PROTAC-PatentDB: A PROTAC Patent Compound Dataset.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41261151", "kind": "science-record", "revision": 1, "content_hash": "sha256:ba6662495a88810fb82a30299e898a521f3df449519de71544eb6fdb9bda53f1", "created_at": "2026-11-01T20:31:17Z", "updated_at": "2026-11-01T20:31:17Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PROTAC-PatentDB: A PROTAC Patent Compound Dataset.", "doi": "10.1038/s41597-025-06136-9", "pmid": "41261151", "authors": ["Hong Cai", "Gengyuan Yao", "Yulong Shi", "Tianyi Zhang", "Yuanjia Hu"], "journal": "Scientific data", "year": 2025, "abstract": "Proteolysis-targeting chimeras (PROTAC) are emerging and promising molecules for targeted protein degradation which have the potential to overcome critical bottlenecks in traditional small molecule drug development. However, the scarcity of publicly available data on molecular compound structures has significantly hindered computational drug discovery and AI-aided drug discovery/design (AIDD) in this field. Patents are an important but underutilized source of novel chemical structures in medicinal chemistry. In this study, we collected PROTAC patents published in 2013-2023 and the associated chemical structures disclosed therein. Through manual screening and expert curation, we identified 63,136 unique PROTAC compounds under 590 patent families, along with 252 targets. Additionally, we employed the ADMETlab 3.0 platform to predict 120 physicochemical properties for all compounds. The dataset is publicly available on the Figshare platform, and an online webserver ( http://protacpatentdb.com ) has also been established. Given the rapid growth of PROTAC patent literature, this dataset can be further expanded as new patents are continuously published.", "claims": [{"id": "claim-data-access", "statement": "The dataset has been deposited in the repository Figshare and is available for unrestricted access via the following link: 10.6084/m9.figshare.2935132114. It can also be accessed through an interactive webserver: PROTAC-PatentDB (http://protacpatentdb.com).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41261151", "locator": "sections[19] \"notes\" paragraph 1", "quote": "The dataset has been deposited in the repository Figshare and is available for unrestricted access via the following link: 10.6084/m9.figshare.2935132114. It can also be accessed through an interactive webserver: PROTAC-PatentDB (http://protacpatentdb.com)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 63,136 unique PROTAC compounds under 590 patent families, covering 252 targets, and predicted 120 physicochemical properties for all compounds.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41261151", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Through manual screening and expert curation, we identified 63,136 unique PROTAC compounds under 590 patent families, along with 252 targets. Additionally, we employed the ADMETlab 3.0 platform to predict 120 physicochemical properties for all compounds."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study identified 63,136 unique PROTAC compounds under 590 patent families, covering 252 targets, and predicted 120 physicochemical properties for all compounds.", "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:41261151"], "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:41261151", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41597-025-06136-9", "sha256": "sha256:e943cb43ae2a230bfb5788e658a5b3e8d5487bd5db9729688a3ecb8ed507e32e", "bytes": 33978, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41597-025-06136-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12630821", "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": ["The dataset has been deposited in the repository Figshare and is available for unrestricted access via the following link: 10.6084/m9.figshare.2935132114. It can also be accessed through an interactive webserver: PROTAC-PatentDB (http://protacpatentdb.com)."], "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:41261151"], "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": "2026-11-01T20:06:05Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8316, "completion_tokens": 1245, "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:41261151", "type": "paper", "label": "pmid:41261151"}, {"id": "source:pmid:41261151", "type": "manuscript", "label": "PMID 41261151 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41261151", "type": "paper", "label": "pmid:41261151"}, {"id": "source:pmid:41261151", "type": "manuscript", "label": "PMID 41261151 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41261151", "type": "extraction", "used": ["source:pmid:41261151"], "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"]}