Derek Jones
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Derek Jones has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Jonathan E. Allen
Global Security Computing Applications Division, Lawrence Livermore National Laboratory, Livermore, CA, USA
4 shared publications - William F. Drew Bennett
Lawrence Livermore National Laboratory, Livermore, CA 94550, USA
3 shared publications Xiaohua Zhang
Biosciences and Biotechnology Division, Lawrence Livermore National Laboratory, Livermore, USA
3 shared publicationsAdam Zemla
Global Security Computing Applications Division, Lawrence Livermore National Laboratory, Livermore, California 94550, United States
2 shared publicationsBrian J. Bennion
Biosciences and Biotechnology Division, Lawrence Livermore National Laboratory, Livermore, USA
2 shared publications- Hyojin Kim
Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA
2 shared publications
Latest Publications
- Open Access
- 11 November 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (11) , 5214-5231
SurGBSA: learning representations from molecular dynamics simulations
SurGBSA combines molecular dynamics pretraining with fine-tuning on snapshot-level MMGBSA energies, enabled by a dataset of short MD simulations of docking poses. The MMGBSA fine-tuned models adapt to binding affinity and decoy pose ranking tasks.
- 11 November 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (11) , 5214-5231
Open AccessSurGBSA: learning representations from molecular dynamics simulations
SurGBSA combines molecular dynamics pretraining with fine-tuning on snapshot-level MMGBSA energies, enabled by a dataset of short MD simulations of docking poses. The MMGBSA fine-tuned models adapt to binding affinity and decoy pose ranking tasks.
- Open Access
- 3 August 2025
- Published by American Chemical Society (ACS) in ChemRxiv
ChemBERTa-3: An Open Source Training Framework for Chemical Foundation Models
The rapid advancement of machine learning in computational chemistry has opened new doors for designing molecules, predicting molecular properties, and discovering novel materials. However, building scalable and robust models for molecular property prediction remains a significant challenge due to the vast size and complexity of chemical space. In this paper, we introduce ChemBERTa-3, an open-source training framework designed to train and fine-tune large-scale chemical foundation models. We explore the potential of multiple model architectures by evaluating their performance across various molecular datasets from the MoleculeNet suite. Our experiments demonstrated that pre-training on the expansive ZINC20 dataset yields models capable of performing well on both classification and regression tasks, providing valuable insights into drug discovery and materials science. For scalability, we leveraged both AWS-based Ray deployments and on-premise high-performance computing clusters to support the processing power required to train on billions of molecules. In support of reproducible and extensible science, we have open-sourced all ChemBERTa3 models.
- 3 August 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessChemBERTa-3: An Open Source Training Framework for Chemical Foundation Models
The rapid advancement of machine learning in computational chemistry has opened new doors for designing molecules, predicting molecular properties, and discovering novel materials. However, building scalable and robust models for molecular property prediction remains a significant challenge due to the vast size and complexity of chemical space. In this paper, we introduce ChemBERTa-3, an open-source training framework designed to train and fine-tune large-scale chemical foundation models. We explore the potential of multiple model architectures by evaluating their performance across various molecular datasets from the MoleculeNet suite. Our experiments demonstrated that pre-training on the expansive ZINC20 dataset yields models capable of performing well on both classification and regression tasks, providing valuable insights into drug discovery and materials science. For scalability, we leveraged both AWS-based Ray deployments and on-premise high-performance computing clusters to support the processing power required to train on billions of molecules. In support of reproducible and extensible science, we have open-sourced all ChemBERTa3 models.
- Open Access
- 23 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-16
HDBind: encoding of molecular structure with hyperdimensional binary representations
Traditional methods for identifying “hit” molecules from a large collection of potential drug-like candidates rely on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug and its protein target. These approaches have a significant limitation in that they require exceptional computing capabilities for even relatively small collections of molecules. Increasingly large and complex state-of-the-art deep learning approaches have gained popularity with the promise to improve the productivity of drug design, notorious for its numerous failures. However, as deep learning models increase in their size and complexity, their acceleration at the hardware level becomes more challenging. Hyperdimensional Computing (HDC) has recently gained attention in the computer hardware community due to its algorithmic simplicity relative to deep learning approaches. The HDC learning paradigm, which represents data with high-dimension binary vectors, allows the use of low-precision binary vector arithmetic to create models of the data that can be learned without the need for the gradient-based optimization required in many conventional machine learning and deep learning methods. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated in a range of application areas (computer vision, bioinformatics, mass spectrometery, remote sensing, edge devices, etc.). To the best of our knowledge, our work is the first to consider HDC for the task of fast and efficient screening of modern drug-like compound libraries. We also propose the first HDC graph-based encoding methods for molecular data, demonstrating consistent and substantial improvement over previous work. We compare our approaches to alternative approaches on the well-studied MoleculeNet dataset and the recently proposed LIT-PCBA dataset derived from high quality PubChem assays. We demonstrate our methods on multiple target hardware platforms, including Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs), showing at least an order of magnitude improvement in energy efficiency versus even our smallest neural network baseline model with a single hidden layer. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools. We make our code publicly available at https://github.com/LLNL/hdbind.
- 23 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-16
Open AccessHDBind: encoding of molecular structure with hyperdimensional binary representations
Traditional methods for identifying “hit” molecules from a large collection of potential drug-like candidates rely on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug and its protein target. These approaches have a significant limitation in that they require exceptional computing capabilities for even relatively small collections of molecules. Increasingly large and complex state-of-the-art deep learning approaches have gained popularity with the promise to improve the productivity of drug design, notorious for its numerous failures. However, as deep learning models increase in their size and complexity, their acceleration at the hardware level becomes more challenging. Hyperdimensional Computing (HDC) has recently gained attention in the computer hardware community due to its algorithmic simplicity relative to deep learning approaches. The HDC learning paradigm, which represents data with high-dimension binary vectors, allows the use of low-precision binary vector arithmetic to create models of the data that can be learned without the need for the gradient-based optimization required in many conventional machine learning and deep learning methods. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated in a range of application areas (computer vision, bioinformatics, mass spectrometery, remote sensing, edge devices, etc.). To the best of our knowledge, our work is the first to consider HDC for the task of fast and efficient screening of modern drug-like compound libraries. We also propose the first HDC graph-based encoding methods for molecular data, demonstrating consistent and substantial improvement over previous work. We compare our approaches to alternative approaches on the well-studied MoleculeNet dataset and the recently proposed LIT-PCBA dataset derived from high quality PubChem assays. We demonstrate our methods on multiple target hardware platforms, including Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs), showing at least an order of magnitude improvement in energy efficiency versus even our smallest neural network baseline model with a single hidden layer. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools. We make our code publicly available at https://github.com/LLNL/hdbind.
- Open Access
- 17 October 2023
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 63 (21) , 6655-6666
Clustering Protein Binding Pockets and Identifying Potential Drug Interactions: A Novel Ligand-Based Featurization Method
Protein-ligand interactions are essential to drug discovery and drug development efforts. Desirable on-target or multitarget interactions are the first step in finding an effective therapeutic, while undesirable off-target interactions are the first step in assessing safety. In this work, we introduce a novel ligand-based featurization and mapping of human protein pockets to identify closely related protein targets and to project novel drugs into a hybrid protein-ligand feature space to identify their likely protein interactions. Using structure-based template matches from PDB, protein pockets are featured by the ligands that bind to their best co-complex template matches. The simplicity and interpretability of this approach provide a granular characterization of the human proteome at the protein-pocket level instead of the traditional protein-level characterization by family, function, or pathway. We demonstrate the power of this featurization method by clustering a subset of the human proteome and evaluating the predicted cluster associations of over 7000 compounds.
- 17 October 2023
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 63 (21) , 6655-6666
Open AccessClustering Protein Binding Pockets and Identifying Potential Drug Interactions: A Novel Ligand-Based Featurization Method
Protein-ligand interactions are essential to drug discovery and drug development efforts. Desirable on-target or multitarget interactions are the first step in finding an effective therapeutic, while undesirable off-target interactions are the first step in assessing safety. In this work, we introduce a novel ligand-based featurization and mapping of human protein pockets to identify closely related protein targets and to project novel drugs into a hybrid protein-ligand feature space to identify their likely protein interactions. Using structure-based template matches from PDB, protein pockets are featured by the ligands that bind to their best co-complex template matches. The simplicity and interpretability of this approach provide a granular characterization of the human proteome at the protein-pocket level instead of the traditional protein-level characterization by family, function, or pathway. We demonstrate the power of this featurization method by clustering a subset of the human proteome and evaluating the predicted cluster associations of over 7000 compounds.
- Open Access
- 16 June 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 18 (7) , 4047-4069
Accelerators for Classical Molecular Dynamics Simulations of Biomolecules
Atomistic Molecular Dynamics (MD) simulations provide researchers the ability to model biomolecular structures such as proteins and their interactions with drug-like small molecules with greater spatiotemporal resolution than is otherwise possible using experimental methods. MD simulations are notoriously expensive computational endeavors that have traditionally required massive investment in specialized hardware to access biologically relevant spatiotemporal scales. Our goal is to summarize the fundamental algorithms that are employed in the literature to then highlight the challenges that have affected accelerator implementations in practice. We consider three broad categories of accelerators: Graphics Processing Units (GPUs), Field-Programmable Gate Arrays (FPGAs), and Application Specific Integrated Circuits (ASICs). These categories are comparatively studied to facilitate discussion of their relative trade-offs and to gain context for the current state of the art. We conclude by providing insights into the potential of emerging hardware platforms and algorithms for MD.
- 16 June 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 18 (7) , 4047-4069
Open AccessAccelerators for Classical Molecular Dynamics Simulations of Biomolecules
Atomistic Molecular Dynamics (MD) simulations provide researchers the ability to model biomolecular structures such as proteins and their interactions with drug-like small molecules with greater spatiotemporal resolution than is otherwise possible using experimental methods. MD simulations are notoriously expensive computational endeavors that have traditionally required massive investment in specialized hardware to access biologically relevant spatiotemporal scales. Our goal is to summarize the fundamental algorithms that are employed in the literature to then highlight the challenges that have affected accelerator implementations in practice. We consider three broad categories of accelerators: Graphics Processing Units (GPUs), Field-Programmable Gate Arrays (FPGAs), and Application Specific Integrated Circuits (ASICs). These categories are comparatively studied to facilitate discussion of their relative trade-offs and to gain context for the current state of the art. We conclude by providing insights into the potential of emerging hardware platforms and algorithms for MD.
- Top Cited PapersOpen Access
- 23 March 2021
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 61 (4) , 1583-1592
Improved Protein–Ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference
Predicting accurate protein–ligand binding affinities is an important task in drug discovery but remains a challenge even with computationally expensive biophysics-based energy scoring methods and state-of-the-art deep learning approaches. Despite the recent advances in the application of deep convolutional and graph neural network-based approaches, it remains unclear what the relative advantages of each approach are and how they compare with physics-based methodologies that have found more mainstream success in virtual screening pipelines. We present fusion models that combine features and inference from complementary representations to improve binding affinity prediction. This, to our knowledge, is the first comprehensive study that uses a common series of evaluations to directly compare the performance of three-dimensional (3D)-convolutional neural networks (3D-CNNs), spatial graph neural networks (SG-CNNs), and their fusion. We use temporal and structure-based splits to assess performance on novel protein targets. To test the practical applicability of our models, we examine their performance in cases that assume that the crystal structure is not available. In these cases, binding free energies are predicted using docking pose coordinates as the inputs to each model. In addition, we compare these deep learning approaches to predictions based on docking scores and molecular mechanic/generalized Born surface area (MM/GBSA) calculations. Our results show that the fusion models make more accurate predictions than their constituent neural network models as well as docking scoring and MM/GBSA rescoring, with the benefit of greater computational efficiency than the MM/GBSA method. Finally, we provide the code to reproduce our results and the parameter files of the trained models used in this work. The software is available as open source at https://github.com/llnl/fast. Model parameter files are available at ftp://gdo-bioinformatics.ucllnl.org/fast/pdbbind2016_model_checkpoints/.
- 23 March 2021
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 61 (4) , 1583-1592
Top Cited PapersOpen AccessImproved Protein–Ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference
Predicting accurate protein–ligand binding affinities is an important task in drug discovery but remains a challenge even with computationally expensive biophysics-based energy scoring methods and state-of-the-art deep learning approaches. Despite the recent advances in the application of deep convolutional and graph neural network-based approaches, it remains unclear what the relative advantages of each approach are and how they compare with physics-based methodologies that have found more mainstream success in virtual screening pipelines. We present fusion models that combine features and inference from complementary representations to improve binding affinity prediction. This, to our knowledge, is the first comprehensive study that uses a common series of evaluations to directly compare the performance of three-dimensional (3D)-convolutional neural networks (3D-CNNs), spatial graph neural networks (SG-CNNs), and their fusion. We use temporal and structure-based splits to assess performance on novel protein targets. To test the practical applicability of our models, we examine their performance in cases that assume that the crystal structure is not available. In these cases, binding free energies are predicted using docking pose coordinates as the inputs to each model. In addition, we compare these deep learning approaches to predictions based on docking scores and molecular mechanic/generalized Born surface area (MM/GBSA) calculations. Our results show that the fusion models make more accurate predictions than their constituent neural network models as well as docking scoring and MM/GBSA rescoring, with the benefit of greater computational efficiency than the MM/GBSA method. Finally, we provide the code to reproduce our results and the parameter files of the trained models used in this work. The software is available as open source at https://github.com/llnl/fast. Model parameter files are available at ftp://gdo-bioinformatics.ucllnl.org/fast/pdbbind2016_model_checkpoints/.
- Open Access
- 1 August 2020
- Published by Frontline Medical Communications, Inc. in Cutis
- Vol. 106 (2) , 59-60
Are You Up-to-date on Dermal Fillers?
The popularity of injectable fillers for aesthetic use continues to rise, and cosmetic injectors must select from an increasing range of options to achieve opti
- 1 August 2020
- Published by Frontline Medical Communications, Inc. in Cutis
- Vol. 106 (2) , 59-60
Open AccessAre You Up-to-date on Dermal Fillers?
The popularity of injectable fillers for aesthetic use continues to rise, and cosmetic injectors must select from an increasing range of options to achieve opti
- 1 July 2018
- Published by Wolters Kluwer Health in Dermatologic Surgery
- Vol. 44 (7) , 1002-1011
Cohesive Polydensified Matrix Hyaluronic Acid for the Treatment of Etched-In Fine Facial Lines: A 6-Month, Open-Label Clinical Trial
BACKGROUND: Available hyaluronic acid dermal fillers have unique biophysical properties that influence their clinical utility, longevity, and aesthetic outcomes. OBJECTIVE: To evaluate the effectiveness and durability of a cohesive polydensified matrix hyaluronic acid dermal filler (CPM-HA) for the treatment of etched-in fine facial lines. MATERIALS AND METHODS: Subjects with etched-in fine lines of the forehead, cutaneous lip, melolabial folds, nasolabial folds, and/or radial cheek received treatment with CPM-HA mixed with lidocaine and epinephrine, with an optional touch-up treatment at Week 2, if deemed necessary. Response to treatment (as measured by the Merz Aesthetics Scales, Lemperle Facial Wrinkle Scales, and subject self-assessment) and safety/tolerability were monitored over the course of 26 weeks. RESULTS: Thirty-one subjects received treatment with CPM-HA to 1 or more facial areas. All 5 treatment areas showed clinically meaningful and statistically significant improvements in average clinician rating scale scores at all study visits (p < .001 vs baseline). Most subjects reported maintained improvement from baseline of 50% or more throughout the 26-week study. Injection site reactions were mild and resolved without intervention. CONCLUSION: Cohesive polydensified matrix hyaluronic acid dermal filler treatment was well tolerated and provided consistent and durable improvement in the appearance of a diverse range of etched-in fine facial lines.
- 1 July 2018
- Published by Wolters Kluwer Health in Dermatologic Surgery
- Vol. 44 (7) , 1002-1011
Cohesive Polydensified Matrix Hyaluronic Acid for the Treatment of Etched-In Fine Facial Lines: A 6-Month, Open-Label Clinical Trial
BACKGROUND: Available hyaluronic acid dermal fillers have unique biophysical properties that influence their clinical utility, longevity, and aesthetic outcomes. OBJECTIVE: To evaluate the effectiveness and durability of a cohesive polydensified matrix hyaluronic acid dermal filler (CPM-HA) for the treatment of etched-in fine facial lines. MATERIALS AND METHODS: Subjects with etched-in fine lines of the forehead, cutaneous lip, melolabial folds, nasolabial folds, and/or radial cheek received treatment with CPM-HA mixed with lidocaine and epinephrine, with an optional touch-up treatment at Week 2, if deemed necessary. Response to treatment (as measured by the Merz Aesthetics Scales, Lemperle Facial Wrinkle Scales, and subject self-assessment) and safety/tolerability were monitored over the course of 26 weeks. RESULTS: Thirty-one subjects received treatment with CPM-HA to 1 or more facial areas. All 5 treatment areas showed clinically meaningful and statistically significant improvements in average clinician rating scale scores at all study visits (p < .001 vs baseline). Most subjects reported maintained improvement from baseline of 50% or more throughout the 26-week study. Injection site reactions were mild and resolved without intervention. CONCLUSION: Cohesive polydensified matrix hyaluronic acid dermal filler treatment was well tolerated and provided consistent and durable improvement in the appearance of a diverse range of etched-in fine facial lines.
- 1 October 2014
- Published by Wolters Kluwer Health in Plastic and Reconstructive Surgery
- Vol. 134, 123
A Pooled Analysis of the Safety and Efficacy Results of the Multicenter, Double-Blind, Randomized, Placebo-Controlled Phase 3 REFINE-1 and REFINE-2 Trials of ATX-101, a Submental Contouring Injectable Drug for the Reduction of Submental Fat
- 1 October 2014
- Published by Wolters Kluwer Health in Plastic and Reconstructive Surgery
- Vol. 134, 123
A Pooled Analysis of the Safety and Efficacy Results of the Multicenter, Double-Blind, Randomized, Placebo-Controlled Phase 3 REFINE-1 and REFINE-2 Trials of ATX-101, a Submental Contouring Injectable Drug for the Reduction of Submental Fat
- 1 November 2006
- Published by Wolters Kluwer Health in Dermatologic Surgery
- Vol. 32 (11) , 1407-1409
Persistent Granulomatous Inflammatory Response Induced by Injectable Poly-L-lactic Acid for HIV Lipoatrophy
- 1 November 2006
- Published by Wolters Kluwer Health in Dermatologic Surgery
- Vol. 32 (11) , 1407-1409
Persistent Granulomatous Inflammatory Response Induced by Injectable Poly-L-lactic Acid for HIV Lipoatrophy