| 1 | //  ==================================================================== // | 
|---|
| 2 | //                                                                       // | 
|---|
| 3 | //    File      : SQ_main.cxx                                            // | 
|---|
| 4 | //    Purpose   : Entrypoint to Seq. Quality analysis; calls functions   // | 
|---|
| 5 | //                                                                       // | 
|---|
| 6 | //                                                                       // | 
|---|
| 7 | //  Coded by Juergen Huber in July 2003 - February 2004                  // | 
|---|
| 8 | //  Coded by Kai Bader (baderk@in.tum.de) in 2007 - 2008                 // | 
|---|
| 9 | //  Copyright Department of Microbiology (Technical University Munich)   // | 
|---|
| 10 | //                                                                       // | 
|---|
| 11 | //  Visit our web site at: http://www.arb-home.de/                       // | 
|---|
| 12 | //                                                                       // | 
|---|
| 13 | //  ==================================================================== // | 
|---|
| 14 |  | 
|---|
| 15 | #include "seq_quality.h" | 
|---|
| 16 | #include "SQ_functions.h" | 
|---|
| 17 |  | 
|---|
| 18 | #include <awt_filter.hxx> | 
|---|
| 19 | #include <awt_sel_boxes.hxx> | 
|---|
| 20 |  | 
|---|
| 21 | #include <aw_awars.hxx> | 
|---|
| 22 | #include <aw_msg.hxx> | 
|---|
| 23 | #include <aw_root.hxx> | 
|---|
| 24 |  | 
|---|
| 25 | #include <arb_progress.h> | 
|---|
| 26 | #include <TreeNode.h> | 
|---|
| 27 | #include <arb_global_defs.h> | 
|---|
| 28 | #include <awt_config_manager.hxx> | 
|---|
| 29 |  | 
|---|
| 30 | // -------------------------------------------------------------------------------- | 
|---|
| 31 |  | 
|---|
| 32 | #define AWAR_SQ_PERM "seq_quality/"     // saved in properties | 
|---|
| 33 | #define AWAR_SQ_TEMP "tmp/seq_quality/" // not saved in properties | 
|---|
| 34 |  | 
|---|
| 35 | #define AWAR_SQ_WEIGHT_BASES     AWAR_SQ_PERM "weight_bases" | 
|---|
| 36 | #define AWAR_SQ_WEIGHT_DEVIATION AWAR_SQ_PERM "weight_deviation" | 
|---|
| 37 | #define AWAR_SQ_WEIGHT_HELIX     AWAR_SQ_PERM "weight_helix" | 
|---|
| 38 | #define AWAR_SQ_WEIGHT_CONSENSUS AWAR_SQ_PERM "weight_consensus" | 
|---|
| 39 | #define AWAR_SQ_WEIGHT_IUPAC     AWAR_SQ_PERM "weight_iupac" | 
|---|
| 40 | #define AWAR_SQ_WEIGHT_GC        AWAR_SQ_PERM "weight_gc" | 
|---|
| 41 |  | 
|---|
| 42 | #define AWAR_SQ_MARK_ONLY_FLAG AWAR_SQ_PERM "mark_only_flag" | 
|---|
| 43 | #define AWAR_SQ_MARK_FLAG      AWAR_SQ_PERM "mark_flag" | 
|---|
| 44 | #define AWAR_SQ_MARK_BELOW     AWAR_SQ_PERM "mark_below" | 
|---|
| 45 | #define AWAR_SQ_REEVALUATE     AWAR_SQ_PERM "reevaluate" | 
|---|
| 46 | #define AWAR_SQ_FILTER_NAME    AWAR_SQ_TEMP "filter/name" | 
|---|
| 47 |  | 
|---|
| 48 | void SQ_create_awars(AW_root *aw_root, AW_default aw_def) { | 
|---|
| 49 | aw_root->awar_int(AWAR_SQ_WEIGHT_BASES,     5,  aw_def); | 
|---|
| 50 | aw_root->awar_int(AWAR_SQ_WEIGHT_DEVIATION, 15, aw_def); | 
|---|
| 51 | aw_root->awar_int(AWAR_SQ_WEIGHT_HELIX,     15, aw_def); | 
|---|
| 52 | aw_root->awar_int(AWAR_SQ_WEIGHT_CONSENSUS, 50, aw_def); | 
|---|
| 53 | aw_root->awar_int(AWAR_SQ_WEIGHT_IUPAC,     5,  aw_def); | 
|---|
| 54 | aw_root->awar_int(AWAR_SQ_WEIGHT_GC,        10, aw_def); | 
|---|
| 55 | aw_root->awar_int(AWAR_SQ_MARK_ONLY_FLAG,   0,  aw_def); | 
|---|
| 56 | aw_root->awar_int(AWAR_SQ_MARK_FLAG,        1,  aw_def); | 
|---|
| 57 | aw_root->awar_int(AWAR_SQ_MARK_BELOW,       40, aw_def); | 
|---|
| 58 | aw_root->awar_int(AWAR_SQ_REEVALUATE,       0,  aw_def); | 
|---|
| 59 |  | 
|---|
| 60 | awt_create_filter_awars(aw_root, aw_def, AWAR_SQ_FILTER_NAME, AWAR_DEFAULT_ALIGNMENT); | 
|---|
| 61 | } | 
|---|
| 62 |  | 
|---|
| 63 | // -------------------------------------------------------------------------------- | 
|---|
| 64 |  | 
|---|
| 65 |  | 
|---|
| 66 | inline size_t count_nodes(TreeNode *node) { | 
|---|
| 67 | // calculate number of nodes in tree | 
|---|
| 68 | return GBT_count_leafs(node)*2-1; | 
|---|
| 69 | } | 
|---|
| 70 |  | 
|---|
| 71 | static void sq_calc_seq_quality_cb(AW_window * aww, adfiltercbstruct *acbs, GBDATA *gb_main) { | 
|---|
| 72 | AW_root  *aw_root     = aww->get_root(); | 
|---|
| 73 | GB_ERROR  error       = NULp; | 
|---|
| 74 | TreeNode *tree        = NULp; | 
|---|
| 75 | bool      marked_only = (aw_root->awar(AWAR_SQ_MARK_ONLY_FLAG)->read_int() > 0); | 
|---|
| 76 |  | 
|---|
| 77 | arb_progress main_progress("Calculating sequence quality"); | 
|---|
| 78 |  | 
|---|
| 79 | { | 
|---|
| 80 | char *treename = aw_root->awar(AWAR_TREE)->read_string(); | 
|---|
| 81 |  | 
|---|
| 82 | if (treename && strcmp(treename, NO_TREE_SELECTED) != 0) { | 
|---|
| 83 | error = GB_push_transaction(gb_main); | 
|---|
| 84 |  | 
|---|
| 85 | if (!error) { | 
|---|
| 86 | tree = GBT_read_tree(gb_main, treename, new SimpleRoot); | 
|---|
| 87 | if (!tree) error = GB_await_error(); | 
|---|
| 88 | else { | 
|---|
| 89 | error = GBT_link_tree(tree, gb_main, false); | 
|---|
| 90 | if (!error) { | 
|---|
| 91 | GBT_TreeRemoveType mode = marked_only ? GBT_KEEP_MARKED : GBT_REMOVE_ZOMBIES; | 
|---|
| 92 | tree = GBT_remove_leafs(tree, mode, NULp, NULp, NULp); | 
|---|
| 93 | if (!tree || tree->is_leaf()) { | 
|---|
| 94 | error = GBS_global_string("Tree contains less than 2 species after removing zombies%s", | 
|---|
| 95 | marked_only ? " and non-marked" : ""); | 
|---|
| 96 | } | 
|---|
| 97 | } | 
|---|
| 98 | } | 
|---|
| 99 | } | 
|---|
| 100 |  | 
|---|
| 101 | error = GB_end_transaction(gb_main, error); | 
|---|
| 102 | } | 
|---|
| 103 | free(treename); | 
|---|
| 104 | } | 
|---|
| 105 |  | 
|---|
| 106 | // if tree == 0 -> do basic quality calculations that are possible without tree information | 
|---|
| 107 | // otherwise    -> use all groups found in tree and compare sequences against the groups they are contained in | 
|---|
| 108 |  | 
|---|
| 109 | if (!error) { | 
|---|
| 110 | struct SQ_weights weights; | 
|---|
| 111 |  | 
|---|
| 112 | weights.bases = aw_root->awar(AWAR_SQ_WEIGHT_BASES)->read_int(); | 
|---|
| 113 | weights.diff_from_average = aw_root->awar(AWAR_SQ_WEIGHT_DEVIATION)->read_int(); | 
|---|
| 114 | weights.helix = aw_root->awar(AWAR_SQ_WEIGHT_HELIX)->read_int(); | 
|---|
| 115 | weights.consensus = aw_root->awar(AWAR_SQ_WEIGHT_CONSENSUS)->read_int(); | 
|---|
| 116 | weights.iupac = aw_root->awar(AWAR_SQ_WEIGHT_IUPAC)->read_int(); | 
|---|
| 117 | weights.gc = aw_root->awar(AWAR_SQ_WEIGHT_GC)->read_int(); | 
|---|
| 118 |  | 
|---|
| 119 | int mark_flag = aw_root->awar(AWAR_SQ_MARK_FLAG)->read_int(); | 
|---|
| 120 | int mark_below = aw_root->awar(AWAR_SQ_MARK_BELOW)->read_int(); | 
|---|
| 121 | int reevaluate = aw_root->awar(AWAR_SQ_REEVALUATE)->read_int(); | 
|---|
| 122 |  | 
|---|
| 123 | // Load and use Sequence-Filter | 
|---|
| 124 | AP_filter *filter = awt_get_filter(acbs); | 
|---|
| 125 | error             = awt_invalid_filter(filter); | 
|---|
| 126 |  | 
|---|
| 127 | /* | 
|---|
| 128 | SQ_evaluate() generates the final estimation for the quality of an alignment. | 
|---|
| 129 | It takes the values from the different containers, which are generated by the other functions, weights them | 
|---|
| 130 | and calculates a final value. The final value is stored in "value_of_evaluation" (see options). | 
|---|
| 131 | With the values stored in "weights" one can customize how important a value stored in a container becomes | 
|---|
| 132 | for the final result. | 
|---|
| 133 | */ | 
|---|
| 134 |  | 
|---|
| 135 | if (!error) { | 
|---|
| 136 | if (!tree) { | 
|---|
| 137 | if (reevaluate) { | 
|---|
| 138 | SQ_mark_species(gb_main, mark_below, marked_only); | 
|---|
| 139 | } | 
|---|
| 140 | else { | 
|---|
| 141 | arb_progress  progress(GBT_get_species_count(gb_main)*2); | 
|---|
| 142 | SQ_GroupData *globalData = new SQ_GroupData_RNA; | 
|---|
| 143 |  | 
|---|
| 144 | progress.subtitle("pass1"); | 
|---|
| 145 | error = SQ_pass1_no_tree(globalData, gb_main, filter, progress); | 
|---|
| 146 | if (!error) { | 
|---|
| 147 | progress.subtitle("pass2"); | 
|---|
| 148 | error = SQ_pass2_no_tree(globalData, gb_main, filter, progress); | 
|---|
| 149 | if (!error) { | 
|---|
| 150 | error = SQ_evaluate(gb_main, weights, marked_only); | 
|---|
| 151 | if (mark_flag && !error) { | 
|---|
| 152 | SQ_mark_species(gb_main, mark_below, marked_only); | 
|---|
| 153 | } | 
|---|
| 154 | } | 
|---|
| 155 | } | 
|---|
| 156 | if (error) progress.done(); | 
|---|
| 157 | delete globalData; | 
|---|
| 158 | } | 
|---|
| 159 | } | 
|---|
| 160 | else { | 
|---|
| 161 | SQ_TREE_ERROR check = SQ_check_tree_structure(tree); | 
|---|
| 162 | if (check != NONE) { | 
|---|
| 163 | switch (check) { | 
|---|
| 164 | case ZOMBIE: | 
|---|
| 165 | error = "Found one or more zombies in the tree.\n" | 
|---|
| 166 | "Please remove them or use another tree before running the quality check tool."; | 
|---|
| 167 | break; | 
|---|
| 168 | case MISSING_NODE: | 
|---|
| 169 | error = "Missing node(s) or unusable tree structure.\n" | 
|---|
| 170 | "Please fix the tree before running the quality check tool."; | 
|---|
| 171 | break; | 
|---|
| 172 | default: | 
|---|
| 173 | error = "An error occurred while traversing the tree.\n" | 
|---|
| 174 | "Please fix the tree before running the quality check tool."; | 
|---|
| 175 | break; | 
|---|
| 176 | } | 
|---|
| 177 | } | 
|---|
| 178 | else if (reevaluate) { | 
|---|
| 179 | SQ_mark_species(gb_main, mark_below, marked_only); | 
|---|
| 180 | } | 
|---|
| 181 | else { | 
|---|
| 182 | arb_progress progress(count_nodes(tree)*2); | 
|---|
| 183 | SQ_GroupData *globalData = new SQ_GroupData_RNA; | 
|---|
| 184 |  | 
|---|
| 185 | progress.subtitle("pass1"); | 
|---|
| 186 | SQ_calc_and_apply_group_data(tree, gb_main, globalData, filter, progress); | 
|---|
| 187 | progress.subtitle("pass2"); | 
|---|
| 188 | SQ_calc_and_apply_group_data2(tree, gb_main, globalData, filter, progress); | 
|---|
| 189 | SQ_evaluate(gb_main, weights, marked_only); | 
|---|
| 190 | if (mark_flag) SQ_mark_species(gb_main, mark_below, marked_only); | 
|---|
| 191 | delete globalData; | 
|---|
| 192 | } | 
|---|
| 193 | } | 
|---|
| 194 | } | 
|---|
| 195 | awt_destroy_filter(filter); | 
|---|
| 196 | } | 
|---|
| 197 |  | 
|---|
| 198 | if (error) aw_message(error); | 
|---|
| 199 |  | 
|---|
| 200 | SQ_clear_group_dictionary(); | 
|---|
| 201 | UNCOVERED(); | 
|---|
| 202 | destroy(tree); | 
|---|
| 203 | } | 
|---|
| 204 |  | 
|---|
| 205 | static void sq_remove_quality_entries_cb(AW_window*, GBDATA *gb_main) { | 
|---|
| 206 | GB_ERROR error = SQ_remove_quality_entries(gb_main); | 
|---|
| 207 | aw_message_if(error); | 
|---|
| 208 | } | 
|---|
| 209 |  | 
|---|
| 210 | static AWT_config_mapping_def seq_quality_config_mapping[] = { | 
|---|
| 211 | { AWAR_SQ_WEIGHT_BASES,     "wbases" }, | 
|---|
| 212 | { AWAR_SQ_WEIGHT_DEVIATION, "wdeviation" }, | 
|---|
| 213 | { AWAR_SQ_WEIGHT_HELIX,     "whelix" }, | 
|---|
| 214 | { AWAR_SQ_WEIGHT_CONSENSUS, "wconsens" }, | 
|---|
| 215 | { AWAR_SQ_WEIGHT_IUPAC,     "wiupac" }, | 
|---|
| 216 | { AWAR_SQ_WEIGHT_GC,        "wgc" }, | 
|---|
| 217 | { AWAR_SQ_MARK_ONLY_FLAG,   "onlymarked" }, | 
|---|
| 218 | { AWAR_SQ_MARK_FLAG,        "markbad" }, | 
|---|
| 219 | { AWAR_SQ_MARK_BELOW,       "markbelow" }, | 
|---|
| 220 | { AWAR_SQ_REEVALUATE,       "reeval" }, | 
|---|
| 221 |  | 
|---|
| 222 | { NULp, NULp } | 
|---|
| 223 | }; | 
|---|
| 224 |  | 
|---|
| 225 | AW_window *SQ_create_seq_quality_window(AW_root *aw_root, GBDATA *gb_main) { | 
|---|
| 226 | // create window for sequence quality calculation (called only once) | 
|---|
| 227 |  | 
|---|
| 228 | AW_window_simple *aws = new AW_window_simple; | 
|---|
| 229 |  | 
|---|
| 230 | aws->init(aw_root, "CALC_SEQ_QUALITY", "CALCULATE SEQUENCE QUALITY"); | 
|---|
| 231 | aws->load_xfig("seq_quality.fig"); | 
|---|
| 232 |  | 
|---|
| 233 | aws->at("close"); | 
|---|
| 234 | aws->callback(AW_POPDOWN); | 
|---|
| 235 | aws->create_button("CLOSE", "CLOSE", "C"); | 
|---|
| 236 |  | 
|---|
| 237 | aws->at("help"); | 
|---|
| 238 | aws->callback(makeHelpCallback("seq_quality.hlp")); | 
|---|
| 239 | aws->create_button("HELP", "HELP", "H"); | 
|---|
| 240 |  | 
|---|
| 241 | aws->at("base"); | 
|---|
| 242 | aws->create_input_field(AWAR_SQ_WEIGHT_BASES, 3); | 
|---|
| 243 |  | 
|---|
| 244 | aws->at("deviation"); | 
|---|
| 245 | aws->create_input_field(AWAR_SQ_WEIGHT_DEVIATION, 3); | 
|---|
| 246 |  | 
|---|
| 247 | aws->at("no_helices"); | 
|---|
| 248 | aws->create_input_field(AWAR_SQ_WEIGHT_HELIX, 3); | 
|---|
| 249 |  | 
|---|
| 250 | aws->at("consensus"); | 
|---|
| 251 | aws->create_input_field(AWAR_SQ_WEIGHT_CONSENSUS, 3); | 
|---|
| 252 |  | 
|---|
| 253 | aws->at("iupac"); | 
|---|
| 254 | aws->create_input_field(AWAR_SQ_WEIGHT_IUPAC, 3); | 
|---|
| 255 |  | 
|---|
| 256 | aws->at("gc_proportion"); | 
|---|
| 257 | aws->create_input_field(AWAR_SQ_WEIGHT_GC, 3); | 
|---|
| 258 |  | 
|---|
| 259 | aws->at("monly"); | 
|---|
| 260 | aws->create_toggle(AWAR_SQ_MARK_ONLY_FLAG); | 
|---|
| 261 |  | 
|---|
| 262 | aws->at("mark"); | 
|---|
| 263 | aws->create_toggle(AWAR_SQ_MARK_FLAG); | 
|---|
| 264 |  | 
|---|
| 265 | aws->at("mark_below"); | 
|---|
| 266 | aws->create_input_field(AWAR_SQ_MARK_BELOW, 3); | 
|---|
| 267 |  | 
|---|
| 268 | aws->at("tree"); | 
|---|
| 269 | awt_create_TREE_selection_list(gb_main, aws, AWAR_TREE, true); | 
|---|
| 270 |  | 
|---|
| 271 | aws->at("filter"); | 
|---|
| 272 | adfiltercbstruct *adfilter = awt_create_select_filter(aws->get_root(), gb_main, AWAR_SQ_FILTER_NAME); | 
|---|
| 273 | aws->callback(makeCreateWindowCallback(awt_create_select_filter_win, adfilter)); | 
|---|
| 274 | aws->create_button("SELECT_FILTER", AWAR_SQ_FILTER_NAME); | 
|---|
| 275 |  | 
|---|
| 276 | aws->at("go"); | 
|---|
| 277 | aws->callback(makeWindowCallback(sq_calc_seq_quality_cb, adfilter, gb_main)); | 
|---|
| 278 | aws->highlight(); | 
|---|
| 279 | aws->create_button("GO", "GO", "G"); | 
|---|
| 280 |  | 
|---|
| 281 | aws->at("config"); | 
|---|
| 282 | AWT_insert_config_manager(aws, AW_ROOT_DEFAULT, "seq_quality", seq_quality_config_mapping); | 
|---|
| 283 |  | 
|---|
| 284 | aws->at("reevaluate"); | 
|---|
| 285 | aws->label("Re-Evaluate only"); | 
|---|
| 286 | aws->create_toggle(AWAR_SQ_REEVALUATE); | 
|---|
| 287 |  | 
|---|
| 288 | aws->at("remove"); | 
|---|
| 289 | aws->callback(makeWindowCallback(sq_remove_quality_entries_cb, gb_main)); | 
|---|
| 290 | aws->create_button("Remove", "Remove", "R"); | 
|---|
| 291 |  | 
|---|
| 292 | return aws; | 
|---|
| 293 | } | 
|---|