The ChEMBL-og

  AI-driven bioassay annotation strategy The continued expansion of ChEMBL bioactivity data makes high-quality, structured assay metadata essential for reproducible analysis and machine-learning applications aligned with FAIR principles. Recent work by our team  published in J. Cheminf. describes coordinated manual and AI-driven strategies to enhance the annotation, classification, and interoperability of ChEMBL bioassays.  In this work, we have developed a spaCy-based named entity recognition (NER) model trained on manually curated assay descriptions to identify the Experimental Method within ChEMBL assay descriptions. The model achieved cross-validated precision, recall, and F1-scores of approximately 0.93, 0.95, and 0.94, respectively, and detected experimental methods in ~57 % of binding and functional assays in ChEMBL 35. Extracted method terms were subsequently mapped to the Bioassay Ontology (BAO) , demonstrating good precision at higher confidence thresholds bu...

We are excited to announce the start of the LIGAND-AI project, a 5-year project involving 18 partners to find ligands for thousands of understudied protein targets. This project, led by the SGC (Structural Genomics Consortium) and Pfizer, is part of the SGC Target 2035 strategy to discover chemical modulators for every human protein by the year 2035. There are press releases on the EMBL-EBI and SGC webpages with additional information. Let's begin with chemical probes. These are potent and selective small molecules used to pharmacologically modulate a protein's function. These are not necessarily the starting point of a drug discovery campaign (though they may be); what they allow is the study of the target and investigation of its function. The key point is that for many protein targets we do not have a chemical probe, nor do we know their function. Targets without a chemical probe tend to be understudied as the lack of a chemical probe rules out many studies, and it ca...

    Drug modalities continue to evolve and the capture of data from recent literature ensures that ChEMBL remains up-to-date with recent developments. Drugs and clinical candidates in ChEMBL undergo enhanced curation , including annotation of their drug mechanisms (the therapeutic target with a role in disease efficacy and the action type of the drug against the entity, e.g. INHIBITOR). Classical small-molecule modulators typically bind to the active site of a target, leading to either a loss or, in some cases, an increase in protein function. More recently, emerging strategies such as Targeted Protein Degradation (TPD) have gained traction and instead remove (degrade) the target. The growing body of TPD data in ChEMBL will be discussed in this blog post.    Targeted Protein Degraders ( PROTACs ) from the ChEMBL database. To explore TPD data in ChEMBL, we’ve used a combination of TPD-relevant keywords and effector protein accessions (UniProt). If you’re interested in...

I am delighted to announce that registration is open for the 2nd ChEMBL User Group Meeting , which is dedicated to building and supporting the ChEMBL and SureChEMBL user communities. The last meeting took place in 2011, so it feels like it might be time for a second :-). The UGM will take place on 10-11 June here on the Wellcome Genome Campus, Hinxton, near Cambridge, UK. It is a two-day event, with participant numbers limited for Day 2. Day 1 (Hybrid, in-person recommended): Talks, discussions, and networking, followed by an evening reception with drinks. Lunch will be provided. Day 2 (In-person only): A chance to influence the future development of ChEMBL and SureChEMBL. Deeper community sessions together with the ChEMBL and SureChEMBL teams, discussion of collaboration opportunities. As a community event, we encourage poster and oral presentations from community members on any topic related to the use of ChEMBL or SureChEMBL. Please indicate when registering if you would like...

Over the years, ChEMBL has accepted 336 datasets deposited by the community. In fact, these data now comprise around 50% of the bioactivity data points. This is in addition to ChEMBL’s core data, bioactivity data extracted from the medicinal chemistry literature, and drug and clinical candidate data curated from regulatory authorities and clinical trials. However, ChEMBL - like many other open access databases - is currently facing a reduction in funding. While we remain committed to maintaining the core of ChEMBL’s literature-extracted bioactivity data as well as drug data annotations, these constraints mean that in the future we may not be able to accept data depositions unless they are accompanied by appropriate funding. This applies particularly to those that require extensive curation or substantial manual intervention (*). Any depositions that have been agreed or are already in progress will be handled as planned. Beyond this, we will continue to prioritise depositions that a...

  photo by B. Zdrazil, Wellcome Genome Campus in morning glory, Dec. 2025 The Chemical Biology Services Team is looking back at a year full of changes, new beginnings, and the farewell of a few long-standing team members. In February, we welcomed our new Team Leader Noel O'Boyle . He brought fresh perspectives and new energy to the team, but he also had to see several team members leave as they reached the end of their contracts. We are grateful for all the contributions that Eloy Felix, Fiona Hunter, David Mendez, Juan Mosquera, A. Lina Heinzke, Cote Falguera, Melanie Schneider, and Sybilla Corbett have made to our great resources: ChEMBL, SureChEMBL, ChEBI & UniChem.  2025 has been a very productive year! OPSIN found a new home under the EBI umbrella, ChEMBL 36 - the largest data release for ChEMBL ever - was released in autumn, ChEBI 2.0 was launched and its restructuring has been published in a recent NAR article . The team also made some great advances to push ...