isoSeQL: comparing long-read isoforms across multiple datasets.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41452740", "kind": "science-record", "revision": 1, "content_hash": "sha256:ac78d86d7c249383e0083dab47e5a6b2853662f71dd5007266d4296b24428062", "created_at": "2026-11-01T20:31:26Z", "updated_at": "2026-11-01T20:31:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "isoSeQL: comparing long-read isoforms across multiple datasets.", "doi": "10.1093/bioinformatics/btaf680", "pmid": "41452740", "authors": ["Christine S Liu", "Jerold Chun"], "journal": "Bioinformatics (Oxford, England)", "year": 2026, "abstract": "MOTIVATION: Long-read sequencing has made RNA isoform detection and characterization more accessible. While several bioinformatics tools have been developed to examine the data generated by these approaches, a major challenge in the field has been comparing isoform profiles across several samples.\nRESULTS: We developed isoSeQL, a tool for compiling long-read transcriptomic data, identifying common and unique isoforms across multiple samples, and extracting and visualizing various metrics. isoSeQL will augment approaches that utilize long-read sequencing to discover novel isoforms and to examine how isoforms vary across different experimental and biological conditions and cell types. We demonstrate how to use isoSeQL with publicly available datasets.\nAVAILABILITY AND IMPLEMENTATION: isoSeQL is available on Github: https://github.com/christine-liu/isoSeQL and Zenodo:https://doi.org/10.5281/zenodo.15717809.", "claims": [{"id": "claim-data-access", "statement": "Example bulk sequencing datasets were downloaded from https://github.com/nanopore-wgs-consortium/NA12878 (ONT dRNA and cDNA), https://www.encodeproject.org/experiments/ENCSR962BVU/ (accession code ENCFF913VJX; PacBio Iso-seq), and the NCBI Sequence Read Archive (accession SRR29438432; PacBio Kinnex). These datasets were accessed in June 2025.\nExample single-cell datasets were made publicly available through PacBio (https://downloads.pacbcloud.com/public/dataset/Kinnex-single-cell-RNA/). DATA-SQ2-PBMC_10kcells and DATA-SQ2-PBMC_5kcells were accessed in November 2023.\nThe modified version of SQANTI3 can be found on github: github.com/christine-liu/SQANTI3/tree/SQANTICL (Liu et al. 2024).\nisoSeQL can be found on github: https://github.com/christine-liu/isoSeQL and Zenodo: https://doi.org/10.5281/zenodo.15717809.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41452740", "locator": "sections[24] \"Data availability\" paragraphs 1-5", "quote": "Example bulk sequencing datasets were downloaded from https://github.com/nanopore-wgs-consortium/NA12878 (ONT dRNA and cDNA), https://www.encodeproject.org/experiments/ENCSR962BVU/ (accession code ENCFF913VJX; PacBio Iso-seq), and the NCBI Sequence Read Archive (accession SRR29438432; PacBio Kinnex). These datasets were accessed in June 2025.\nExample single-cell datasets were made publicly available through PacBio (https://downloads.pacbcloud.com/public/dataset/Kinnex-single-cell-RNA/). DATA-SQ2-PBMC_10kcells and DATA-SQ2-PBMC_5kcells were accessed in November 2023.\nThe modified version of SQANTI3 can be found on github: github.com/christine-liu/SQANTI3/tree/SQANTICL (Liu et al. 2024).\nisoSeQL can be found on github: https://github.com/christine-liu/isoSeQL and Zenodo: https://doi.org/10.5281/zenodo.15717809."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "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:41452740"], "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:SRR29438432"], "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:SRR29438432"], "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:41452740", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf680", "sha256": "sha256:5fa902fb957c984a9f341da8ffeaa83e2fb387f3fd45006d21bf9806c5dc41ff", "bytes": 30111, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf680", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12790818", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:SRR29438432", "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=SRR29438432", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR29438432", "version": null, "note": "Example bulk sequencing datasets were downloaded from https://github.com/nanopore-wgs-consortium/NA12878 (ONT dRNA and cDNA), https://www.encodeproject.org/experiments/ENCSR962BVU/ (accession code ENCFF913VJX; PacBio Iso-seq), and the NCBI Sequence Read Archive (accession SRR29438432; PacBio Kinnex). These datasets were accessed in June 2025.\nExample single-cell datasets were made publicly available through PacBio (https://downloads.pacbcloud.com/public/dataset/Kinnex-single-cell-RNA/). DATA-SQ2-PBMC_10kcells and DATA-SQ2-PBMC_5kcells were accessed in November 2023.\nThe modified version of SQANTI3 can be found on github: github.com/christine-liu/SQANTI3/tree/SQANTICL (Liu et al. 2024).\nisoSeQL can be found on github: https://github.com/christine-liu/isoSeQL and Zenodo: https://doi.org/10.5281/zenodo.15717809.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Example bulk sequencing datasets were downloaded from https://github.com/nanopore-wgs-consortium/NA12878 (ONT dRNA and cDNA), https://www.encodeproject.org/experiments/ENCSR962BVU/ (accession code ENCFF913VJX; PacBio Iso-seq), and the NCBI Sequence Read Archive (accession SRR29438432; PacBio Kinnex). These datasets were accessed in June 2025.\nExample single-cell datasets were made publicly available through PacBio (https://downloads.pacbcloud.com/public/dataset/Kinnex-single-cell-RNA/). DATA-SQ2-PBMC_10kcells and DATA-SQ2-PBMC_5kcells were accessed in November 2023.\nThe modified version of SQANTI3 can be found on github: github.com/christine-liu/SQANTI3/tree/SQANTICL (Liu et al. 2024).\nisoSeQL can be found on github: https://github.com/christine-liu/isoSeQL and Zenodo: https://doi.org/10.5281/zenodo.15717809.", "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": "2026-11-01T20:16:09Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:SRR29438432 not downloaded", "asset:data:geo:SRR29438432 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["SRR29438432"], "resolved_accessions": [], "statements": ["Example bulk sequencing datasets were downloaded from https://github.com/nanopore-wgs-consortium/NA12878 (ONT dRNA and cDNA), https://www.encodeproject.org/experiments/ENCSR962BVU/ (accession code ENCFF913VJX; PacBio Iso-seq), and the NCBI Sequence Read Archive (accession SRR29438432; PacBio Kinnex). These datasets were accessed in June 2025.\nExample single-cell datasets were made publicly available through PacBio (https://downloads.pacbcloud.com/public/dataset/Kinnex-single-cell-RNA/). DATA-SQ2-PBMC_10kcells and DATA-SQ2-PBMC_5kcells were accessed in November 2023.\nThe modified version of SQANTI3 can be found on github: github.com/christine-liu/SQANTI3/tree/SQANTICL (Liu et al. 2024).\nisoSeQL can be found on github: https://github.com/christine-liu/isoSeQL and Zenodo: https://doi.org/10.5281/zenodo.15717809."], "basis": "The paper names SRR29438432, but the accession does not resolve in the repository (not_in_ncbi_sra), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41452740", "data:geo:SRR29438432"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:SRR29438432"]}, "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": "2026-11-01T20:09:02Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8607, "completion_tokens": 2613, "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:41452740", "type": "paper", "label": "pmid:41452740"}, {"id": "source:pmid:41452740", "type": "manuscript", "label": "PMID 41452740 full text"}, {"id": "data:geo:SRR29438432", "type": "dataset", "label": "GEO SRR29438432"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41452740", "type": "paper", "label": "pmid:41452740"}, {"id": "source:pmid:41452740", "type": "manuscript", "label": "PMID 41452740 full text"}, {"id": "data:geo:SRR29438432", "type": "dataset", "label": "GEO SRR29438432"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41452740", "type": "extraction", "used": ["source:pmid:41452740"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-SRR29438432", "type": "accession_resolution", "used": ["data:geo:SRR29438432"], "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": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["asset:data:geo:SRR29438432 licence not read", "asset:data:geo:SRR29438432 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"]}