From a8a8aba3ec1ff5e1066962d1a1a3a7315836d0ac Mon Sep 17 00:00:00 2001
From: Antonio Gonzalez <antgonza@gmail.com>
Date: Wed, 2 Oct 2024 14:13:42 -0600
Subject: [PATCH] adding fastq_pair

---
 qp_woltka/tests/test_woltka.py | 11 +++++++++--
 qp_woltka/woltka.py            | 12 ++++++++++--
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/qp_woltka/tests/test_woltka.py b/qp_woltka/tests/test_woltka.py
index 65df7ad..8949a08 100644
--- a/qp_woltka/tests/test_woltka.py
+++ b/qp_woltka/tests/test_woltka.py
@@ -456,7 +456,7 @@ def test_woltka_syndna_to_array(self):
             f'#SBATCH --error {out_dir}/{job_id}_%a.err\n',
             '#SBATCH --array 1-1%8\n',
             f'cd {out_dir}\n',
-            'mkdir -p reads sams\n',
+            'mkdir -p reads/uneven sams\n',
             f'{self.environment}\n',
             'date\n',
             'hostname\n',
@@ -470,7 +470,8 @@ def test_woltka_syndna_to_array(self):
             f'    bowtie2 -p 8 -x {database} -q '
             '${f} -S $PWD/sams/${sn}.sam --seed 42 --very-sensitive -k 16 '
             '--np 1 --mp "1,1" --rdg "0,1" --rfg "0,1" --score-min '
-            '"L,0,-0.05" --no-head --no-unal --un $PWD/reads/${fn/.gz/}\n',
+            '"L,0,-0.05" --no-head --no-unal --un '
+            '$PWD/reads/uneven/${fn/.gz/}\n',
             '  done < sample_details_${SLURM_ARRAY_TASK_ID}.txt\n',
             'date']
         self.assertEqual(main, exp_main)
@@ -495,6 +496,12 @@ def test_woltka_syndna_to_array(self):
             'sjobs=`ls sams/*.sam | wc -l`\n',
             'if [[ $sruns -eq $sjobs ]]; then\n',
             '  mkdir -p sams/final\n',
+            '  while read -r fwd rev; do \n'
+            '    echo fastq_pair -t 50000000 reads/uneven/${fwd} ',
+            'reads/uneven/${rev}; mv reads/uneven/${fwd}.paired.fq ',
+            'reads/${fwd}; mv reads/uneven/${rev}.paired.fq reads/${rev};',
+            'gzip reads/${fwd} reads/${rev}\n  done < ',
+            'finish_sample_details.txt | parallel -j 8\n',
             '  for f in `ls sams/fwd_*`;\n',
             '    do\n',
             '      fn=`basename $f`;\n',
diff --git a/qp_woltka/woltka.py b/qp_woltka/woltka.py
index 14203f5..e9b206f 100644
--- a/qp_woltka/woltka.py
+++ b/qp_woltka/woltka.py
@@ -425,7 +425,7 @@ def woltka_syndna_to_array(files, output, database_bowtie2, prep, url, name):
               '-q ${f} -S $PWD/sams/${sn}.sam ' +\
               '--seed 42 --very-sensitive -k 16 --np 1 --mp "1,1" ' + \
               '--rdg "0,1" --rfg "0,1" --score-min "L,0,-0.05" ' + \
-              '--no-head --no-unal --un $PWD/reads/${fn/.gz/}'
+              '--no-head --no-unal --un $PWD/reads/uneven/${fn/.gz/}'
 
     # all the setup pieces
     lines = ['#!/bin/bash',
@@ -440,7 +440,7 @@ def woltka_syndna_to_array(files, output, database_bowtie2, prep, url, name):
              f'#SBATCH --error {output}/{name}_%a.err',
              f'#SBATCH --array 1-{n_files}%{MAX_RUNNING}',
              f'cd {output}',
-             'mkdir -p reads sams',
+             'mkdir -p reads/uneven sams',
              f'{environment}',
              'date',  # start time
              'hostname',  # executing system
@@ -482,6 +482,14 @@ def woltka_syndna_to_array(files, output, database_bowtie2, prep, url, name):
              'sjobs=`ls sams/*.sam | wc -l`',
              'if [[ $sruns -eq $sjobs ]]; then',
              '  mkdir -p sams/final',
+             '  while read -r fwd rev; do ',
+             '    echo fastq_pair -t 50000000 reads/uneven/${fwd} '
+             'reads/uneven/${rev}; '
+             'mv reads/uneven/${fwd}.paired.fq reads/${fwd};'
+             'mv reads/uneven/${rev}.paired.fq reads/${rev};'
+             'gzip reads/${fwd} reads/${rev}',
+             '  done < finish_sample_details.txt | '
+             f'parallel -j {PPN}'
              '  for f in `ls sams/fwd_*`;',
              '    do',
              '      fn=`basename $f`;',