Sanity check rna sequence strings on library generation

BimberLab · Nov 5, 2024 · f0f11fb · f0f11fb
1 parent fdeab1c
commit f0f11fb
Show file tree

Hide file tree

Showing 4 changed files with 120 additions and 3 deletions.
diff --git a/src/reference_library.rs b/src/reference_library.rs
@@ -134,9 +134,15 @@ pub fn get_reference_library(path: &Path, strand_filter: LibraryChemistry) -> (a
         let mut row = Vec::new();
         let mut revcomp_row = Vec::new();
 
-        for col in &columns {
-            row.push(col[row_idx].clone());
-            revcomp_row.push(col[row_idx].clone());
+        for (col_idx, col) in columns.iter().enumerate() {
+            let mut value = col[row_idx].clone();
+
+            if col_idx == sequence_idx {
+                value = value.replace('U', "T").replace('u', "t");
+            }
+
+            row.push(value.clone());
+            revcomp_row.push(value.clone());
         }
 
         revcomp_row[sequence_name_idx] = revcomp_row[sequence_name_idx].clone() + SPECIAL_REVCOMP_FEATURE_NAME_SEPARATOR + "rev";
@@ -436,4 +442,40 @@ mod tests {
 
         sanity_check_align_config(&align_config);  // Should pass without panic
     }
+
+    #[test]
+    fn test_get_reference_library_rna_to_dna_conversion() {
+        let path = Path::new("tests/test-sequences/libraries/reference-library-rna.json");
+        let strand_filter = LibraryChemistry::None;
+        let (_align_config, reference_metadata) = get_reference_library(path, strand_filter);
+
+        assert_eq!(reference_metadata.columns[3][0], "ATGCTT".to_string());
+        assert_eq!(reference_metadata.columns[3][1], "AAGCAT".to_string());
+        assert_eq!(reference_metadata.columns[3][2], "tTgcAT".to_string());
+        assert_eq!(reference_metadata.columns[3][3], "ATgcAa".to_string());
+    }
+
+    #[test]
+    fn test_get_reference_library_mixed_case_rna_to_dna_conversion() {
+        let path = Path::new("tests/test-sequences/libraries/reference-library-mixed-case-rna.json");
+        let strand_filter = LibraryChemistry::None;
+        let (_align_config, reference_metadata) = get_reference_library(path, strand_filter);
+
+        assert_eq!(reference_metadata.columns[3][0], "atGcTt".to_string());
+        assert_eq!(reference_metadata.columns[3][1], "aAgCat".to_string());
+        assert_eq!(reference_metadata.columns[3][2], "TtgCAt".to_string());
+        assert_eq!(reference_metadata.columns[3][3], "aTGcaA".to_string());
+    }
+
+    #[test]
+    fn test_get_reference_library_sequence_without_rna_bases() {
+        let path = Path::new("tests/test-sequences/libraries/reference-library-no-rna-bases.json");
+        let strand_filter = LibraryChemistry::None;
+        let (_align_config, reference_metadata) = get_reference_library(path, strand_filter);
+
+        assert_eq!(reference_metadata.columns[3][0], "ATGCGT".to_string());
+        assert_eq!(reference_metadata.columns[3][1], "ACGCAT".to_string());
+        assert_eq!(reference_metadata.columns[3][2], "CGTACG".to_string());
+        assert_eq!(reference_metadata.columns[3][3], "CGTACG".to_string());
+    }
 }
diff --git a/tests/test-sequences/libraries/reference-library-mixed-case-rna.json b/tests/test-sequences/libraries/reference-library-mixed-case-rna.json
@@ -0,0 +1,25 @@
+[
+    {
+        "score_percent": 0.85,
+        "score_filter": 200,
+        "score_threshold": 300,
+        "num_mismatches": 2,
+        "discard_multiple_matches": true,
+        "require_valid_pair": false,
+        "discard_multi_hits": 1,
+        "intersect_level": 1,
+        "max_hits_to_report": 10,
+        "group_on": "feature_id",
+        "trim_target_length": 40,
+        "trim_strictness": 0.9
+    },
+    {
+        "headers": ["id", "feature_id", "sequence_name", "sequence"],
+        "columns": [
+            ["1", "2"],
+            ["fid1", "fid2"],
+            ["seq_name1", "seq_name2"],
+            ["auGcTt", "UugCAu"]
+        ]
+    }
+]
diff --git a/tests/test-sequences/libraries/reference-library-no-rna-bases.json b/tests/test-sequences/libraries/reference-library-no-rna-bases.json
@@ -0,0 +1,25 @@
+[
+    {
+        "score_percent": 0.85,
+        "score_filter": 200,
+        "score_threshold": 300,
+        "num_mismatches": 2,
+        "discard_multiple_matches": true,
+        "require_valid_pair": false,
+        "discard_multi_hits": 1,
+        "intersect_level": 1,
+        "max_hits_to_report": 10,
+        "group_on": "feature_id",
+        "trim_target_length": 40,
+        "trim_strictness": 0.9
+    },
+    {
+        "headers": ["id", "feature_id", "sequence_name", "sequence"],
+        "columns": [
+            ["1", "2"],
+            ["fid1", "fid2"],
+            ["seq_name1", "seq_name2"],
+            ["ATGCGT", "CGTACG"]
+        ]
+    }
+]
diff --git a/tests/test-sequences/libraries/reference-library-rna.json b/tests/test-sequences/libraries/reference-library-rna.json
@@ -0,0 +1,25 @@
+[
+    {
+        "score_percent": 0.85,
+        "score_filter": 200,
+        "score_threshold": 300,
+        "num_mismatches": 2,
+        "discard_multiple_matches": true,
+        "require_valid_pair": false,
+        "discard_multi_hits": 1,
+        "intersect_level": 1,
+        "max_hits_to_report": 10,
+        "group_on": "feature_id",
+        "trim_target_length": 40,
+        "trim_strictness": 0.9
+    },
+    {
+        "headers": ["id", "feature_id", "sequence_name", "sequence"],
+        "columns": [
+            ["1", "2"],
+            ["fid1", "fid2"],
+            ["seq_name1", "seq_name2"],
+            ["AUGCUU", "uUgcAU"]
+        ]
+    }
+]