logo
ResearchBunny Logo
Autonomous design of new chemical reactions using a variational autoencoder

Chemistry

Autonomous design of new chemical reactions using a variational autoencoder

R. Tempke and T. Musho

This groundbreaking study by Robert Tempke and Terence Musho explores the bias in current chemical reaction datasets, introducing AGoRaS, an AI model that generates over 7 million synthetic reactions from a mere 7,000, enhancing diversity and applicability in molecular research.

00:00
00:00
Playback language: English
Abstract
This study addresses the inherent bias in existing chemical reaction datasets by developing an AI model based on a Variational AutoEncoder (VAE) to synthetically generate a larger, more comprehensive dataset. The model, AGoRaS, generates over 7,000,000 new reactions from a training set of only 7,000, including larger and more diverse molecular species than in the original dataset.
Publisher
Communications Chemistry
Published On
Mar 22, 2022
Authors
Robert Tempke, Terence Musho
Tags
chemical reactions
AI model
Variational AutoEncoder
synthetic dataset
molecular species
data bias
AGoRaS

Related Publications

Explore these studies to deepen your understanding of the subject.

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets
Medicine and Health

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets

X. Xue, S. Chinnaperumal, et al.

Design of a recombinant asparaginyl ligase for site-specific modification using efficient recognition and nucleophile motifs
Biology

Design of a recombinant asparaginyl ligase for site-specific modification using efficient recognition and nucleophile motifs

J. Tang, M. Hao, et al.

AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning
Chemistry

AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning

A. A. Volk, R. W. Epps, et al.

Design and assessment of a teaching program to address temporal concepts in Early Childhood Education and Primary Education using stories
Education

Design and assessment of a teaching program to address temporal concepts in Early Childhood Education and Primary Education using stories

V. Vivas-moreno, P. Miralles-martínez, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny