Dear Sergei,

I have a very easy question for you about a batch file to reconstruct the ancestor sequence. I attached here the batch file (you send me it about 2 months ago).
I would like to change the model for the reconstruction, now it is working by GY94 codon model and I would like using the simple JC nucleotide model, but I have some problems changing it about Global/Local analysis options.

Thank you very much.
Regards,
Miguel

SetDialogPrompt ("CSV file with pathnames and genetic codes");
ExecuteAFile (HYPHY_BASE_DIRECTORY+ "TemplateBatchFiles" + DIRECTORY_SEPARATOR +
                                                     "Utility" + DIRECTORY_SEPARATOR + "ReadDelimitedFiles.bf");

fscanf                  (PROMPT_FOR_FILE,"Lines",listOfFiles);
linesRead =      Columns (listOfFiles);

fileNames = {};
fileCodes = {};

fprintf (stdout, "\n");

for (k=0; k<linesRead; k=k+1)
{
     aLine = splitOnRegExp (listOfFiles[k], "\\ *\\,\\ *");
     if (Abs (aLine) == 2)
     {
           fileNames [Abs(fileNames)] = aLine[0];
           fileCodes [Abs(fileCodes)] = aLine[1];
           fprintf (stdout, "[FILE ", Abs(fileNames), " ", aLine[0], " - ", aLine[1], "]\n");
     }
}

DATA_FILE_PRINT_FORMAT = 9;
/* FASTA */

for (fileCount = 0; fileCount < Abs(fileNames); fileCount = fileCount + 1)
{
     analysisOptions      = {};
     analysisOptions["0"] = fileCodes[fileCount];
     ExecuteAFile (HYPHY_BASE_DIRECTORY+ "TemplateBatchFiles" + DIRECTORY_SEPARATOR +
                         "TemplateModels" + DIRECTORY_SEPARATOR + "chooseGeneticCode.def", analysisOptions);

     DataSet        ds               = ReadDataFile (fileNames[fileCount]);
     DataSetFilter filteredData = CreateFilter (ds,3,"","",GeneticCodeExclusions);
     
     analysisOptions["0"] = "Global";
     ExecuteAFile (HYPHY_BASE_DIRECTORY+ "TemplateBatchFiles" + DIRECTORY_SEPARATOR +
                         "TemplateModels" + DIRECTORY_SEPARATOR + "GY94.mdl", analysisOptions);
                        
     kappa := 1;
     fprintf (stdout, "[WORKING ON FILE ", fileNames[fileCount], "]\n");
     Tree givenTree = DATAFILE_TREE;
     fprintf (stdout, "\t[FITTING THE GY94_JC69 MODEL]\n");
     LikelihoodFunction lf = (filteredData, givenTree);
     Optimize (res, lf);
     fprintf (stdout, "\t[RECONSTRUCTING ANCESTORS]\n");      
     DataSet ancestors = ReconstructAncestors(lf);      
     DataSetFilter recFilter = CreateFilter(ancestors,1);
     ancestorOutFile = "Ancestors_" + fileNames[fileCount] + "_.fas";
     fprintf (stdout, "\t[WRITING ANCESTORS TO ",ancestorOutFile,"]\n");      
     fprintf (ancestorOutFile,CLEAR_FILE,recFilter);
}

Dear Sergei,

For changing the model (from GY94 codon model to JC nucleotide model), I introduced the JC69.mdl file. However, I still have an output error:

Not a valid option: 'Global' passed to Choice List 'Model Options' using redirected stdin input
Current BL Command:Choice List for Model Options with choice list:SKIP_NONE. Store result in modelType

I know I must change 'Global' for 'Local', but in analysisOptions lines (lines 63 and 70) I have to introduce a number for 'Local' (0 is for 'Global') and I am not sure about what is that number.
Well, I do not know if I have to introduce more changes in this batchfile for the reconstruction of the ancestor sequence by JC nucleotide model.
Below you can see the batch file that I am working about.

Regards,
Miguel


/*SetDialogPrompt ("CSV file with pathnames and genetic codes");*/
ExecuteAFile (HYPHY_BASE_DIRECTORY+ "TemplateBatchFiles" + DIRECTORY_SEPARATOR +
                                                     "Utility" + DIRECTORY_SEPARATOR + "ReadDelimitedFiles.bf");

/*fscanf                  (PROMPT_FOR_FILE,"Lines",listOfFiles);*/
fscanf                  (test.csv,"Lines",listOfFiles);

linesRead =      Columns (listOfFiles);

fileNames = {};
fileCodes = {};

fprintf (stdout, "\n");

for (k=0; k<linesRead; k=k+1)
{
     aLine = splitOnRegExp (listOfFiles[k], "\\ *\\,\\ *");
     if (Abs (aLine) == 2)
     {
           fileNames [Abs(fileNames)] = aLine[0];
           fileCodes [Abs(fileCodes)] = aLine[1];
           fprintf (stdout, "[FILE ", Abs(fileNames), " ", aLine[0], " - ", aLine[1], "]\n");
     }
}

DATA_FILE_PRINT_FORMAT = 9;
/* FASTA */

for (fileCount = 0; fileCount < Abs(fileNames); fileCount = fileCount + 1)
{


/* MA */

#include "myFunctions.bf";

     /* load data in */
     inputfile = fileNames[fileCount];
     DataSet ds = ReadDataFile (inputfile);
     DataSetFilter filteredData = CreateFilter (ds,1);
     dataType = 0; /* DNA sequences */
     fprintf (stdout, "\n\n*********** NEW DATA: ",inputfile," ***********");

     /* define the model JC */
     equalFreqs = {{.25}{.25}{.25}{.25}};
     JC69 = {{*,a,a,a}{a,*,a,a}{a,a,*,a}{a,a,a,*}};
     Model JC69model = (JC69, equalFreqs);
     UseModel (JC69model);

     /* build NJ */
     distanceChoice = 0; /* raw distances */
     modelType = 0; /* no rate variation*/
     methodIndex = 1; /* Negative Branch Lengths are Allowed */
     p = InferTreeTopology(1.0); /* in myFunctions.bf */
     treeString = TreeMatrix2TreeString (1); /* treeString stores the tree in Newick format */
     fprintf (stdout,"\nInferred NJ tree before rerooting: ", treeString);
     treeString = RerootTree (treeString,0);
     fprintf (stdout,"\nInferred NJ tree: ", treeString);

/* MA */

     analysisOptions      = {};
     analysisOptions["0"] = fileCodes[fileCount];
     ExecuteAFile (HYPHY_BASE_DIRECTORY+ "TemplateBatchFiles" + DIRECTORY_SEPARATOR +
                         "TemplateModels" + DIRECTORY_SEPARATOR + "chooseGeneticCode.def", analysisOptions);

     DataSet        ds               = ReadDataFile (fileNames[fileCount]);
     DataSetFilter filteredData = CreateFilter (ds,3,"","",GeneticCodeExclusions);
     
     analysisOptions["0"] = "Global";
     ExecuteAFile (HYPHY_BASE_DIRECTORY+ "TemplateBatchFiles" + DIRECTORY_SEPARATOR +
                         "TemplateModels" + DIRECTORY_SEPARATOR + "JC69.mdl", analysisOptions);
                        
     kappa := 1;
     fprintf (stdout, "[WORKING ON FILE ", fileNames[fileCount], "]\n");
     
     /*Tree givenTree = DATAFILE_TREE;*/
     Tree givenTree = treeString;
     
     fprintf (stdout, "\t[FITTING THE JC69 MODEL]\n");
     LikelihoodFunction lf = (filteredData, givenTree);
     Optimize (res, lf);
     fprintf (stdout, "\n\nResults from the likelihood optimization:\n",lf);
     fprintf (stdout, "\t[RECONSTRUCTING ANCESTORS]\n");      
     DataSet ancestors = ReconstructAncestors(lf);      
     DataSetFilter recFilter = CreateFilter(ancestors,1);
     
     ancestorOutFile = fileNames[fileCount] + "_ancestors.fas";
     
     fprintf (stdout, "\t[WRITING ANCESTORS TO ",ancestorOutFile,"]\n");      
     fprintf (ancestorOutFile,CLEAR_FILE,recFilter);
     fprintf (ancestorOutFile, "\nNJtree (NJ): ",treeString);
     fprintf (ancestorOutFile, "\n\nTreeUsed: ",givenTree);      
     
}

It is Perfect.
Thank you!

Cheers,
Miguel