1 | // =============================================================== // |
---|
2 | // // |
---|
3 | // File : GEN_gene.cxx // |
---|
4 | // Purpose : // |
---|
5 | // // |
---|
6 | // Coded by Ralf Westram (coder@reallysoft.de) in 2001 // |
---|
7 | // Institute of Microbiology (Technical University Munich) // |
---|
8 | // http://www.arb-home.de/ // |
---|
9 | // // |
---|
10 | // =============================================================== // |
---|
11 | |
---|
12 | #include "GEN_gene.hxx" |
---|
13 | #include "GEN_local.hxx" |
---|
14 | #include "GEN_nds.hxx" |
---|
15 | |
---|
16 | #include <aw_awar.hxx> |
---|
17 | #include <aw_msg.hxx> |
---|
18 | #include <aw_root.hxx> |
---|
19 | #include <arbdbt.h> |
---|
20 | #include <adGene.h> |
---|
21 | |
---|
22 | // Standard fields of a gb_gene entry: |
---|
23 | // ----------------------------------- |
---|
24 | // name = short name of gene (unique in one species) |
---|
25 | // type = type of gene (e.g. 'gene', 'CDS', 'tRNA', 'misc_feature') |
---|
26 | // pos_start = start-position(s) of gene(-parts); range is 1...genomeLength |
---|
27 | // pos_stop = end-position(s) of gene(-parts); range is 1...genomeLength |
---|
28 | // pos_certain = contains pairs of chars (1. for start-pos, 2. for end-pos) |
---|
29 | // |
---|
30 | // '=' means 'pos is exact' |
---|
31 | // '<' means 'pos may be lower' |
---|
32 | // '>' means 'pos may be higher' |
---|
33 | // '+' means 'pos is directly behind' |
---|
34 | // '-' means 'pos is directly before' |
---|
35 | // |
---|
36 | // if pos_certain is missing -> like '==' |
---|
37 | // |
---|
38 | // pos_complement = 1 -> CDS is on opposite strand |
---|
39 | |
---|
40 | // fields for splitted genes: |
---|
41 | // -------------------------- |
---|
42 | // pos_joined = xxx -> gene consists of abs(xxx) parts (if missing xxx == 1 is assumed) |
---|
43 | // |
---|
44 | // if abs(xxx)>1, the gene consists of several parts. |
---|
45 | // In that case the fields 'pos_start', 'pos_stop', 'pos_certain' and 'pos_complement' |
---|
46 | // contain multiple comma-separated values - one for each joined part. |
---|
47 | // |
---|
48 | // if xxx is < -1, then joining the parts does not make sense (or nothing is known about it) |
---|
49 | // |
---|
50 | // Note: Please do not access these fields manually - use GEN_read_position! |
---|
51 | |
---|
52 | // other fields added by importer: |
---|
53 | // ------------------------------- |
---|
54 | // |
---|
55 | // During import ARB tries to reproduce existing translations. |
---|
56 | // If it succeeds, it removes the translation. |
---|
57 | // |
---|
58 | // ARB_translation = written if ARB translation differs from original translation |
---|
59 | // (original translation is not deleted in this case) |
---|
60 | // ARB_translation_note = additional info about failed translation |
---|
61 | // ARB_translation_rm = 1 -> translation was reproduced and deleted |
---|
62 | // |
---|
63 | // if a gene with type 'gene' exists and another gene with different type, but |
---|
64 | // identical location exists as well, ARB sets ARB_display_hidden to 1 for |
---|
65 | // the 'gene'. For the other gene with diff. type ARB sets a reference to the |
---|
66 | // hidden 'gene': |
---|
67 | // |
---|
68 | // ARB_is_gene = shortname of related hidden gene |
---|
69 | |
---|
70 | |
---|
71 | // fields used for display: |
---|
72 | // ------------------------ |
---|
73 | // ARB_display_hidden = 1 -> do not display this gene (depends on AWAR_GENMAP_SHOW_HIDDEN too) |
---|
74 | // ARB_color = color group |
---|
75 | |
---|
76 | |
---|
77 | |
---|
78 | // Old format standard fields of a gb_gene entry: |
---|
79 | // ---------------------------------------------- |
---|
80 | // name = short name of gene (unique in one species) |
---|
81 | // pos_begin = start-position of gene |
---|
82 | // pos_end = end-position of gene |
---|
83 | // pos_uncertain = contains 2 chars (1. for start-pos, 2. for end-pos); = means 'pos is exact'; < means 'pos may be lower'; > means 'pos may be higher'; missing -> like == |
---|
84 | // complement = 1 -> encoding from right to left |
---|
85 | // |
---|
86 | // fields for splitted genes: |
---|
87 | // -------------------------- |
---|
88 | // pos_joined = xxx -> gene consists of xxx parts (may not exist if xxx == 1) |
---|
89 | // pos_beginxxx, pos_endxxx = start-/end-positions for parts 2...n |
---|
90 | // pos_uncertainxxx = like above for parts 2...n |
---|
91 | // |
---|
92 | |
---|
93 | using namespace std; |
---|
94 | |
---|
95 | static const GEN_position *loadPositions4gene(GBDATA *gb_gene) { |
---|
96 | static GEN_position *loaded_position = 0; |
---|
97 | static GBDATA *positionLoaded4gene = 0; |
---|
98 | |
---|
99 | if (positionLoaded4gene != gb_gene) { |
---|
100 | if (loaded_position) { |
---|
101 | GEN_free_position(loaded_position); |
---|
102 | loaded_position = 0; |
---|
103 | positionLoaded4gene = 0; |
---|
104 | } |
---|
105 | |
---|
106 | if (gb_gene) { |
---|
107 | loaded_position = GEN_read_position(gb_gene); |
---|
108 | if (loaded_position) positionLoaded4gene = gb_gene; |
---|
109 | } |
---|
110 | } |
---|
111 | return loaded_position; |
---|
112 | } |
---|
113 | |
---|
114 | void GEN_gene::init(GBDATA *gb_gene_, GEN_root *root_) { |
---|
115 | gb_gene = gb_gene_; |
---|
116 | root = root_; |
---|
117 | name = GBT_read_name(gb_gene); |
---|
118 | |
---|
119 | GBDATA *gbd = GB_entry(gb_gene, "complement"); |
---|
120 | complement = gbd ? GB_read_byte(gbd) == 1 : false; |
---|
121 | } |
---|
122 | |
---|
123 | void GEN_gene::load_location(int part, const GEN_position *location) { |
---|
124 | gen_assert(part >= 1); |
---|
125 | gen_assert(part <= location->parts); |
---|
126 | |
---|
127 | pos1 = location->start_pos[part-1]; |
---|
128 | pos2 = location->stop_pos[part-1]; |
---|
129 | complement = location->complement[part-1]; |
---|
130 | |
---|
131 | gen_assert(pos1 <= pos2); |
---|
132 | } |
---|
133 | |
---|
134 | GEN_gene::GEN_gene(GBDATA *gb_gene_, GEN_root *root_, const GEN_position *location) { |
---|
135 | init(gb_gene_, root_); |
---|
136 | load_location(1, location); |
---|
137 | nodeInfo = GEN_make_node_text_nds(root->GbMain(), gb_gene, 0); |
---|
138 | } |
---|
139 | |
---|
140 | GEN_gene::GEN_gene(GBDATA *gb_gene_, GEN_root *root_, const GEN_position *location, int partNumber) { |
---|
141 | // partNumber 1..n which part of a splitted gene |
---|
142 | // maxParts 1..n of how many parts consists this gene? |
---|
143 | |
---|
144 | init(gb_gene_, root_); |
---|
145 | load_location(partNumber, location); |
---|
146 | |
---|
147 | { |
---|
148 | char buffer[30]; |
---|
149 | sprintf(buffer, " (%i/%i)", partNumber, location->parts); |
---|
150 | nodeInfo = name+buffer; |
---|
151 | } |
---|
152 | } |
---|
153 | |
---|
154 | void GEN_gene::reinit_NDS() const { |
---|
155 | nodeInfo = GEN_make_node_text_nds(root->GbMain(), gb_gene, 0); |
---|
156 | } |
---|
157 | |
---|
158 | // ------------------ |
---|
159 | // GEN_root |
---|
160 | |
---|
161 | GEN_root::GEN_root(const char *organism_name_, const char *gene_name_, GBDATA *gb_main_, AW_root *aw_root, GEN_graphic *gen_graphic_) |
---|
162 | : gb_main(gb_main_) |
---|
163 | , gen_graphic(gen_graphic_) |
---|
164 | , organism_name(organism_name_) |
---|
165 | , gene_name(gene_name_) |
---|
166 | , error_reason("") |
---|
167 | , length(-1) |
---|
168 | , gb_gene_data(0) |
---|
169 | { |
---|
170 | GB_transaction ta(gb_main); |
---|
171 | GBDATA *gb_organism = GBT_find_species(gb_main, organism_name.c_str()); |
---|
172 | |
---|
173 | if (!gb_organism) { |
---|
174 | error_reason = strdup("Please select a species."); |
---|
175 | } |
---|
176 | else { |
---|
177 | GBDATA *gb_data = GBT_read_sequence(gb_organism, GENOM_ALIGNMENT); |
---|
178 | if (!gb_data) { |
---|
179 | error_reason = GBS_global_string_copy("'%s' has no data in '%s'", organism_name.c_str(), GENOM_ALIGNMENT); |
---|
180 | } |
---|
181 | else { |
---|
182 | length = GB_read_count(gb_data); |
---|
183 | |
---|
184 | gb_gene_data = GEN_find_gene_data(gb_organism); |
---|
185 | GBDATA *gb_gene = gb_gene_data ? GEN_first_gene_rel_gene_data(gb_gene_data) : 0; |
---|
186 | |
---|
187 | if (!gb_gene) { |
---|
188 | error_reason = GBS_global_string("Species '%s' has no gene-information", organism_name.c_str()); |
---|
189 | } |
---|
190 | else { |
---|
191 | bool show_hidden = aw_root->awar(AWAR_GENMAP_SHOW_HIDDEN)->read_int() != 0; |
---|
192 | |
---|
193 | while (gb_gene) { |
---|
194 | bool show_this = show_hidden; |
---|
195 | |
---|
196 | if (!show_this) { |
---|
197 | GBDATA *gbd = GB_entry(gb_gene, ARB_HIDDEN); |
---|
198 | |
---|
199 | if (!gbd || !GB_read_byte(gbd)) { // gene is not hidden |
---|
200 | show_this = true; |
---|
201 | } |
---|
202 | } |
---|
203 | |
---|
204 | if (show_this) { |
---|
205 | const GEN_position *location = loadPositions4gene(gb_gene); |
---|
206 | |
---|
207 | if (!location) { |
---|
208 | GB_ERROR warning = GB_await_error(); |
---|
209 | char *id = GEN_global_gene_identifier(gb_gene, gb_organism); |
---|
210 | aw_message(GBS_global_string("Can't load gene '%s':\nReason: %s", id, warning)); |
---|
211 | free(id); |
---|
212 | } |
---|
213 | else { |
---|
214 | int parts = location->parts; |
---|
215 | if (parts == 1) { |
---|
216 | gene_set.insert(GEN_gene(gb_gene, this, location)); |
---|
217 | } |
---|
218 | else { // joined gene |
---|
219 | for (int p = 1; p <= parts; ++p) { |
---|
220 | gene_set.insert(GEN_gene(gb_gene, this, location, p)); |
---|
221 | } |
---|
222 | } |
---|
223 | } |
---|
224 | } |
---|
225 | gb_gene = GEN_next_gene(gb_gene); |
---|
226 | } |
---|
227 | } |
---|
228 | } |
---|
229 | } |
---|
230 | } |
---|
231 | |
---|
232 | void GEN_root::reinit_NDS() const { |
---|
233 | GEN_iterator end = gene_set.end(); |
---|
234 | for (GEN_iterator gene = gene_set.begin(); gene != end; ++gene) { |
---|
235 | gene->reinit_NDS(); |
---|
236 | } |
---|
237 | } |
---|