1.2.1b lspcalc seq/seq (LArge Scale Sequence compArison Package) Glemet, Codani lspcalc_seqseq lspcalc_seqseq perl "lspcalc" 0 type_of_run Type of run perl "" -M -M -M: Compute -I -I: Info, do not compute method Comparison method perl " $type_of_run $value" 10 BLAST BLAST BLSW BLSW: Blast+Smith/Waterman. A mix of Blast and SW. KERR KERR: Approximate string matching. Find inclusions with errors allowed. PATT PATT: Pattern Matching. Find motif, e.g. PROSITE searching. BM BM: Boyer Moore. Find exact inclusions. SW SW: Smith/Waterman. Best local gapped alignment. NW NW: Needleman/Wunsch. Best global gapped alignment. SWR SWR: Z-value computation (gives a significance estimate by the use of a schuffling). ZVAL ZVAL: Z-value computation optimized. Variant of SWR with parameters for clustering. SWT SWT: Fast Smith/Waterman. Optimized version of SW. KBEST KBEST: K-best. k-best gapped local alignments. BLKERR BLKERR: Blast+Approximate string matching. A mix of Blast and KERR type_of_scan Type of scan PP 20 PP protein db/protein query NN nucleic db/nucleic query PTN proteic db/trans. nucleic query TNP trans. nucleic db/proteic query TNTN trans. nucleic db/trans. nucleic query PP " -mp " PTN " -mp " TNP " -mp " NN " -mn " TNTN " -mp " perl ! $blast_matrix && ($method eq "BLAST" || $method eq "SW" || $method eq "SWT" || $method eq "KBEST" || $method eq "NW" || $method eq "SWR" || $method eq "ZVAL" || $method eq "BLSW" || $method eq "BLKERR") matrix Choose a scoring matrix BLOSUM62 21 swgapdna swgapdna (Nucleic) NUC.4.4 NUC.4.4 (Nucleic) BLOSUM62 BLOSUM62 (Proteic) PAM250 PAM250 (Proteic) DAYHOFF DAYHOFF (Proteic) ID ID (Proteic) ID1 ID1 (Proteic) nwsgappep nwsgappep (Proteic) DAYHOFF " dayhoff" swgapdna " swgapdna" PAM250 " pam250" nwsgappep " nwsgappep" BLOSUM62 " BLOSUM62" NUC.4.4 " NUC.4.4" ID " id" ID1 " id1" For BLAST,SW*, KBEST, NW, ZVAL, BLSW and BLKERR. The matrix is not coherent with the type of scan perl ($type_of_scan eq "NN" && $matrix !~ /sw|NUC/) || ($type_of_scan ne "NN" && $matrix =~ /sw|NUC/) perl ! $blast_matrix && ($method eq "BLAST" || $method eq "SW" || $method eq "SWT" || $method eq "KBEST" || $method eq "NW" || $method eq "SWR" || $method eq "ZVAL" || $method eq "BLSW" || $method eq "BLKERR") query_opt perl " -dr " 400 query Query sequence perl " $query" 450 8 seq_opt perl " -dr " 300 sequences_file Your sequences database perl ($value)? " $value" : "" 350 8 lspread Save results for further analysis (lspread) perl "" 1 998 results_file perl " -o results" results 700 perl (! $view_alignment) && $lspread lspcalc_result_seqseq perl 1 lspcalc_result_seqseq cmdfile query sequences_file cmdfile perl "" "$results_file.cmd" 701 perl $lspread method_parameters Methods parameters gap_options Gap options (SW, SWT, SWR, KBEST, NW, BLSW and ZVAL) perl $method eq "SW" || $method eq "SWT" || $method eq "SWR" || $method eq "KBEST" || $method eq "NW" || $method eq "ZVAL"|| $method eq "BLSW" 15 gapo Gap open penalty (-gapo) perl (defined $value && $value ne $vdef)? " -gapo $value" : "" 10 15 no message perl defined $value && $value ne $vdef && ($algo_opt=1) && 0 perl $method eq "SW" || $method eq "SWT" || $method eq "SWR" || $method eq "KBEST" || $method eq "NW" || $method eq "ZVAL"|| $method eq "BLSW" gape Gap extension penalty (-gape) perl (defined $value && $value ne $vdef)? " -gape $value" : "" 1 15 no message perl (defined $value && $value ne $vdef && ($algo_opt=1) && 0) perl $method eq "SW" || $method eq "SWT" || $method eq "SWR" || $method eq "KBEST" || $method eq "NW" || $method eq "ZVAL"|| $method eq "BLSW" blast_options Blast options (BLSW and BLKERR as well) perl $method eq "BLAST" || $method eq "BLSW" || $method eq "BLKERR" 15 E Expect: Expected value cutoff (-E) perl (defined $value && $value != $vdef )? " -E $value":"" 10 15 no message perl (defined $value && $value != $vdef && ($algo_opt=1) && 0) perl $method eq "BLAST" || $method eq "BLSW" || $method eq "BLKERR" S Primary cutoff score [prot:1, nuc:20] (-S) perl (defined $value)? " -S $value":"" 15 no message perl (defined $value && ($algo_opt=1) && 0) perl $method eq "BLAST" || $method eq "BLSW" || $method eq "BLKERR" S2 Secondary cutoff score [prot:0, nuc:20] (-S2) perl (defined $value)? " -S2 $value":"" 15 no message perl (defined $value && ($algo_opt=1) && 0) perl $method eq "BLAST" || $method eq "BLSW" || $method eq "BLKERR" W Word length used by the automata [prot:3, nuc:11] (-W) perl (defined $value)? " -W $value":"" 15 no message perl (defined $value && ($algo_opt=1) && 0) perl $method eq "BLAST" || $method eq "BLSW" || $method eq "BLKERR" T Neighborhood cutoff score. Not used in nucleic mode (-T) perl (defined $value && $value != $vdef)? " -T $value":"" 13 15 no message perl (defined $value && $value != $vdef && ($algo_opt=1) && 0) perl $method eq "BLAST" || $method eq "BLSW" || $method eq "BLKERR" X Extension cutoff score (-X) perl (defined $value && $value != $vdef)? " -X $value":"" 20 15 no message perl (defined $value && $value != $vdef && ($algo_opt=1) && 0) perl $method eq "BLAST" || $method eq "BLSW" || $method eq "BLKERR" SWR_options Schuffling SW (SWR & ZVAL) perl $method eq "SWR" || $method eq "ZVAL" 15 ran Number of times the sequences are schuffled (-ran) perl (defined $value && $value ne $vdef)? " -ran $value":"" 10 15 no message perl (defined $value && $value ne $vdef && ($algo_opt=1) && 0) perl $method eq "SWR" || $method eq "ZVAL" noswap Only the sequence from the database is schuffled (-noswap) perl ($value)? " -noswap":"" 0 15 no message perl ($value && ($algo_opt=1) && 0) perl $method eq "SWR" || $method eq "ZVAL" swr_cutoff Cutoff value of Smith/Waterman score (-cutoff) perl (defined $value && $value ne $vdef)? " -cutoff $value" : "" 0 15 Only alignments whose scores are above this cutoff value are computed by the schuffling method. Setting this value reduces greatly computation time. no message perl (defined $value && $value ne $vdef && ($algo_opt=1) && 0) perl $method eq "SWR" || $method eq "ZVAL" BM_options BM (Boyer-Moore) options perl $method eq "BM" 15 swap Look for inclusion in both senses (-swap) perl (! $value)? " -swap":"" 1 15 no message perl ((! $value) && ($algo_opt=1) && 0) perl $method eq "BM" KBEST_options KBEST options perl $method eq "KBEST" 15 k Maximum number of local alignments retained (-K) perl ($value && $value ne $vdef)? " -K $value":"" 10 15 no message perl ($value && $value ne $vdef && ($algo_opt=1) && 0) perl $method eq "KBEST" kbest_cutoff Cutoff score (-cutoff) perl (defined $value && $value ne $vdef)? " -cutoff $value" : "" 0 15 no message perl (defined $value && $value ne $vdef&& ($algo_opt=1) && 0) perl $method eq "KBEST" KERR_options Approximate string matching options (KERR, BLKERR) perl $method eq "KERR" || $method eq "BLKERR" 15 errs Maximun number of errors admitted (-errs) perl (defined $value && $value ne $vdef)? " -errs $value":"" 2 15 no message perl (defined $value && $value ne $vdef && ($algo_opt=1) && 0) perl $method eq "KERR" || $method eq "BLKERR" perc Errors < % of the length of the smallest sequence (-perc) perl (defined $value && $value ne $vdef)? " -perc $value":"" 0 15 Number of errors is a function of the length of the smallest sequence. The maximum numbers of errors admitted must not exceed x % of the length of the smallest sequence. no message perl (defined $value && $value ne $vdef && ($algo_opt=1) && 0) perl $method eq "KERR" || $method eq "BLKERR" flag_algo_opt perl ($algo_opt)? " -O [ " : "" 14 flag_algo_opt2 perl ($algo_opt)? " ] " : "" 19 output_options Output options view_alignment View alignment (-a) perl ($value)? " -a" : "" 0 1000 Not available for all methods. scut Score cutoff (report results of scores greater than cutoff) (-scut) perl (defined $value)? " -scut $value" : "" 800 ecut Expect cutoff (Report results of expect values lower than cutoff) (-ecut) perl (defined $value)? " -ecut $value" : "" 800 max Maximum number of results reported (-max) perl (defined $value)? " -max $value" : "" 800 strand_options Strand options perl $type_of_scan eq "NN" db_strand Database strand (-s) perl ($value)? " $value" : "" 320 r reverse strand fr forward and reverse strands fr " -s [for, rev]" r " -s [rev]" perl $type_of_scan eq "NN" query_strand Query strand (-s) perl ($value)? " $value" : "" 420 r reverse strand fr forward and reverse strands fr " -s [for, rev]" r " -s [rev]" perl $type_of_scan eq "NN" frame_options Frame options perl $type_of_scan =~ /TN/ db_frame Database frames (-f) perl ($value && $value ne $vdef)? " $value" : "" a 320 a all (6 frames) t top frames +1, +2, +3 b bottom frames -1 -2 -3 a "-f a" b "-f b" t "-f t" perl $type_of_scan =~ /TN/ && (! $db_frame_nb) && $type_of_scan =~ /^TN/ db_frame_nb ... or you can give a list of frame numbers, separated by commas perl ($value)? " -f [ $value ]" : "" 320 Example: 1, -2 perl $type_of_scan =~ /TN/ && $type_of_scan =~ /^TN/ db_gc Genetic Code for database perl ($value && $value ne $vdef)? " -gc $value" : "" 1 340 1 Standard 2 Vertebrate Mitochondrial 3 Yeast Mitochondrial 4 Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma 5 Invertebrate Mitochondrial 6 Ciliate Macronuclear and Dasycladacean 9 Echinoderm Mitochondrial 10 Euplotid Nuclear 11 Bacterial 12 Alternative Yeast Nuclear 13 Ascidian Mitochondrial 14 Flatworm Mitochondrial 15 Blepharisma Macronuclear perl $type_of_scan =~ /TN/ && ($type_of_scan =~ /^TN/ ) query_frame Query frames (-f) perl ($value && $value ne $vdef)? " $value" : "" a 420 a all (6 frames) t top frames +1, +2, +3 b bottom frames -1 -2 -3 a "-f a" b "-f b" t "-f t" perl $type_of_scan =~ /TN/ && $type_of_scan =~ /TN$/ && (! $query_frame_nb) query_frame_nb ... or you can give a list of frame numbers, separated by commas perl ($value)? " -f [ $value ]" : "" 420 Example: 1, -2 perl $type_of_scan =~ /TN/ && $type_of_scan =~ /TN$/ query_gc Genetic Code for query perl ($value && $value ne $vdef)? " -gc $value" : "" 1 440 1 Standard 2 Vertebrate Mitochondrial 3 Yeast Mitochondrial 4 Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma 5 Invertebrate Mitochondrial 6 Ciliate Macronuclear and Dasycladacean 9 Echinoderm Mitochondrial 10 Euplotid Nuclear 11 Bacterial 12 Alternative Yeast Nuclear 13 Ascidian Mitochondrial 14 Flatworm Mitochondrial 15 Blepharisma Macronuclear perl $type_of_scan =~ /TN/ && $type_of_scan =~ /TN$/ control_flow_options Control Flow selections options 2100 cf_bc Boolean connector for control flow perl "" & 2001 | |: OR & &: AND ! !: NOT RL_op Ratio length operator perl "" > 2500 < < <= <= = = >= >= > > no message perl $RL && ($cf_sel_options=($cf_sel_options)? "($cf_sel_options $cf_bc RL $RL_op $RL)" : "RL $RL_op $RL") && 0 perl $RL RL Ratio length perl "" 2499 Exemple: comparisons on sequences whose lengths do not differ by more than 10%: RL > 0.9 SSP SSP: The same frame perl "" 2100 no message perl $SSP && ($cf_sel_options=($cf_sel_options)? "($cf_sel_options $cf_bc SSP)" : "SSP") && 0 NSP NSP: Not the same frame perl "" 2100 no message perl $NSP && ($cf_sel_options=($cf_sel_options)? "($cf_sel_options $cf_bc NSP)" : "NSP") && 0 flag_cf_selection perl ($cf_sel_options)? " -bp \\"{ " : "" 2000 flag_cf_selection2 perl ($cf_sel_options)? " $cf_sel_options }\\" " : "" 3000 other_options Other options dd Do not compute all against all (-dd) perl ($value)? " -dd" : "" 0 1000 blast_matrix You can enter a Blast matrix (PAM or BLOSUM, see help) perl ($value)?" -mp $value":"" 200 You can give the name of: . a PAM matrix : PAMxxx, where xxx ranges from 10 to 500, with a step of 10 . a BLOSUM matrix : BLOSUMxxx, where xxx ranges from 30 to 100, with a step of 5 - with the exception of BLOSUM62 which is the default scoring matrix Several PAM (point accepted mutations per 100 residues) amino acid scoring matrices are provided in the BLAST software distribution, including the PAM40, PAM120, and PAM250. While the BLOSUM62 matrix is a good general purpose scoring matrix and is the default matrix used by the BLAST programs, if one is restricted to using only PAM scoring matrices, then the PAM120 is recommended for general protein similarity searches (Altschul, 1991). The pam(1) program can be used to produce PAM matrices of any desired iteration from 2 to 511. Each matrix is most sensitive at finding similarities at its particular PAM distance. For more thorough searches, particularly when the mutational distance between potential homologs is unknown and the significance of their similarity may be only marginal, Altschul (1991, 1992) recommends performing at least three searches, one each with the PAM40, PAM120 and PAM250 matrices.