Skip to content

Commit

Permalink
added option to exclude execution of the (experimental) ccp-count
Browse files Browse the repository at this point in the history
  • Loading branch information
@egaffo
egaffo committed Oct 2, 2019
1 parent 35ecdaa commit c70abcc
Show file tree
Hide file tree
Showing 2 changed files with 61 additions and 43 deletions.
51 changes: 26 additions & 25 deletions src/ccp_collect_circrnas.scons
View file
Original file line number Diff line number Diff line change
Expand Up @@ -69,31 +69,32 @@ circ_gtf_cmd = circ_gtf_cmd + '''} | sort -k1,1 -k4,4n > ${TARGETS[0]}'''
circ_gtf_target = 'circrnas.gtf'
circ_gtf = env.Command(circ_gtf_target, circ_gtf_sources, circ_gtf_cmd)

## compute CirComPara merged read counts
ccp_counts_dir = 'ccp_counts'
circular_reads_bed_gz_txt_sources = []
for s in env['RUNS_DICT'].keys():
for m in env['RUNS_DICT'][s]['CIRCULAR_EXPRESSION']['CIRC_METHODS'].keys():
res = env['RUNS_DICT'][s]['CIRCULAR_EXPRESSION']['CIRC_METHODS'][m]
if res:
circular_reads_bed_gz_txt_sources.append(res['CIRC_READS'])
circular_reads_bed_gz_txt_target = os.path.join(ccp_counts_dir,
'circular.reads.bed.gz.txt')

circular_reads_bed_gz_txt = env.WriteLinesInTxt(circular_reads_bed_gz_txt_target,
circular_reads_bed_gz_txt_sources)

ccp_counts_targets = [os.path.join(ccp_counts_dir, f) for f in
['bks.counts.intersect.csv',
'bks.counts.union.csv',
'bks.counts.union.intersected.csv']]
ccp_counts_cmd = 'get_circompara_counts.R -i ${SOURCES[0]} '\
'-q $MIN_METHODS -o ${TARGETS[0].dir}'\
+ os.path.sep + 'bks.counts.'
ccp_counts = env.Command(ccp_counts_targets,
[circular_reads_bed_gz_txt,
circular_reads_bed_gz_txt_sources],
ccp_counts_cmd)
if env['CCP_COUNTS']:
## compute CirComPara merged read counts
ccp_counts_dir = 'ccp_counts'
circular_reads_bed_gz_txt_sources = []
for s in env['RUNS_DICT'].keys():
for m in env['RUNS_DICT'][s]['CIRCULAR_EXPRESSION']['CIRC_METHODS'].keys():
res = env['RUNS_DICT'][s]['CIRCULAR_EXPRESSION']['CIRC_METHODS'][m]
if res:
circular_reads_bed_gz_txt_sources.append(res['CIRC_READS'])
circular_reads_bed_gz_txt_target = os.path.join(ccp_counts_dir,
'circular.reads.bed.gz.txt')

circular_reads_bed_gz_txt = env.WriteLinesInTxt(circular_reads_bed_gz_txt_target,
circular_reads_bed_gz_txt_sources)

ccp_counts_targets = [os.path.join(ccp_counts_dir, f) for f in
['bks.counts.intersect.csv',
'bks.counts.union.csv',
'bks.counts.union.intersected.csv']]
ccp_counts_cmd = 'get_circompara_counts.R -i ${SOURCES[0]} '\
'-q $MIN_METHODS -o ${TARGETS[0].dir}'\
+ os.path.sep + 'bks.counts.'
ccp_counts = env.Command(ccp_counts_targets,
[circular_reads_bed_gz_txt,
circular_reads_bed_gz_txt_sources],
ccp_counts_cmd)

## compute gene introns
merge_exons_cmd = '''grep -w exon ${SOURCES[0]} | '''\
Expand Down
53 changes: 35 additions & 18 deletions src/ccp_main.scons
View file
Original file line number Diff line number Diff line change
Expand Up @@ -141,52 +141,62 @@ vars.Add('PREPROCESSOR_PARAMS',
'MAXINFO:40:0.5 LEADING:20 TRAILING:20 SLIDINGWINDOW:4:30 MINLEN:50 AVGQUAL:30 ',
'')
vars.Add('LINEAR_EXPRESSION_METHODS', 'The method to be used for the linear expression estimates'\
'/transcriptome reconstruction. To run more methods use a comma separated list. '\
'However, only the first method in the list will be used in downstream processing. '\
'Currently supported methods: stringtie,cufflinks,htseq.', 'stringtie')
'/transcriptome reconstruction. To run more methods use a comma separated list. '\
'However, only the first method in the list will be used in downstream processing. '\
'Currently supported methods: stringtie,cufflinks,htseq.',
'stringtie')
vars.Add('TOGGLE_TRANSCRIPTOME_RECONSTRUCTION', 'Set True to enable transcriptome '\
'reconstruction. Default only quantifies genes and transcripts from the given '\
'annotation GTF file', 'False')
vars.Add('DIFF_EXP', 'Set the method to and enable differential expression '\
'computation for linear genes/transcripts. Current methods '\
'supported: cufflinks, ballgown, DESeq2.'\
'Only available if more than one sample and more than one condition are given. '\
'N.B: differential expression tests for circRNAs is not yet '\
'implemented', '')
vars.Add('CIRC_DIFF_EXP', '(Experimental) Set True to enable differential gene expression computation '\
'also with DESeq2. Only available if more than one sample and more than one condition are given',
'False')
vars.Add('QRE_FIND', '(Experimental) Set True to toggle analysis of QKI response elements sequences',
'False')
'N.B: differential expression tests for circRNAs is not yet implemented',
'')
vars.Add('READSTAT_METHODS', 'Comma separated list of methods to use for read statistics. '\
'Currently supported: fastqc,fastx', 'fastqc')
vars.Add('MIN_METHODS', 'Number of methods that commmonly detect a circRNA to '\
'define the circRNA as reliable. If this value exceeds the number '\
'of methods specified, it will be set to the number of methods.', 2)
vars.Add('MIN_READS', 'Number of reads to consider a circRNA as expressed', 2)
'of methods specified, it will be set to the number of methods.',
2)
vars.Add('MIN_READS', 'Number of reads to consider a circRNA as expressed',
2)
vars.Add('BYPASS', 'Skip analysis of linear/circular transcripts. This will also skip '\
'the analysis of linear-to-circular expression correlation.'\
'{linear,circular}',
'False')
'False')
vars.Add('CIRC_PE_MAPPING', 'By default, linearly unmapped reads are'\
'collapsed into single-end reads to search for circRNA backsplices. Set'\
'this option to "True" to force circRNA method aligners to'\
'maintain paired-end read alignment', 'False')
vars.Add('LIN_COUNTER', 'The method to estimate circRNA-host gene '\
'linear expression. Available are using the DCC '\
'[dcc], or the CirComPara [ccp] method', 'ccp')
'[dcc], or the CirComPara [ccp] method',
'ccp')
vars.Add('FIX_READ_HEADER', 'Trim FASTQ headers to the read ids. '\
'Recommended when processing SRA datasets', 'True')
'Recommended when processing SRA datasets',
'True')
vars.Add('UNSTRANDED_CIRCS', 'Force unstranded circRNAs even if stranded library '\
'was used',
'False')
'False')

## performance options
vars.Add('SAM_SORT_MM', 'Value for samtools sort -m option', '768M')

## experimental
vars.Add('CIRC_DIFF_EXP', '(Experimental) Set True to enable differential expression computation '\
'for circRNAs. Only available if >1 conditions are given.',
'False')
vars.Add('QRE_FIND', '(Experimental) Set True to toggle analysis of QKI response elements sequences',
'False')
vars.Add('CCP_COUNTS', '(Experimental) Use the CirComPara merged alignment counts',
'False')

## deprecated parameters (legacy)
vars.Add('CIRI', 'The full path to the CIRI_vx.x.pl perl script (DEPRECATED). '\
'By default the symlink in CirComPara bin/ directory will be used', '')
vars.Add('CIRI', '(DEPRECATED) The full path to the CIRI_vx.x.pl perl script. '\
'By default, the symlink in CirComPara bin/ directory will be used',
'')


env = Environment(ENV=os.environ, SHELL = '/bin/bash',
Expand Down Expand Up @@ -259,6 +269,13 @@ if env['CIRC_DIFF_EXP'].lower() == 'true':
else:
env.Replace(CIRC_DIFF_EXP = False)

env.SetDefault(CCP_COUNTS = False)
if env['CCP_COUNTS'].strip().lower() == 'true':
env.Replace(CCP_COUNTS = True)
else:
env.Replace(CCP_COUNTS = False)


env.SetDefault(ORIGINAL_ANNOTATION = env['ANNOTATION'])

## convert relative paths to absolute
Expand Down

0 comments on commit c70abcc

Please sign in to comment.