N-Terminomics for the Identification of In Vitro Substrates and Cleavage Site Specificity of the SARS-CoV-2 Main Protease.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33111431", "kind": "science-record", "revision": 3, "content_hash": "sha256:c92b2ff87e048011ecc22890b7cfbe2fd99cfd93a4cde821795c06199ad6b9ef", "created_at": "2026-11-01T15:41:14Z", "updated_at": "2026-11-01T21:24:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "N-Terminomics for the Identification of In Vitro Substrates and Cleavage Site Specificity of the SARS-CoV-2 Main Protease.", "doi": "10.1002/pmic.202000246", "pmid": "33111431", "authors": ["Tomas Koudelka", "Juliane Boger", "Alessandra Henkel", "Robert Schönherr", "Stefanie Krantz", "Sabine Fuchs", "Estefanía Rodríguez", "Lars Redecke", "Andreas Tholey"], "journal": "Proteomics", "year": 2021, "abstract": "The genome of coronaviruses, including SARS-CoV-2, encodes for two proteases, a papain like (PLpro ) protease and the so-called main protease (Mpro ), a chymotrypsin-like cysteine protease, also named 3CLpro or non-structural protein 5 (nsp5). Mpro is activated by autoproteolysis and is the main protease responsible for cutting the viral polyprotein into functional units. Aside from this, it is described that Mpro proteases are also capable of processing host proteins, including those involved in the host innate immune response. To identify substrates of the three main proteases from SARS-CoV, SARS-CoV-2, and hCoV-NL63 coronviruses, an LC-MS based N-terminomics in vitro analysis is performed using recombinantly expressed proteases and lung epithelial and endothelial cell lysates as substrate pools. For SARS-CoV-2 Mpro , 445 cleavage events from more than 300 proteins are identified, while 151 and 331 Mpro derived cleavage events are identified for SARS-CoV and hCoV-NL63, respectively. These data enable to better understand the cleavage site specificity of the viral proteases and will help to identify novel substrates in vivo. All data are available via ProteomeXchange with identifier PXD021406.", "claims": [{"id": "claim-data-access", "statement": "All data are available via ProteomeXchange with identifier PXD021406.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33111431", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All data are available via ProteomeXchange with identifier PXD021406."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:33111431"], "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:PXD021406"], "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:PXD021406"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33111431", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/pmic.202000246", "sha256": "sha256:02e6b006fa76a94a8f43359ff75f56ca72d99c8a473fbce05da4f39292c81808", "bytes": 19661, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/pmic.202000246", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7645863", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD021406", "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=PXD021406", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD021406", "version": null, "note": "All data are available via ProteomeXchange with identifier PXD021406.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data are available via ProteomeXchange with identifier PXD021406.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "N-terminomics for the identification of in-vitro substrates and cleavage site specificity of the SARS-CoV-2 main protease", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD021406 not downloaded", "asset:data:geo:PXD021406 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "N-termini were filtered by log2 fold-change and an acceptable q-value (0.05). Source data were available through ProteomeXchange under identifier PXD021406.", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“N‐termini were filtered by log2 fold‐change and an acceptable q‐value (0.05).” “All data are available via ProteomeXchange with identifier PXD021406.”"}}], "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 (N-termini were filtered by log2 fold-change and an acceptable q-value (0.05). Source data were available through ProteomeXchange under identifier PXD021406.), 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": ["PXD021406"], "resolved_accessions": ["PXD021406"], "statements": ["All data are available via ProteomeXchange with identifier PXD021406."], "basis": "The paper names PXD021406 in ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33111431", "data:geo:PXD021406"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD021406"]}, "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": "2026-10-31T18:23:39Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 16375, "completion_tokens": 1124, "cached_tokens": 528}}, "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:33111431", "type": "paper", "label": "pmid:33111431"}, {"id": "source:pmid:33111431", "type": "manuscript", "label": "PMID 33111431 full text"}, {"id": "data:geo:PXD021406", "type": "dataset", "label": "GEO PXD021406"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33111431", "type": "paper", "label": "pmid:33111431"}, {"id": "source:pmid:33111431", "type": "manuscript", "label": "PMID 33111431 full text"}, {"id": "data:geo:PXD021406", "type": "dataset", "label": "GEO PXD021406"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33111431", "type": "extraction", "used": ["source:pmid:33111431"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD021406", "type": "accession_resolution", "used": ["data:geo:PXD021406"], "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:33111431", "parent_hash": "sha256:bf12b3b3624236231984ceaed2d935e8049a6941c95d5418c9a3dcf44cafc8d3", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD021406 licence not read", "asset:data:geo:PXD021406 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["s and will help to identify novel substrates in vivo. All data are available via ProteomeXchange"], "order_basis": "paper_text_order:1213", "id": "assay:1"}]}