Kevin P. Greenman

Kevin P. Greenman

Auto-generated profile, based on publicly available information

Kevin P. Greenman

Massachusetts Institute of Technology

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 December 2023 in Journal of Chemical Information and Modeling
Verified
Journal Article
Open access
EHEsther Heid
Esther Heid
KGKevin P. Greenman
Kevin P. Greenman
YCYunsie Chung
Yunsie Chung
SLShih-Cheng Li
Shih-Cheng Li
DGDavid E. Graff
David E. Graff
CMCharles McGill
Charles McGill
Deep learning has become a powerful and frequently employed tool for the prediction of molecular properties, thus creating a need for open-source and versatile software solutions that can be operated by nonexperts. Among the current approaches, directed message-passing neural networks (D-MPNNs) have proven to perform well on a variety of property prediction tasks. The software package Chemprop implements the D-MPNN architecture and offers simple, easy, and fast access to machine-learned molecular properties. Compared to its initial version, we present a multitude of new Chemprop functionalities such as the support of multimolecule properties, reactions, atom/bond-level properties, and spectra. Further, we incorporate various uncertainty quantification and calibration methods along with related metrics as well as pretraining and transfer learning workflows, improved hyperparameter optimization, and other customization options concerning loss functions or atom/bond features. We benchmark D-MPNN models trained using Chemprop with the new reaction, atom-level, and spectra functionality on a variety of property prediction data sets, including MoleculeNet and SAMPL, and observe state-of-the-art performance on the prediction of water-octanol partition coefficients, reaction barrier heights, atomic partial charges, and absorption spectra. Chemprop enables out-of-the-box training of D-MPNN models for a variety of problem settings in fast, user-friendly, and open-source software.

22 December 2023 in Science
Verified
Journal Article
Closed access
BKBrent A. Koscher
Brent A. Koscher
RCRichard B. Canty
Richard B. Canty
MMMatthew McDonald
Matthew McDonald
KGKevin P. Greenman
Kevin P. Greenman
CMCharles J. McGill
Charles J. McGill
KJKlavs F. Jensen
Klavs F. Jensen
A closed-loop, autonomous molecular discovery platform driven by integrated machine learning tools was developed to accelerate the design of molecules with desired properties. We demonstrated two case studies on dye-like molecules, targeting absorption wavelength, lipophilicity, and photooxidative stability. In the first study, the platform experimentally realized 294 unreported molecules across three automatic iterations of molecular design-make-test-analyze cycles while exploring the structure-function space of four rarely reported scaffolds. In each iteration, the property prediction models that guided exploration learned the structure-property space of diverse scaffold derivatives, which were realized with multistep syntheses and a variety of reactions. The second study exploited property models trained on the explored chemical space and previously reported molecules to discover nine top-performing molecules within a lightly explored structure-property space.

21 February 2022 in Accounts of Materials Research
Verified
Journal Article
Closed access
SASimon Axelrod
Simon Axelrod
DSDaniel Schwalbe-Koda
Daniel Schwalbe-Koda
SMSomesh Mohapatra
Somesh Mohapatra
JDJames Damewood
James Damewood
KGKevin P. Greenman
Kevin P. Greenman
RGRafael Gómez-Bombarelli
Rafael Gómez-Bombarelli

4 January 2022 in Chemical Science
Verified
Journal Article
Open access
PDF file
KGKevin P. Greenman
Kevin P. Greenman
WGWilliam H. Green
William H. Green
RGRafael Gómez-Bombarelli
Rafael Gómez-Bombarelli
Optical properties are central to molecular design for many applications, including solar cells and biomedical imaging. A variety of ab initio and statistical methods have been developed for their prediction, each with a trade-off between accuracy, generality, and cost. Existing theoretical methods such as time-dependent density functional theory (TD-DFT) are generalizable across chemical space because of their robust physics-based foundations but still exhibit random and systematic errors with respect to experiment despite their high computational cost. Statistical methods can achieve high accuracy at a lower cost, but data sparsity and unoptimized molecule and solvent representations often limit their ability to generalize. Here, we utilize directed message passing neural networks (D-MPNNs) to represent both dye molecules and solvents for predictions of molecular absorption peaks in solution. Additionally, we demonstrate a multi-fidelity approach based on an auxiliary model trained on over 28 000 TD-DFT calculations that further improves accuracy and generalizability, as shown through rigorous splitting strategies. Combining several openly-available experimental datasets, we benchmark these methods against a state-of-the-art regression tree algorithm and compare the D-MPNN solvent representation to several alternatives. Finally, we explore the interpretability of the learned representations using dimensionality reduction and evaluate the use of ensemble variance as an estimator of the epistemic uncertainty in our predictions of molecular peak absorption in solution. The prediction methods proposed herein can be integrated with active learning, generative modeling, and experimental workflows to enable the more rapid design of molecules with targeted optical properties.

26 December 2025 in Journal of Chemical Information and Modeling
Verified
Journal Article
Closed access
DGDavid E. Graff
David E. Graff
NMNathan K. Morgan
Nathan K. Morgan
JBJackson W. Burns
Jackson W. Burns
ADAnna C. Doner
Anna C. Doner
BLBrian Li
Brian Li
KGKevin P. Greenman
Kevin P. Greenman

7 January 2025 in PLOS Computational Biology
Verified
Journal Article
Open access
PDF file
KGKevin P Greenman
Kevin P Greenman
AAAva P Amini
Ava P Amini
KYKevin K Yang
Kevin K Yang
Machine learning sequence-function models for proteins could enable significant advances in protein engineering, especially when paired with state-of-the-art methods to select new sequences for property optimization and/or model improvement. Such methods (Bayesian optimization and active learning) require calibrated estimations of model uncertainty. While studies have benchmarked a variety of deep learning uncertainty quantification (UQ) methods on standard and molecular machine-learning datasets, it is not clear if these results extend to protein datasets. In this work, we implemented a panel of deep learning UQ methods on regression tasks from the Fitness Landscape Inference for Proteins (FLIP) benchmark. We compared results across different degrees of distributional shift using metrics that assess each UQ method’s accuracy, calibration, coverage, width, and rank correlation. Additionally, we compared these metrics using one-hot encoding and pretrained language model representations, and we tested the UQ methods in retrospective active learning and Bayesian optimization settings. Our results indicate that there is no single best UQ method across all datasets, splits, and metrics, and that uncertainty-based sampling is often unable to outperform greedy sampling in Bayesian optimization. These benchmarks enable us to provide recommendations for more effective design of biological sequences using machine learning.