Call for data on the permeability of Gram-negative bacteria

The AMR Accelerator is looking for data and needs YOUR help!
Our Scientific Interest Group in Machine Learning needs datasets to build a permeability prediction model for Gram-negative bacteria. Membrane permeability is a major barrier to antibiotic efficacy in Gram-negative pathogens. By enabling the in silico pre-selection of compounds with favourable permeability profiles, we aim to reduce time and cost in early-stage drug discovery and gain a better understanding of the underlying determinants of compound uptake.

We aim to build a machine learning model that predicts the permeability of compounds across Gram-negative bacterial membranes based on chemical structure. The model may incorporate both classical algorithms and deep learning approaches. Depending on the available data, we may develop species-specific models or train across species to improve generalisability.

If you have suitable datasets, fill out this form, and we will contact you!

Take me to the form

We are looking for experimental datasets that capture how well small-molecule compounds permeate Gram-negative bacteria – ideally through direct measurements of uptake or accumulation, but we also welcome MIC values or other relevant proxy readouts where direct permeability is not available:

  • Measurements of compound uptake
  • Measurements of compound accumulation
  • Related surrogate endpoints (e.g. MIC shifts in efflux-deficient strains) ideally linked to chemical structure (e.g. SMILES).

Escherichia coli, Pseudomonas aeruginosa, Klebsiella pneumoniae, or any other clinically relevant Gram-negative species are all welcome.

Beyond the general goals of improving early-stage antibiotic drug discovery, you might also find some direct benefits:

  • BECOME A CO-AUTHOR: We are planning a joint publication to present the model and its findings, and all data contributors will be invited to co-author or be acknowledged, depending on preference and level of contribution.
  • GET AN EARLY PREVIEW OF THE RESULTS: As a data contributor, you will get access to the results of the analyses before they are made public.
  • GET MORE OUT OF YOUR DATA: Should we identify new findings specifically from your data, we will engage with you. We may also consider running specific analyses on your data upon your request, if they are within the scope of COMBINE.
  • GET INVOLVED IN THE ANALYSIS: Do you have a research question you were never able to answer using your available resources? Let us know: maybe we can investigate it on your data!
  • IMPROVE YOUR OVERALL DATA MANAGEMENT PROCESS: We can provide hands-on training on FAIRification of data for SME and academia – a process that is now increasingly becoming a pre-requisite imposed by funding agencies for grant application.

The COMBINE researchers are committed to the highest standards of data security and protection to preserve the rights of data providers and the personal rights and interests of all study participants, particularly in cases involving sensitive clinical data. We plan to only collect data that is either published, the source data of aggregated published data, or data that is planned to be published. Please contact Leonie von Berlin (leonie.von.berlin@itmp.fraunhofer.de) for more details and technical questions on data protection and FAIRification.

Fill out this form, and we will contact you! For technical questions on data protection and FAIRification, please contact Leonie von Berlin (leonie.von.berlin@itmp.fraunhofer.de). For questions, ideas and suggestions regarding the AMR Accelerator Scientific Interest Group in Machine Learning, please contact Frederik Deroose (frederik@connectingpharma.be).

About the AMR Accelerator

The AMR Accelerator programme was launched in 2019, with the aim to accelerate the development of medicines for patients suffering from infections with drug-resistant Mycobacterium tuberculosis, nontuberculous mycobacteria (NTM), and Gram-negative bacteria, and build capability for antibiotics research and development. The programme is funded by the Innovative Medicines Initiative (IMI). The AMR Accelerator programme includes nine projects: AB-Direct, COMBINE, ERA4TB, GNA NOW, PrIMAVeRa, RespiriNTM, RespiriTB, TRIC-TB, and UNITE4TB. Together, the projects have a €479 million budget. The 98 partners represent key stakeholders from academia, industry, small- and medium-sized companies, patient organisations, regulators, and Health Technology Assessment.

About COMBINE

COMBINE has a coordinating role in the AMR Accelerator, and a scientific mission aiming to improve 1) the design and analysis of clinical trials, and 2) animal infection model reproducibility and translation to clinical efficacy. COMBINE has received funding from the Innovative Medicines Initiative 2 Joint Undertaking under Grant Agreement No 853967.