Set warnings according to the advice by StefanFlaumberg; Set an error that occurs when when users tries to apply MixtureFInder to amino acid data; Create the --force-aa-mix-finder option to force IQ-TREE to run MixtureFinder for amino acid data

Author: HS6986

main/phylotesting.cpp

@@ -6765,6 +6765,15 @@ void runMixtureFinder(Params &params, IQTree* &iqtree, ModelCheckpoint &model_in
 
     if (iqtree->isSuperTree())
         outError("Error! The option -m '" + params.model_name + "' cannot work on data set with partitions");
+        
+    if (iqtree->aln->seq_type != SEQ_DNA)
+        outWarning("MixtureFinder has not been tested for non-DNA data types. Be cautious about interpreting the results");
+        
+    if (iqtree->aln->getMaxNumStates() > 6)
+        outWarning("Running MixtureFinder for the given data type can take much time. Please consider restricting the set of the models to test as much as possible");
+        
+    if (iqtree->aln->seq_type == SEQ_PROTEIN && !params.force_aa_mix_finder)
+        outError("Error! We already have probably effective mixture frequency vectors C10–C60 for amino acid data, and they should explain data well.\nPlease make sure running MixtureFinder for your amino acid data makes sense.\nIf you are determined to do that, please add an option --force-aa-mix-finder to the command line.");
 
     if (params.morph_mix_finder && iqtree->aln->seq_type != SEQ_MORPH) {
         outError("Error! The option -morph-mix can only work on morphological data set");

utils/tools.cpp

@@ -1487,6 +1487,7 @@ void parseArg(int argc, char *argv[], Params &params) {
     params.ignore_checkpoint = false;
     params.checkpoint_dump_interval = 60;
     params.force_unfinished = false;
+    params.force_aa_mix_finder = false;
     params.print_all_checkpoints = false;
     params.suppress_output_flags = 0;
     params.ufboot2corr = false;
@@ -5486,6 +5487,11 @@ void parseArg(int argc, char *argv[], Params &params) {
 				params.force_unfinished = true;
 				continue;
 			}
+      
+      if (strcmp(argv[cnt], "-force-aa-mix-finder") == 0 || strcmp(argv[cnt], "--force-aa-mix-finder") == 0) {
+        params.force_aa_mix_finder = true;
+        continue;
+      }
 
 			if (strcmp(argv[cnt], "-cptime") == 0 || strcmp(argv[cnt], "--cptime") == 0) {
 				cnt++;

utils/tools.h

@@ -2458,6 +2458,9 @@ class Params {
     /** true if ignoring the "finished" flag in checkpoint file */
     bool force_unfinished;
 
+    /** true if forcing IQ-TREE to run MixtureFinder for amino acid data */
+    bool force_aa_mix_finder;
+    
     /** TRUE to print checkpoints to 1.ckp.gz, 2.ckp.gz,... */
     bool print_all_checkpoints;