DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Generalizable, fast, and accurate DeepQSPR with fastprop

Journal Article · · Journal of Cheminformatics

Abstract Quantitative Structure–Property Relationship studies (QSPR), often referred to interchangeably as QSAR, seek to establish a mapping between molecular structure and an arbitrary target property. Historically this was done on a target-by-target basis with new descriptors being devised to specifically map to a given target. Today software packages exist that calculate thousands of these descriptors, enabling general modeling typically with classical and machine learning methods. Also present today are learned representation methods in which deep learning models generate a target-specific representation during training. The former requires less training data and offers improved speed and interpretability while the latter offers excellent generality, while the intersection of the two remains under-explored. This paper introduces , a software package and general Deep-QSPR framework that combines a cogent set of molecular descriptors with deep learning to achieve state-of-the-art performance on datasets ranging from tens to tens of thousands of molecules. provides both a user-friendly Command Line Interface and highly interoperable set of Python modules for the training and deployment of feedforward neural networks for property prediction. This approach yields improvements in speed and interpretability over existing methods while statistically equaling or exceeding their performance across most of the tested benchmarks. is designed with Research Software Engineering best practices and is free and open source, hosted at github.com/jacksonburns/fastprop.

Sponsoring Organization:
USDOE
Grant/Contract Number:
SC0023112
OSTI ID:
2565981
Journal Information:
Journal of Cheminformatics, Journal Name: Journal of Cheminformatics Journal Issue: 1 Vol. 17; ISSN 1758-2946
Publisher:
Springer Science + Business MediaCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (36)

Molecular Descriptors for Chemoinformatics: Volume I: Alphabetical Listing / Volume II: Appendices, References book July 2009
Measuring and predicting sooting tendencies of oxygenates, alkanes, alkenes, cycloalkanes, and aromatics on a unified scale journal April 2018
A systematic method for selecting molecular descriptors as features when training models for predicting physiochemical properties journal August 2022
Uncertainty quantification of a deep learning fuel property prediction model journal December 2023
Deep-Learning Architecture in QSPR Modeling for the Prediction of Energy Conversion Efficiency of Solar Cells journal October 2020
Chemprop: A Machine Learning Package for Chemical Property Prediction journal December 2023
QuantumScents: Quantum-Mechanical Properties for 3.5k Olfactory Molecules journal November 2023
Molecular Contrastive Pretraining with Collaborative Featurizations journal February 2024
Comparative Study of Multitask Toxicity Modeling on a Broad Chemical Space journal December 2018
Computational Model To Predict the Fraction of Unbound Drug in the Brain journal July 2019
Analyzing Learned Molecular Representations for Property Prediction journal July 2019
Prediction of Organic Reaction Outcomes Using Machine Learning journal April 2017
SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules journal February 1988
Stereo Signature Molecular Descriptor journal April 2013
Deep Neural Nets as a Method for Quantitative Structure–Activity Relationships journal February 2015
Flash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methods journal September 2011
Structural Determination of Paraffin Boiling Points journal January 1947
A Novel Approach for Predicting P-Glycoprotein (ABCB1) Inhibition Using Molecular Interaction Fields journal February 2011
Quantum chemistry structures and properties of 134 kilo molecules journal August 2014
MoleculeNet: a benchmark for molecular machine learning journal January 2018
QSAR without borders journal January 2020
Novel molecular hybrid geometric-harmonic-Zagreb degree based descriptors and their efficacy in QSPR studies of polycyclic aromatic hydrocarbons journal July 2023
From intuition to AI: evolution of small molecule representations in drug discovery journal November 2023
Molecular property prediction based on graph structure learning journal May 2024
Mordred: a molecular descriptor calculator journal February 2018
Transformer-CNN: Swiss knife for QSAR modeling and interpretation journal March 2020
DeepAR: a novel deep learning-based hybrid framework for the interpretable prediction of androgen receptor antagonists journal May 2023
Be aware of overfitting by hyperparameter optimization! journal December 2024
Machine Learning Validation via Rational Dataset Sampling with astartes journal November 2023
Communicative Representation Learning on Attributed Molecular Graphs
  • Song, Ying; Zheng, Shuangjia; Niu, Zhangming
  • Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}, Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence https://doi.org/10.24963/ijcai.2020/392
conference July 2020
Uni-Mol: A Universal 3D Molecular Representation Learning Framework preprint May 2022
Deep learning for low-data drug discovery: hurdles and opportunities preprint January 2024
A Unified Approach to Interpreting Model Predictions preprint January 2017
Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development preprint January 2021
ADMET property prediction through combinations of molecular fingerprints preprint January 2023
Molecular Hypergraph Neural Networks preprint January 2023

Similar Records

How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?
Conference · Mon May 07 04:00:00 UTC 2018 · OSTI ID:1558182

DeepAndes: A Self-Supervised Vision Foundation Model for Multispectral Remote Sensing Imagery of the Andes
Journal Article · Wed Oct 08 00:00:00 UTC 2025 · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · OSTI ID:3006502

Artificial Neural Network Models for Octane Number and Octane Sensitivity: A Quantitative Structure Property Relationship Approach to Fuel Design
Journal Article · Mon Apr 17 00:00:00 UTC 2023 · Journal of Energy Resources Technology · OSTI ID:2283717

Related Subjects