Add RNACentral ID column to gene result table

Refs pombase/website#1989
pombase · Jun 27, 2024 · b27c642 · b27c642
1 parent 50e3e04
commit b27c642
Show file tree

Hide file tree

Showing 5 changed files with 13 additions and 1 deletion.
diff --git a/src/pombase/api/query.rs b/src/pombase/api/query.rs
@@ -1071,6 +1071,7 @@ impl Query {
                let mut reference_uniquenames = HashSet::new();
                let mut tmm = None;
                let mut pdb_ids = HashSet::new();
+               let mut rnacentral_id = None;
                let mut gocam_ids = HashSet::new();
                let mut molecular_weight = None;
                let mut protein_length = None;
@@ -1103,6 +1104,7 @@ impl Query {
                                 go_function = gene_data.go_function.clone(),
                            "tmm" => tmm = gene_data.tmm.clone(),
                            "pdb_ids" => pdb_ids = gene_data.pdb_ids.clone(),
+                           "rnacentral_id" => rnacentral_id = gene_data.rnacentral_urs_identifier.clone(),
                            "gocam_ids" => gocam_ids = gene_data.gocam_ids.clone(),
                            "molecular_weight" =>
                                molecular_weight = gene_data.molecular_weight,
@@ -1125,7 +1127,7 @@ impl Query {
                                                                     &gene_uniquename);
                                    gene_expression.extend(results_measurements);
                                } else {
-                                   eprintln!("warning - no such option field: {}", field_name);
+                                   eprintln!("warning - no such field: {}", field_name);
                                }
                            }
                        }
@@ -1165,6 +1167,7 @@ impl Query {
                    unspliced_rna_length,
                    reference_uniquenames,
                    pdb_ids,
+                   rnacentral_id,
                    gocam_ids,
                    subsets,
                    gene_expression,

diff --git a/src/pombase/api/result.rs b/src/pombase/api/result.rs
@@ -51,6 +51,8 @@ pub struct ResultRow {
     pub reference_uniquenames: HashSet<ReferenceUniquename>,
     #[serde(skip_serializing_if="HashSet::is_empty", default)]
     pub pdb_ids: HashSet<PdbId>,
+    #[serde(skip_serializing_if="Option::is_none")]
+    pub rnacentral_id: Option<FlexStr>,
     #[serde(skip_serializing_if="HashSet::is_empty", default)]
     pub gocam_ids: HashSet<GoCamId>,
     #[serde(skip_serializing_if="HashSet::is_empty", default)]

diff --git a/src/pombase/data_types.rs b/src/pombase/data_types.rs
@@ -2229,6 +2229,8 @@ pub struct GeneQueryData {
     pub subset_termids: HashSet<TermId>,
 #[serde(skip_serializing_if="HashSet::is_empty", default)]
     pub pdb_ids: HashSet<PdbId>,
+#[serde(skip_serializing_if="Option::is_none")]
+    pub rnacentral_urs_identifier: Option<FlexStr>,
 #[serde(skip_serializing_if="HashSet::is_empty", default)]
     pub gocam_ids: HashSet<GoCamId>,
 }

diff --git a/src/pombase/web/data_build.rs b/src/pombase/web/data_build.rs
@@ -5126,6 +5126,7 @@ phenotypes, so just the first part of this extension will be used:
             let pdb_ids = gene_details.pdb_entries.iter()
                 .map(|pdb_entry| pdb_entry.pdb_id.clone())
                 .collect();
+            let rnacentral_urs_identifier = gene_details.rnacentral_urs_identifier.clone();
             let gocam_ids =
                 gene_details.gocams.iter().map(|gocam| gocam.gocam_id.clone()).collect();
 
@@ -5147,6 +5148,7 @@ phenotypes, so just the first part of this extension will be used:
                 unspliced_rna_length,
                 reference_uniquenames,
                 pdb_ids,
+                rnacentral_urs_identifier,
                 gocam_ids,
                 subset_termids: gene_details.subset_termids.clone(),
             };

diff --git a/tests/test_query.rs b/tests/test_query.rs
@@ -181,6 +181,7 @@ async fn test_output_options() {
                 gaf_lines: None,
                 reference_uniquenames: HashSet::new(),
                 pdb_ids: HashSet::new(),
+                rnacentral_id: None,
                 gocam_ids: HashSet::new(),
                 subsets: HashSet::new(),
                 gene_expression: vec![],
@@ -205,6 +206,7 @@ async fn test_output_options() {
                 gaf_lines: None,
                 reference_uniquenames: HashSet::new(),
                 pdb_ids: HashSet::new(),
+                rnacentral_id: None,
                 gocam_ids: HashSet::new(),
                 subsets: HashSet::new(),
                 gene_expression: vec![],
@@ -232,6 +234,7 @@ async fn test_output_options() {
                 gaf_lines: None,
                 reference_uniquenames: HashSet::new(),
                 pdb_ids: HashSet::new(),
+                rnacentral_id: None,
                 gocam_ids: HashSet::new(),
                 subsets: HashSet::new(),
                 gene_expression: vec![],