Advances in AI Platform Provide an Ability to Rapidly Predict, Identify and Design Biomolecular Structures to Accelerate the Pace and Reduce the Cost of Drug Discovery and Development
Iambic Therapeutics, a biotechnology company developing novel therapeutics using its unique generative AI discovery platform, announced the publication of research in Nature Machine Intelligence showing that its NeuralPLexer technology outperforms other state-of-the art systems in predicting the structure of protein-ligand complexes as well as the conformational changes to these structures from the addition of drug molecules.
“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,” said Tom Miller, PhD, Iambic Therapeutic’s CEO and co-author of the paper. “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, State-specific protein-ligand complex structure prediction with a multi-scale deep generative model, was published online today and was the result of a collaboration between scientists at Iambic, Caltech and NVIDIA.
While there has been great progress in using AI-driven systems to predict 3D protein structures, NeuralPLexer is advancing the field by predicting the conformational response of proteins on ligand binding, which is essential for understanding the impact of drug molecules on protein function.
The Company today also released a white paper highlighting the improvements in its next-generation NeuralPLexer2. Trained in October 2023, NeuralPLexer2 has already demonstrated significant improvements in the technology’s prediction accuracy and has scaled the model to include most categories of biological structures adding protein-protein complexes, cofactors, post-translational modifications (PTMs), and protein-nucleic acid complexes, and encompassing almost all structures in the Protein Data Bank (PDB).
Iambic Therapeutics uses NeuralPLexer in building its own pipeline, including the discovery of IAM1363, a selective and brain-penetrant small molecule inhibitor of HER2 wildtype and oncogenic mutant proteins, designed to expand therapeutic index compared to available HER2 inhibitors and to avoid toxicities from off-target inhibition of EGFR, a related receptor tyrosine kinase. In preclinical studies, IAM1363 has demonstrated over 1000-fold selectivity for HER2 compared to EGFR. An IND for IAM1363 was recently accepted by FDA and clinical trials are planned to commence in early 2024 – a timeline that has the drug candidate moving from program start to clinical studies in under two years.
“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,” said Rory Kelleher, Global Head of Business Development for Life Sciences at NVIDIA. “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.”
SOURCE: BusinessWire
