA\n->FBgn0000155_roo|2161|R|25|n=1\n+>FBgn0000155_roo|coord=2161|strand -|size=25|nreads=1\n TTGGTCAAAAACTCCCAAGTGGCTT\n->FBgn0000155_roo|2692|F|24|n=1\n-TTGGTAAAAAATGTATAAGTGAGC\n->FBgn0000155_roo|2675|R|27|n=1\n+>FBgn0000155_roo|coord=2176|strand +|size=24|nreads=1\n+TTTTGACCAAGCGGTATGAGAATA\n+>FBgn0000155_roo|coord=2675|strand -|size=27|nreads=1\n TTTTTACCAAACGGATGCCTCAGACAT\n->FBgn0000155_roo|2676|R|26|n=5\n+>FBgn0000155_roo|coord=2676|strand -|size=26|nreads=5\n TTTTTACCAAACGGATGCCTCAGACA\n->FBgn0000155_roo|2677|R|25|n=14\n+>FBgn0000155_roo|coord=2677|strand -|size=25|nreads=14\n TTTTTACCAAACGGATGCCTCAGAC\n->FBgn0000155_roo|2678|R|24|n=14\n+>FBgn0000155_roo|coord=2678|strand -|size=24|nreads=14\n TTTTTACCAAACGGATGCCTCAGA\n->FBgn0000155_roo|2679|R|23|n=2\n+>FBgn0000155_roo|coord=2679|strand -|size=23|nreads=2\n TTTTTACCAAACGGATGCCTCAG\n->FBgn0000155_roo|2692|F|27|n=1\n+>FBgn0000155_roo|coord=2692|strand +|size=24|nreads=1\n+TTGGTAAAAAATGTATAAGTGAGC\n+>FBgn0000155_roo|coord=2692|strand +|size=27|nreads=1\n TTGGTAAAAAATGTATAAGTGAGCAGC\n->FBgn0000155_roo|3149|F|26|n=1\n-TTTTAATAAACCGGGTCGCATTGATT\n->FBgn0000155_roo|3132|R|27|n=1\n+>FBgn0000155_roo|coord=3132|strand -|size=27|nreads=1\n TTTATTAAAATCGGGGTCGGCTAATTT\n->FBgn0000155_roo|3241|F|24|n=1\n-TTGGGCAAAAAACTGATTTCGGGT\n->FBgn0000155_roo|3225|R|26|n=1\n+>FBgn0000155_roo|coord=3149|strand +|size=26|nreads=1\n+TTTTAATAAACCGGGTCGCATTGATT\n+>FBgn0000155_roo|coord=3225|strand -|size=26|nreads=1\n TTTTGCCCAAGGAGACCGTCTATTTT\n->FBgn0000155_roo|3226|R|25|n=1\n+>FBgn0000155_roo|coord=3226|strand -|size=25|nreads=1\n TTTTGCCCAAGGAGACCGTCTATTT\n->FBgn0000155_roo|3227|R|24|n=2\n+>FBgn0000155_roo|coord=3227|strand -|size=24|nreads=2\n TTTTGCCCAAGGAGACCGTCTATT\n->FBgn0000155_roo|3228|R|23|n=1\n+>FBgn0000155_roo|coord=3228|strand -|size=23|nreads=1\n TTTTGCCCAAGGAGACCGTCTAT\n->FBgn0000155_roo|3241|F|27|n=1\n+>FBgn0000155_roo|coord=3241|strand +|size=24|nreads=1\n+TTGGGCAAAAAACTGATTTCGGGT\n+>FBgn0000155_roo|coord=3241|strand +|size=27|nreads=1\n TTGGGCAAAAAACTGATTTCGGGTGGA\n->FBgn0000155_roo|3241|F|28|n=1\n+>FBgn0000155_roo|coord=3241|strand +|size=28|nreads=1\n TTGGGCAAAAAACTGATTTCGGGTGGAT\n->FBgn0000155_roo|8655|F|25|n=1\n-TTTGGCAGAATGTTCACACATGAAA\n->FBgn0000155_roo|8639|R|26|n=1\n+>FBgn0000155_roo|coord'..b'34_Doc2-element|3606|R|27|n=2\n+>FBgn0063534_Doc2-element|coord=3606|strand -|size=27|nreads=2\n TTTTTGCGAAAGCCAAACTGATGCGAT\n->FBgn0063534_Doc2-element|3607|R|26|n=4\n+>FBgn0063534_Doc2-element|coord=3607|strand -|size=26|nreads=4\n TTTTTGCGAAAGCCAAACTGATGCGA\n->FBgn0063534_Doc2-element|3608|R|25|n=7\n+>FBgn0063534_Doc2-element|coord=3608|strand -|size=25|nreads=7\n TTTTTGCGAAAGCCAAACTGATGCG\n->FBgn0063534_Doc2-element|3609|R|24|n=1\n+>FBgn0063534_Doc2-element|coord=3609|strand -|size=24|nreads=1\n TTTTTGCGAAAGCCAAACTGATGC\n->FBgn0063534_Doc2-element|3610|R|23|n=3\n+>FBgn0063534_Doc2-element|coord=3610|strand -|size=23|nreads=3\n TTTTTGCGAAAGCCAAACTGATG\n->FBgn0063534_Doc2-element|3623|F|26|n=1\n+>FBgn0063534_Doc2-element|coord=3623|strand +|size=23|nreads=1\n+TTCGCAAAAATCACGGAACGATC\n+>FBgn0063534_Doc2-element|coord=3623|strand +|size=26|nreads=1\n TTCGCAAAAATCACGGAACGATCGAA\n->FBgn0063594_Cr1a|2054|F|24|n=2\n-TTTGTAACAAGTCCTGAAAGTGTG\n->FBgn0063594_Cr1a|2037|R|27|n=1\n+>FBgn0063594_Cr1a|coord=2037|strand -|size=27|nreads=1\n TTGTTACAAGACATAGATCCAACAGTC\n->FBgn0063594_Cr1a|2039|R|25|n=1\n+>FBgn0063594_Cr1a|coord=2039|strand -|size=25|nreads=1\n TTGTTACAAAACATAGATCCAACAG\n->FBgn0063919_Max-element|3898|F|23|n=1\n-TTCTCAGCAAGTTCTGGGAGGTG\n->FBgn0063919_Max-element|3879|R|29|n=1\n+>FBgn0063594_Cr1a|coord=2054|strand +|size=24|nreads=2\n+TTTGTAACAAGTCCTGAAAGTGTG\n+>FBgn0063919_Max-element|coord=3879|strand -|size=29|nreads=1\n TTGCTGAGAAGCGTGTTGAGCGAATCAGG\n->FBgn0063919_Max-element|3880|R|28|n=1\n+>FBgn0063919_Max-element|coord=3880|strand -|size=28|nreads=1\n TTGCTGAGAAGCGTGTCGAGCGAATCAG\n->FBgn0063919_Max-element|3880|R|28|n=1\n+>FBgn0063919_Max-element|coord=3880|strand -|size=28|nreads=1\n TTGCTGAGAAGCGTGTTGAGCGAATCAG\n->FBgn0063919_Max-element|3882|R|26|n=1\n+>FBgn0063919_Max-element|coord=3882|strand -|size=26|nreads=1\n TTGCTGAGAAGCGTGTCGAGCGAATC\n->FBgn0063919_Max-element|3883|R|25|n=1\n+>FBgn0063919_Max-element|coord=3883|strand -|size=25|nreads=1\n TTGCTGAGAAGCGTGTCGAGCGAAT\n->FBgn0063919_Max-element|3884|R|24|n=1\n+>FBgn0063919_Max-element|coord=3884|strand -|size=24|nreads=1\n TTGCTGAGAAGCGTGTTGAGCGAA\n->FBgn0063919_Max-element|3898|F|24|n=2\n-TTCTCAGCAAGTTCTGGGAGGTGG\n->FBgn0063919_Max-element|3898|F|25|n=1\n-TTCTCAGCAAGTTCTGGGAGGTGGA\n->FBgn0063919_Max-element|3898|F|24|n=1\n+>FBgn0063919_Max-element|coord=3898|strand +|size=23|nreads=1\n+TTCTCAGCAAGTTCTGGGAGGTG\n+>FBgn0063919_Max-element|coord=3898|strand +|size=24|nreads=1\n TTCTCAGCAAGTTCTGGGAGGTGT\n->FBgn0067385_invader6|3024|F|26|n=1\n-TTGACTAGAATGACTTAGACTTAGAA\n->FBgn0067385_invader6|3007|R|27|n=4\n+>FBgn0063919_Max-element|coord=3898|strand +|size=24|nreads=2\n+TTCTCAGCAAGTTCTGGGAGGTGG\n+>FBgn0063919_Max-element|coord=3898|strand +|size=25|nreads=1\n+TTCTCAGCAAGTTCTGGGAGGTGGA\n+>FBgn0067385_invader6|coord=3007|strand -|size=27|nreads=4\n TTCTAGTCAAAGTCGAAGGACTGCATA\n->FBgn0067385_invader6|3008|R|26|n=3\n+>FBgn0067385_invader6|coord=3008|strand -|size=26|nreads=3\n TTCTAGTCAAAGTCGAAGGACTGCAT\n->FBgn0067385_invader6|3009|R|25|n=5\n+>FBgn0067385_invader6|coord=3009|strand -|size=25|nreads=5\n TTCTAGTCAAAGTCGAAGGACTGCA\n->FBgn0067385_invader6|3010|R|24|n=4\n+>FBgn0067385_invader6|coord=3010|strand -|size=24|nreads=4\n TTCTAGTCAAAGTCGAAGGACTGC\n->FBgn0067385_invader6|3011|R|23|n=1\n+>FBgn0067385_invader6|coord=3011|strand -|size=23|nreads=1\n TTCTAGTCAAAGTCGAAGGACTG\n->FBgn0067624_BS3|1026|F|26|n=1\n-TTGGCATCAATGGTGACAAATCAGCG\n->FBgn0067624_BS3|1011|R|25|n=3\n+>FBgn0067385_invader6|coord=3024|strand +|size=26|nreads=1\n+TTGACTAGAATGACTTAGACTTAGAA\n+>FBgn0067624_BS3|coord=1011|strand -|size=25|nreads=3\n TTGATGCCAATGTTCCAGCGTTTTG\n->FBgn0067624_BS3|1013|R|23|n=3\n+>FBgn0067624_BS3|coord=1013|strand -|size=23|nreads=3\n TTGATGCCAATGTTCCAACGTCT\n->FBgn0067624_BS3|1026|F|24|n=1\n+>FBgn0067624_BS3|coord=1026|strand +|size=24|nreads=1\n TTGGCATCAATGGTGACAAATCTG\n->FBgn0067624_BS3|1026|F|25|n=1\n+>FBgn0067624_BS3|coord=1026|strand +|size=25|nreads=1\n TTGGCATCAATGGTGACAAATCTGC\n+>FBgn0067624_BS3|coord=1026|strand +|size=26|nreads=1\n+TTGGCATCAATGGTGACAAATCAGCG\n' |
| b |
| diff -r 20d28cfdeefe -r a7fd04208764 test-data/paired_2.fa --- a/test-data/paired_2.fa Fri Sep 08 04:44:22 2017 -0400 +++ b/test-data/paired_2.fa Sat Sep 09 11:57:39 2017 -0400 |
| b |
| b'@@ -1,370 +1,416 @@\n->FBgn0000004_17.6|5844|R|21|n=1\n+>FBgn0000004_17.6|coord=5844|strand -|size=21|nreads=1\n TTTTCGTCAAGTGTGCTAAAT\n->FBgn0000004_17.6|5855|F|23|n=1\n+>FBgn0000004_17.6|coord=5855|strand +|size=23|nreads=1\n TTGACGAAAATGATCGAGTGGAT\n->FBgn0000005_297|1347|F|21|n=1\n+>FBgn0000005_297|coord=1334|strand -|size=23|nreads=1\n+TTTTGCGCAATGGTAATTAAGGA\n+>FBgn0000005_297|coord=1347|strand +|size=21|nreads=1\n TTGCACAAAATGAGGGAATTT\n->FBgn0000005_297|1334|R|23|n=1\n-TTTTGCGCAATGGTAATTAAGGA\n->FBgn0000007_1731|4545|R|20|n=1\n+>FBgn0000007_1731|coord=4545|strand -|size=20|nreads=1\n TTGAGAGCAAAGGCCGAATG\n->FBgn0000007_1731|4555|F|24|n=1\n+>FBgn0000007_1731|coord=4555|strand +|size=24|nreads=1\n TTGCTCTCAATGCGCTGAGTTTGG\n->FBgn0000155_roo|2682|R|20|n=2\n+>FBgn0000155_roo|coord=2682|strand -|size=20|nreads=2\n TTTTTACCAAACGGATGCCT\n->FBgn0000155_roo|2692|F|24|n=1\n+>FBgn0000155_roo|coord=2692|strand +|size=24|nreads=1\n TTGGTAAAAAATGTATAAGTGAGC\n->FBgn0000155_roo|2692|F|27|n=1\n+>FBgn0000155_roo|coord=2692|strand +|size=27|nreads=1\n TTGGTAAAAAATGTATAAGTGAGCAGC\n->FBgn0000155_roo|3241|F|20|n=1\n-TTGGGCAAAAAACTGATTTC\n->FBgn0000155_roo|3225|R|26|n=1\n+>FBgn0000155_roo|coord=3225|strand -|size=26|nreads=1\n TTTTGCCCAAGGAGACCGTCTATTTT\n->FBgn0000155_roo|3226|R|25|n=1\n+>FBgn0000155_roo|coord=3226|strand -|size=25|nreads=1\n TTTTGCCCAAGGAGACCGTCTATTT\n->FBgn0000155_roo|3227|R|24|n=2\n+>FBgn0000155_roo|coord=3227|strand -|size=24|nreads=2\n TTTTGCCCAAGGAGACCGTCTATT\n->FBgn0000155_roo|3228|R|23|n=1\n+>FBgn0000155_roo|coord=3228|strand -|size=23|nreads=1\n TTTTGCCCAAGGAGACCGTCTAT\n->FBgn0000155_roo|3229|R|22|n=2\n+>FBgn0000155_roo|coord=3229|strand -|size=22|nreads=2\n TTTTGCCCAAGGAGACCGTCTA\n->FBgn0000155_roo|3241|F|24|n=1\n+>FBgn0000155_roo|coord=3230|strand -|size=21|nreads=1\n+TTTTGCCCAAGGAGACCGTCT\n+>FBgn0000155_roo|coord=3231|strand -|size=20|nreads=2\n+TTTTGCCCAAGGAGACCGTC\n+>FBgn0000155_roo|coord=3241|strand +|size=20|nreads=1\n+TTGGGCAAAAAACTGATTTC\n+>FBgn0000155_roo|coord=3241|strand +|size=24|nreads=1\n TTGGGCAAAAAACTGATTTCGGGT\n->FBgn0000155_roo|3241|F|27|n=1\n+>FBgn0000155_roo|coord=3241|strand +|size=27|nreads=1\n TTGGGCAAAAAACTGATTTCGGGTGGA\n->FBgn0000155_roo|3241|F|28|n=1\n+>FBgn0000155_roo|coord=3241|strand +|size=28|nreads=1\n TTGGGCAAAAAACTGATTTCGGGTGGAT\n->FBgn0000155_roo|8644|R|21|n=1\n+>FBgn0000155_roo|coord=8644|strand -|size=21|nreads=1\n TTCTGCCAAAGGGCCAGCAAG\n->FBgn0000155_roo|8655|F|25|n=1\n+>FBgn0000155_roo|coord=8645|strand -|size=20|nreads=1\n+TTCTGCCAAAGGGCCAGCAA\n+>FBgn0000155_roo|coord=8655|strand +|size=25|nreads=1\n TTTGGCAGAATGTTCACACATGAAA\n->FBgn0000349_copia|658|R|22|n=1\n+>FBgn0000349_copia|coord=658|strand -|size=22|nreads=1\n TTCTCAAGAATCTGACGCGCCG\n->FBgn0000349_copia|670|F|25|n=1\n+>FBgn0000349_copia|coord=670|strand +|size=25|nreads=1\n TTCTTGAGAATTTGGACGCCGTTTA\n->FBgn0000349_copia|4628|F|20|n=1\n+>FBgn0000349_copia|coord=4614|strand -|size=24|nreads=1\n+TTGCAGCAAACCCAATTTGTCTCG\n+>FBgn0000349_copia|coord=4628|strand +|size=20|nreads=1\n TTTGCTGCAAGACGACCAAT\n->FBgn0000349_copia|4614|R|24|n=1\n-TTGCAGCAAACCCAATTTGTCTCG\n->FBgn0000652_F-element|1564|F|20|n=2\n-TTTTCTCGAAAGCAGCAAGT\n->FBgn0000652_F-element|1546|R|28|n=1\n+>FBgn0000652_F-element|coord=1546|strand -|size=28|nreads=1\n TTCGAGAAAATTACTTCAGGATTTGTCT\n->FBgn0000652_F-element|1546|R|28|n=1\n+>FBgn0000652_F-element|coord=1546|strand -|size=28|nreads=1\n TTCGGGAAAATTACTTCAGGATTTGTCT\n->FBgn0000652_F-element|1547|R|27|n=74\n+>FBgn0000652_F-element|coord=1547|strand -|size=27|nreads=1\n+TTCGGGAAAATTACTTCAGGATTTGTC\n+>FBgn0000652_F-element|coord=1547|strand -|size=27|nreads=1\n+TTTGAGAAAATTACTTCAGGATTTGTC\n+>FBgn0000652_F-element|coord=1547|strand -|size=27|nreads=74\n TTCGAGAAAATTACTTCAGGATTTGTC\n->FBgn0000652_F-element|1547|R|27|n=1\n-TTCGGGAAAATTACTTCAGGATTTGTC\n->FBgn0000652_F-element|1547|R|27|n=1\n-TTTGAGAAAATTACTTCAGGATTTGTC\n->FBgn0000652_F-element|1548|R|26|n=3\n+>FBgn0000652_F-element|coord=1548|strand -|size=26|nreads=3\n TTCGAGAAAATTACTTCAGGATTTGT\n->FBgn0000652_F-element|1549|R|25|n=22\n+>FBgn0000652_F-element|coord=1'..b'4221|strand +|size=24|nreads=1\n TTCTAACCAAGAATTTGAATAGAT\n->FBgn0063427_invader4|707|F|22|n=2\n+>FBgn0063427_invader4|coord=691|strand -|size=26|nreads=15\n+TTCCTACGAATCGCTGTATGAACAGT\n+>FBgn0063427_invader4|coord=707|strand +|size=22|nreads=2\n TTCGTAGGAATGGAGACGTCGG\n->FBgn0063427_invader4|691|R|26|n=15\n-TTCCTACGAATCGCTGTATGAACAGT\n->FBgn0063428_invader3|440|F|22|n=2\n+>FBgn0063428_invader3|coord=425|strand -|size=25|nreads=1\n+TTCTGGGGAAATGGCCTGCAGACGC\n+>FBgn0063428_invader3|coord=427|strand -|size=23|nreads=1\n+TTCTGGGGAAATGGCCTGCAGAC\n+>FBgn0063428_invader3|coord=440|strand +|size=22|nreads=2\n TTCCCCAGAAACGCGTGGCGAT\n->FBgn0063428_invader3|425|R|25|n=1\n-TTCTGGGGAAATGGCCTGCAGACGC\n->FBgn0063428_invader3|427|R|23|n=1\n-TTCTGGGGAAATGGCCTGCAGAC\n->FBgn0063430_invader1|2082|R|20|n=1\n+>FBgn0063430_invader1|coord=2082|strand -|size=20|nreads=1\n TTTTATCGAACCAATAGAAC\n->FBgn0063430_invader1|2092|F|24|n=1\n+>FBgn0063430_invader1|coord=2092|strand +|size=24|nreads=1\n TTCGATAAAATGTCTAAGTATGTT\n->FBgn0063430_invader1|2092|F|26|n=1\n+>FBgn0063430_invader1|coord=2092|strand +|size=26|nreads=1\n TTCGATAAAATGTCTAAGTATGTTCG\n->FBgn0063433_gypsy4|3058|F|22|n=1\n+>FBgn0063433_gypsy4|coord=3040|strand -|size=28|nreads=1\n+TTTTGAAGAACTTGGATTTTTCTTGAGA\n+>FBgn0063433_gypsy4|coord=3044|strand -|size=24|nreads=1\n+TTTTGAAGAACTTGGATTTTTCTT\n+>FBgn0063433_gypsy4|coord=3058|strand +|size=22|nreads=1\n TTCTTCAAAAAGAGCGTGGAAT\n->FBgn0063433_gypsy4|3040|R|28|n=1\n-TTTTGAAGAACTTGGATTTTTCTTGAGA\n->FBgn0063433_gypsy4|3044|R|24|n=1\n-TTTTGAAGAACTTGGATTTTTCTT\n->FBgn0063440_baggins|5170|F|21|n=1\n+>FBgn0063440_baggins|coord=5154|strand -|size=26|nreads=1\n+TTTTGTGCAAATGGCTGTGAAGTCGG\n+>FBgn0063440_baggins|coord=5170|strand +|size=21|nreads=1\n TTGCACAAAATTGGCATTGCA\n->FBgn0063440_baggins|5154|R|26|n=1\n-TTTTGTGCAAATGGCTGTGAAGTCGG\n->FBgn0063919_Max-element|3887|R|21|n=2\n+>FBgn0063919_Max-element|coord=3887|strand -|size=21|nreads=2\n TTGCTGAGAAGCGTGTTGAGC\n->FBgn0063919_Max-element|3898|F|23|n=1\n+>FBgn0063919_Max-element|coord=3898|strand +|size=23|nreads=1\n TTCTCAGCAAGTTCTGGGAGGTG\n->FBgn0063919_Max-element|3898|F|24|n=2\n-TTCTCAGCAAGTTCTGGGAGGTGG\n->FBgn0063919_Max-element|3898|F|25|n=1\n-TTCTCAGCAAGTTCTGGGAGGTGGA\n->FBgn0063919_Max-element|3898|F|24|n=1\n+>FBgn0063919_Max-element|coord=3898|strand +|size=24|nreads=1\n TTCTCAGCAAGTTCTGGGAGGTGT\n->FBgn0067385_invader6|3024|F|21|n=1\n-TTGACTAGAATGACTTAGACT\n->FBgn0067385_invader6|3007|R|27|n=4\n+>FBgn0063919_Max-element|coord=3898|strand +|size=24|nreads=2\n+TTCTCAGCAAGTTCTGGGAGGTGG\n+>FBgn0063919_Max-element|coord=3898|strand +|size=25|nreads=1\n+TTCTCAGCAAGTTCTGGGAGGTGGA\n+>FBgn0067385_invader6|coord=3007|strand -|size=27|nreads=4\n TTCTAGTCAAAGTCGAAGGACTGCATA\n->FBgn0067385_invader6|3008|R|26|n=3\n+>FBgn0067385_invader6|coord=3008|strand -|size=26|nreads=3\n TTCTAGTCAAAGTCGAAGGACTGCAT\n->FBgn0067385_invader6|3009|R|25|n=5\n+>FBgn0067385_invader6|coord=3009|strand -|size=25|nreads=5\n TTCTAGTCAAAGTCGAAGGACTGCA\n->FBgn0067385_invader6|3010|R|24|n=4\n+>FBgn0067385_invader6|coord=3010|strand -|size=24|nreads=4\n TTCTAGTCAAAGTCGAAGGACTGC\n->FBgn0067385_invader6|3011|R|23|n=1\n+>FBgn0067385_invader6|coord=3011|strand -|size=23|nreads=1\n TTCTAGTCAAAGTCGAAGGACTG\n->FBgn0067385_invader6|3014|R|20|n=1\n+>FBgn0067385_invader6|coord=3014|strand -|size=20|nreads=1\n TTCTAGTCAAAGTCGAAGGA\n->FBgn0067385_invader6|3024|F|26|n=1\n+>FBgn0067385_invader6|coord=3024|strand +|size=21|nreads=1\n+TTGACTAGAATGACTTAGACT\n+>FBgn0067385_invader6|coord=3024|strand +|size=26|nreads=1\n TTGACTAGAATGACTTAGACTTAGAA\n->FBgn0067624_BS3|1016|R|20|n=1\n+>FBgn0067624_BS3|coord=1016|strand -|size=20|nreads=1\n TTGATGCCAATGTTCCAACG\n->FBgn0067624_BS3|1026|F|26|n=1\n+>FBgn0067624_BS3|coord=1026|strand +|size=24|nreads=1\n+TTGGCATCAATGGTGACAAATCTG\n+>FBgn0067624_BS3|coord=1026|strand +|size=25|nreads=1\n+TTGGCATCAATGGTGACAAATCTGC\n+>FBgn0067624_BS3|coord=1026|strand +|size=26|nreads=1\n TTGGCATCAATGGTGACAAATCAGCG\n->FBgn0067624_BS3|1026|F|24|n=1\n-TTGGCATCAATGGTGACAAATCTG\n->FBgn0067624_BS3|1026|F|25|n=1\n-TTGGCATCAATGGTGACAAATCTGC\n' |
| b |
| diff -r 20d28cfdeefe -r a7fd04208764 test-data/paired_3.fa --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/paired_3.fa Sat Sep 09 11:57:39 2017 -0400 |
| b |
| b'@@ -0,0 +1,416 @@\n+>FBgn0000004_17.6|coord=5844|strand -|size=21|nreads=1\n+TTTTCGTCAAGTGTGCTAAAT\n+>FBgn0000004_17.6|coord=5855|strand +|size=23|nreads=1\n+TTGACGAAAATGATCGAGTGGAT\n+>FBgn0000005_297|coord=1334|strand -|size=23|nreads=1\n+TTTTGCGCAATGGTAATTAAGGA\n+>FBgn0000005_297|coord=1347|strand +|size=21|nreads=1\n+TTGCACAAAATGAGGGAATTT\n+>FBgn0000007_1731|coord=4545|strand -|size=20|nreads=1\n+TTGAGAGCAAAGGCCGAATG\n+>FBgn0000007_1731|coord=4555|strand +|size=24|nreads=1\n+TTGCTCTCAATGCGCTGAGTTTGG\n+>FBgn0000155_roo|coord=2682|strand -|size=20|nreads=2\n+TTTTTACCAAACGGATGCCT\n+>FBgn0000155_roo|coord=2692|strand +|size=24|nreads=1\n+TTGGTAAAAAATGTATAAGTGAGC\n+>FBgn0000155_roo|coord=2692|strand +|size=27|nreads=1\n+TTGGTAAAAAATGTATAAGTGAGCAGC\n+>FBgn0000155_roo|coord=3225|strand -|size=26|nreads=1\n+TTTTGCCCAAGGAGACCGTCTATTTT\n+>FBgn0000155_roo|coord=3226|strand -|size=25|nreads=1\n+TTTTGCCCAAGGAGACCGTCTATTT\n+>FBgn0000155_roo|coord=3227|strand -|size=24|nreads=2\n+TTTTGCCCAAGGAGACCGTCTATT\n+>FBgn0000155_roo|coord=3228|strand -|size=23|nreads=1\n+TTTTGCCCAAGGAGACCGTCTAT\n+>FBgn0000155_roo|coord=3229|strand -|size=22|nreads=2\n+TTTTGCCCAAGGAGACCGTCTA\n+>FBgn0000155_roo|coord=3230|strand -|size=21|nreads=1\n+TTTTGCCCAAGGAGACCGTCT\n+>FBgn0000155_roo|coord=3231|strand -|size=20|nreads=2\n+TTTTGCCCAAGGAGACCGTC\n+>FBgn0000155_roo|coord=3241|strand +|size=20|nreads=1\n+TTGGGCAAAAAACTGATTTC\n+>FBgn0000155_roo|coord=3241|strand +|size=24|nreads=1\n+TTGGGCAAAAAACTGATTTCGGGT\n+>FBgn0000155_roo|coord=3241|strand +|size=27|nreads=1\n+TTGGGCAAAAAACTGATTTCGGGTGGA\n+>FBgn0000155_roo|coord=3241|strand +|size=28|nreads=1\n+TTGGGCAAAAAACTGATTTCGGGTGGAT\n+>FBgn0000155_roo|coord=8644|strand -|size=21|nreads=1\n+TTCTGCCAAAGGGCCAGCAAG\n+>FBgn0000155_roo|coord=8645|strand -|size=20|nreads=1\n+TTCTGCCAAAGGGCCAGCAA\n+>FBgn0000155_roo|coord=8655|strand +|size=25|nreads=1\n+TTTGGCAGAATGTTCACACATGAAA\n+>FBgn0000349_copia|coord=658|strand -|size=22|nreads=1\n+TTCTCAAGAATCTGACGCGCCG\n+>FBgn0000349_copia|coord=670|strand +|size=25|nreads=1\n+TTCTTGAGAATTTGGACGCCGTTTA\n+>FBgn0000349_copia|coord=4614|strand -|size=24|nreads=1\n+TTGCAGCAAACCCAATTTGTCTCG\n+>FBgn0000349_copia|coord=4628|strand +|size=20|nreads=1\n+TTTGCTGCAAGACGACCAAT\n+>FBgn0000652_F-element|coord=1546|strand -|size=28|nreads=1\n+TTCGAGAAAATTACTTCAGGATTTGTCT\n+>FBgn0000652_F-element|coord=1546|strand -|size=28|nreads=1\n+TTCGGGAAAATTACTTCAGGATTTGTCT\n+>FBgn0000652_F-element|coord=1547|strand -|size=27|nreads=1\n+TTCGGGAAAATTACTTCAGGATTTGTC\n+>FBgn0000652_F-element|coord=1547|strand -|size=27|nreads=1\n+TTTGAGAAAATTACTTCAGGATTTGTC\n+>FBgn0000652_F-element|coord=1547|strand -|size=27|nreads=74\n+TTCGAGAAAATTACTTCAGGATTTGTC\n+>FBgn0000652_F-element|coord=1548|strand -|size=26|nreads=3\n+TTCGAGAAAATTACTTCAGGATTTGT\n+>FBgn0000652_F-element|coord=1549|strand -|size=25|nreads=1\n+TTCGGGAAAATTACTTCAGGATTTG\n+>FBgn0000652_F-element|coord=1549|strand -|size=25|nreads=22\n+TTCGAGAAAATTACTTCAGGATTTG\n+>FBgn0000652_F-element|coord=1550|strand -|size=24|nreads=2\n+TTCGAGAAAATTACTTCAGGATTT\n+>FBgn0000652_F-element|coord=1551|strand -|size=23|nreads=7\n+TTCGAGAAAATTACTTCAGGATT\n+>FBgn0000652_F-element|coord=1554|strand -|size=20|nreads=1\n+TTCGAGAAAATTACTTCAGG\n+>FBgn0000652_F-element|coord=1564|strand +|size=20|nreads=1\n+TTTTCTCGAAAGCAGCTAGT\n+>FBgn0000652_F-element|coord=1564|strand +|size=20|nreads=2\n+TTTTCTCGAAAGCAGCAAGT\n+>FBgn0000652_F-element|coord=1564|strand +|size=23|nreads=2\n+TTTTCTCGAAAGCAGCAAGTTTC\n+>FBgn0000652_F-element|coord=1564|strand +|size=23|nreads=2\n+TTTTCTCGAAAGCAGCTAGTTTC\n+>FBgn0000652_F-element|coord=1564|strand +|size=24|nreads=2\n+TTTTCTCGAAAGCAGCAAGTTTCG\n+>FBgn0000652_F-element|coord=1564|strand +|size=24|nreads=5\n+TTTTCTCGAAAGCAGCTAGTTTCG\n+>FBgn0000652_F-element|coord=1564|strand +|size=25|nreads=1\n+TTTTCTCGAAAGCAGCTAGTTTCGC\n+>FBgn0000652_F-element|coord=2231|strand -|size=27|nreads=1\n+TTGGAAGAAATCCAGGAATTGAGCTTC\n+>FBgn0000652_F-element|coord=2233|strand -|size=25|nreads=5\n+TTGGAAGAAATCCAGGAATTGAGCT\n+>FBgn0000652_F-element|coord=2248|strand +|size=20|nreads='..b'coord=2907|strand -|size=23|nreads=1\n+TTGGTAACAAGCTTGGAGGCGAG\n+>FBgn0042682_Rt1b|coord=2907|strand -|size=23|nreads=15\n+TTGGTAACAAGCTTGTAGGCGAG\n+>FBgn0042682_Rt1b|coord=2908|strand -|size=22|nreads=1\n+TTGGTAACAAGCTTGTAGGCGA\n+>FBgn0042682_Rt1b|coord=2909|strand -|size=21|nreads=6\n+TTGGTAACAAGCTTGTAGGCG\n+>FBgn0042682_Rt1b|coord=2920|strand +|size=22|nreads=1\n+TTGTTACCAAAAAGCTAAGGAG\n+>FBgn0042682_Rt1b|coord=2920|strand +|size=23|nreads=1\n+TTGTTACCAAAAAGCTAAGGAGG\n+>FBgn0042682_Rt1b|coord=2920|strand +|size=23|nreads=1\n+TTGTTACCAACAAGCTAAGGAGG\n+>FBgn0042682_Rt1b|coord=2920|strand +|size=24|nreads=2\n+TTGTTACCAACAAGCTAAGGAGGA\n+>FBgn0042682_Rt1b|coord=2920|strand +|size=25|nreads=1\n+TTGTTACCAAAAAGCTAAGGAGGAG\n+>FBgn0042682_Rt1b|coord=2920|strand +|size=26|nreads=1\n+TTGTTACCAAAAAGCTAAGGAGGAGA\n+>FBgn0042682_Rt1b|coord=2920|strand +|size=27|nreads=1\n+TTGTTACCAAAAAGCTAAGGAGGAGAG\n+>FBgn0042682_Rt1b|coord=4364|strand -|size=22|nreads=1\n+TTGCCTGGAAGCGCCACTCCGC\n+>FBgn0042682_Rt1b|coord=4365|strand -|size=21|nreads=1\n+TTGCCTGGAAGCGCCACTCCG\n+>FBgn0042682_Rt1b|coord=4366|strand -|size=20|nreads=4\n+TTGCCTGGAAGCGCCACTCC\n+>FBgn0042682_Rt1b|coord=4376|strand +|size=24|nreads=1\n+TTCCAGGCAAGAGGCACACGAGTG\n+>FBgn0042682_Rt1b|coord=4376|strand +|size=26|nreads=1\n+TTCCAGGCAAGAGGCACACGAGTGGC\n+>FBgn0062343_Dm88|coord=4210|strand -|size=21|nreads=1\n+TTGGTTAGAACATCTGCCATC\n+>FBgn0062343_Dm88|coord=4221|strand +|size=24|nreads=1\n+TTCTAACCAAGAATTTGAATAGAT\n+>FBgn0063427_invader4|coord=691|strand -|size=26|nreads=15\n+TTCCTACGAATCGCTGTATGAACAGT\n+>FBgn0063427_invader4|coord=707|strand +|size=22|nreads=2\n+TTCGTAGGAATGGAGACGTCGG\n+>FBgn0063428_invader3|coord=425|strand -|size=25|nreads=1\n+TTCTGGGGAAATGGCCTGCAGACGC\n+>FBgn0063428_invader3|coord=427|strand -|size=23|nreads=1\n+TTCTGGGGAAATGGCCTGCAGAC\n+>FBgn0063428_invader3|coord=440|strand +|size=22|nreads=2\n+TTCCCCAGAAACGCGTGGCGAT\n+>FBgn0063430_invader1|coord=2082|strand -|size=20|nreads=1\n+TTTTATCGAACCAATAGAAC\n+>FBgn0063430_invader1|coord=2092|strand +|size=24|nreads=1\n+TTCGATAAAATGTCTAAGTATGTT\n+>FBgn0063430_invader1|coord=2092|strand +|size=26|nreads=1\n+TTCGATAAAATGTCTAAGTATGTTCG\n+>FBgn0063433_gypsy4|coord=3040|strand -|size=28|nreads=1\n+TTTTGAAGAACTTGGATTTTTCTTGAGA\n+>FBgn0063433_gypsy4|coord=3044|strand -|size=24|nreads=1\n+TTTTGAAGAACTTGGATTTTTCTT\n+>FBgn0063433_gypsy4|coord=3058|strand +|size=22|nreads=1\n+TTCTTCAAAAAGAGCGTGGAAT\n+>FBgn0063440_baggins|coord=5154|strand -|size=26|nreads=1\n+TTTTGTGCAAATGGCTGTGAAGTCGG\n+>FBgn0063440_baggins|coord=5170|strand +|size=21|nreads=1\n+TTGCACAAAATTGGCATTGCA\n+>FBgn0063919_Max-element|coord=3887|strand -|size=21|nreads=2\n+TTGCTGAGAAGCGTGTTGAGC\n+>FBgn0063919_Max-element|coord=3898|strand +|size=23|nreads=1\n+TTCTCAGCAAGTTCTGGGAGGTG\n+>FBgn0063919_Max-element|coord=3898|strand +|size=24|nreads=1\n+TTCTCAGCAAGTTCTGGGAGGTGT\n+>FBgn0063919_Max-element|coord=3898|strand +|size=24|nreads=2\n+TTCTCAGCAAGTTCTGGGAGGTGG\n+>FBgn0063919_Max-element|coord=3898|strand +|size=25|nreads=1\n+TTCTCAGCAAGTTCTGGGAGGTGGA\n+>FBgn0067385_invader6|coord=3007|strand -|size=27|nreads=4\n+TTCTAGTCAAAGTCGAAGGACTGCATA\n+>FBgn0067385_invader6|coord=3008|strand -|size=26|nreads=3\n+TTCTAGTCAAAGTCGAAGGACTGCAT\n+>FBgn0067385_invader6|coord=3009|strand -|size=25|nreads=5\n+TTCTAGTCAAAGTCGAAGGACTGCA\n+>FBgn0067385_invader6|coord=3010|strand -|size=24|nreads=4\n+TTCTAGTCAAAGTCGAAGGACTGC\n+>FBgn0067385_invader6|coord=3011|strand -|size=23|nreads=1\n+TTCTAGTCAAAGTCGAAGGACTG\n+>FBgn0067385_invader6|coord=3014|strand -|size=20|nreads=1\n+TTCTAGTCAAAGTCGAAGGA\n+>FBgn0067385_invader6|coord=3024|strand +|size=21|nreads=1\n+TTGACTAGAATGACTTAGACT\n+>FBgn0067385_invader6|coord=3024|strand +|size=26|nreads=1\n+TTGACTAGAATGACTTAGACTTAGAA\n+>FBgn0067624_BS3|coord=1016|strand -|size=20|nreads=1\n+TTGATGCCAATGTTCCAACG\n+>FBgn0067624_BS3|coord=1026|strand +|size=24|nreads=1\n+TTGGCATCAATGGTGACAAATCTG\n+>FBgn0067624_BS3|coord=1026|strand +|size=25|nreads=1\n+TTGGCATCAATGGTGACAAATCTGC\n+>FBgn0067624_BS3|coord=1026|strand +|size=26|nreads=1\n+TTGGCATCAATGGTGACAAATCAGCG\n' |
| b |
| diff -r 20d28cfdeefe -r a7fd04208764 test-data/paired_4.fa --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/paired_4.fa Sat Sep 09 11:57:39 2017 -0400 |
| b |
| @@ -0,0 +1,70 @@ +>FBgn0000155_roo|coord=3229|strand -|size=22|nreads=2 +TTTTGCCCAAGGAGACCGTCTA +>FBgn0000155_roo|coord=3230|strand -|size=21|nreads=1 +TTTTGCCCAAGGAGACCGTCT +>FBgn0000155_roo|coord=3231|strand -|size=20|nreads=2 +TTTTGCCCAAGGAGACCGTC +>FBgn0000155_roo|coord=3241|strand +|size=20|nreads=1 +TTGGGCAAAAAACTGATTTC +>FBgn0000652_F-element|coord=1554|strand -|size=20|nreads=1 +TTCGAGAAAATTACTTCAGG +>FBgn0000652_F-element|coord=1564|strand +|size=20|nreads=1 +TTTTCTCGAAAGCAGCTAGT +>FBgn0000652_F-element|coord=1564|strand +|size=20|nreads=2 +TTTTCTCGAAAGCAGCAAGT +>FBgn0000652_F-element|coord=2471|strand -|size=21|nreads=2 +TTTAACCAAACTGCGGGAAAT +>FBgn0000652_F-element|coord=2472|strand -|size=20|nreads=1 +TTTAACCAAACTGCGGGAAA +>FBgn0000652_F-element|coord=2482|strand +|size=21|nreads=1 +TTTGGTTAAAGCTGAATGTCT +>FBgn0000652_F-element|coord=2482|strand +|size=22|nreads=2 +TTTGGTTAAAGCTGAATGTCTG +>FBgn0000652_F-element|coord=3513|strand -|size=21|nreads=3 +TTTCGCGAAATCCAAATTGGT +>FBgn0000652_F-element|coord=3524|strand +|size=20|nreads=2 +TTTCGCGAAAGCCATGGAAC +>FBgn0000652_F-element|coord=3524|strand +|size=21|nreads=2 +TTTCGCGAAAGCCACGGAACC +>FBgn0000652_F-element|coord=3524|strand +|size=22|nreads=1 +TTTCGCGAAAGCCACGGAACCA +>FBgn0002697_mdg1|coord=4646|strand -|size=21|nreads=1 +TTTCTCAGAAAAGTTCTTAAT +>FBgn0002697_mdg1|coord=4657|strand +|size=22|nreads=1 +TTCTGAGAAATCACGCCACTTA +>FBgn0002697_mdg1|coord=5354|strand -|size=21|nreads=2 +TTTCAACAAACACTTATGCTT +>FBgn0002697_mdg1|coord=5365|strand +|size=21|nreads=2 +TTTGTTGAAAAGAGGAAAACA +>FBgn0003519_Stalker|coord=6708|strand -|size=21|nreads=1 +TTTGTCTCAAAGCATTTTTGT +>FBgn0003519_Stalker|coord=6719|strand +|size=21|nreads=1 +TTGAGACAAAACATTGCTAAT +>FBgn0003908_R1A1-element|coord=4678|strand -|size=22|nreads=1 +TTTTCGCCAAGGCGCTGCACTT +>FBgn0003908_R1A1-element|coord=4678|strand -|size=22|nreads=18 +TTTTCGCCAAGGCGCTGCACTC +>FBgn0003908_R1A1-element|coord=4679|strand -|size=21|nreads=1 +TTTTCGCCAAGGCGCTGCACC +>FBgn0003908_R1A1-element|coord=4679|strand -|size=21|nreads=6 +TTTTCGCCAAGGCGCTGCACT +>FBgn0003908_R1A1-element|coord=4680|strand -|size=20|nreads=4 +TTTTCGCCAAGGCGCTGCAC +>FBgn0003908_R1A1-element|coord=4690|strand +|size=20|nreads=2 +TTGGCGAAAACTGGATCTTC +>FBgn0003908_R1A1-element|coord=4690|strand +|size=21|nreads=6 +TTGGCGAAAACTGGATCTTCG +>FBgn0003908_R1A1-element|coord=4690|strand +|size=22|nreads=1 +TTGGCGAAAACTAGATCTTCGA +>FBgn0003908_R1A1-element|coord=4690|strand +|size=22|nreads=8 +TTGGCGAAAACTGGATCTTCGA +>FBgn0042682_Rt1b|coord=2908|strand -|size=22|nreads=1 +TTGGTAACAAGCTTGTAGGCGA +>FBgn0042682_Rt1b|coord=2909|strand -|size=21|nreads=6 +TTGGTAACAAGCTTGTAGGCG +>FBgn0042682_Rt1b|coord=2920|strand +|size=22|nreads=1 +TTGTTACCAAAAAGCTAAGGAG +>FBgn0067385_invader6|coord=3014|strand -|size=20|nreads=1 +TTCTAGTCAAAGTCGAAGGA +>FBgn0067385_invader6|coord=3024|strand +|size=21|nreads=1 +TTGACTAGAATGACTTAGACT |