Gram-negative membrane permeability is a major bottleneck in antibiotic discovery. We team up to combine models and data for improved permeability prediction and compound prioritisation.
\nWithin the AMR Accelerator, the COMBINE project coordinates an established Scientific Interest Group in Machine Learning, bringing together academic and industry partners to develop predictive models for Gram-negative permeability. Building on existing work by partners (Gadiya et al. 2025; Le Goff et al. 2025; Scalia et al. 2025), we combine complementary datasets and tools to enable the in silico prioritisation of compounds from large screening libraries.
\nBy pooling resources across the AMR Accelerator community, we aim to reduce time and cost in early-stage antibiotic discovery and improve our understanding of the determinants of compound uptake in Gram-negative bacteria.
\nThe AMR Accelerator is looking for data. We need YOUR help! Following our successful Antibacterial property prediction ML model we now seek experimental datasets that inform on compound permeability in Gram-negative bacteria. This includes direct measurements such as uptake or accumulation assays, as well as relevant proxy readouts (e.g. MIC-based data) where direct permeability measurements are not available. We also welcome expertise, tools, and methodologies related to permeability assessment, data analysis, or predictive modeling.
\nPrevious work using public data sets to build Antibacterial property prediction ML models. See DOI: 10.1021/acs.jcim.4c02347
\nContact Leonie von Berlin (Fraunhofer ITMP, leonie.von.berlin@itmp.fraunhofer.de) or scan the QR code for more information!
", "funding": [ { "award": { "acronym": "COMBINE", "id": "00k4n6c32::853967", "identifiers": [ { "identifier": "https://cordis.europa.eu/projects/853967", "scheme": "url" } ], "number": "853967", "program": "H2020-EU.3.1.", "title": { "en": "Collaboration for Prevention and Treatment\nof MDR Bacterial Infections" } }, "funder": { "id": "00k4n6c32", "name": "European Commission" } } ], "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2026-03-03", "publisher": "Zenodo", "references": [ { "reference": "https://pubs.acs.org/doi/10.1021/acs.jcim.4c02347" } ], "resource_type": { "id": "poster", "title": { "de": "Poster", "en": "Poster" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "subjects": [ { "id": "euroscivoc:1437", "identifiers": [ { "identifier": "http://data.europa.eu/8mn/euroscivoc/54ca0648-4321-4706-912c-46955e303049", "scheme": "url" } ], "props": { "parents": "euroscivoc:21,euroscivoc:35,euroscivoc:159,euroscivoc:649" }, "scheme": "EuroSciVoc", "subject": "Antibiotic resistance" }, { "id": "euroscivoc:8052398", "identifiers": [ { "identifier": "http://data.europa.eu/8mn/euroscivoc/2ad97719-f178-4451-8311-022eb5a96b91", "scheme": "url" } ], "props": { "parents": "euroscivoc:21,euroscivoc:35,euroscivoc:159,euroscivoc:653" }, "scheme": "EuroSciVoc", "subject": "Antibiotics" }, { "id": "mesh:D006090", "scheme": "MeSH", "subject": "Gram-Negative Bacteria" }, { "id": "euroscivoc:933", "identifiers": [ { "identifier": "http://data.europa.eu/8mn/euroscivoc/527ab165-56f2-4020-8975-e7cd3f21d01d", "scheme": "url" } ], "props": { "parents": "euroscivoc:23,euroscivoc:47,euroscivoc:297" }, "scheme": "EuroSciVoc", "subject": "Machine learning" }, { "id": "mesh:D000069550", "scheme": "MeSH", "subject": "Machine Learning" }, { "subject": "Antibacterial Property Prediction" }, { "subject": "Membrane Permeability" } ], "title": "Tackling the Gram-Negative Permeability Barrier Through Collaborative Data-Driven Prediction", "version": "v1" }, "parent": { "access": { "owned_by": { "user": "1416927" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": { "default": "a2130e43-823c-4cf0-93cd-5d48f66c3b4d", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_submission_policy": "open", "review_policy": "closed", "visibility": "public" }, "children": { "allow": false }, "created": "2025-02-12T12:28:25.184462+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "a2130e43-823c-4cf0-93cd-5d48f66c3b4d", "links": {}, "metadata": { "description": "COMBINE is part of IMI's Antimicrobial Resistance (AMR) Accelerator program with the shared goal of progressing the development of new medicines to treat or even prevent resistant bacterial infections in Europe and worldwide.", "title": "IMI-COMBINE", "type": { "id": "project" }, "website": "https://amr-accelerator.eu/project/combine/" }, "revision_id": 7, "slug": "imi-combine", "updated": "2025-02-12T12:41:51.585128+00:00" } ], "ids": [ "a2130e43-823c-4cf0-93cd-5d48f66c3b4d" ] }, "id": "19221950", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.19221950", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.19221951", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:19221951", "provider": "oai" } }, "revision_id": 8, "stats": { "all_versions": { "data_volume": 19099800.0, "downloads": 24, "unique_downloads": 18, "unique_views": 39, "views": 41 }, "this_version": { "data_volume": 19099800.0, "downloads": 24, "unique_downloads": 18, "unique_views": 39, "views": 41 } }, "status": "published", "swh": {}, "updated": "2026-03-25T14:15:57.081656+00:00", "versions": { "index": 1, "is_latest": true } }