Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability
Authors:
Preprint
Abstract
Gaussian process (GP) is a Bayesian model which provides several advantages for regression tasks in machine learning such as reliable quantitation of uncertainty and improved interpretability. Their adoption has been precluded by their excessive computational cost and by the difficulty in adapting them for analyzing sequences (e.g. amino acid and nucleotide sequences) and graphs (e.g. ones representing small molecules). In this study, we develop efficient and scalable approaches for fitting GP models as well as fast convolution kernels which scale linearly with graph or sequence size. We implement these improvements by building an open-source Python library called xGPR. We compare the performance of xGPR with the reported performance of various deep learning models on 20 benchmarks, including small molecule, protein sequence and tabular data. We show that xGRP achieves highly competitive performance with much shorter training time. Furthermore, we also develop new kernels for sequence and graph data and show that xGPR generally outperforms convolutional neural networks on predicting key properties of proteins and small molecules. Importantly, xGPR provides uncertainty information not available from typical deep learning models. Additionally, xGPR provides a representation of the input data that can be used for clustering and data visualization. These results demonstrate that xGPR provides a powerful and generic tool that can be broadly useful in protein engineering and drug discovery.Keywords
All Related Versions
This publication has 39 references indexed in Scilit:
- Adaptive machine learning for protein engineeringCurrent Opinion in Structural Biology, 2022
- Learning the protein language: Evolution, structure, and functionCell Systems, 2021
- Data-driven computational protein designCurrent Opinion in Structural Biology, 2021
- Leveraging Uncertainty in Machine Learning Accelerates Biological Discovery and DesignCell Systems, 2020
- Randomized numerical linear algebra: Foundations and algorithmsActa Numerica, 2020
- A survey on graph kernelsApplied Network Science, 2020
- PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial ChargesJournal of Chemical Theory and Computation, 2019
- Protein Engineering: Past, Present, and Future2017
- Randomized matrix-free trace and log-determinant estimatorsNumerische Mathematik, 2017
- Local fitness landscape of the green fluorescent proteinNature, 2016