Fix allowed sequence characters

mitobench · Mar 27, 2019 · a27a29d · a27a29d
1 parent a54561f
commit a27a29d
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 5 deletions.
diff --git a/src/IO/FastaReader.java b/src/IO/FastaReader.java
@@ -77,15 +77,15 @@ void readSequenceFromFile(String file)
         for (int i=0; i< seq.size(); i++)
         {
             String acc = (String) desc.get(i);
-            description[i] = acc.split(" ")[0];
+            description[i] = acc.split(" ")[0].split("\\.")[0];
             sequence[i]=(String) seq.get(i);
         }
 
     }
 
     private boolean isSequenceValid(String seq) {
 
-        String specialCharacters = "[" + "ACGTUWSMKRYBDHVNZ"+ "]+" ;
+        String specialCharacters = "[" + "ACGTUWSMKRYBDHVNZacgtuwsmkrybdhvnz"+ "]+" ;
 
         if (seq.matches(specialCharacters)) {
             return true;

diff --git a/src/Main.java b/src/Main.java
@@ -20,6 +20,7 @@ public static void main(String[] args) throws Exception {
         // init functionality
         ArgumentParser optionsParser = new ArgumentParser(args);
         Validator validator = new Validator();
+        System.out.println("Reading fast file...");
 
         mt_sequences_filepath = optionsParser.getFasta();
         String[] fileName = mt_sequences_filepath.replaceFirst("[.][^.]+$", "").split("/");
@@ -34,6 +35,8 @@ public static void main(String[] args) throws Exception {
 
         logfile.write("Data validation report based on files:\n" + mt_sequences_filepath + "\n"+ data_template_filepath + "\n\n");
 
+        System.out.println("Running validation...");
+
         validator.validate(data_template_filepath, logfile, fastaheaders, fastaReader.getLog_sequence_corretness());
         logfile.close();
 

diff --git a/src/calculations/Validator.java b/src/calculations/Validator.java
@@ -70,7 +70,7 @@ public class Validator {
     private List<String> publication_type = Arrays.asList("paper","peerprint","direct submission to genbank","direct submission to mitoDB","article");
     private List<String> publication_status = Arrays.asList("published","protected","private","in press",
             "in preparation","submitted","unpublished");
-    private List<String> sequencing_platform = Arrays.asList("illumina","454","sanger","nanopore","pacbio");
+    private List<String> sequencing_platform = Arrays.asList("illumina","454","sanger","nanopore","pacbio", "affymetrix");
 
 
     private String log_missing_sequences="";
@@ -408,7 +408,7 @@ public boolean validate(String data_template, BufferedWriter logfile, List<Strin
                     string_accession_default += "--------------------------------------------------\n" + accession + ":\n";
 
 
-                    if(!fastaheaders.contains(accession)){
+                    if(!fastaheaders.contains(accession.split("\\.")[0])){
                         log_missing_sequences += "Sequence with this accession ID: "+ accession +" does not exist in fasta file.\n";
                     }
 
@@ -565,7 +565,7 @@ public boolean validate(String data_template, BufferedWriter logfile, List<Strin
                         String geographic_info_TMA_inferred_region = line_splitted[index_geographic_info_TMA_inferred_region].toLowerCase();
                         if (geographic_info_TMA_inferred_region.equals("")) {
                             log_missing_value += "\tGeographic info TMA inferred region is missing.\n";
-                        } else if(!region.contains(geographic_info_TMA_inferred_region)){
+                        } else if(!region.contains(geographic_info_TMA_inferred_region) || !isStringInt(geographic_info_TMA_inferred_region)){
                             log_incorrect_format += "\tGeographic info TMA inferred region is not in correct format: " + geographic_info_TMA_inferred_region + "\n";
                         }
                     }