Drug discovery projects entail cycles of design, synthesis, and testing that
yield a series of chemically related small molecules whose properties, such as
binding affinity to a given target protein, are progressively tailored to a
particular drug discovery goal. The use of deep learning technologies could
augment the typical practice of using human intuition in the design cycle, and
thereby expedite drug discovery projects. Here we present DESMILES, a deep
neural network model that advances the state of the art in machine learning
approaches to molecular design. We applied DESMILES to a previously published
benchmark that assesses the ability of a method to modify input molecules to
inhibit the dopamine receptor D2, and DESMILES yielded a 77% lower failure rate
compared to state-of-the-art models. To explain the ability of DESMILES to hone
molecular properties, we visualize a layer of the DESMILES network, and further
demonstrate this ability by using DESMILES to tailor the same molecules used in
the D2 benchmark test to dock more potently against seven different receptors.
Description
A deep-learning view of chemical space designed to facilitate drug discovery
%0 Journal Article
%1 maragakis2020deeplearning
%A Maragakis, Paul
%A Nisonoff, Hunter
%A Cole, Brian
%A Shaw, David E.
%D 2020
%K chemical deep discovery drug generative global learning model optimization space
%T A deep-learning view of chemical space designed to facilitate drug
discovery
%U http://arxiv.org/abs/2002.02948
%V abs/2002.02948
%X Drug discovery projects entail cycles of design, synthesis, and testing that
yield a series of chemically related small molecules whose properties, such as
binding affinity to a given target protein, are progressively tailored to a
particular drug discovery goal. The use of deep learning technologies could
augment the typical practice of using human intuition in the design cycle, and
thereby expedite drug discovery projects. Here we present DESMILES, a deep
neural network model that advances the state of the art in machine learning
approaches to molecular design. We applied DESMILES to a previously published
benchmark that assesses the ability of a method to modify input molecules to
inhibit the dopamine receptor D2, and DESMILES yielded a 77% lower failure rate
compared to state-of-the-art models. To explain the ability of DESMILES to hone
molecular properties, we visualize a layer of the DESMILES network, and further
demonstrate this ability by using DESMILES to tailor the same molecules used in
the D2 benchmark test to dock more potently against seven different receptors.
@article{maragakis2020deeplearning,
abstract = {Drug discovery projects entail cycles of design, synthesis, and testing that
yield a series of chemically related small molecules whose properties, such as
binding affinity to a given target protein, are progressively tailored to a
particular drug discovery goal. The use of deep learning technologies could
augment the typical practice of using human intuition in the design cycle, and
thereby expedite drug discovery projects. Here we present DESMILES, a deep
neural network model that advances the state of the art in machine learning
approaches to molecular design. We applied DESMILES to a previously published
benchmark that assesses the ability of a method to modify input molecules to
inhibit the dopamine receptor D2, and DESMILES yielded a 77% lower failure rate
compared to state-of-the-art models. To explain the ability of DESMILES to hone
molecular properties, we visualize a layer of the DESMILES network, and further
demonstrate this ability by using DESMILES to tailor the same molecules used in
the D2 benchmark test to dock more potently against seven different receptors.},
added-at = {2020-02-21T21:00:28.000+0100},
author = {Maragakis, Paul and Nisonoff, Hunter and Cole, Brian and Shaw, David E.},
biburl = {https://www.bibsonomy.org/bibtex/2bc610aa4fcfa070de079929391bcd5ca/plm},
description = {A deep-learning view of chemical space designed to facilitate drug discovery},
interhash = {c9c90ea9b70bf0e8f28f6178f449f32c},
intrahash = {bc610aa4fcfa070de079929391bcd5ca},
keywords = {chemical deep discovery drug generative global learning model optimization space},
note = {cite arxiv:2002.02948},
timestamp = {2020-02-21T21:00:28.000+0100},
title = {A deep-learning view of chemical space designed to facilitate drug
discovery},
url = {http://arxiv.org/abs/2002.02948},
volume = {abs/2002.02948},
year = 2020
}