Multitask methods for predicting molecular properties from heterogeneous data

2024-01-31 · Katharine Fisher, Michael Herbst, Youssef Marzouk

Data generation remains a bottleneck in training surrogate models to predict molecular properties. We demonstrate that multitask Gaussian process regression overcomes this limitation by leveraging both expensive and cheap data sources. In particular, we consider training sets constructed from coupled-cluster (CC) and density functional theory (DFT) data. We report that multitask surrogates can predict at CC-level accuracy with a reduction to data generation cost by over an order of magnitude. Of note, our approach allows the training set to include DFT data generated by a heterogeneous mix of exchange-correlation functionals without imposing any artificial hierarchy on functional accuracy. More generally, the multitask framework can accommodate a wider range of training set structures -- including full disparity between the different levels of fidelity -- than existing kernel approaches based on $\Delta$-learning, though we show that the accuracy of the two approaches can be similar. Consequently, multitask regression can be a tool for reducing data generation costs even further by opportunistically exploiting existing data sources.

📄 PDF Abstract BibTeX arXiv:2401.17898

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Pushing the boundaries of molecular property prediction for drug discovery with multitask learning BERT enhanced by SMILES enumeration

2022-12-15 · Research 2022 12 · XC Zhang, CK Wu, JC Yi, XX Zeng 외

Accurate prediction of pharmacological properties of small molecules is becoming increasingly important in drug discovery. Traditional feature-engineering approaches heavily rely on handcrafted descriptors and/or fingerp…

Drug Discovery Feature Engineering Molecular Property Prediction Property Prediction

Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions

2019-10-29 · Fabio Capela, Vincent Nouchi, Ruud Van Deursen, Igor V. Tetko 외

Prediction of molecular properties, including physico-chemical properties, is a challenging task in chemistry. Herein we present a new state-of-the-art multitask prediction method based on existing graph neural network m…

Data Augmentation Graph Neural Network Prediction

Knowledge-aware contrastive heterogeneous molecular graph learning

2025-02-17 · Mukun Chen, Jia Wu, Shirui Pan, Fu Lin 외

Molecular representation learning is pivotal in predicting molecular properties and advancing drug design. Traditional methodologies, which predominantly rely on homogeneous graph encoding, are limited by their inability…

Benchmarking Contrastive Learning Drug Design Graph Learning+5

Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties

2020-09-26 · Zeren Shui, George Karypis

As they carry great potential for modeling complex interactions, graph neural network (GNN)-based methods have been widely used to predict quantum mechanical properties of molecules. Most of the existing methods treat mo…

Formation Energy Graph Neural Network

Boosting Multitask Learning on Graphs through Higher-Order Task Affinities

2023-06-24 · Dongyue Li, Haotian Ju, Aneesh Sharma, Hongyang R. Zhang

Predicting node labels on a given graph is a widely studied problem with many applications, including community detection and molecular graph prediction. This paper considers predicting multiple node labeling functions o…

Community Detection Node Classification