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 can be seen from the literature that once a probe is found, the number of studies increases. Apart from the importance of this basic biomedical research, in some cases this may lead to new therapies.
The previous SGC Target 2035 project, EUbOPEN, was all about finding new chemical probes, characterising them, and making that information available. It just finished in Oct 2025 and was very successful, finding something like 200 probes over the lifetime of the project.
However, to meet the goals of Target 2035, LIGAND-AI needs to scale things up by taking a different approach, one that combines large scale screening with AI. The screening will be done using DNA-encoded libraries (DEL) as well as with affinity selection mass spectrometry (ASMS). For the first time the raw output from DEL screens will be made available for use with machine learning, via the AIRCHECK platform. Note that the same DEL library will be run across all protein targets (potentially thousands of them) which will help with false positive detection. It is expected that these data will help spur the development of new ML approaches to analyse DEL data to identify binders.
The ambition, scale and potential of this project is very impressive, and we are very much looking forward to being a part of it. If these data sound of interest, and you want to get involved, you are encouraged to join MAINFRAME, the community of ML researchers associated with AIRCHECK. Looking forward to seeing what the next 5 years brings!
Comments