| 1 | AUTODETECT "LOCUS *\nORIGIN*" |
|---|
| 2 | |
|---|
| 3 | KEYWIDTH 12 |
|---|
| 4 | FILETAG GB |
|---|
| 5 | |
|---|
| 6 | BEGIN "LOCUS*" |
|---|
| 7 | |
|---|
| 8 | # set variables used by feature table |
|---|
| 9 | SETGLOBAL t GB |
|---|
| 10 | SETGLOBAL u gb |
|---|
| 11 | |
|---|
| 12 | # uncomment next line to tag ALL fields with [GB] |
|---|
| 13 | # AUTOTAG "GB" |
|---|
| 14 | |
|---|
| 15 | |
|---|
| 16 | MATCH "LOCUS *" |
|---|
| 17 | SRT "* *=*1" |
|---|
| 18 | WRITE "name" |
|---|
| 19 | |
|---|
| 20 | MATCH "LOCUS *" |
|---|
| 21 | SRT "* *=*1" |
|---|
| 22 | TAG "GB" |
|---|
| 23 | WRITE "id" |
|---|
| 24 | |
|---|
| 25 | #MATCH "LOCUS *" |
|---|
| 26 | # SRT " = : = : = : = :* * *=*2" |
|---|
| 27 | # TAG "GB" |
|---|
| 28 | # WRITE "db_nuc" |
|---|
| 29 | |
|---|
| 30 | MATCH "ACCESSION *" |
|---|
| 31 | ACI "extract_words("0123456789",2.0)" |
|---|
| 32 | WRITE "acc" |
|---|
| 33 | |
|---|
| 34 | #MATCH "ACCESSION *" |
|---|
| 35 | # ACI "extract_words("0123456789",4.0)" |
|---|
| 36 | # TAG "GB" |
|---|
| 37 | # WRITE "db_acc" |
|---|
| 38 | |
|---|
| 39 | MATCH "PROJECT" |
|---|
| 40 | # TAG "GB" |
|---|
| 41 | WRITE_INT "insdc" |
|---|
| 42 | |
|---|
| 43 | MATCH "LOCUS *" |
|---|
| 44 | SRT " = : = : = : = :* * * * * * *=*7" |
|---|
| 45 | # TAG "GB" |
|---|
| 46 | WRITE "date" |
|---|
| 47 | |
|---|
| 48 | MATCH "DEFINITION" |
|---|
| 49 | # TAG "GB" |
|---|
| 50 | WRITE "description" |
|---|
| 51 | |
|---|
| 52 | MATCH "KEYWORDS *" |
|---|
| 53 | # TAG "GB" |
|---|
| 54 | APPEND "keywords" |
|---|
| 55 | |
|---|
| 56 | MATCH " ORGANISM *" |
|---|
| 57 | SRT "* * *=*1 *2:*|*=*1" |
|---|
| 58 | WRITE "full_name" |
|---|
| 59 | |
|---|
| 60 | MATCH " ORGANISM *" |
|---|
| 61 | # TAG "GB" |
|---|
| 62 | SRT "*|*=*1" |
|---|
| 63 | WRITE "tax_gb_name" |
|---|
| 64 | |
|---|
| 65 | MATCH " ORGANISM *" |
|---|
| 66 | # TAG "GB" |
|---|
| 67 | SRT "*|*=*2" |
|---|
| 68 | WRITE "tax_gb" |
|---|
| 69 | |
|---|
| 70 | MATCH "REFERENCE *" |
|---|
| 71 | SRT "* *=*1" |
|---|
| 72 | SETVAR x |
|---|
| 73 | IFNOTSET x "No REFERENCE seen" |
|---|
| 74 | # TAG "GB" |
|---|
| 75 | # APPEND "num_bib" |
|---|
| 76 | |
|---|
| 77 | MATCH "REFERENCE *" |
|---|
| 78 | SRT "*(*=*2:bases=:to=-: =:)=:*=[$x]\: *" |
|---|
| 79 | # TAG "GB" |
|---|
| 80 | APPEND "nuc_rp" |
|---|
| 81 | |
|---|
| 82 | MATCH " MEDLINE *" |
|---|
| 83 | # SRT "*=[$x]\: *" |
|---|
| 84 | # TAG "GB" |
|---|
| 85 | APPEND "medline_id" |
|---|
| 86 | |
|---|
| 87 | MATCH " PUBMED *" |
|---|
| 88 | # SRT "*=[$x]\: *" |
|---|
| 89 | # TAG "GB" |
|---|
| 90 | APPEND "pubmed_id" |
|---|
| 91 | |
|---|
| 92 | MATCH " CONSRTM *" |
|---|
| 93 | SRT "*=[$x]\: *" |
|---|
| 94 | TAG "GB" |
|---|
| 95 | APPEND "refgrp" |
|---|
| 96 | |
|---|
| 97 | MATCH " AUTHORS *" |
|---|
| 98 | SRT "*=[$x]\: *" |
|---|
| 99 | # TAG "GB" |
|---|
| 100 | APPEND "author" |
|---|
| 101 | |
|---|
| 102 | MATCH " TITLE *" |
|---|
| 103 | SRT "*=[$x]\: *" |
|---|
| 104 | # TAG "GB" |
|---|
| 105 | APPEND "title" |
|---|
| 106 | |
|---|
| 107 | MATCH " JOURNAL *" |
|---|
| 108 | SRT "*=[$x]\: *" |
|---|
| 109 | # TAG "GB" |
|---|
| 110 | APPEND "journal" |
|---|
| 111 | |
|---|
| 112 | MATCH " JOURNAL *Submitted*" |
|---|
| 113 | SRT "*Submitted*=*2:\(*\)*=*1" |
|---|
| 114 | # TAG "GB" |
|---|
| 115 | WRITE "submit_date" |
|---|
| 116 | |
|---|
| 117 | MATCH " Protein*note*" |
|---|
| 118 | SRT "*/note\=\"*\"*=*2" |
|---|
| 119 | TAG "GB" |
|---|
| 120 | APPEND "note" |
|---|
| 121 | |
|---|
| 122 | #MATCH " Protein*EC_number*" |
|---|
| 123 | # SRT "*/EC_number\=\"*\"*=*2" |
|---|
| 124 | # TAG "GB" |
|---|
| 125 | # APPEND "EC_number" |
|---|
| 126 | |
|---|
| 127 | #MATCH " Protein*product=*" |
|---|
| 128 | # SRT "*/product\=\"*\"*=*2" |
|---|
| 129 | # TAG "GB" |
|---|
| 130 | # APPEND "gene_prod" |
|---|
| 131 | |
|---|
| 132 | # maybe works with FT prefix (untested): |
|---|
| 133 | # (@@@ put into feature table when tested) |
|---|
| 134 | #MATCH "FTx*Protein*note*" |
|---|
| 135 | # SRT "*/note\=\"*\"*=*2" |
|---|
| 136 | # TAG "GB" |
|---|
| 137 | # APPEND "description" |
|---|
| 138 | #MATCH "FTx*Protein*EC_number*" |
|---|
| 139 | # SRT "*/EC_number\=\"*\"*=*2" |
|---|
| 140 | # TAG "GB" |
|---|
| 141 | # APPEND "EC_number" |
|---|
| 142 | #MATCH "FTx*Protein*product=*" |
|---|
| 143 | # SRT "*/product\=\"*\"*=*2" |
|---|
| 144 | # TAG "GB" |
|---|
| 145 | # APPEND "gene_prod" |
|---|
| 146 | |
|---|
| 147 | # ----------------------------------------------------------------- |
|---|
| 148 | # Feature table (used by longebi.ift and longgenbank.ift!) |
|---|
| 149 | |
|---|
| 150 | INCLUDE "feature_table.ift" |
|---|
| 151 | |
|---|
| 152 | # --------------------------------------------------------------- |
|---|
| 153 | |
|---|
| 154 | SEQUENCEAFTER "ORIGIN*" |
|---|
| 155 | SEQUENCESRT " =:~=.:*Check*..=" |
|---|
| 156 | SEQUENCEACI "remove("0123456789 /")" |
|---|
| 157 | SEQUENCECOLUMN 0 |
|---|
| 158 | SEQUENCEEND "//" |
|---|
| 159 | |
|---|
| 160 | CREATE_ACC_FROM_SEQUENCE |
|---|
| 161 | |
|---|
| 162 | END "//" |
|---|
into separate filter which is included by longebi.ift and longgenbank.ift
