The heterogeneous pharmacological medical biochemical network PharMeBINet.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35821017", "kind": "science-record", "revision": 2, "content_hash": "sha256:35aea6edea50ac674c8bd9cf4257e5f66aa9069041717333acf9bf3cc3d28558", "created_at": "2026-11-01T18:14:53Z", "updated_at": "2026-11-01T18:59:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "The heterogeneous pharmacological medical biochemical network PharMeBINet.", "doi": "10.1038/s41597-022-01510-3", "pmid": "35821017", "authors": ["Cassandra Königs", "Marcel Friedrichs", "Theresa Dietrich"], "journal": "Scientific data", "year": 2022, "abstract": "Heterogeneous biomedical pharmacological databases are important for multiple fields in bioinformatics. Hetionet is a freely available database combining diverse entities and relationships from 29 public resources. Therefore, it is used as the basis for this project. 19 additional pharmacological medical and biological databases such as CTD, DrugBank, and ClinVar are parsed and integrated into Neo4j. Afterwards, the information is merged into the Hetionet structure. Different mapping methods are used such as external identification systems or name mapping. The resulting open-source Neo4j database PharMeBINet has 2,869,407 different nodes with 66 labels and 15,883,653 relationships with 208 edge types. It is a heterogeneous database containing interconnected information on ADRs, diseases, drugs, genes, gene variations, proteins, and more. Relationships between these entities represent drug-drug interactions or drug-causes-ADR relations, to name a few. It has much potential for developing further data analyses including machine learning applications. A web application for accessing the database is free to use for everyone and available at https://pharmebi.net . Additionally, the database is deposited on Zenodo at https://doi.org/10.5281/zenodo.6578218 .", "claims": [{"id": "claim-data-access", "statement": "The script to generate PharMeBINet is available from Zenodo52 and from GitHub https://github.com/ckoenigs/PharMeBINet. The repository contains python (3.8.5) programs and bash (4.4.20) scripts to execute all python programs, download databases, and execute the Neo4j Cypher tool. The website is available at https://pharmebi.net. The download of PharMeBINet is provided on the website.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35821017", "locator": "sections[15] \"Code availability\" paragraph 2", "quote": "The script to generate PharMeBINet is available from Zenodo52 and from GitHub https://github.com/ckoenigs/PharMeBINet. The repository contains python (3.8.5) programs and bash (4.4.20) scripts to execute all python programs, download databases, and execute the Neo4j Cypher tool. The website is available at https://pharmebi.net. The download of PharMeBINet is provided on the website."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The resulting open-source Neo4j database PharMeBINet has 2,869,407 different nodes with 66 labels and 15,883,653 relationships with 208 edge types.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35821017", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The resulting open-source Neo4j database PharMeBINet has 2,869,407 different nodes with 66 labels and 15,883,653 relationships with 208 edge types."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The resulting open-source Neo4j database PharMeBINet has 2,869,407 different nodes with 66 labels and 15,883,653 relationships with 208 edge types.", "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:35821017"], "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:35821017", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41597-022-01510-3", "sha256": "sha256:53ed9e7f24f7c6932e146bb017202e02f47fb6e1109166e2d274d92c1ff7402c", "bytes": 64615, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41597-022-01510-3", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9276653", "source": "europe_pmc_fulltext", "coverage": "whole_body", "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 script to generate PharMeBINet is available from Zenodo52 and from GitHub https://github.com/ckoenigs/PharMeBINet. The repository contains python (3.8.5) programs and bash (4.4.20) scripts to execute all python programs, download databases, and execute the Neo4j Cypher tool. The website is available at https://pharmebi.net. The download of PharMeBINet is provided on the website."], "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:35821017"], "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": "2026-11-01T17:54:55Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 17218, "completion_tokens": 1519, "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:35821017", "type": "paper", "label": "pmid:35821017"}, {"id": "source:pmid:35821017", "type": "manuscript", "label": "PMID 35821017 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35821017", "type": "paper", "label": "pmid:35821017"}, {"id": "source:pmid:35821017", "type": "manuscript", "label": "PMID 35821017 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35821017", "type": "extraction", "used": ["source:pmid:35821017"], "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": "pmid:35821017", "parent_hash": "sha256:f4fd030ead266c8dbc72fe6d5d1f963eca4c5a666e34933d77ae50c0d378f617", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}