Anyo Labs Publishes Score

Intro

In early 2025, Anyo Labs proudly announced the publication of a ground-breaking paper in the Journal of Chemical Information and Modelling, titled "iScore: A ML-Based Scoring Function for De Novo Drug Discovery" (DOI: 10.1021/acs.jcim.4c02192). The paper introduces Anyo Labs scoring method, a novel machine learning (ML) based scoring function designed to predict the binding affinity of protein–ligand complexes with unprecedented speed and precision. Unlike traditional methods that rely heavily on explicit knowledge of protein–ligand interactions and extensive atomic contact data, iScore leverages a unique set of ligand and binding pocket descriptors. This innovative approach bypasses the time-consuming conformational sampling stage, enabling rapid screening of vast molecular libraries—a critical advancement in navigating the near-infinite chemical space. The development of iScore involved rigorous training and validation using multiple high-quality datasets, including the PDBbind 2020 refined set, CASF 2016, CSAR NRC-HiQ Set1/2, DUD-E, and target fishing datasets. Three distinct ML methodologies were employed: deep neural networks (iScore-DNN), random forest (iScore-RF), and extreme gradient boosting (iScore-XGB). The results demonstrated iScore’s ability to deliver highly accurate binding affinity predictions, setting a new standard for efficiency in de novo drug discovery.

This innovative approach bypasses the time-consuming conformational sampling stage...

Implications

The publication of the Score paper marks a pivotal milestone for Anyo Labs, reinforcing our position as a leader in computational drug discovery. By streamlining the process of evaluating protein–ligand interactions, Score significantly accelerates the identification of promising drug candidates, reducing both time and costs associated with early-stage drug development. This efficiency is particularly impactful given the vast scale of chemical space, which poses a persistent challenge in drug discovery. For the broader scientific community, Score offers a transformative tool that enhances the ability to screen giga-scale molecular libraries with precision. Its independence from detailed atomic interaction data makes it a versatile solution, applicable across diverse protein targets and ligand types. This adaptability positions Score as a potential cornerstone for future drug discovery pipelines, enabling researchers to explore novel therapeutic avenues with greater confidence.

Applied to real-world cases, this efficiency has helped Anyo Labs partner earlier and on more projects than otherwise possible. This helped the company reach out to researchers and even contract research organisations to help implement better efficiency and more sustainable in silico alternatives for drug discovery.

As Anyo Labs continue to refine and expand Score’s applications, we anticipate it will play a central role in shaping the future of precision medicine, delivering faster and more effective solutions to patients worldwide