X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=erange.git;a=blobdiff_plain;f=docs%2FrunStandardAnalysis.sh;h=aa5fe60588a30ceba6a65301db81b13ac4f6051f;hp=6d83297bf4f39964793ced9800e46a3eb7bbcbc0;hb=0d3e3112fd04c2e6b44a25cacef1d591658ad181;hpb=5e4ae21098dba3d1edcf11e7279da0d84c3422e4 diff --git a/docs/runStandardAnalysis.sh b/docs/runStandardAnalysis.sh index 6d83297..aa5fe60 100755 --- a/docs/runStandardAnalysis.sh +++ b/docs/runStandardAnalysis.sh @@ -11,25 +11,25 @@ if [ -z "$ERANGEPATH" ] then - ERANGEPATH='../commoncode' + ERANGEPATH='../erange' fi -echo 'runStandardAnalysis.sh: version 4.2' +echo 'runStandardAnalysis.sh: version 4.3' models="" if [ $# -eq 5 ]; then - models=" -models "$5 + models=" --models "$5 fi replacemodels="" if [ $# -eq 6 ]; then - replacemodels=" -models $5 -replacemodels " + replacemodels=" --models $5 --replacemodels " fi if [ -z "$1" ] then echo - echo 'usage:runStandardAnalysis.sh genome rdsprefix repeatmaskdb bpradius [modelfile] [-replacemodels]' + echo 'usage:runStandardAnalysis.sh genome rdsprefix repeatmaskdb bpradius [modelfile] [--replacemodels]' echo echo 'where rdsprefix is the name of the rds file without the .rds extension' echo 'use "none" for the repeatmaskdb if you do not have one' @@ -44,48 +44,48 @@ python $ERANGEPATH/recordLog.py rna.log runStandardAnalysis.sh "with parameters: # count the unique reads falling on the gene models ; the nomatch files are # mappable reads that fell outside of the Cistematic gene models and not the # unmappable of Eland (i.e, the "NM" reads) -echo "python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.uniqs.count -markGID -cache 1 $models $replacemodels" -python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.uniqs.count -markGID -cache 1 $models $replacemodels +echo "python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.uniqs.count --markGID --cache 1 $models $replacemodels" +python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.uniqs.count --markGID --cache 1 $models $replacemodels # calculate a first-pass RPKM to re-weigh the unique reads, # using 'none' for the splice count -echo "python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.count none $2.firstpass.rpkm -cache $models $replacemodels" -python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.count none $2.firstpass.rpkm -cache $models $replacemodels +echo "python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.count none $2.firstpass.rpkm --cache $models $replacemodels" +python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.count none $2.firstpass.rpkm --cache $models $replacemodels # recount the unique reads with weights calculated during the first pass -echo "python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.firstpass.rpkm $2.uniqs.recount -uniq -cache 1 $models $replacemodels" -python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.firstpass.rpkm $2.uniqs.recount -uniq -cache 1 $models $replacemodels +echo "python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.firstpass.rpkm $2.uniqs.recount --uniq --cache 1 $models $replacemodels" +python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.firstpass.rpkm $2.uniqs.recount --uniq --cache 1 $models $replacemodels # count splice reads -echo "python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.splices.count -splices -noUniqs -cache 1 $models $replacemodels" -python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.splices.count -splices -noUniqs -cache 1 $models $replacemodels +echo "python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.splices.count --splices --noUniqs --cache 1 $models $replacemodels" +python $ERANGEPATH/geneMrnaCounts.py $1 $2.rds $2.splices.count --splices --noUniqs --cache 1 $models $replacemodels # Alternative 1: find new regions outside of gene models with reads piled up -echo "python $ERANGEPATH/findall.py RNAFAR $2.rds $2.newregions.txt -RNA -minimum 1 -nomulti -flag NM -log rna.log -cache 1" -python $ERANGEPATH/findall.py RNAFAR $2.rds $2.newregions.txt -RNA -minimum 1 -nomulti -flag NM -log rna.log -cache 1 +echo "python $ERANGEPATH/findall.py RNAFAR $2.rds $2.newregions.txt --RNA --minimum 1 --nomulti --flag NM --log rna.log --cache 1" +python $ERANGEPATH/findall.py RNAFAR $2.rds $2.newregions.txt --RNA --minimum 1 --nomulti --flag NM --log rna.log --cache 1 # Alternative 1: filter out new regions that overlap repeats more than a certain fraction -echo "python $ERANGEPATH/checkrmask.py $3 $2.newregions.txt $2.newregions.repstatus $2.newregions.good -startField 1 -cache 1" -python $ERANGEPATH/checkrmask.py $3 $2.newregions.txt $2.newregions.repstatus $2.newregions.good -log rna.log -startField 1 -cache 1 +echo "python $ERANGEPATH/checkrmask.py $3 $2.newregions.txt $2.newregions.repstatus $2.newregions.good --log rna.log --startField 1 --cache 1" +python $ERANGEPATH/checkrmask.py $3 $2.newregions.txt $2.newregions.repstatus $2.newregions.good --log rna.log --startField 1 --cache 1 # map all candidate regions that are within a given radius of a gene in bp -echo "python $ERANGEPATH/getallgenes.py $1 $2.newregions.good $2.candidates.txt -radius $4 -trackfar -cache $models $replacemodels" -python $ERANGEPATH/getallgenes.py $1 $2.newregions.good $2.candidates.txt -radius $4 -trackfar -cache $models $replacemodels +echo "python $ERANGEPATH/getallgenes.py $1 $2.newregions.good $2.candidates.txt --radius $4 --trackfar --cache $models $replacemodels" +python $ERANGEPATH/getallgenes.py $1 $2.newregions.good $2.candidates.txt --radius $4 --trackfar --cache $models $replacemodels # make sure candidates.txt file exists echo "touch $2.candidates.txt" touch $2.candidates.txt # calculate expanded exonic read density -echo "python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.recount $2.splices.count $2.expanded.rpkm $2.candidates.txt $2.accepted.rpkm -cache $models $replacemodels" -python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.recount $2.splices.count $2.expanded.rpkm $2.candidates.txt $2.accepted.rpkm -cache $models $replacemodels +echo "python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.recount $2.splices.count $2.expanded.rpkm $2.candidates.txt $2.accepted.rpkm --cache $models $replacemodels" +python $ERANGEPATH/normalizeExpandedExonic.py $1 $2.rds $2.uniqs.recount $2.splices.count $2.expanded.rpkm $2.candidates.txt $2.accepted.rpkm --cache $models $replacemodels # weigh multi-reads -echo "python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.expanded.rpkm $2.multi.count -accept $2.accepted.rpkm -multi -cache 1 $models $replacemodels" -python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.expanded.rpkm $2.multi.count -accept $2.accepted.rpkm -multi -cache 1 $models $replacemodels +echo "python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.expanded.rpkm $2.multi.count --accept $2.accepted.rpkm --multi --cache 1 $models $replacemodels" +python $ERANGEPATH/geneMrnaCountsWeighted.py $1 $2.rds $2.expanded.rpkm $2.multi.count --accept $2.accepted.rpkm --multi --cache 1 $models $replacemodels # calculate final exonic read density -echo "python $ERANGEPATH/normalizeFinalExonic.py $2.rds $2.expanded.rpkm $2.multi.count $2.final.rpkm -multifraction -withGID -cache" -python $ERANGEPATH/normalizeFinalExonic.py $2.rds $2.expanded.rpkm $2.multi.count $2.final.rpkm -multifraction -withGID -cache +echo "python $ERANGEPATH/normalizeFinalExonic.py $2.rds $2.expanded.rpkm $2.multi.count $2.final.rpkm --multifraction --withGID --cache" +python $ERANGEPATH/normalizeFinalExonic.py $2.rds $2.expanded.rpkm $2.multi.count $2.final.rpkm --multifraction --withGID --cache fi \ No newline at end of file