back icon
close icon

Capture phrases in quotes for more specific queries (e.g. "rocket ship" or "Fred Lynn")

  December 1, 2020

Transformer Based Molecule Encoding for Property Prediction

SRI Authors Andrew Silberfarb, John Byrnes

Citation

COPY

Prateeth Nayak, Andrew Silberfarb, Ran Chen, Tulay Muezzinoglu and John Byrnes, (September, 2020) Transformer based Molecule Encoding for Property Prediction, SRI International.

Abstract

Neural methods of molecule property prediction require efficient encoding of structure and property relationship to be accurate. Recent work using graph algorithms shows limited generalization in the latent molecule encoding space. We build a Transformer-based molecule encoder and property predictor network with novel input featurization that performs significantly better than existing methods. We adapt our model to semi-supervised learning to further perform well on the limited experimental data usually available in practice.

How can we help?

    Once you hit send…

    We’ll match your inquiry to the person who can best help you. Expect a response within 48 hours.

    Our Privacy Policy