ScisorWiz: visualizing differential isoform expression in single-cell long-read data.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35604081", "kind": "science-record", "revision": 3, "content_hash": "sha256:6a595c82bcd7dadcd5a38912fbaa2c0e60b041bd6e50959cfaabe73ff33d4a43", "created_at": "2026-11-01T18:14:31Z", "updated_at": "2026-11-01T21:27:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "ScisorWiz: visualizing differential isoform expression in single-cell long-read data.", "doi": "10.1093/bioinformatics/btac340", "pmid": "35604081", "authors": ["Alexander N Stein", "Anoushka Joglekar", "Chi-Lam Poon", "Hagen U Tilgner"], "journal": "Bioinformatics (Oxford, England)", "year": 2022, "abstract": "SUMMARY: RNA isoforms contribute to the diverse functionality of the proteins they encode within the cell. Visualizing how isoform expression differs across cell types and brain regions can inform our understanding of disease and gain or loss of functionality caused by alternative splicing with potential negative impacts. However, the extent to which this occurs in specific cell types and brain regions is largely unknown. This is the kind of information that ScisorWiz plots can provide in an informative and easily communicable manner. ScisorWiz affords its user the opportunity to visualize specific genes across any number of cell types, and provides various sorting options for the user to gain different ways to understand their data. ScisorWiz provides a clear picture of differential isoform expression through various clustering methods and highlights features such as alternative exons and single-nucleotide variants. Tools like ScisorWiz are key for interpreting single-cell isoform sequencing data. This tool applies to any single-cell long-read RNA sequencing data in any cell type, tissue or species.\nAVAILABILITY AND IMPLEMENTATION: Source code is available at http://github.com/ans4013/ScisorWiz. No new data were generated for this publication. Data used to generate figures was sourced from GEO accession token GSE158450 and available on GitHub as example data.", "claims": [{"id": "claim-method", "statement": "By default, the package clusters read according to intron chains.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35604081", "locator": "sections[3] \"3 Approach\" paragraph 2", "quote": "By default, the package clusters read according to intron chains."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Source code is available at http://github.com/ans4013/ScisorWiz. No new data were generated for this publication. Data used to generate figures was sourced from GEO accession token GSE158450 and available on GitHub as example data.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35604081", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Source code is available at http://github.com/ans4013/ScisorWiz. No new data were generated for this publication. Data used to generate figures was sourced from GEO accession token GSE158450 and available on GitHub as example data."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:35604081"], "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": "complete", "blocked_on": null, "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:GSE158450"], "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:GSE158450"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35604081", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btac340", "sha256": "sha256:3e4bb7ca07b0fdb6906ec4114398733c184d3d02450cb00b54e2591d1042c356", "bytes": 8695, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btac340", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9237735", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE158450", "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=GSE158450", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE158450", "version": null, "note": "Source code is available at http://github.com/ans4013/ScisorWiz. No new data were generated for this publication. Data used to generate figures was sourced from GEO accession token GSE158450 and available on GitHub as example data.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Source code is available at http://github.com/ans4013/ScisorWiz. No new data were generated for this publication. Data used to generate figures was sourced from GEO accession token GSE158450 and available on GitHub as example data.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4800800", "GSM4800801", "GSM4800802", "GSM4800803", "GSM4800804", "GSM4800805", "GSM4800806", "GSM4800807", "GSM4800808", "GSM4800809", "GSM4800810"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "21103;29177;26624;24247", "taxon": "Mus musculus", "title": "Cell-type, single-cell, and spatial signatures of brain-region specific splicing in postnatal development", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE158450 not downloaded", "asset:data:geo:GSE158450 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "clustering by intron chains", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "By default, the package clusters read according to intron chains."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (clustering by intron chains), 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": "R1", "reachable": true, "accessions": ["GSE158450"], "resolved_accessions": ["GSE158450"], "statements": ["Source code is available at http://github.com/ans4013/ScisorWiz. No new data were generated for this publication. Data used to generate figures was sourced from GEO accession token GSE158450 and available on GitHub as example data."], "basis": "The paper names GSE158450 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:35604081", "data:geo:GSE158450"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE158450"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:47:10Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 3692, "completion_tokens": 1341, "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:35604081", "type": "paper", "label": "pmid:35604081"}, {"id": "source:pmid:35604081", "type": "manuscript", "label": "PMID 35604081 full text"}, {"id": "data:geo:GSE158450", "type": "dataset", "label": "GEO GSE158450"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35604081", "type": "paper", "label": "pmid:35604081"}, {"id": "source:pmid:35604081", "type": "manuscript", "label": "PMID 35604081 full text"}, {"id": "data:geo:GSE158450", "type": "dataset", "label": "GEO GSE158450"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35604081", "type": "extraction", "used": ["source:pmid:35604081"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE158450", "type": "accession_resolution", "used": ["data:geo:GSE158450"], "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:35604081", "parent_hash": "sha256:34eef159591d85eccd8e95e10edac29b6a87d03c92452c648e0726a80174613e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE158450 licence not read", "asset:data:geo:GSE158450 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["is tool applies to any single-cell long-read RNA sequencing data in any cell type, tissue or species. AV"], "order_basis": "paper_text_order:1102", "id": "assay:1"}]}