| Previous changeset 0:a35e6f9c1d34 (2017-08-28) Next changeset 2:320e06bf99b9 (2017-08-30) |
|
Commit message:
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_signatures commit 6133bb114c76a795fa12a4a11edb1a8b80fd104d |
|
added:
overlapping_reads.py overlapping_reads.xml test-data/paired.fa |
| b |
| diff -r a35e6f9c1d34 -r 6f1378738798 overlapping_reads.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/overlapping_reads.py Tue Aug 29 20:02:15 2017 -0400 |
| [ |
| @@ -0,0 +1,140 @@ +import argparse +from collections import defaultdict + +import pysam + + +def Parser(): + the_parser = argparse.ArgumentParser() + the_parser.add_argument( + '--input', action="store", type=str, help="bam alignment file") + the_parser.add_argument( + '--minquery', type=int, + help="Minimum readsize of query reads (nt) - must be an integer") + the_parser.add_argument( + '--maxquery', type=int, + help="Maximum readsize of query reads (nt) - must be an integer") + the_parser.add_argument( + '--mintarget', type=int, + help="Minimum readsize of target reads (nt) - must be an integer") + the_parser.add_argument( + '--maxtarget', type=int, + help="Maximum readsize of target reads (nt) - must be an integer") + the_parser.add_argument( + '--overlap', type=int, + help="Overlap analyzed (nt) - must be an integer") + the_parser.add_argument( + '--output', action="store", type=str, + help="Pairable sequences") + args = the_parser.parse_args() + return args + + +class Map: + + def __init__(self, bam_file): + self.bam_object = pysam.AlignmentFile(bam_file, 'rb') + self.chromosomes = dict(zip(self.bam_object.references, + self.bam_object.lengths)) + self.map_dict = self.create_map(self.bam_object) + + def create_map(self, bam_object): + ''' + Returns a map_dictionary {(chromosome,read_position,polarity): + [read_length, ...]} + ''' + map_dictionary = defaultdict(list) + # get empty value for start and end of each chromosome + for chrom in self.chromosomes: + map_dictionary[(chrom, 1, 'F')] = [] + map_dictionary[(chrom, self.chromosomes[chrom], 'F')] = [] + for chrom in self.chromosomes: + for read in bam_object.fetch(chrom): + positions = read.positions # a list of covered positions + if read.is_reverse: + map_dictionary[(chrom, positions[-1]+1, + 'R')].append(read.query_alignment_length) + else: + map_dictionary[(chrom, positions[0]+1, + 'F')].append(read.query_alignment_length) + return map_dictionary + + def signature_tables(self, minquery, maxquery, mintarget, maxtarget): + query_range = range(minquery, maxquery + 1) + target_range = range(mintarget, maxtarget + 1) + Query_table = defaultdict(dict) + Target_table = defaultdict(dict) + for key in self.map_dict: + for size in self.map_dict[key]: + if size in query_range or size in target_range: + if key[2] == 'F': + coordinate = key[1] + else: + coordinate = -key[1] + if size in query_range: + Query_table[key[0]][coordinate] = Query_table[key[0]].get( + coordinate, 0) + 1 + if size in target_range: + Target_table[key[0]][coordinate] = \ + Target_table[key[0]].get(coordinate, 0) + 1 + return Query_table, Target_table + + def search_overlaps(self, minquery, maxquery, mintarget, maxtarget, + overlap=10): + Query_table, Target_table = self.signature_tables(minquery, maxquery, + mintarget, maxtarget) + overlap_groups = defaultdict(list) + for chrom in Query_table: + for coord in Query_table[chrom]: + if Target_table[chrom].get(-coord - overlap + 1, 0): + overlap_groups[chrom].append(coord) + return overlap_groups + + def feed_overlaps(self, overlap_groups, minquery, output, overlap=10): + F = open(output, 'w') + for chrom in sorted(overlap_groups): + for pos in sorted(overlap_groups[chrom]): + if pos > 0: # read are forward + reads = self.bam_object.fetch(chrom, start=pos-1, + end=pos-1+overlap-1) + for read in reads: + positions = read.positions + if pos-1 == positions[0] and \ + read.query_alignment_length >= minquery: + F.write('>%s|%s|%s|%s\n%s\n' % ( + chrom, pos, 'F', + read.query_alignment_length, + read.query_sequence)) + else: # reads are reverse + reads = self.bam_object.fetch(chrom, + start=-pos-1-overlap+1, + end=-pos-1) + for read in reads: + positions = read.positions + if -pos-1 == positions[-1] and \ + read.query_alignment_length >= minquery: + readseq = self.revcomp(read.query_sequence) + readsize = read.query_alignment_length + F.write('>%s|%s|%s|%s\n%s\n' % (chrom, + positions[0] + 1, + 'R', readsize, readseq)) + F.close() + return + + def revcomp(self, sequence): + antidict = {"A": "T", "T": "A", "G": "C", "C": "G", "N": "N"} + revseq = sequence[::-1] + return "".join([antidict[i] for i in revseq]) + + +def main(input, minquery, maxquery, mintarget, maxtarget, output, overlap=10): + mapobj = Map(input) + mapobj.feed_overlaps(mapobj.search_overlaps(minquery, maxquery, + mintarget, maxtarget, + overlap), minquery, output) + + +if __name__ == "__main__": + args = Parser() + main(args.input, args.minquery, args.maxquery, args.mintarget, + args.maxtarget, args.output) |
| b |
| diff -r a35e6f9c1d34 -r 6f1378738798 overlapping_reads.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/overlapping_reads.xml Tue Aug 29 20:02:15 2017 -0400 |
| [ |
| @@ -0,0 +1,78 @@ +<tool id="overlapping_reads" name="Get overlapping reads" version="0.9.0"> + <description /> + <requirements> + <requirement type="package" version="0.11.2.1=py27_0">pysam</requirement> + </requirements> + <stdio> + <exit_code range="1:" level="fatal" description="Tool exception" /> + </stdio> + <command detect_errors="exit_code"><![CDATA[ + samtools index '$input' && + python '$__tool_directory__'/overlapping_reads.py + --input '$input' + --minquery '$minquery' + --maxquery '$maxquery' + --mintarget '$mintarget' + --maxtarget '$maxtarget' + --overlap '$overlap' + --output '$output' + ]]></command> + <inputs> + <param format="bam" label="Compute signature from this bowtie standard output" name="input" type="data" /> + <param help="'23' = 23 nucleotides" label="Min size of query small RNAs" name="minquery" size="3" type="integer" value="23" /> + <param help="'29' = 29 nucleotides" label="Max size of query small RNAs" name="maxquery" size="3" type="integer" value="29" /> + <param help="'23' = 23 nucleotides" label="Min size of target small RNAs" name="mintarget" size="3" type="integer" value="23" /> + <param help="'29' = 29 nucleotides" label="Max size of target small RNAs" name="maxtarget" size="3" type="integer" value="29" /> + <param help="'10' = 10 nucleotides overlap" label="Overlap (in nt)" name="overlap" size="3" type="integer" value="10" /> + </inputs> + <outputs> + <data format="fasta" label="pairable reads" name="output" /> + </outputs> + <tests> + <test> + <param ftype="bam" name="input" value="sr_bowtie.bam" /> + <param name="minquery" value="23" /> + <param name="maxquery" value="29" /> + <param name="mintarget" value="23" /> + <param name="maxtarget" value="29" /> + <param name="overlap" value="10" /> + <output file="paired.fa" ftype="fasta" name="output" /> + </test> + </tests> + <help> + +**What it does** + +Extract reads with overlap signatures of the specified overlap (in nt) and +return a fasta file of these "pairable" reads. + +See `Antoniewski (2014)`_ for background and details + +.. _Antoniewski (2014): https://link.springer.com/protocol/10.1007%2F978-1-4939-0931-5_12 + +**Input** + +A **sorted** BAM alignment file. + +**Outputs** + +a fasta file of pairable reads such as : + +>FBgn0000004_17.6|5839|R|26 + +TTTTCGTCAATTGTGCCAAATAGGTA + +>FBgn0000004_17.6|5855|F|23 + +TTGACGAAAATGATCGAGTGGAT + +where FBgn0000004_17.6 stands for the chromosome, 5839 stands for the 1-based read position, +R stand for reverse strand (F forward strand) and 26 stands for the size of the read. + +the second sequence in this example is a read that overlap by 10 nt with the first read. + + </help> + <citations> + <citation type="doi">10.1007/978-1-4939-0931-5_12</citation> + </citations> +</tool> |
| b |
| diff -r a35e6f9c1d34 -r 6f1378738798 test-data/paired.fa --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/paired.fa Tue Aug 29 20:02:15 2017 -0400 |
| b |
| b'@@ -0,0 +1,2182 @@\n+>FBgn0000004_17.6|5839|R|26\n+TTTTCGTCAATTGTGCCAAATAGGTA\n+>FBgn0000004_17.6|5855|F|23\n+TTGACGAAAATGATCGAGTGGAT\n+>FBgn0000006_412|744|R|26\n+TTTCGACCAAACCGGTGGCGTTTGCT\n+>FBgn0000006_412|744|R|26\n+TTTCGACCAAACCGGTGGCGTTTGCT\n+>FBgn0000006_412|745|R|25\n+TTTCGACCAAACCGGTGGCGTTTGC\n+>FBgn0000006_412|742|R|27\n+TTCGACCAAACCGGTGGCGTTTGCTGA\n+>FBgn0000006_412|744|R|25\n+TTCGACCAAACCGGTGGCGTTTGCT\n+>FBgn0000006_412|744|R|25\n+TTCGACCAAACCGGTGGCGTTTGCT\n+>FBgn0000006_412|745|R|24\n+TTCGACCAAACCGGTGGCGTTTGC\n+>FBgn0000006_412|745|R|24\n+TTCGACCAAACCGGTGGCGTTTGC\n+>FBgn0000006_412|759|F|24\n+TTTGGTCGAAAGCTCTAAAGCTAC\n+>FBgn0000006_412|759|F|24\n+TTTGGTCGAAAGCTCTAAAGCTAC\n+>FBgn0000006_412|759|F|24\n+TTTGGTCGAAAGCTCTAAAGCTAC\n+>FBgn0000006_412|759|F|25\n+TTTGGTCGAAAGCTCTAAAGCTACA\n+>FBgn0000006_412|759|F|27\n+TTTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|759|F|27\n+TTTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|759|F|27\n+TTTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|760|F|26\n+TTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|760|F|26\n+TTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|760|F|26\n+TTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|760|F|26\n+TTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|760|F|26\n+TTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000006_412|760|F|26\n+TTGGTCGAAAGCTCTAAAGCTACATG\n+>FBgn0000007_1731|4539|R|26\n+TTGAGAGCAAAGGCCGAATGAGTAAA\n+>FBgn0000007_1731|4555|F|24\n+TTGCTCTCAATGCGCTGAGTTTGG\n+>FBgn0000155_roo|8639|R|26\n+TTCTGCCAAAGGGCCAGCAAAGCTGA\n+>FBgn0000155_roo|8639|R|26\n+TTCTGCCAAAGTGCCAGCAAAGCTGA\n+>FBgn0000155_roo|3225|R|26\n+TTTTGCCCAAGGAGACCGTCTATTTT\n+>FBgn0000155_roo|3226|R|25\n+TTTTGCCCAAGGAGACCGTCTATTT\n+>FBgn0000155_roo|3227|R|24\n+TTTTGCCCAAGGAGACCGTCTATT\n+>FBgn0000155_roo|3227|R|24\n+TTTTGCCCAAGGAGACCGTCTATT\n+>FBgn0000155_roo|3228|R|23\n+TTTTGCCCAAGGAGACCGTCTAT\n+>FBgn0000155_roo|3132|R|27\n+TTTATTAAAATCGGGGTCGGCTAATTT\n+>FBgn0000155_roo|2675|R|27\n+TTTTTACCAAACGGATGCCTCAGACAT\n+>FBgn0000155_roo|2676|R|26\n+TTTTTACCAAACGGATGCCTCAGACA\n+>FBgn0000155_roo|2676|R|26\n+TTTTTACCAAACGGATGCCTCAGACA\n+>FBgn0000155_roo|2676|R|26\n+TTTTTACCAAACGGATGCCTCAGACA\n+>FBgn0000155_roo|2676|R|26\n+TTTTTACCAAACGGATGCCTCAGACA\n+>FBgn0000155_roo|2676|R|26\n+TTTTTACCAAACGGATGCCTCAGACA\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2677|R|25\n+TTTTTACCAAACGGATGCCTCAGAC\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2678|R|24\n+TTTTTACCAAACGGATGCCTCAGA\n+>FBgn0000155_roo|2679|R|23\n+TTTTTACCAAACGGATGCCTCAG\n+>FBgn0000155_roo|2679|R|23\n+TTTTTACCAAACGGATGCCTCAG\n+>FBgn0000155_roo|2159|R|27\n+TTGGTCAAAAACTCCCAAGTGGCTTCA\n+>FBgn0000155_roo|2161|R|25\n+TTGGTCAAAAACTCCCAAGTGGCTT\n+>FBgn0000155_roo|2176|F|24\n+TTTTGACCAAGCGGTATGAGAATA\n+>FBgn0000155_roo|2692|F|24\n+TTGGTAA'..b'08|R|25\n+TTCCGTGGGATCGCCTGAAGCCAAA\n+>FBgn0063507_G2|1923|F|29\n+TTCCACGGAACACCCGAGCAATGCCACCG\n+>FBgn0063534_Doc2-element|3605|R|28\n+TTTTTGCGAAAGCCAAACTGATGCGATG\n+>FBgn0063534_Doc2-element|3606|R|27\n+TTTTTGCGAAAGCCAAACTGATGCGAT\n+>FBgn0063534_Doc2-element|3606|R|27\n+TTTTTGCGAAAGCCAAACTGATGCGAT\n+>FBgn0063534_Doc2-element|3607|R|26\n+TTTTTGCGAAAGCCAAACTGATGCGA\n+>FBgn0063534_Doc2-element|3607|R|26\n+TTTTTGCGAAAGCCAAACTGATGCGA\n+>FBgn0063534_Doc2-element|3607|R|26\n+TTTTTGCGAAAGCCAAACTGATGCGA\n+>FBgn0063534_Doc2-element|3607|R|26\n+TTTTTGCGAAAGCCAAACTGATGCGA\n+>FBgn0063534_Doc2-element|3608|R|25\n+TTTTTGCGAAAGCCAAACTGATGCG\n+>FBgn0063534_Doc2-element|3608|R|25\n+TTTTTGCGAAAGCCAAACTGATGCG\n+>FBgn0063534_Doc2-element|3608|R|25\n+TTTTTGCGAAAGCCAAACTGATGCG\n+>FBgn0063534_Doc2-element|3608|R|25\n+TTTTTGCGAAAGCCAAACTGATGCG\n+>FBgn0063534_Doc2-element|3608|R|25\n+TTTTTGCGAAAGCCAAACTGATGCG\n+>FBgn0063534_Doc2-element|3608|R|25\n+TTTTTGCGAAAGCCAAACTGATGCG\n+>FBgn0063534_Doc2-element|3608|R|25\n+TTTTTGCGAAAGCCAAACTGATGCG\n+>FBgn0063534_Doc2-element|3609|R|24\n+TTTTTGCGAAAGCCAAACTGATGC\n+>FBgn0063534_Doc2-element|3610|R|23\n+TTTTTGCGAAAGCCAAACTGATG\n+>FBgn0063534_Doc2-element|3610|R|23\n+TTTTTGCGAAAGCCAAACTGATG\n+>FBgn0063534_Doc2-element|3610|R|23\n+TTTTTGCGAAAGCCAAACTGATG\n+>FBgn0063534_Doc2-element|327|R|25\n+TTCGTTGCAATGAGAGCCGGCGATC\n+>FBgn0063534_Doc2-element|342|F|25\n+TTGCAACGAAACAACGCGTACTTCT\n+>FBgn0063534_Doc2-element|3623|F|23\n+TTCGCAAAAATCACGGAACGATC\n+>FBgn0063534_Doc2-element|3623|F|26\n+TTCGCAAAAATCACGGAACGATCGAA\n+>FBgn0063594_Cr1a|2037|R|27\n+TTGTTACAAGACATAGATCCAACAGTC\n+>FBgn0063594_Cr1a|2039|R|25\n+TTGTTACAAAACATAGATCCAACAG\n+>FBgn0063594_Cr1a|2054|F|24\n+TTTGTAACAAGTCCTGAAAGTGTG\n+>FBgn0063594_Cr1a|2054|F|24\n+TTTGTAACAAGTCCTGAAAGTGTG\n+>FBgn0063919_Max-element|3879|R|29\n+TTGCTGAGAAGCGTGTTGAGCGAATCAGG\n+>FBgn0063919_Max-element|3880|R|28\n+TTGCTGAGAAGCGTGTCGAGCGAATCAG\n+>FBgn0063919_Max-element|3880|R|28\n+TTGCTGAGAAGCGTGTTGAGCGAATCAG\n+>FBgn0063919_Max-element|3882|R|26\n+TTGCTGAGAAGCGTGTCGAGCGAATC\n+>FBgn0063919_Max-element|3883|R|25\n+TTGCTGAGAAGCGTGTCGAGCGAAT\n+>FBgn0063919_Max-element|3884|R|24\n+TTGCTGAGAAGCGTGTTGAGCGAA\n+>FBgn0063919_Max-element|3898|F|23\n+TTCTCAGCAAGTTCTGGGAGGTG\n+>FBgn0063919_Max-element|3898|F|24\n+TTCTCAGCAAGTTCTGGGAGGTGG\n+>FBgn0063919_Max-element|3898|F|24\n+TTCTCAGCAAGTTCTGGGAGGTGG\n+>FBgn0063919_Max-element|3898|F|25\n+TTCTCAGCAAGTTCTGGGAGGTGGA\n+>FBgn0063919_Max-element|3898|F|24\n+TTCTCAGCAAGTTCTGGGAGGTGT\n+>FBgn0067385_invader6|3007|R|27\n+TTCTAGTCAAAGTCGAAGGACTGCATA\n+>FBgn0067385_invader6|3007|R|27\n+TTCTAGTCAAAGTCGAAGGACTGCATA\n+>FBgn0067385_invader6|3007|R|27\n+TTCTAGTCAAAGTCGAAGGACTGCATA\n+>FBgn0067385_invader6|3007|R|27\n+TTCTAGTCAAAGTCGAAGGACTGCATA\n+>FBgn0067385_invader6|3008|R|26\n+TTCTAGTCAAAGTCGAAGGACTGCAT\n+>FBgn0067385_invader6|3008|R|26\n+TTCTAGTCAAAGTCGAAGGACTGCAT\n+>FBgn0067385_invader6|3008|R|26\n+TTCTAGTCAAAGTCGAAGGACTGCAT\n+>FBgn0067385_invader6|3009|R|25\n+TTCTAGTCAAAGTCGAAGGACTGCA\n+>FBgn0067385_invader6|3009|R|25\n+TTCTAGTCAAAGTCGAAGGACTGCA\n+>FBgn0067385_invader6|3009|R|25\n+TTCTAGTCAAAGTCGAAGGACTGCA\n+>FBgn0067385_invader6|3009|R|25\n+TTCTAGTCAAAGTCGAAGGACTGCA\n+>FBgn0067385_invader6|3009|R|25\n+TTCTAGTCAAAGTCGAAGGACTGCA\n+>FBgn0067385_invader6|3010|R|24\n+TTCTAGTCAAAGTCGAAGGACTGC\n+>FBgn0067385_invader6|3010|R|24\n+TTCTAGTCAAAGTCGAAGGACTGC\n+>FBgn0067385_invader6|3010|R|24\n+TTCTAGTCAAAGTCGAAGGACTGC\n+>FBgn0067385_invader6|3010|R|24\n+TTCTAGTCAAAGTCGAAGGACTGC\n+>FBgn0067385_invader6|3011|R|23\n+TTCTAGTCAAAGTCGAAGGACTG\n+>FBgn0067385_invader6|3024|F|26\n+TTGACTAGAATGACTTAGACTTAGAA\n+>FBgn0067624_BS3|1011|R|25\n+TTGATGCCAATGTTCCAGCGTTTTG\n+>FBgn0067624_BS3|1011|R|25\n+TTGATGCCAATGTTCCAGCGTTTTG\n+>FBgn0067624_BS3|1011|R|25\n+TTGATGCCAATGTTCCAGCGTTTTG\n+>FBgn0067624_BS3|1013|R|23\n+TTGATGCCAATGTTCCAACGTCT\n+>FBgn0067624_BS3|1013|R|23\n+TTGATGCCAATGTTCCAACGTCT\n+>FBgn0067624_BS3|1013|R|23\n+TTGATGCCAATGTTCCAACGTCT\n+>FBgn0067624_BS3|1026|F|26\n+TTGGCATCAATGGTGACAAATCAGCG\n+>FBgn0067624_BS3|1026|F|24\n+TTGGCATCAATGGTGACAAATCTG\n+>FBgn0067624_BS3|1026|F|25\n+TTGGCATCAATGGTGACAAATCTGC\n' |