adding repo qc

Author: pnrobinson

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "ga4ghphetools"
-version = "0.5.1"
+version = "0.5.2"
 edition = "2021"
 keywords = ["GA4GH", "Phenopacket Schema", "Human Phenotype Ontology"]
 description = "Generate GA4GH phenopackets from tabular data"

src/ppkt/ppkt_exporter.rs

@@ -9,23 +9,14 @@ use ontolius::{Identified, TermId};
 use ontolius::ontology::csr::FullCsrOntology;
 use ontolius::ontology::{MetadataAware, OntologyTerms};
 use phenopacket_tools::builders::time_elements::time_element_from_str;
-use phenopackets::ga4gh::vrsatile::v1::{Expression, GeneDescriptor, MoleculeContext, VariationDescriptor, VcfRecord};
-use phenopackets::schema::v2::core::genomic_interpretation::{Call, InterpretationStatus};
-use phenopackets::schema::v2::core::interpretation::ProgressStatus;
-use phenopackets::schema::v2::core::{Diagnosis, KaryotypicSex, OntologyClass};
+use phenopackets::schema::v2::core::{KaryotypicSex, OntologyClass};
 use phenopackets::schema::v2::core::vital_status::Status;
-use phenopackets::schema::v2::core::{AcmgPathogenicityClassification, Disease, ExternalReference, GenomicInterpretation, Individual, Interpretation, MetaData, PhenotypicFeature, Sex, TherapeuticActionability, VariantInterpretation, VitalStatus};
+use phenopackets::schema::v2::core::{Disease, ExternalReference, Individual, MetaData, PhenotypicFeature, Sex, VitalStatus};
 use phenopackets::schema::v2::Phenopacket;
-
-use rand::Rng;
 use regex::Regex;
 use serde_json::Value;
 use crate::dto::cohort_dto::{CohortData, DiseaseData, RowData};
-
-use crate::dto::hgvs_variant::HgvsVariant;
 use crate::dto::hpo_term_dto::HpoTermDuplet;
-use crate::dto::intergenic_variant::IntergenicHgvsVariant;
-use crate::dto::structural_variant::StructuralVariant;
 use crate::ppkt::ppkt_variant_exporter::PpktVariantExporter;
 use phenopacket_tools;
 use phenopacket_tools::builders::builder::Builder;
@@ -200,7 +191,6 @@ impl PpktExporter {
         if disease_id_list.is_empty() {
             return Err("No disease data found".to_string());
         }
-        println!("{}{}: ppkt:row-{:?}", file!(), line!(), ppkt_row);
         let has_multiple_dx = disease_id_list.len() > 1;
         let mut disease_list: Vec<Disease> = Vec::new();
         for dx_id in disease_id_list {
@@ -240,23 +230,6 @@ impl PpktExporter {
     }
 
 
-
-
-
-   
-
-    /// Generate a random identifier (used in this struct for Interpretation objects).
-    pub fn generate_id() -> String {
-        rand::rng()
-            .sample_iter(&rand::distr::Alphanumeric)
-            .take(24)
-            .map(char::from)
-            .collect()
-    }
-
-  
-    
-  
 
     fn get_ontology_class(&self, term: &HpoTermDuplet) -> Result<OntologyClass, String> {
         let hpo_id = term.hpo_id();

src/repo/cohort_qc.rs

@@ -1,8 +1,8 @@
-use std::{collections::HashMap, fs, path::PathBuf};
+use std::collections::HashMap;
 
 use phenopackets::schema::v2::Phenopacket;
 
-use crate::{dto::cohort_dto::{CohortData, CohortType, DiseaseData}, repo::{disease_qc::DiseaseQc, qc_report::QcReport}};
+use crate::{dto::cohort_dto::{CohortData, CohortType}, repo::{disease_qc::DiseaseQc, qc_report::QcReport}};
 
 
 

src/repo/disease_qc.rs

@@ -46,12 +46,19 @@ impl DiseaseQc {
         for ppkt in &self.ppkt_list {
             let ac = Self::get_allele_count(ppkt);
             if ! allowable_allele_counts.contains(&ac) {
-                return Some(format!("Expected counts of {:?} but got {} for {} ({})", allowable_allele_counts, ac, self.disease_data.disease_label, self.disease_data.disease_id))
+                return Some(format!("{}: Expected counts of {:?} but got {} for {}.", ppkt.id,allowable_allele_counts, ac, self.disease_data_display()))
             }
         }
         None
     }
 
+    fn disease_data_display(&self) -> String {
+       format!("{} ({}/{})",  
+       self.disease_data.disease_label, 
+       self.disease_data.disease_id,
+       self.disease_data.gene_transcript_list[0].gene_symbol)
+    }
+
 
     fn get_allele_count(ppkt: &Phenopacket) -> usize {
         let mut ac = 0 as usize;

src/variant/intergenic_hgvs_validator.rs

@@ -320,7 +320,7 @@ response
         assert_eq!("NC_000019.10:g.12887294G>A", intergen.g_hgvs());
         assert!(intergen.gene_hgvs().is_some());
         assert_eq!("NG_009292.1:g.1135G>A", intergen.gene_hgvs().unwrap());
-        let expected_var_key= "NC_000019_10_g_12887294GtoA";
+        let expected_var_key= "NC_000019_10_g12887294GtoA";
         assert_eq!(expected_var_key, intergen.variant_key());
 
     }

tests/integration_cohort.rs

@@ -102,6 +102,26 @@ pub fn acvr1_cohort_with_repeated_term(
     assert!(result.is_err());
     let err_str = result.err().unwrap();
     assert_eq!("Duplicate entry in HPO Header: Ectopic ossification in muscle tissue (HP:0011987)", err_str);
+}
+
+
+#[rstest]
+fn export_with_het(
+    hpo: Arc<FullCsrOntology>
+) {
+    let cohort = "/Users/robin/GIT/phenopacket-store/notebooks/KLF1/KLF1_CDAN4B_individuals.json";
+    let file_data = std::fs::read_to_string(cohort)
+            .map_err(|e| 
+                format!("Could not extract string data from {}: {}", cohort, e.to_string())).unwrap();
+        let cohort: CohortData = serde_json::from_str(&file_data)
+            .map_err(|e| format!("Could not transform string {} to CohortDto: {}",
+                file_data, e.to_string())).unwrap();
+    let orcid = "0000-0000-0000-0001".to_string();
+    let ppkt_list = ga4ghphetools::ppkt::get_phenopackets(cohort, orcid, hpo).unwrap();
+    let interp = ppkt_list[2].interpretations[0].clone();
+    if let Some(dx) = interp.diagnosis {
+        println!("# genomic interpretations = {}", dx.genomic_interpretations.len());
+    }
 
 }
 

tests/integration_combine_cohort_test.rs

@@ -4,7 +4,7 @@ use ga4ghphetools::dto::{cohort_dto::{CohortData, RowData}, hpo_term_dto::{CellV
 use ontolius::ontology::csr::FullCsrOntology;
 use rstest::{rstest};
 mod common;
-use common::cohort_data_fixtures::{cohort_data_1, cohort_data_2, hpo_term_pool};
+use common::cohort_data_fixtures::{cohort_data_1, cohort_data_2};
 
 use crate::common::hpo_fixture::hpo;
 

tests/integration_new_row_tests.rs

@@ -15,10 +15,11 @@ use serde_json::Value;
 /// Make sure that our test matrix is valid before we start changing fields to check if we pick up errors
 #[rstest]
 fn test_valid_input(matrix: Vec<Vec<String>>, hpo: Arc<FullCsrOntology>) {
-    let res = CohortFactory::dto_from_mendelian_template(matrix, hpo.clone(), false,  |p,q|{// no progress bar for test
-    });
+    let res = CohortFactory::dto_from_mendelian_template(matrix, hpo.clone(), false,  |_p:u32,_q:u32|{/*  no progress bar for test*/});
     assert!(res.is_ok());
 }
+
+
 pub fn strip_phenopacket_defaults(root: &mut Value) {
     // Top-level `subject`
     if let Value::Object(root_map) = root {
@@ -155,104 +156,3 @@ fn validity_of_previous_column(
     }
     return Ok(());
 }
-
-/*
-#[rstest]
-fn add_new_row_test_1(
-    one_case_matrix: Vec<Vec<String>>, 
-    hpo: Arc<FullCsrOntology>,
-    case_5_dto: CaseDto
-) {
-    let mut phetools = PheTools::new(hpo);
-    assert_eq!(3, one_case_matrix.len()); // original matrix has headers and four data rows
-    let original_matrix = one_case_matrix.clone();
-    let res = phetools.load_matrix(one_case_matrix);
-    assert!(res.is_ok());
-    let dto_cloned = case_5_dto.clone(); // needed only for testing
-    let strab = HpoTermDto::new("HP:0000486", "Strabismus", "observed");
-    let hpo_dto_list = vec![strab];
-    let res = phetools.add_row_with_hpo_data(case_5_dto, hpo_dto_list);
-    assert!(res.is_ok());
-    // Check that the constant items are what we want
-    let new_matrix = phetools.get_string_matrix().expect("Could not unwrap matrix with added row");
-    assert_eq!(4, new_matrix.len());
-    // Check that the first six rows are identical to the original matrix
-    // Note that we can only do this for the constant columns, because we have added new HPO columns
-    let first_four_new_rows: Vec<Vec<String>> = new_matrix.iter().take(4).cloned().collect();
-    //debug_matrix_comparison(&original_matrix, &new_matrix, 17);
-    let are_equal = first_n_columns_equal(&original_matrix, &first_four_new_rows, 17);
-    assert!(are_equal);
-    // now check that the non-HPO entries in the new line are OK
-    let fourth_row = new_matrix[3].clone();
-    assert_eq!(dto_cloned.pmid, fourth_row[0]);
-    assert_eq!(dto_cloned.title, fourth_row[1]);
-    assert_eq!(dto_cloned.individual_id, fourth_row[2]);
-    assert_eq!(dto_cloned.comment, fourth_row[3]);
-    assert_eq!(dto_cloned.allele_1, fourth_row[9]);
-    assert_eq!(dto_cloned.allele_2, fourth_row[10]);
-    assert_eq!(dto_cloned.variant_comment, fourth_row[11]);
-    assert_eq!(dto_cloned.age_of_onset, fourth_row[12]);
-    assert_eq!(dto_cloned.age_at_last_encounter, fourth_row[13]);
-    assert_eq!(dto_cloned.deceased, fourth_row[14]);
-    assert_eq!(dto_cloned.sex, fourth_row[15]);
-    println!("VII: {:?}\n", &fourth_row);
-    assert_eq!("na", fourth_row[16]); // constant HPO separator column
-    // Now check the HPO columns
-    // The DTO added: thick_eye_brow: excluded; grand_mal: observed; strabismus: observed; esotropia_observed
-    validity_of_new_column("Strabismus", "HP:0000486", "observed", &new_matrix).expect("Strabismus observed in DTO");
-    // If we get here, we have passed all tests!
-    assert!(true);
-}
-
-
-///Check that all entries in a column are the same
-fn check_data_entries_unique(
-    new_matrix: &Vec<Vec<String>>, 
-    colname: &str, 
-    new_entry: &str) -> Result<(), String>
-{
-    let col = get_index_of_column(&new_matrix, colname)?;
-    for i in 2..new_matrix.len() {
-        if new_matrix[i][col] != new_entry {
-            return Err(format!("Expected new_matrix[{}][{}]={}  but got {}",
-                i, col, new_entry, new_matrix[i][col]));  
-        }
-    }
-    Ok(())
-}
-
-
-
-
-/// Check that all entries in the constant, disease-gene-bundle block are identical
-/// If so, then the new row contains the same values for
-/// disease_id, disease_label, HGNC_id, gene_symbol, and transcript
-#[rstest]
-fn add_new_row_check_disease_gene_bundle(
-    matrix: Vec<Vec<String>>, 
-    hpo: Arc<FullCsrOntology>,
-    case_5_dto: CaseDto,
-    hpo_dto_list_1: Vec<HpoTermDto>
-) {
-    let mut phetools = PheTools::new(hpo);
-    assert_eq!(6, matrix.len()); // original matrix has headers and four data rows
-    let original_matrix = matrix.clone();
-    let res = phetools.load_matrix(matrix);
-    assert!(res.is_ok());
-    let dto_cloned = case_5_dto.clone(); // needed only for testing
-    let res = phetools.add_row_with_hpo_data(case_5_dto, hpo_dto_list_1);
-    assert!(res.is_ok());
-    // Check that the constant items are what we want
-    let new_matrix = phetools.get_string_matrix().expect("Could not unwrap matrix with added row");
-    assert_eq!(7, new_matrix.len());
-    check_data_entries_unique(&new_matrix, "disease_id", "OMIM:617865").expect("Expected all entries to be 'OMIM:617865'");
-    check_data_entries_unique(&new_matrix, "disease_label", "Neurodevelopmental disorder with movement abnormalities, abnormal gait, and autistic features")
-        .expect("Expected all entries to be 'Neurodevelopmental disorder with movement abnormalities, abnormal gait, and autistic features'");
-    check_data_entries_unique(&new_matrix, "HGNC_id", "HGNC:29316").expect("Expected all entries to be 'HGNC:29316'");
-    check_data_entries_unique(&new_matrix, "gene_symbol", "ZSWIM6").expect("Expected all entries to be 'ZSWIM6'");
-    check_data_entries_unique(&new_matrix, "transcript", "NM_020928.2").expect("Expected all entries to be 'NM_020928.2'");
-    // if we get here, all tests were OK!
-    assert!(true);
-}
-
- */