Dr Vidhi Lalchand, an adjunct postdoctoral scientist at Sixfold Bioscience, postdoctoral researcher at Cambridge University and an Eric and Wendy Schmidt center fellow at the Broad Institute of MIT and Harvard, will participate in the ICML 2024 Next Generation of Sequence Modeling Architectures workshop, with the following poster presentation:  

‍

Recurrent VAE with Gaussian Process Decoders for De Novo Molecular Generation

Authors: Vidhi L^1,2,3, Lines D¹; Perdrix Rosell A¹, Lawrence, N²

Affiliations: ¹Sixfold Bioscience Ltd, ²University of Cambridge, ³Broad Institute of MIT & Harvard

‍

Workshop on Next Generation of Sequence Modeling Architectures

Fri 26 Jul, 9 a.m. CEST - Straus 3, Messe Wien Exhibition Congress Center, Vienna, Austria

‍

Abstract

This work proposes a variational sequential architecture based on recurrent neural nets for de novo drug design. The variational autoencoding framework induces a compressed continuous representation of discrete molecules through a low-dimensional latent space. The continuous latent space allows for optimisation, interpolation, unconditional and conditional generation of novel molecules through gradient-based techniques. However, the success of gradient-based optimisation is tied to the structure and smoothness of the latent space and this is precisely what we target through our generative architecture. Beyond structure generation we leverage nonparametric Gaussian process (GP) decoders for the auxiliary task of property prediction on the shared latent space. Training the architecture on shared latent embeddings for both structure and property generation enforces a soft stratification of the latent space as a function of the properties making it amenable to gradient-based optimisation of objectives tied to molecular properties. We moderate the smoothness of the non-parametric GP decoder with the choice of the kernel function. We demonstrate several capabilities of our generative architecture on widely used benchmark datasets of small drug-like molecules - the ZINC-250K and the QM9 dataset with fewer than nine heavy atoms. 

‍

About ICML

The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics.ICML is one of the fastest growing artificial intelligence conferences in the world. Along with NeurIPS and ICLR, it is one of the three primary conferences of high impact in machine learning and artificial intelligence research. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

‍

Sixfold Bioscience is solving one of the most critical challenges preventing the greater utilisation of RNA: delivery. Using advanced AI/ML, automated chemistry and high throughput screening, Sixfold is learning the language that encodes RNA destination and unlocking new cell types for treatment.

‍