Removing unwanted Drosophila specific prefixes from UniprotKB Blast H…

…it descriptions

src/annotation_process.rs

@@ -355,7 +355,7 @@ impl AnnotationProcess {
         stored_query.n_parsed_from_sssr_tables += 1;
         // Have all input SSSR files provided data for the argument `query`?
         if stored_query.n_parsed_from_sssr_tables == self.seq_sim_search_tables.len() as u16 {
-            drop(stored_query);
+            let _ = stored_query;
             // If yes, then process the parsed data:
             self.process_query_data_complete(qacc);
         }

src/default.rs

@@ -47,6 +47,7 @@ lazy_static! {
     /// The default regular expressions used to filter a Hit title (`stitle`) and retain the short
     /// human readable description.
     pub static ref FILTER_REGEXS: Vec<Regex> = vec![
+        Regex::new(r"(?i)low\s+quality\s+protein:").unwrap(),
         Regex::new(r"\sOS=.*$").unwrap(),
         Regex::new(r"(?i)OS.*[.].*protein").unwrap(),
         Regex::new(r"(?i)^H0.*protein").unwrap(),
@@ -72,7 +73,6 @@ lazy_static! {
         Regex::new(r"(?i)\bfragment\b").unwrap(),
         Regex::new(r"(?i)\bcontig\b").unwrap(),
         Regex::new(r"(?i)\bblast:\b").unwrap(),
-        Regex::new(r"(?i)\blow quality protein:\b").unwrap(),
         ];
 
     /// The default header definition of sequence similarity search result tables, i.e. mapping

src/model_funcs.rs

@@ -225,11 +225,11 @@ mod tests {
             )
         );
 
-        // Test 7 checks that the identifier is filtered out 
+        // Test 7 checks that the identifier is filtered out
         hit_words = "sp|Q9C8M9|SRF6_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 6 OS=Arabidopsis thaliana OX=3702 GN=SRF6 PE=1 SV=1".to_string();
         expected = "protein strubbelig receptor family";
         assert_eq!(
-            expected, 
+            expected,
             filter_stitle(
                 &hit_words,
                 &(*FILTER_REGEXS),
@@ -241,27 +241,50 @@ mod tests {
         hit_words = "sp|Q6R2K2|SRF4_ARATH n Transferase Domain Containing Protein OS=Arabidopsis thaliana OX=3702 GN=SRF4 PE=2 SV=1".to_string();
         expected = "n transferase domain containing protein";
         assert_eq!(
-            expected, 
+            expected,
             filter_stitle(
                 &hit_words,
                 &(*FILTER_REGEXS),
                 Some(&(*CAPTURE_REPLACE_DESCRIPTION_PAIRS))
             )
         );
 
-        // Test 8 also checks that no additional letters are deleted
+        // Test 9 also checks that no additional letters are deleted
         hit_words = "sp|Q6R2K2|SRF4_ARATH P Transferase Domain Containing Protein OS=Arabidopsis thaliana OX=3702 GN=SRF4 PE=2 SV=1".to_string();
         expected = "p transferase domain containing protein";
         assert_eq!(
-            expected, 
+            expected,
             filter_stitle(
                 &hit_words,
                 &(*FILTER_REGEXS),
                 Some(&(*CAPTURE_REPLACE_DESCRIPTION_PAIRS))
             )
         );
-
 
+        // Test 10 checks that the Drosophila specific HRD description prefix 'LOW QUALITY
+        // PROTEIN:' is removed:
+        hit_words = "tr|A0A6P4E2J9|A0A6P4E2J9_DRORH LOW QUALITY PROTEIN: muscarinic acetylcholine receptor DM1 OS=Drosophila rhopaloa OX=1041015 GN=LOC108039593 PE=3 SV=1".to_string();
+        expected = "muscarinic acetylcholine receptor dm";
+        assert_eq!(
+            expected,
+            filter_stitle(
+                &hit_words,
+                &(*FILTER_REGEXS),
+                Some(&(*CAPTURE_REPLACE_DESCRIPTION_PAIRS))
+            )
+        );
+
+        // Test 11 checks that the Drosophila specific HRD description prefix 'Blast:' is removed:
+        hit_words = "tr|A0A3B0K592|A0A3B0K592_DROGU Blast:Homeobox protein abdominal-A OS=Drosophila guanche OX=7266 GN=DGUA_6G017991 PE=3 SV=1".to_string();
+        expected = "homeobox protein abdominal a";
+        assert_eq!(
+            expected,
+            filter_stitle(
+                &hit_words,
+                &(*FILTER_REGEXS),
+                Some(&(*CAPTURE_REPLACE_DESCRIPTION_PAIRS))
+            )
+        );
     }
 
     #[test]