#!/bin/tcsh # tandxmiss.sh set td=/bio/bio-grid/dpulex/prots/ set pred=EISE_CGW # set pred=GLEANR # set pred=NCBI_GNO #set dspp=(dsec dsim dyak dere dana dpse dmoj dvir dgri) set dspp=(dpse) foreach dp ($dspp) echo "# pred:$pred species:$dp :: tandem exons missed inside gene models" if( ! -f ${dp}1/${dp}_tandy6jmd_hspnear.gff ) then gzcat ${dp}1/${dp}_exons_tandy6jmd.gff.gz | grep HSP | egrep -v 'tandyweak|terepeat' | grep '=-2' \ > ${dp}1/${dp}_tandy6jmd_hspnear.gff endif gzcat ${dp}1/${dp}*_predict.gff.gz | grep "$pred.CDS" | \ $td/overlapfilter.perl -act drop -overlaps stdin -typeover overlap -pctover 50 \ -in ${dp}1/${dp}_tandy6jmd_hspnear.gff > ${dp}1/${dp}_tandy6jmd_hspnear-x$pred.gff gzcat ${dp}1/${dp}*_predict.gff.gz | grep "$pred.mRNA" | \ $td/overlapfilter.perl -act keep -overlaps stdin -typeover overlap -pctover 80 \ -in ${dp}1/${dp}_tandy6jmd_hspnear-x$pred.gff > ${dp}1/${dp}_tandy6jmd_hspnear-gx$pred.gff /bin/rm ${dp}1/${dp}_tandy6jmd_hspnear-x$pred.gff wc -l ${dp}1/${dp}_tandy6jmd_hspnear-gx$pred.gff echo -n "$pred in hsp: " grep -c $pred ${dp}1/${dp}_tandy6jmd_hspnear-gx$pred.gff echo "# ---------------------------------------------------" end