Using intrahost single nucleotide variant data to predict SARS-CoV-2 detection cycle threshold values.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39475880", "kind": "science-record", "revision": 4, "content_hash": "sha256:5369734c40b761e562e1ccede6ade63c1bdaf2c5e72eae8dc1007a9b424d0234", "created_at": "2026-11-01T20:29:44Z", "updated_at": "2026-11-01T22:55:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Using intrahost single nucleotide variant data to predict SARS-CoV-2 detection cycle threshold values.", "doi": "10.1371/journal.pone.0312686", "pmid": "39475880", "authors": ["Lea Duesterwald", "Marcus Nguyen", "Paul Christensen", "S Wesley Long", "Randall J Olsen", "James M Musser", "James J Davis"], "journal": "PloS one", "year": 2024, "abstract": "Over the last four years, each successive wave of the COVID-19 pandemic has been caused by variants with mutations that improve the transmissibility of the virus. Despite this, we still lack tools for predicting clinically important features of the virus. In this study, we show that it is possible to predict the PCR cycle threshold (Ct) values from clinical detection assays using sequence data. Ct values often correspond with patient viral load and the epidemiological trajectory of the pandemic. Using a collection of 36,335 high quality genomes, we built models from SARS-CoV-2 intrahost single nucleotide variant (iSNV) data, computing XGBoost models from the frequencies of A, T, G, C, insertions, and deletions at each position relative to the Wuhan-Hu-1 reference genome. Our best model had an R2 of 0.604 [0.593-0.616, 95% confidence interval] and a Root Mean Square Error (RMSE) of 5.247 [5.156-5.337], demonstrating modest predictive power. Overall, we show that the results are stable relative to an external holdout set of genomes selected from SRA and are robust to patient status and the detection instruments that were used. This study highlights the importance of developing modeling strategies that can be applied to publicly available genome sequence data for use in disease prevention and control.", "claims": [{"id": "claim-method", "statement": "Regression models were built using Extreme Gradient Boosting (XGBoost) [35].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39475880", "locator": "sections[3] \"Models built from iSNV frequencies are predictive\" paragraph 5", "quote": "Regression models were built using Extreme Gradient Boosting (XGBoost) [35]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The code for the Ct value prediction model and the documentation for running the code and model are available at the following GitHub page: https://github.com/Tinyman392/Pileup_Ct_Prediction. Sequence data are available at SRA under the BioProject, PRJNA767338, and are listed in S1 Table. SRA run accessions for external genomes are listed in S4 Table.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39475880", "locator": "sections[21] \"Data Availability\" paragraph 2", "quote": "The code for the Ct value prediction model and the documentation for running the code and model are available at the following GitHub page: https://github.com/Tinyman392/Pileup_Ct_Prediction. Sequence data are available at SRA under the BioProject, PRJNA767338, and are listed in S1 Table. SRA run accessions for external genomes are listed in S4 Table."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Our best model had an R2 of 0.604 [0.593–0.616, 95% confidence interval] and a Root Mean Square Error (RMSE) of 5.247 [5.156–5.337], demonstrating modest predictive power.", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "Our best model had an R2 of 0.604 [0.593–0.616, 95% confidence interval] and a Root Mean Square Error (RMSE) of 5.247 [5.156–5.337], demonstrating modest predictive power."}, "evidence": [{"asset": "source:pmid:39475880", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Our best model had an R2 of 0.604 [0.593–0.616, 95% confidence interval] and a Root Mean Square Error (RMSE) of 5.247 [5.156–5.337], demonstrating modest predictive power."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Our best model had an R2 of 0.604 [0.593–0.616, 95% confidence interval] and a Root Mean Square Error (RMSE) of 5.247 [5.156–5.337], demonstrating modest predictive power.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39475880"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_unresolved", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:PRJNA767338"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:PRJNA767338"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39475880", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0312686", "sha256": "sha256:973a6aacc1136ebd4d7173981a6d9bfeb6c454bd9e9e9b7ff97a8618693e4914", "bytes": 49134, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0312686", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11524481", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PRJNA767338", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=PRJNA767338", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJNA767338", "version": null, "note": "The code for the Ct value prediction model and the documentation for running the code and model are available at the following GitHub page: https://github.com/Tinyman392/Pileup_Ct_Prediction. Sequence data are available at SRA under the BioProject, PRJNA767338, and are listed in S1 Table. SRA run accessions for external genomes are listed in S4 Table.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The code for the Ct value prediction model and the documentation for running the code and model are available at the following GitHub page: https://github.com/Tinyman392/Pileup_Ct_Prediction. Sequence data are available at SRA under the BioProject, PRJNA767338, and are listed in S1 Table. SRA run accessions for external genomes are listed in S4 Table.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T20:16:20Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PRJNA767338 not downloaded", "asset:data:geo:PRJNA767338 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Regression models were built using Extreme Gradient Boosting (XGBoost) [35]."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cross_validate", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-correlation-coefficient", "claim_id": "claim-target-result", "operation": "cross_validate", "expected_value": 2.0, "unit": "correlation coefficient", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: gradient_boosting."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": ["PRJNA767338"], "resolved_accessions": [], "statements": ["The code for the Ct value prediction model and the documentation for running the code and model are available at the following GitHub page: https://github.com/Tinyman392/Pileup_Ct_Prediction. Sequence data are available at SRA under the BioProject, PRJNA767338, and are listed in S1 Table. SRA run accessions for external genomes are listed in S4 Table."], "basis": "The paper names PRJNA767338, but the accession does not resolve in the repository (not_in_ncbi_bioproject), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:39475880", "data:geo:PRJNA767338"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PRJNA767338"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:37:10Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13940, "completion_tokens": 1909, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:39475880", "type": "paper", "label": "pmid:39475880"}, {"id": "source:pmid:39475880", "type": "manuscript", "label": "PMID 39475880 full text"}, {"id": "data:geo:PRJNA767338", "type": "dataset", "label": "GEO PRJNA767338"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39475880", "type": "paper", "label": "pmid:39475880"}, {"id": "source:pmid:39475880", "type": "manuscript", "label": "PMID 39475880 full text"}, {"id": "data:geo:PRJNA767338", "type": "dataset", "label": "GEO PRJNA767338"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39475880", "type": "extraction", "used": ["source:pmid:39475880"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PRJNA767338", "type": "accession_resolution", "used": ["data:geo:PRJNA767338"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:39475880", "parent_hash": "sha256:ca781cc2f931db73473e14961ff618c236166eb6ee9c72f912c3ef39faeddec9", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PRJNA767338 licence not read", "asset:data:geo:PRJNA767338 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Regression models were built using Extreme Gradient Boosting (XGBoost) [35]."], "order_basis": "analysis_only", "id": "assay:1"}]}