FlatProt: 2D visualization eases protein structure comparison.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40804367", "kind": "science-record", "revision": 1, "content_hash": "sha256:7429858d324b0000f4b94bdf2da93534d1082976f537f9820a335e16f820f0b5", "created_at": "2026-11-01T20:30:54Z", "updated_at": "2026-11-01T20:30:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "FlatProt: 2D visualization eases protein structure comparison.", "doi": "10.1186/s12859-025-06233-x", "pmid": "40804367", "authors": ["Tobias Olenyi", "Constantin Carl", "Tobias Senoner", "Ivan Koludarov", "Burkhard Rost"], "journal": "BMC bioinformatics", "year": 2025, "abstract": "BACKGROUND: Understanding and comparing three-dimensional (3D) structures of proteins can advance bioinformatics, molecular biology, and drug discovery. While 3D models offer detailed insights, comparing multiple structures simultaneously remains challenging, especially on two-dimensional (2D) displays. Existing 2D visualization tools lack standardized approaches for pipelined inspection of large protein sets, limiting their utility in large-scale pre-filtering.\nRESULTS: We introduce FlatProt, a tool designed to complement 3D viewers by enabling standardized 2D visualization of individual protein structures or large sets thereof. By including Foldseek-based family rotation alignment or an inertia-based fallback, FlatProt creates consistent and scalable visual representations for user-defined protein structures. It supports domain-aware decomposition, family-level overlays, and lightweight visual abstraction of secondary structures. FlatProt processes proteins efficiently, as showcased on a subset of the human-proteome.\nCONCLUSION: FlatProt provides clear, consistent, user-friendly visualizations that support rapid, comparative inspection of protein structures at scale. By bridging the gap between interactive 3D tools and static visual summaries, it enables users to explore conserved features, detect outliers, and prioritize structures for further analysis.\nAVAILABILITY: GitHub ( https://github.com/t03i/FlatProt ); Zenodo ( https://doi.org/10.5281/zenodo.15697296 ).", "claims": [{"id": "claim-data-access", "statement": "All data generated or analyzed during this study are included in this published article and its supplementary information files. The SCOP2 database (version 2022-06-29) used for family mapping was obtained from https://www.ebi.ac.uk/pdbe/scop (annotation file: scop-ca-latest.txt). The Snakemake pipeline for database construction is available at https://github.com/t03i/flatprot/tree/main/db_builder. Our processed SCOP superfamily database is available on Zenodo: 10.5281/zenodo.15697296. The human proteome data were obtained from UniProtKB/SwissProt (https://www.uniprot.org/) with structures from AlphaFoldDB (https://alphafold.ebi.ac.uk/). Kallikrein family structures are provided in the supplementary files (KLK.zip). The Three-Finger Toxin dataset is from reference [28].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40804367", "locator": "sections[23] \"notes\" paragraph 1", "quote": "All data generated or analyzed during this study are included in this published article and its supplementary information files. The SCOP2 database (version 2022-06-29) used for family mapping was obtained from https://www.ebi.ac.uk/pdbe/scop (annotation file: scop-ca-latest.txt). The Snakemake pipeline for database construction is available at https://github.com/t03i/flatprot/tree/main/db_builder. Our processed SCOP superfamily database is available on Zenodo: 10.5281/zenodo.15697296. The human proteome data were obtained from UniProtKB/SwissProt (https://www.uniprot.org/) with structures from AlphaFoldDB (https://alphafold.ebi.ac.uk/). Kallikrein family structures are provided in the supplementary files (KLK.zip). The Three-Finger Toxin dataset is from reference [28]."}], "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:40804367"], "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:40804367", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12859-025-06233-x", "sha256": "sha256:a05bbcc6dcbef5582cc093f8e03b3f6a30dcd58386a5d06f653ee62186e3dce0", "bytes": 34705, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12859-025-06233-x", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12344939", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "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": [], "resolved_accessions": [], "statements": ["All data generated or analyzed during this study are included in this published article and its supplementary information files. The SCOP2 database (version 2022-06-29) used for family mapping was obtained from https://www.ebi.ac.uk/pdbe/scop (annotation file: scop-ca-latest.txt). The Snakemake pipeline for database construction is available at https://github.com/t03i/flatprot/tree/main/db_builder. Our processed SCOP superfamily database is available on Zenodo: 10.5281/zenodo.15697296. The human proteome data were obtained from UniProtKB/SwissProt (https://www.uniprot.org/) with structures from AlphaFoldDB (https://alphafold.ebi.ac.uk/). Kallikrein family structures are provided in the supplementary files (KLK.zip). The Three-Finger Toxin dataset is from reference [28]."], "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:40804367"], "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": "2026-11-01T19:59:35Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9018, "completion_tokens": 2750, "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:40804367", "type": "paper", "label": "pmid:40804367"}, {"id": "source:pmid:40804367", "type": "manuscript", "label": "PMID 40804367 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40804367", "type": "paper", "label": "pmid:40804367"}, {"id": "source:pmid:40804367", "type": "manuscript", "label": "PMID 40804367 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40804367", "type": "extraction", "used": ["source:pmid:40804367"], "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": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}