esloco: simulation-based estimation of local coverage in long-read DNA sequencing.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41512287", "kind": "science-record", "revision": 2, "content_hash": "sha256:2c9c09c54ad688bfabe3fff24ab2a17b88cda9773fb07f7140b8c03a9c32c4b5", "created_at": "2026-11-01T20:31:29Z", "updated_at": "2026-11-01T21:36:17Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "esloco: simulation-based estimation of local coverage in long-read DNA sequencing.", "doi": "10.1093/bioinformatics/btag009", "pmid": "41512287", "authors": ["Adrian Weich", "Christopher Lischer", "Julio Vera"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "SUMMARY: Long-read DNA sequencing is increasingly applied for whole-genome studies, yet experimental planning often lacks reliable estimates of target region coverage, leading to costly and time-consuming pilot studies and replicates. We present esloco, a Monte Carlo-based simulation framework for estimating local coverage in long-read sequencing experiments, including scenarios with unknown target regions (e.g. viral integration, CRISPR-Cas9) or PCR-free designs (e.g. base modifications). By modeling coverage as a function of sequencing depth and read length distribution, esloco enables informed predictions of local sequencing outcomes. Benchmarking across a 45-gene panel demonstrated close agreement with empirical data, underscoring the framework's reliability.\nAVAILABILITY AND IMPLEMENTATION: esloco is a Python package available on PyPI (https://pypi.org/project/esloco/), GitHub (https://github.com/aweich/esloco), and Zenodo (https://doi.org/10.5281/zenodo.17776161).\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "We computed the significant differences between simulation and sequencing for each panel gene’s number of OTBs using two-sided empirical P-values, followed by Benjamini–Hochbergs’s false-discovery-rate (FDR) correction for multiple testing (Benjamini and Hochberg 1995). Additionally, concordance correlation coefficients (Lin 1989) were calculated and Bland-Altman (Altman and Bland 1983) plots were generated.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41512287", "locator": "sections[11] \"2.6 Benchmarking simulated coverage estimations against empirical data\" paragraph 7", "quote": "We computed the significant differences between simulation and sequencing for each panel gene’s number of OTBs using two-sided empirical P-values, followed by Benjamini–Hochbergs’s false-discovery-rate (FDR) correction for multiple testing (Benjamini and Hochberg 1995). Additionally, concordance correlation coefficients (Lin 1989) were calculated and Bland-Altman (Altman and Bland 1983) plots were generated."}], "state": "complete"}, {"id": "claim-data-access", "statement": "No new data were generated or analysed in support of this research.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41512287", "locator": "sections[22] \"Data availability\" paragraph 2", "quote": "No new data were generated or analysed in support of this research."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Benchmarking across a 45-gene panel demonstrated close agreement with empirical data, underscoring the framework’s reliability.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41512287", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Benchmarking across a 45-gene panel demonstrated close agreement with empirical data, underscoring the framework’s reliability."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Benchmarking across a 45-gene panel demonstrated close agreement with empirical data, underscoring the framework’s reliability.", "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:41512287"], "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_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41512287", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btag009", "sha256": "sha256:eaf2cadb1674eea5dc12eb3031cafd0b3a5fb1ef0301f095e7c6776acf8d7ac5", "bytes": 23415, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btag009", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12866673", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Concordance correlation coefficients, two-sided empirical P-values, and Benjamini–Hochberg false-discovery-rate correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We computed the significant differences between simulation and sequencing for each panel gene’s number of OTBs using two-sided empirical P-values, followed by Benjamini–Hochbergs’s false-discovery-rate (FDR) correction for multiple testing (Benjamini and Hochberg 1995). Additionally, concordance correlation coefficients (Lin 1989) were calculated and Bland-Altman (Altman and Bland 1983) plots were generated."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Concordance correlation coefficients, two-sided empirical P-values, and Benjamini–Hochberg false-discovery-rate correction), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": [], "resolved_accessions": [], "statements": ["No new data were generated or analysed in support of this research."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41512287"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "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": "2026-11-01T20:09:53Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7164, "completion_tokens": 2045, "cached_tokens": 128}}, "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:41512287", "type": "paper", "label": "pmid:41512287"}, {"id": "source:pmid:41512287", "type": "manuscript", "label": "PMID 41512287 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41512287", "type": "paper", "label": "pmid:41512287"}, {"id": "source:pmid:41512287", "type": "manuscript", "label": "PMID 41512287 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41512287", "type": "extraction", "used": ["source:pmid:41512287"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:41512287", "parent_hash": "sha256:b4c71de2480d610bbd021308218c8c44f26fa95f24fc703acac7ffe44bdc433e", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["nown target regions (e.g. viral integration, CRISPR-Cas9) or PCR-free designs (e.g. base modific"], "order_basis": "paper_text_order:473", "id": "assay:1"}]}