Iambic Therapeutics, a pioneering biotechnology company renowned for its cutting-edge generative AI discovery platform, has unveiled research published in Nature Machine Intelligence, showcasing the superior performance of its NeuralPLexer technology. The study demonstrates NeuralPLexer's remarkable capability in predicting the structure of protein-ligand complexes and anticipating conformational changes induced by the addition of drug molecules.

Tom Miller, PhD, CEO of Iambic Therapeutics and co-author of the paper, stated: “Our benchmarking shows we have set a new standard for predicting protein-ligand binding, directly generating 3D coordinates for full binding complexes, rapidly making available new reference structures, while improving prediction accuracy for novel targets and large-scale in silico screening.” “NeuralPLexer is allowing us to discover pharmacological patterns for increasingly complex protein targets and target areas and achieve unprecedented selectivity, novel mechanisms of structural engagement, the ability to expand patient populations by adding multiple target mutations as well as identify new mechanisms of action at protein-protein interfaces and at other unspecified sites. We are now generating structures that once took many months and significant investment to generate in just a matter of seconds.”

The peer-reviewed manuscript, titled "State-specific protein-ligand complex structure prediction with a multi-scale deep generative model," emerged from a collaborative effort between scientists at Iambic, Caltech, and NVIDIA, marking a significant milestone in the realm of biotechnology.

While AI-driven systems have made notable strides in predicting 3D protein structures, NeuralPLexer stands out by forecasting the conformational response of proteins to ligand binding, a critical aspect for comprehending the impact of drug molecules on protein function.

Furthermore, the company has unveiled a white paper spotlighting the advancements in its next-generation NeuralPLexer2. Trained in October 2023, NeuralPLexer2 has already exhibited substantial enhancements in prediction accuracy, scaling the model to include various categories of biological structures, from protein-protein complexes to protein-nucleic acid complexes, encompassing almost all structures in the Protein Data Bank (PDB).

Iambic Therapeutics harnesses NeuralPLexer in developing its pipeline, notably IAM1363, a promising small molecule inhibitor designed to target HER2 wildtype and oncogenic mutant proteins with exceptional selectivity. IAM1363 has demonstrated over 1000-fold selectivity for HER2 compared to EGFR in preclinical studies, showcasing its potential to avoid toxicities associated with off-target inhibition.

Rory Kelleher, Global Head of Business Development for Life Sciences at NVIDIA, said: “Iambic’s NeuralPLexer2 is pushing the boundaries of generative AI in 3D protein prediction, helping to enable new capabilities by accurately representing how structures alter their shape as a result of drug interactions.”“These advances demonstrate the possibilities of a new era of computer-aided drug discovery that aims to accelerate the process as well as develop better drug candidates – and, as part of this movement, Iambic’s innovations are being translated into important new medicines for patients.”

‍