ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction
Conference
·
OSTI ID:1415704
With access to large datasets, deep neural networks through representation learning have been able to identify patterns from raw data, achieving human-level accuracy in image and speech recognition tasks. However, in chemistry, availability of large standardized and labelled datasets is scarce, and with a multitude of chemical properties of interest, chemical data is inherently small and fragmented. In this work, we explore transfer learning techniques in conjunction with the existing Chemception CNN model, to create a transferable and generalizable deep neural network for small-molecule property prediction. Our latest model, ChemNet learns in a semi-supervised manner from inexpensive labels computed from the ChEMBL database. When fine-tuned to the Tox21, HIV and FreeSolv dataset, which are 3 separate chemical tasks that ChemNet was not originally trained on, we demonstrate that ChemNet exceeds the performance of existing Chemception models, contemporary MLP models that trains on molecular fingerprints, and it matches the performance of the ConvGraph algorithm, the current state-of-the-art. Furthermore, as ChemNet has been pre-trained on a large diverse chemical database, it can be used as a universal “plug-and-play” deep neural network, which accelerates the deployment of deep neural networks for the prediction of novel small-molecule chemical properties.
- Research Organization:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 1415704
- Report Number(s):
- PNNL-SA-129942
- Country of Publication:
- United States
- Language:
- English
Similar Records
Using Rule-Based Models for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction
How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?
On the Generalizability of Time-of-Flight Convolutional Neural Networks for Noninvasive Acoustic Measurements
Conference
·
Sun Aug 19 00:00:00 EDT 2018
·
OSTI ID:1764978
How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?
Conference
·
Mon May 07 00:00:00 EDT 2018
·
OSTI ID:1558182
On the Generalizability of Time-of-Flight Convolutional Neural Networks for Noninvasive Acoustic Measurements
Journal Article
·
Fri May 31 20:00:00 EDT 2024
· Sensors
·
OSTI ID:2433939