skip to main content


Title: Retrospective on a decade of machine learning for chemical discovery
Over the last decade, we have witnessed the emergence of ever more machine learning applications in all aspects of the chemical sciences. Here, we highlight specific achievements of machine learning models in the field of computational chemistry by considering selected studies of electronic structure, interatomic potentials, and chemical compound space in chronological order  more » « less
Award ID(s):
1856165
NSF-PAR ID:
10220446
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Nature communications
Issue:
11
ISSN:
2041-1723
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. We report a comprehensive computational study of unsupervised machine learning for extraction of chemically relevant information in X-ray absorption near edge structure (XANES) and in valence-to-core X-ray emission spectra (VtC-XES) for classification of a broad ensemble of sulphorganic molecules. By progressively decreasing the constraining assumptions of the unsupervised machine learning algorithm, moving from principal component analysis (PCA) to a variational autoencoder (VAE) to t-distributed stochastic neighbour embedding (t-SNE), we find improved sensitivity to steadily more refined chemical information. Surprisingly, when embedding the ensemble of spectra in merely two dimensions, t-SNE distinguishes not just oxidation state and general sulphur bonding environment but also the aromaticity of the bonding radical group with 87% accuracy as well as identifying even finer details in electronic structure within aromatic or aliphatic sub-classes. We find that the chemical information in XANES and VtC-XES is very similar in character and content, although they unexpectedly have different sensitivity within a given molecular class. We also discuss likely benefits from further effort with unsupervised machine learning and from the interplay between supervised and unsupervised machine learning for X-ray spectroscopies. Our overall results, i.e. , the ability to reliably classify without user bias and to discover unexpected chemical signatures for XANES and VtC-XES, likely generalize to other systems as well as to other one-dimensional chemical spectroscopies. 
    more » « less
  2. Abstract

    Exploratory analysis of the chemical space is an important task in the field of cheminformatics. For example, in drug discovery research, chemists investigate sets of thousands of chemical compounds in order to identify novel yet structurally similar synthetic compounds to replace natural products. Manually exploring the chemical space inhabited by all possible molecules and chemical compounds is impractical, and therefore presents a challenge. To fill this gap, we present ChemoGraph, a novel visual analytics technique for interactively exploring related chemicals. In ChemoGraph, we formalize a chemical space as a hypergraph and apply novel machine learning models to compute related chemical compounds. It uses a database to find related compounds from a known space and a machine learning model to generate new ones, which helps enlarge the known space. Moreover, ChemoGraph highlights interactive features that support users in viewing, comparing, and organizing computationally identified related chemicals. With a drug discovery usage scenario and initial expert feedback from a case study, we demonstrate the usefulness of ChemoGraph.

     
    more » « less
  3. Supervised machine learning approaches have been increasingly used in accelerating electronic structure prediction as surrogates of first-principle computational methods, such as density functional theory (DFT). While numerous quantum chemistry datasets focus on chemical properties and atomic forces, the ability to achieve accurate and efficient prediction of the Hamiltonian matrix is highly desired, as it is the most important and fundamental physical quantity that determines the quantum states of physical systems and chemical properties. In this work, we generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 2,399 molecular dynamics trajectories and 130,831 stable molecular geometries, based on the QM9 dataset. By designing benchmark tasks with various molecules, we show that current machine learning models have the capacity to predict Hamiltonian matrices for arbitrary molecules. Both the QH9 dataset and the baseline models are provided to the community through an open-source benchmark, which can be highly valuable for developing machine learning methods and accelerating molecular and materials design for scientific and technological applications. Our benchmark is publicly available at \url{https://github.com/divelab/AIRS/tree/main/OpenDFT/QHBench}. 
    more » « less
  4. Supervised machine learning approaches have been increasingly used in accelerating electronic structure prediction as surrogates of first-principle computational methods, such as density functional theory (DFT). While numerous quantum chemistry datasets focus on chemical properties and atomic forces, the ability to achieve accurate and efficient prediction of the Hamiltonian matrix is highly desired, as it is the most important and fundamental physical quantity that determines the quantum states of physical systems and chemical properties. In this work, we generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 2,399 molecular dynamics trajectories and 130,831 stable molecular geometries, based on the QM9 dataset. By designing benchmark tasks with various molecules, we show that current machine learning models have the capacity to predict Hamiltonian matrices for arbitrary molecules. Both the QH9 dataset and the baseline models are provided to the community through an open-source benchmark, which can be highly valuable for developing machine learning methods and accelerating molecular and materials design for scientific and technological applications. 
    more » « less
  5. Mechanical stresses generated at the cell-cell level and cell-substrate level have been suggested to be important in a host of physiological and pathological processes. However, the influence various chemical compounds have on the mechan- ical stresses mentioned above is poorly understood, hindering the discovery of novel therapeutics, and representing a barrier in the field. To overcome this barrier, we implemented two approaches: 1) monolayer boundary predictor and 2) discretized window predictor utilizing either stepwise linear regression or quadratic support vector machine machine learning model to predict the dose-dependent response of tractions and intercellular stresses to chemical perturbation. We used experimental traction and intercellular stress data gathered from samples subject to 0.2 or 2 mg/mL drug concentrations along with cell morphological prop- erties extracted from the bright-field images as predictors to train our model. To demonstrate the predictive capability of our ma- chine learning models, we predicted tractions and intercellular stresses in response to 0 and 1 mg/mL drug concentrations which were not utilized in the training sets. Results revealed the discretized window predictor trained just with four samples (292 im- ages) to best predict both intercellular stresses and tractions using the quadratic support vector machine and stepwise linear regression models, respectively, for the unseen sample images. 
    more » « less