/var/lib/mobyle/programs/fasta.xml is in mobyle-programs 5.1.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 | <?xml version='1.0' encoding='UTF-8'?>
<!-- XML Authors: Corinne Maufrais, Nicolas Joly and Bertrand Neron, -->
<!-- 'Biological Software and Databases' Group, Institut Pasteur, Paris. -->
<!-- Distributed under LGPLv2 License. Please refer to the COPYING.LIB document. -->
<program>
<head>
<name>fasta</name>
<version>3.6</version>
<doc>
<title>FASTA</title>
<description>
<text lang="en">Sequence database search</text>
</description>
<authors>W. Pearson</authors>
<reference>Pearson, W. R. (1999) Flexible sequence similarity searching with the FASTA3 program package. Methods in Molecular Biology</reference>
<reference>W. R. Pearson and D. J. Lipman (1988), Improved Tools for Biological Sequence Analysis, PNAS 85:2444-2448</reference>
<reference>W. R. Pearson (1998) Empirical statistical estimates for sequence similarity searches. In J. Mol. Biol. 276:71-84</reference>
<reference>Pearson, W. R. (1996) Effective protein sequence comparison. In Meth. Enz., R. F. Doolittle, ed. (San Diego: Academic Press) 266:227-258</reference>
<homepagelink>http://fasta.bioch.virginia.edu/fasta_www2/fasta_list2.shtml</homepagelink>
<sourcelink>http://faculty.virginia.edu/wrpearson/fasta/</sourcelink>
</doc>
<category>database:search:homology</category>
</head>
<parameters xmlns:xi="http://www.w3.org/2001/XInclude">
<parameter ismandatory="1" iscommand="1" issimple="1">
<name>fasta</name>
<prompt lang="en">Fasta program</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>null</value>
</vdef>
<vlist>
<velem undef="1">
<value>null</value>
<label>Choose a program</label>
</velem>
<velem>
<value>fasta</value>
<label>fasta (protein or nucleotide query vs similar db )</label>
</velem>
<velem>
<value>tfasta</value>
<label>tfasta (protein query vs translated nucleic db)</label>
</velem>
<velem>
<value>fastx</value>
<label>fastx (translated nucleotide query vs protein db (frameshifts only only between codons)) </label>
</velem>
<velem>
<value>tfastx</value>
<label>tfastx (protein query vs translated DNA db (frameshifts only between codons))</label>
</velem>
<velem>
<value>fasty</value>
<label>fasty (fastx + frameshifts anywhere)</label>
</velem>
<velem>
<value>tfasty</value>
<label>tfasty (tfastx + frameshifts anywhere)</label>
</velem>
<velem>
<value>fastf</value>
<label>fastf (mixed peptide seq vs protein db (modified algorithm))</label>
</velem>
<velem>
<value>tfastf</value>
<label>tfastf (mixed peptide seq vs translated DNA db (modified algorithm))</label>
</velem>
<velem>
<value>fasts</value>
<label>fasts (several short peptide seq vs protein db (modified algorithm))</label>
</velem>
<velem>
<value>tfasts</value>
<label>tfasts (several short peptide seq vs translated DNA db (modified algorithm))</label>
</velem>
</vlist>
<format>
<code proglang="perl">"$value -q"</code>
<code proglang="python">str(value) + " -q"</code>
</format>
<argpos>0</argpos>
<comment>
<text lang="en">- fasta: scan a protein or DNA sequence library for similar sequences</text>
<text lang="en">- tfasta: compare a protein sequence to a DNA sequence librarSy, translating the DNA sequence library `on-the-fly' to the 3 forward and the 3 reverse frames without frameshifts.</text>
<text lang="en">- fastx/fasty: compare a DNA sequence to a protein sequence database, comparing the translated DNA sequence in three frames, with frameshifts. fasty2 allows frameshifts inside codons.</text>
<text lang="en">- tfastx/tfasty: compare a protein sequence vs a translated DNA db, with frameshifts. tfasty allows frameshifts inside codons.</text>
<text lang="en">- fastf/tfastf: compare an ordered peptide mixture (obtained for example by Edman degradation of a CNBr cleavage) against a protein or translated DNA database.</text>
<text lang="en">- fasts/tfasts: compare a set of short peptide fragments (obtained from a mass-spec analysis of a protein) against a protein or translated DNA database.</text>
</comment>
</parameter>
<parameter ismandatory="1" issimple="1">
<name>query</name>
<prompt lang="en">Query sequence File</prompt>
<type>
<biotype>Protein</biotype>
<biotype>DNA</biotype>
<datatype>
<class>Sequence</class>
</datatype>
<dataFormat>FASTA</dataFormat>
</type>
<format>
<code proglang="perl">" $value"</code>
<code proglang="python">" "+str(value)</code>
</format>
<argpos>2</argpos>
</parameter>
<parameter ismandatory="1" issimple="1">
<name>seqtype</name>
<prompt lang="en">Is it a DNA or protein sequence (-n)</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>null</value>
</vdef>
<vlist>
<velem undef="1">
<value>null</value>
<label>Choose a biotype</label>
</velem>
<velem>
<value>DNA</value>
<label>DNA</label>
</velem>
<velem>
<value>protein</value>
<label>Protein</label>
</velem>
</vlist>
<format>
<code proglang="perl">(defined $value and $fasta =~ /^fasta/ and $value eq "DNA") or $fasta =~ /^fast(x|y)/) ? " -n" : ""</code>
<code proglang="python">( "" , " -n" )[ value is not None and value == "DNA" and fasta == 'fasta']</code>
</format>
<ctrl>
<message>
<text lang="en">fastf, fasts, tfasta, tfastx, tfasty, tfastf and tfasts take a protein sequence</text>
<text lang="en">fastx and fasty take a DNA sequence</text>
</message>
<code proglang="perl">($fasta =~ /^fast(f|s)/ and $seqtype eq "DNA") or ($fasta =~ /^fast(x|y)/ and $seqtype eq "protein")</code>
<code proglang="python">(seqtype == "protein" and fasta in ["fasta", "fastf", "fasts", "tfasta", "tfastx", "tfasty", "tfastf", "tfasts"]) or (seqtype == "DNA" and fasta in ["fasta", "fastx", "fasty"] ) </code>
</ctrl>
<argpos>1</argpos>
</parameter>
<paragraph>
<name>db</name>
<prompt lang="en">Database</prompt>
<argpos>3</argpos>
<parameters>
<parameter ismandatory="1" issimple="1">
<name>protein_db</name>
<prompt lang="en">Protein Database</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<precond>
<code proglang="perl">($seqtype eq "protein" and $fasta =~ /^fasta/) or $fasta =~ /^fast(x|y|s|f)/</code>
<code proglang="python">(seqtype == "protein" and fasta == "fasta") or fasta in ["fastx", "fasty", "fastf", "fasts"]</code>
</precond>
<vdef>
<value>null</value>
</vdef>
<xi:include href="../../Local/Services/Programs/Env/protdbs.xml" />
<format>
<code proglang="perl">" <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="../../Local/Services/Programs/Env/fasta_data.xml" xpointer="xpointer(/db/text())" />$value.fa"</code>
<code proglang="python">" <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="../../Local/Services/Programs/Env/fasta_data.xml" xpointer="xpointer(/db/text())" />" + str(value)+".fa"</code>
</format>
<comment>
<text lang="en">Choose a protein db for fasta, fastx, fatsf, fasty or fasts.</text>
<text lang="en">Please note that Swissprot usage by and for commercial entities requires a license agreement.</text>
</comment>
</parameter>
<parameter ismandatory="1" issimple="1">
<name>nucleotid_db</name>
<prompt lang="en">Nucleotid Database</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<precond>
<code proglang="perl"> ($seqtype eq "DNA" and $fasta =~ /^fasta/ ) or $fasta =~ /^tfast/ </code>
<code proglang="python">(seqtype == "DNA" and fasta == "fasta") or fasta in [ "tfasta", "tfastx", "tfasty", "tfastf", "tfasts"] </code>
</precond>
<vdef>
<value>null</value>
</vdef>
<xi:include href="../../Local/Services/Programs/Env/nucdbs.xml" />
<format>
<code proglang="perl">" <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="../../Local/Services/Programs/Env/fasta_data.xml" xpointer="xpointer(/db/text())" />$value"</code>
<code proglang="python">" <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="../../Local/Services/Programs/Env/fasta_data.xml" xpointer="xpointer(/db/text())" />" + str(value)</code>
</format>
<comment>
<text lang="en">Choose a nucleotide db for fasta, tfasta, tfastx, tfasty, tfastf or tfasts</text>
</comment>
</parameter>
<parameter>
<name>break_long</name>
<prompt lang="en">Break long library sequences into blocks (-N)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value) ? " -N $value" : ""</code>
<code proglang="python">( "" , " -N " + str(value) )[ value is not None ]</code>
</format>
<comment>
<text lang="en">Break long library sequences into blocks of N residues. Useful for bacterial genomes, which have only one sequence entry. -N 2000 works well for well for bacterial genomes.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>selectivity_opt</name>
<prompt lang="en">Selectivity options</prompt>
<argpos>1</argpos>
<parameters>
<parameter>
<name>ktup</name>
<prompt lang="en">Sensitivity and speed of the search </prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value)? " $value":""</code>
<code proglang="python">("" , " " + str(value) )[ value is not None ]</code>
</format>
<ctrl>
<message>
<text lang="en">ktup can be set to 2 or 1 for protein sequences or from 1 to 6 for DNA sequences.</text>
</message>
<code proglang="perl">($seqtype eq "protein" and ($value == 1 or $value == 2 )) or ($seqtype eq "DNA" and ($value == 1 or $value == 2 or $value == 3 or $value == 4 or $value == 5 or $value == 6 )))</code>
<code proglang="python">(seqtype == "protein" and value in [1,2]) or (seqtype == "DNA" and value in range(1,7,1))</code>
</ctrl>
<argpos>4</argpos>
<comment>
<text lang="en">ktup sets the sensitivity and speed of the search. If ktup=2, similar regions in the two sequences being compared are found by looking at pairs of aligned residues; if ktup=1, single aligned amino acids are examined. ktup can be set to 2 or 1 for protein sequences, or from 1 to 6 for DNA sequences. The default if ktup is not specified is 2 for proteins and 6 for DNA. 1ktup=1 should be used for oligonucleotides (DNA query length < 20).</text>
</comment>
</parameter>
<parameter>
<name>optcut</name>
<prompt lang="en">Threshold for band optimization (FASTA, FASTX). (-c)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value)? " -c $value":""</code>
<code proglang="python">("" , " -c " + str(value) )[ value is not None ]</code>
</format>
<ctrl>
<message>
<text lang="en">Only used for fasta and fastx </text>
</message>
<code proglang="perl">$fasta =~ /^fasta/ or $fasta =~ /^fastx</code>
<code proglang="python">fasta in ["fasta", "fastx"]</code>
</ctrl>
<comment>
<text lang="en">The threshold value is normally calculated based on sequence length.</text>
</comment>
</parameter>
<parameter>
<name>gapinit</name>
<prompt lang="en">Penalty for opening a gap (-f)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value)? " -f $value":""</code>
<code proglang="python">("" , " -f " + str(value))[ value is not None ]</code>
</format>
<comment>
<text lang="en">The default for fasta with proteins is -12 and -16 for DNA</text>
<text lang="en">The default for fastx/fasty/tfastz/tfasty is -15.</text>
</comment>
</parameter>
<parameter>
<name>gapext</name>
<prompt lang="en">Penalty for gap extension (-g)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value)? " -g $value":""</code>
<code proglang="python">("" , " -g " + str(value))[ value is not None ]</code>
</format>
<comment>
<text lang="en">The default for fasta is -2 for proteins and -4 for DNA</text>
<text lang="en">The default for fastx/fasty/tfastz/tfasty is -3.</text>
</comment>
</parameter>
<parameter>
<name>high_expect</name>
<prompt lang="en">Maximal expectation value threshold for displaying scores and alignments (-E)</prompt>
<type>
<datatype>
<class>Float</class>
</datatype>
</type>
<vdef>
<value>10.0</value>
</vdef>
<format>
<code proglang="perl">(defined $value and $value != $vdef)? " -E $value":""</code>
<code proglang="python">("" , " -E " + str(value))[ value is not None and value != vdef]</code>
</format>
<comment>
<text lang="en">Expectation value limit for displaying scores and alignments. Defaults are 10.0 for FASTA protein searches, 5.0 for translated DNA/protein comparisons, and 2.0 for DNA/DNA searches.</text>
</comment>
</parameter>
<parameter>
<name>low_expect</name>
<prompt lang="en">Minimal expectation value threshold for displaying scores and alignments (-F)</prompt>
<type>
<datatype>
<class>Float</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value) ? " -F $value":""</code>
<code proglang="python">("" , " -F " + str(value))[ value is not None ]</code>
</format>
<comment>
<text lang="en">Expectation value lower limit for score and alignment display. If value is 1e-6 prevents library sequences with E()-values lower than 1e-6 from being displayed. This allows the use to focus on more distant relationships. </text>
<text lang="en">This allow one to skip over close relationships in searches for more distant relationships.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>score_opt</name>
<prompt lang="en">Scoring options</prompt>
<argpos>1</argpos>
<parameters>
<paragraph>
<name>scoring_nucleic</name>
<prompt lang="en">Nucleic penalty</prompt>
<precond>
<code proglang="perl">$fasta eq "fasta" and seqtype eq "DNA"</code>
<code proglang="python">fasta == "fasta" and seqtype == "DNA"</code>
</precond>
<parameters>
<parameter>
<name>nucleotid_match</name>
<prompt lang="en">Maximum positive value for a nucleotid match (-r)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>5</value>
</vdef>
<ctrl>
<message>
<text lang="en">Only positive value</text>
</message>
<code proglang="perl">$value >= 0</code>
<code proglang="python">value >= 0</code>
</ctrl>
</parameter>
<parameter>
<name>nucleotid_mismatch</name>
<prompt lang="en">Maximum negative penalty value for a nucleotid mismatch (-r)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<precond>
<code proglang="perl">defined $nucleotid_match</code>
<code proglang="python">nucleotid_match is not None</code>
</precond>
<vdef>
<value>-4</value>
</vdef>
<format>
<code proglang="perl">(defined $value and defined nucleotid_match and ($value != $vdef and $nucleotid_match != 5)) ? " -r \"$nucleotid_match/$value\"" : ""</code>
<code proglang="python">( "" , ' -r "' + str(nucleotid_match) + '/' + str(value)+ '"' )[ value is not None and nucleotid_match is not None and (nucleotid_match != 5 and value != vdef) ]</code>
</format>
<ctrl>
<message>
<text lang="en">Only negative value</text>
</message>
<code proglang="perl">$value < 0</code>
<code proglang="python">value < 0</code>
</ctrl>
<comment>
<text lang="en">'+5/-4' are the default values for nucleotid match/mismatch, but '+3/-2' can perform better in some cases.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>scoring_protein</name>
<prompt lang="en">Protein penalty</prompt>
<precond>
<code proglang="perl">seqtype ne "DNA"</code>
<code proglang="python">seqtype != "DNA"</code>
</precond>
<parameters>
<parameter>
<name>matrix</name>
<prompt lang="en">Scoring matrix file (-s)</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>BL50</value>
</vdef>
<vlist>
<velem>
<value>BL50</value>
<label>BLOSUM50</label>
</velem>
<velem>
<value>BL62</value>
<label>BLOSUM62</label>
</velem>
<velem>
<value>BL80</value>
<label>BLOSUM80</label>
</velem>
<velem>
<value>P20</value>
<label>PAM20</label>
</velem>
<velem>
<value>P40</value>
<label>PAM40</label>
</velem>
<velem>
<value>P120</value>
<label>PAM120</label>
</velem>
<velem>
<value>P250</value>
<label>PAM250</label>
</velem>
<velem>
<value>M10</value>
<label>MDM_10</label>
</velem>
<velem>
<value>M20</value>
<label>MDM_20</label>
</velem>
<velem>
<value>M40</value>
<label>MDM_40</label>
</velem>
</vlist>
<format>
<code proglang="perl">(defined $value and $value ne $vdef) ? " -s $value" : ""</code>
<code proglang="python">( "" , " -s " + str(value) )[ value is not None and value != vdef]</code>
</format>
</parameter>
<parameter>
<name>X_penalty</name>
<prompt lang="en">Penalty for a match to 'X' (independently of the PAM matrix) (-x)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value) ? " -x $value" : ""</code>
<code proglang="python">( "" , " -x " + str(value) )[ value is not None ]</code>
</format>
<comment>
<text lang="en">Particularly useful for fast[xy], where termination codons are encoded as 'X'.</text>
</comment>
</parameter>
</parameters>
</paragraph>
</parameters>
</paragraph>
<paragraph>
<name>frame_transl_opt</name>
<prompt lang="en">Frameshift and translation options</prompt>
<argpos>1</argpos>
<parameters>
<parameter>
<name>frameshift</name>
<prompt lang="en">Penalty for frameshift between two codons (fast[xy]/tfast[xy]) (-h)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<precond>
<code proglang="perl"> ($fasta =~ /fast(x|y)/)</code>
<code proglang="python">fasta in ["fastx", "fasty", "tfastx", "tfasty"] </code>
</precond>
<format>
<code proglang="perl">(defined $value)? " -h $value":""</code>
<code proglang="python">("" , " -h " + str(value))[ value is not None ]</code>
</format>
</parameter>
<parameter>
<name>frameshift_within</name>
<prompt lang="en">Penalty for frameshift within a codon (fasty/tfasty) (-j)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<precond>
<code proglang="perl">($fasta =~ /fasty/)</code>
<code proglang="python">fasta in ["fasty", "tfasty"] </code>
</precond>
<format>
<code proglang="perl">(defined $value)? " -j $value":""</code>
<code proglang="python">("" , " -j " + str(value))[ value is not None ]</code>
</format>
</parameter>
<parameter>
<name>threeframe</name>
<prompt lang="en">Search only the three forward frames (-3)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<precond>
<code proglang="perl">$fasta =~ /^tfast(a|x|y)/</code>
<code proglang="python">fasta in ["tfasta", "tfastx", "tfasty"]</code>
</precond>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value) ? " -3":""</code>
<code proglang="python">("" , " -3")[ value ]</code>
</format>
</parameter>
<parameter>
<name>invert</name>
<prompt lang="en">Reverse complement the query sequence (-i)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<precond>
<code proglang="perl">$fasta =~ /fast(x|y)/</code>
<code proglang="python">fasta in ["fastx", "tfastx", "fasty", "tfasty"] </code>
</precond>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value) ? " -i" : ""</code>
<code proglang="python">( "" , " -i" )[ value ]</code>
</format>
</parameter>
<parameter>
<name>genetic_code</name>
<prompt lang="en">Use genetic code for translation (tfasta/tfast[xy]/fast[xy]) (-t)</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<precond>
<code proglang="perl">$fasta =~ /^tfast/ or $fasta =~ /fast[xy]/</code>
<code proglang="python">fasta in [ "tfasta", "tfastx", "tfasty", "tfastf", "tfasts", "fastx", "fasty" ]</code>
</precond>
<vdef>
<value>1</value>
</vdef>
<vlist>
<velem>
<value>1</value>
<label>Standard (1)</label>
</velem>
<velem>
<value>2</value>
<label>Vertebrate Mitochondrial (1)</label>
</velem>
<velem>
<value>3</value>
<label>Yeast Mitochondrial (2)</label>
</velem>
<velem>
<value>4</value>
<label>Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma (3)</label>
</velem>
<velem>
<value>5</value>
<label>Invertebrate Mitochondrial (4)</label>
</velem>
<velem>
<value>6</value>
<label>Ciliate Macronuclear and Dasycladacean (5)</label>
</velem>
<velem>
<value>9</value>
<label>Echinoderm Mitochondrial (6)</label>
</velem>
<velem>
<value>10</value>
<label>Euplotid Nuclear (7)</label>
</velem>
<velem>
<value>11</value>
<label>Bacterial (8)</label>
</velem>
<velem>
<value>12</value>
<label>Alternative Yeast Nuclear (9)</label>
</velem>
<velem>
<value>13</value>
<label>Ascidian Mitochondrial (10)</label>
</velem>
<velem>
<value>14</value>
<label>Flatworm Mitochondrial (11)</label>
</velem>
<velem>
<value>15</value>
<label>Blepharisma Macronuclear (12)</label>
</velem>
</vlist>
<format>
<code proglang="perl">(defined $value and $value ne $vdef) ? " -t $value" : ""</code>
<code proglang="python">( "" , " -t " + str(value) )[ value is not None and value != vdef]</code>
</format>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>optimize_opt</name>
<prompt lang="en">Optimization options</prompt>
<argpos>1</argpos>
<parameters>
<parameter>
<name>band</name>
<prompt lang="en">Band-width used for optimization (-y)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value)? " -y $value":""</code>
<code proglang="python">("" , " -y " + str(value))[ value is not None ]</code>
</format>
<comment>
<text lang="en">Set the band-width used for optimization. -y 16 is the default for protein when ktup=2 and for all DNA alignments. -y 32 is used for protein and ktup=1. For proteins, optimization slows comparison 2-fold and is highly recommended.</text>
</comment>
</parameter>
<parameter>
<name>swalig</name>
<prompt lang="en">Force Smith-Waterman alignment for DNA (-A)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<precond>
<code proglang="perl">$fasta =~ /^fasta/ and $seqtype eq "DNA"</code>
<code proglang="python">fasta in [ "tfasta", "fasta" ] and seqtype == "DNA"</code>
</precond>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value)? " -A":""</code>
<code proglang="python">("" , " -A")[ value ]</code>
</format>
<comment>
<text lang="en">Force Smith-Waterman alignment for output. Smith-Waterman is the default for protein sequences and FASTX, but not for TFASTA or DNA comparisons with FASTA.</text>
</comment>
</parameter>
<parameter>
<name>noopt</name>
<prompt lang="en">Turn fasta band optimization off during initial phase (-o)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value)? " -o":""</code>
<code proglang="python">("" , " -o")[ value ]</code>
</format>
<comment>
<text lang="en">Turn off default optimization of all scores greater than OPTCUT. Shirt results by 'initn' scores reduces the accuracy of statistical estimates. This was the behavior of fasta1 versions.</text>
</comment>
</parameter>
<parameter>
<name>stat</name>
<prompt lang="en">Specify statistical calculation. (-z)</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>1</value>
</vdef>
<vlist>
<velem>
<value>0</value>
<label>Turn off statistics (0)</label>
</velem>
<velem>
<value>1</value>
<label>Weigthed regression against the length of the library sequence (1)</label>
</velem>
<velem>
<value>2</value>
<label>Maximum likelihood estimates of Lambda abd K (2)</label>
</velem>
<velem>
<value>3</value>
<label>Altschul-Gishas statistical (3)</label>
</velem>
<velem>
<value>4</value>
<label>Alternate regression method: Variation 1 of 1 (4)</label>
</velem>
<velem>
<value>5</value>
<label>Alternate regression method: Variation 2 of 1 (5)</label>
</velem>
<velem>
<value>6</value>
<label>Maximum likelihood estimate based on the method of Mott (6)</label>
</velem>
</vlist>
<format>
<code proglang="perl">(defined $random and defined $value and $value > 0) ? " -z 1$value" : ($value ne $vdef) ? " -z $value" : ""</code>
<code proglang="python">( (( "", " -z " + str(value) ) [ value is not None and value != vdef]) , " -z 1" + str(value) )[value is not None and value > 0 and random is not None ]</code>
</format>
<comment>
<text lang="en">In general, 1 and 2 are the best methods.</text>
</comment>
</parameter>
<parameter>
<name>random</name>
<prompt lang="en">Estimate statistical parameters from shuffled copies of each library sequence (-z)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<precond>
<code proglang="perl">$stat > 0</code>
<code proglang="python">stat > 0</code>
</precond>
<vdef>
<value>0</value>
</vdef>
<comment>
<text lang="en">This doubles the time required for a search, but allows accurate statistics to be estimated for libraries comprised of a single protein family.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>affichage</name>
<prompt lang="en">Report options</prompt>
<argpos>1</argpos>
<parameters>
<parameter>
<name>histogram</name>
<prompt lang="en">Turn off histogram display (-H)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value)? " -H":""</code>
<code proglang="python">("" , " -H" )[ value ]</code>
</format>
</parameter>
<parameter>
<name>scores</name>
<prompt lang="en">Number of similarity scores to be shown (-b)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value and $value <= $high_expect)? " -b $value":""</code>
<code proglang="python">("" , " -b " + str(value))[ value is not None and value <= high_expect]</code>
</format>
<ctrl>
<message>
<text lang="en">Must be <= -E cutoff if -E is given.</text>
</message>
<code proglang="perl">$value <= $high_expect</code>
<code proglang="python">value <= high_expect</code>
</ctrl>
</parameter>
<parameter>
<name>alns</name>
<prompt lang="en">Number of alignments to be shown (-d)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value and $value <= $high_expect)? " -d $value":""</code>
<code proglang="python">("" , " -d " + str(value))[ value is not None and value <= high_expect]</code>
</format>
<ctrl>
<message>
<text lang="en">Must be <= -E cutoff if -E is given.</text>
</message>
<code proglang="perl">$value <= $high_expect</code>
<code proglang="python">value <= high_expect</code>
</ctrl>
</parameter>
<parameter issimple="1">
<name>html_output</name>
<prompt lang="en">HTML output (-m)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value)? " -m 6" : "" </code>
<code proglang="python">( "" , " -m 6" )[ value ]</code>
</format>
</parameter>
<parameter>
<name>markx</name>
<prompt lang="en">Alternate display of matches and mismatches in alignments (-m)</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<precond>
<code proglang="perl">not $html_output</code>
<code proglang="python">not html_output</code>
</precond>
<vdef>
<value>0</value>
</vdef>
<vlist>
<velem>
<value>0</value>
<label>0 [: identities] [. conservative repl] [ non-conserv repl]</label>
</velem>
<velem>
<value>1</value>
<label>1: [ identities] [x conservative repl] [X non-conserv repl]</label>
</velem>
<velem>
<value>2</value>
<label>2: [. identities] [res mismatch] - don't display the 2nd seq</label>
</velem>
<velem>
<value>3</value>
<label>3: writes a file of library sequences in FASTA format</label>
</velem>
<velem>
<value>4</value>
<label>4: displays a graph of the alignment</label>
</velem>
<velem>
<value>9</value>
<label>9: 0 + percent identity + coordinates</label>
</velem>
<velem>
<value>10</value>
<label>10: output more information</label>
</velem>
</vlist>
<format>
<code proglang="perl"> (defined $value and $value ne $vdef )? " -m $value" : "" </code>
<code proglang="python">( "" , " -m " + str(value) )[ value is not None and value != vdef]</code>
</format>
<comment>
<text lang="en">(MARKX) =0,1,2,3,4. Alternate display of matches and mismatches in alignments.</text>
<text lang="en">MARKX=0 uses ':','.',' ', for identities, conservative replacements, and non-conservative replacements, respectively.</text>
<text lang="en">MARKX=1 uses ' ','x', and 'X'. </text>
<text lang="en">MARKX=2 does not show the second sequence, but uses the second alignment line to display matches with a '.' for identity, or with the mismatched residue for mismatches. MARKX=2 is useful for aligning large numbers of similar sequences.</text>
<text lang="en">MARKX=3 writes out a file of library sequences in FASTA format. MARKX=3 should always be used with the 'SHOWALL' (-a) option, but this does not completely ensure that all of the sequences output will be aligned. </text>
<text lang="en">MARKX=4 displays a graph of the alignment of the library sequence with respect to the query sequence, so that one can identify the regions of the query sequence that are conserved.</text>
</comment>
</parameter>
<parameter>
<name>init1</name>
<prompt lang="en">Sequences ranked by the z-score based on the init1 score (-1)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value)? " -1":""</code>
<code proglang="python">("" , " -1")[ value ]</code>
</format>
</parameter>
<parameter>
<name>z_score_out</name>
<prompt lang="en">Show normalize score as (-B)</prompt>
<type>
<datatype>
<class>Choice</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<vlist>
<velem>
<value>1</value>
<label>z-score (1)</label>
</velem>
<velem>
<value>0</value>
<label>bit-score (0)</label>
</velem>
</vlist>
<format>
<code proglang="perl">(defined $value and $value ne $vdef) ? " -B" : ""</code>
<code proglang="python">( "" , " -B" )[ value is not None and value != vdef]</code>
</format>
</parameter>
<parameter>
<name>linlen</name>
<prompt lang="en">Output line length for sequence alignments (-w)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>60</value>
</vdef>
<format>
<code proglang="perl">(defined $value and $value != $vdef)? " -w $value":""</code>
<code proglang="python">("" , " -w " + str(value))[ value is not None and value != vdef ]</code>
</format>
<ctrl>
<message>
<text lang="en">Value must be <= 200.</text>
</message>
<code proglang="perl">$value <= 200</code>
<code proglang="python">value <= 200</code>
</ctrl>
</parameter>
<parameter>
<name>offsets</name>
<prompt lang="en">Start numbering the aligned sequences at position x1 x2 (2 numbers separated by comma) (-X)</prompt>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="perl">(defined $value)? " -X \"$value\"":""</code>
<code proglang="python">("" , ' -X "' + str(value) + '"')[ value is not None ]</code>
</format>
<ctrl>
<message>
<text lang="en">Must be 2 numbers separated by comma.</text>
</message>
<code proglang="perl">$value ~= /\d+(,\d+){1}/ and $value</code>
<code proglang="python">len (value.split(',')) == 2 and value.split(',')[0] != '' and value.split(',')[1] != '' </code>
</ctrl>
<comment>
<text lang="en">Causes fasta/lfasta/plfasta to start numbering the aligned sequences starting with offset1 and offset2, rather than 1 and 1. This is particularly useful for showing alignments of promoter regions.</text>
</comment>
</parameter>
<parameter>
<name>info</name>
<prompt lang="en">Display more information about the library sequence in the alignment (-L)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value)? " -L":""</code>
<code proglang="python">("" , " -L")[ value ]</code>
</format>
</parameter>
<!-- generate huge file
<parameter>
<name>statfile</name>
<prompt lang="en">Write out the sequence identifier, superfamily number, and similarity scores to this file (-R)</prompt>
<type>
<datatype>
<class>Filename</class>
</datatype>
</type>
<format>
<code proglang="perl">($value)? " -R $value":""</code>
<code proglang="python">("" , " -R " + str(value))[ value is not None ]</code>
</format>
</parameter>
-->
</parameters>
</paragraph>
<paragraph>
<name>other_opt</name>
<prompt lang="en">Other options</prompt>
<argpos>1</argpos>
<parameters>
<parameter>
<name>filter</name>
<prompt lang="en">Lower case filtering (-S)</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="perl">($value) ? " -S" : ""</code>
<code proglang="python">( "" , " -S" )[ value ]</code>
</format>
<comment>
<text lang="en">Treat lower-case characters in the query or library sequence as 'low-complexity' residues. These characters are treated as 'X' during the initial scan, but are treated as normal residues during the final alignment. Sinces statistical significance is calculated from similarity score calculated during library search, low complexity regions will not produce statistical significant matches.</text>
<text lang="en">If a significant alignment contains low complexity regions the final score may be higher than the score obtained during the search.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<parameter isstdout="1">
<name>outfile</name>
<prompt>Fasta report</prompt>
<type>
<datatype>
<class>FastaTextReport</class>
<superclass>Report</superclass>
</datatype>
</type>
<filenames>
<code proglang="perl">"fasta.out"</code>
<code proglang="python">"fasta.out"</code>
</filenames>
</parameter>
<parameter isout="1">
<name>html_outfile</name>
<prompt>Html output file</prompt>
<type>
<datatype>
<class>FastaHtmlReport</class>
<superclass>Report</superclass>
</datatype>
</type>
<precond>
<code proglang="perl">$html_output</code>
<code proglang="python">html_output</code>
</precond>
<format>
<code proglang="perl">" > fasta.html"</code>
<code proglang="python">" > fasta.html"</code>
</format>
<argpos>100</argpos>
<filenames>
<code proglang="perl">"fasta.html"</code>
<code proglang="python">"fasta.html"</code>
</filenames>
</parameter>
<!-- huge file
<parameter isout="1">
<name>stat_outfile</name>
<prompt>Statistics file</prompt>
<type>
<datatype>
<class>Text</class>
</datatype>
</type>
<precond>
<code proglang="perl">defined $statfile</code>
<code proglang="python">statfile is not None</code>
</precond>
<filenames>
<code proglang="perl">$statfile</code>
<code proglang="python">str(statfile)</code>
</filenames>
</parameter>
-->
</parameters>
</program>
|