Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Drug discovery”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Assessing the potential of deep learning for protein–ligand docking

The effects of ligand binding on protein structures and their in vivo functions carry numerous implications for modern biomedical research and biotechnology development efforts such as drug discovery. Although several deep learning (DL) methods and benchmarks designed for protein–ligand docking have recently been introduced, so far no previous works have systematically studied the behaviour of the latest docking and structure prediction methods within the broadly applicable context of: (1) using predicted (apo) protein structures for docking (for example, for applicability to new proteins); (2) binding multiple (cofactor) ligands concurrently to a given target protein (for example, for enzyme design); and (3) having no previous knowledge of binding pockets (for example, for generalization to unknown pockets). To enable a deeper understanding of the real-world utility of docking methods, we introduce PoseBench, a comprehensive benchmark for broadly applicable protein–ligand docking. PoseBench enables researchers to rigorously and systematically evaluate DL methods for apo-to-holo protein–ligand docking and protein–ligand structure prediction using both primary ligand and multiligand benchmark datasets, the latter of which we introduce to the DL community. Empirically, using PoseBench, we find that: (1) DL cofolding methods generally outperform comparable conventional and DL docking baseline algorithms, but popular methods such as AlphaFold 3 are still challenged by prediction targets with new protein–ligand binding poses; (2) certain DL cofolding methods are highly sensitive to their input multiple sequence alignments, whereas others are not; and (3) DL methods struggle to strike a balance between structural accuracy and chemical specificity when predicting new or multiligand protein targets.

Morehead, Alex [Lawrence Berkeley National Laborat↗
DOE OSTI2026

SmileyLlama: modifying large language models for directed chemical space exploration

Here we show that large language models (LLMs) can be transformed via supervised fine-tuning of engineered prompts into SmileyLlama for exploring the chemical space of drug molecules. We benchmark SmileyLlama against pretrained LLMs and chemical language models trained from scratch for generating valid and novel drug-like molecules, and use direct preference optimization to both improve SmileyLlama’s adherence to a prompt and as part of the iMiner reinforcement learning framework to predict molecules with optimized three-dimensional conformations and high binding affinity to drug targets. By training an LLM to speak directly as a chemical language model, while retaining most of its natural language capabilities, we show that SmileyLlama can reliably generate molecules with user-specified properties rather than acting only as a chatbot with knowledge of chemistry or as a virtual assistant. While SmileyLlama is geared toward drug discovery, the supervised fine-tuning/direct preference optimization/LLM framework can be extended to other chemical, biological and materials applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

A curated benchmark for cofolding models on kinase conformational states

Abstract Protein kinases are critical drug targets, requiring therapeutics that can modulate their active and inactive conformational states. While cofolding models can generate global folds directly from kinase sequences and ligand SMILES strings, these models have not yet been tested on their ability to recover ligand-induced-fit conformational states of the kinase proteins. Here, we introduce KinConfBench, a curated benchmark of 2225 high-quality human kinase chains to evaluate the ability of four state-of-the-art cofolding models—Boltz-2, Chai-1, Protenix, and RoseTTAFold-All-Atom—to recover both canonical and rare conformational states. We show that geometric success metrics of a ligand pose in the active site do not correlate strongly with the correct kinase conformational state, motivating a new set of dynamical benchmarks for assessing cofolding models. While all four cofolding models achieve ~60–80% prediction accuracy for kinase conformational classification, they exhibit severe mode collapse when performing multiple inferences, show negligible structural diversity in sampling induced-fit motions, and display a prevalent “apo-drift” in which most cofolding models predominantly predict the kinase to be in its ligand-free state. Our results highlight that capturing ligand-induced protein conformational diversity, not just geometric fit, is critical for next-generation structure-based drug discovery.

Sun, Kunyang↗
DOE OSTI2024

Uncertainty quantification for molecular property predictions with graph neural architecture search

Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets, and generalizes well to out-of-distribution datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Dual-action kinase inhibitors influence p38α MAP kinase dephosphorylation

Reversible protein phosphorylation directs essential cellular processes including cell division, cell growth, cell death, inflammation, and differentiation. Because protein phosphorylation drives diverse diseases, kinases and phosphatases have been targets for drug discovery, with some achieving remarkable clinical success. Most protein kinases are activated by phosphorylation of their activation loops, which shifts the conformational equilibrium of the kinase toward the active state. To turn off the kinase, protein phosphatases dephosphorylate these sites, but how the conformation of the dynamic activation loop contributes to dephosphorylation was not known. To answer this, we modulated the activation loop conformational equilibrium of human p38α ΜΑP kinase with existing kinase inhibitors that bind and stabilize specific inactive activation loop conformations. From this, we identified three inhibitors that increase the rate of dephosphorylation of the activation loop phospho-threonine by the PPM serine/threonine phosphatase WIP1. Hence, these compounds are “dual-action” inhibitors that simultaneously block the active site and promote p38α dephosphorylation. Our X-ray crystal structures of phosphorylated p38α bound to the dual-action inhibitors reveal a shared flipped conformation of the activation loop with a fully accessible phospho-threonine. In contrast, our X-ray crystal structure of phosphorylated apo human p38α reveals a different activation loop conformation with an inaccessible phospho-threonine, thereby explaining the increased rate of dephosphorylation upon inhibitor binding. These findings reveal a conformational preference of phosphatases for their targets and suggest a unique approach to achieving improved potency and specificity for therapeutic kinase inhibitors.

Science & Technology - Other Topics↗
DOE OSTI2025

Data imbalance in drug response prediction: multi-objective optimization approach in deep learning setting

Abstract Drug response prediction (DRP) methods tackle the complex task of associating the effectiveness of small molecules with the specific genetic makeup of the patient. Anti-cancer DRP is a particularly challenging task requiring costly experiments as underlying pathogenic mechanisms are broad and associated with multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving a path to various machine learning models that attempt to reason over complex data space of small compounds and biological characteristics of tumors. However, the data depth is still lacking compared to application domains like computer vision or natural language processing domains, limiting current learning capabilities. To combat this issue and improves the generalizability of the DRP models, we are exploring strategies that explicitly address the imbalance in the DRP datasets. We reframe the problem as a multi-objective optimization across multiple drugs to maximize deep learning model performance. We implement this approach by constructing Multi-Objective Optimization Regularized by Loss Entropy loss function and plugging it into a Deep Learning model. We demonstrate the utility of proposed drug discovery methods and make suggestions for further potential application of the work to achieve desirable outcomes in the healthcare field.

Biochemistry & Molecular Biology↗
DOE OSTI2025

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

Atomistic materials modeling is a critical task with wide-ranging applications, from drug discovery to materials science, where accurate predictions of the target material property can lead to significant advancements in scientific discovery. Graph Neural Networks (GNNs) represent the state-of-the-art approach for modeling atomistic material data thanks to their capacity to capture complex relational structures. While machine learning performance has historically improved with larger models and datasets, GNNs for atomistic materials modeling remain relatively small compared to large language models (LLMs), which leverage billions of parameters and terabyte-scale datasets to achieve remarkable performance in their respective domains. To address this gap, we explore the scaling limits of GNNs for atomistic materials modeling by developing a foundational model with billions of parameters, trained on extensive datasets in terabytescale. Our approach incorporates techniques from LLM libraries to efficiently manage large-scale data and models, enabling both effective training and deployment of these large-scale GNN models. This work addresses three fundamental questions in scaling GNNs: the potential for scaling GNN model architectures, the effect of dataset size on model accuracy, and the applicability of LLM-inspired techniques to GNN architectures. Specifically, the outcomes of this study include (1) insights into the scaling laws for GNNs, highlighting the relationship between model size, dataset volume, and accuracy, (2) a foundational GNN model optimized for atomistic materials modeling, and (3) a GNN codebase enhanced with advanced LLM-based training techniques. Our findings lay the groundwork for large-scale GNNs with billions of parameters and terabyte-scale datasets, establishing a scalable pathway for future advancements in atomistic materials modeling.

Li, Chaojian [ORNL] (ORCID:0000000340309777)↗
DOE OSTI2025

Integrating and Characterizing HPC Task Runtime Systems for hybrid AI-HPC workloads

Scientific workflows increasingly involve both HPC and machine-learning tasks, combining MPI-based simulations, training, and inference in a single execution. Launchers such as Slurm’s srun constrain concurrency and throughput, making them unsuitable for dynamic and heterogeneous workloads. We present a performance study of RADICAL-Pilot (RP) integrated with Flux and Dragon, two complementary runtime systems that enable hierarchical resource management and high-throughput function execution. Using synthetic and production-scale workloads on Frontier, we characterize the task execution properties of RP across runtime configurations. RP+Flux sustains up to 930 tasks/s, and RP+Flux+Dragon exceeds 1,500 tasks/s with over 99.6% utilization. In contrast, srun peaks at 152 tasks/s and degrades with scale, with utilization below 50%. For IMPECCABLE.v2 drug discovery campaign, RP+Flux reduces makespan by 30–60% relative to srun/Slurm and increases throughput more than four times on up to 1,024. These results demonstrate hybrid runtime integration in RP as a scalable approach for hybrid AI-HPC workloads.

HPC-AI↗
DOE OSTI2025

Lustre Unveiled: Evolution, Design, Advancements, and Current Trends

The Lustre filesystem serves as a vital element in high-performance parallel storage, meeting the rising demands of scientific, research, and enterprise environments. Widely deployed across HPC environments, ranging from small-scale applications in AI/ML, to domains like oil and gas, drug discovery, and meteorology, and manufacturing, Lustre addresses the universal challenge of efficiently accessing vast and ever-increasing volumes of data. Lustre is the filesystem of choice on six out of the top 10 fastest supercomputers in the world today, over 65% of the top 100, and also for over 60% of the top 500. Despite its widespread popularity, there is a lack of a complete and up-to-date reference, covering Lustre’s evolution, design, and various advancements made over the years. In this journal, we aim to fill this gap by providing a comprehensive journey of Lustre, including its history with significant contributions to HPC, detailed architecture and design elements, exploration of advancements added through its evolution, and future directions. Additionally, we present a comparison of Lustre with other prominent storage technologies of the era. To illustrate the current state of Lustre, we analyze several filesystem trends, including utilization, performance, and usage patterns on Orion, the Lustre filesystem on the first exascale supercomputer Frontier. We hope that this journal serves as a comprehensive educational reference for the current and future generations interested in HPC filesystem storage aspects.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Equivariant Graph Attention Network - 3D Conformers & Feature Fusion

EGAN-3F (Equivariant Graph Attention Network - 3D Conformers & Feature Fusion) presents an innovative approach for predicting binding affinity between small molecules and protein targets, a fundamental task in drug discovery. Traditional structure-based methods often depend on protein-ligand complex structures obtained from crystallography or molecular docking. In contrast, ligand-only machine learning models using 1D or 2D representations such as SMILES have been developed to predict binding affinity without structural information about the target; however, their accuracy is often limited due to the lack of 3D ligand information. EGAN-3F addresses this limitation by integrating spatially aware graph learning with traditional descriptor-based features. We systematically investigate how combining 2D and 3D molecular representations enhances binding affinity prediction from SMILES strings. This approach underscores the importance of modeling conformational diversity and incorporating chemically meaningful descriptors to improve predictive accuracy. The key innovation of EGAN-3F lies in its ability to achieve robust ligand-based binding affinity predictions without requiring protein-ligand complex structures, effectively bridging the gap between purely structural and ligand-only modeling paradigms.

Shim, Heesung [Lawrence Livermore National Laborat↗
DOE OSTI2025

Chemical classification program synthesis using generative artificial intelligence

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

Artificial Intelligence↗
DOE OSTI2026

EvoDiffMol: evolutionary diffusion framework for 3D molecular design with optimized properties

Designing molecules with specific target properties remains a fundamental challenge in computational chemistry. While existing approaches show promise, most rely on simplified representations like SMILES strings or 2D graphs that lack essential three-dimensional geometric information. We present EvoDiffMol, a computational framework that integrates evolutionary algorithms with three-dimensional diffusion models for property-driven molecular generation. The method operates through adaptive evolutionary optimization, where population-based selection guides the generation process toward desired property landscapes. EvoDiffMol supports both unconstrained molecular design and scaffold-constrained generation that preserves fixed substructures while optimizing complementary regions. Comprehensive evaluation demonstrates exceptional performance, achieving the highest drug-likeness score (0.94) among all compared state-of-the-art methods while maintaining excellent validity, uniqueness, and novelty. Beyond single property optimization, the framework demonstrates flexible multi-property optimization capabilities, simultaneously controlling multiple molecular descriptors including synthetic accessibility, lipophilicity, topological polar surface area, and clinically relevant ADMET properties such as cardiotoxicity (hERG) and intestinal permeability (Caco-2). This adaptability spans from simple descriptors to practical pharmaceutical endpoints without requiring complete model retraining. The framework achieves precise control over target property values, generating molecules with properties closely matching specified targets for both single and multiple descriptors. Scaffold-constrained experiments preserve fixed molecular cores while maintaining effective property optimization. The three-dimensional representation offers advantages in maintaining structural validity during iterative optimization, with potential for geometry-aware applications in materials science and drug discovery.

3D molecular generation↗
DOE OSTI2024

Identification, characterization, and structure of a tRNA splicing enzyme RNA 5′-OH kinase from the pathogenic fungi Mucorales

Fungal Trl1 is an essential tRNA splicing enzyme composed of C-terminal cyclic phosphodiesterase and central polynucleotide kinase end-healing domains that convert the 2′,3′-cyclic-PO 4 and 5′-OH ends of tRNA exons into the 3′-OH,2′-PO 4 and 5′-PO 4 termini required for sealing by an N-terminal ATP-dependent ligase domain. Trifunctional Trl1 enzymes are present in most human fungal pathogens and are untapped targets for antifungal drug discovery. Mucorales species, deemed high-priority human pathogens by WHO, elaborate a noncanonical tRNA splicing apparatus in which a stand-alone monofunctional RNA ligase enzyme joins 3′-OH,2′-PO 4 and 5′-PO 4 termini. Here we identify a stand-aloneMucor circinelloidespolynucleotide kinase (MciKIN) and affirm its biological activity in tRNA splicing by genetic complementation in yeast. Recombinant MciKIN catalyzes magnesium-dependent phosphorylation of 5′-OH RNA and DNA ends in vitro. MciKIN displays a strong preference for GTP as the phosphate donor in the kinase reaction, a trait shared with the stand-alone RNA kinase homologs from Mucorales speciesRhizopus azygosporus(RazKIN) andLichtheimia corymbifera(LcoKIN) and with the kinase domains of fungal Trl1 enzymes. We report a 1.65 Å crystal structure of RazKIN in complex with GDP•Mg 2+ that illuminates the basis for guanosine nucleotide specificity.

Biochemistry & Molecular Biology↗
DOE OSTI2026

Quantum Computing Market Report

The quantum computing market is entering a rapid growth phase. Growth was originally driven by private investment interest in high value applications such as drug discovery, materials science, and finance. Currently the main market drivers include technical advances, continued private investment, and rising public funding. The quantum computing market is poised for explosive growth — with its market size estimated at $1.42 billion USD in 2024, and an expected compound annual growth rate of 20.5% from 2025 to 2030 [4]. Superconducting qubits are the largest qubit type by revenue. However, alternative approaches such as trapped ion, neutral atom, spin based, and photonic qubits are also attracting investment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Towards interpretable Cryo-EM: disentangling latent spaces of molecular conformations

Molecules are essential building blocks of life and their different conformations (i.e., shapes) crucially determine the functional role that they play in living organisms. Cryogenic Electron Microscopy (cryo-EM) allows for acquisition of large image datasets of individual molecules. Recent advances in computational cryo-EM have made it possible to learn latent variable models of conformation landscapes. However, interpreting these latent spaces remains a challenge as their individual dimensions are often arbitrary. The key message of our work is that this interpretation challenge can be viewed as an Independent Component Analysis (ICA) problem where we seek models that have the property of identifiability. That means, they have an essentially unique solution, representing a conformational latent space that separates the different degrees of freedom a molecule is equipped with in nature. Thus, we aim to advance the computational field of cryo-EM beyond visualizations as we connect it with the theoretical framework of (nonlinear) ICA and discuss the need for identifiable models, improved metrics, and benchmarks. Moving forward, we propose future directions for enhancing the disentanglement of latent spaces in cryo-EM, refining evaluation metrics and exploring techniques that leverage physics-based decoders of biomolecular systems. Moreover, we discuss how future technological developments in time-resolved single particle imaging may enable the application of nonlinear ICA models that can discover the true conformation changes of molecules in nature. The pursuit of interpretable conformational latent spaces will empower researchers to unravel complex biological processes and facilitate targeted interventions. This has significant implications for drug discovery and structural biology more broadly. More generally, latent variable models are deployed widely across many scientific disciplines. Thus, the argument we present in this work has much broader applications in AI for science if we want to move from impressive nonlinear neural network models to mathematically grounded methods that can help us learn something new about nature.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Protein-ligand binding affinity prediction using multi-instance learning with docking structures

Recent advances in 3D structure-based deep learning approaches demonstrate improved accuracy in predicting protein-ligand binding affinity in drug discovery. These methods complement physics-based computational modeling such as molecular docking for virtual high-throughput screening. Despite recent advances and improved predictive performance, most methods in this category primarily rely on utilizing co-crystal complex structures and experimentally measured binding affinities as both input and output data for model training. Nevertheless, co-crystal complex structures are not readily available and the inaccurate predicted structures from molecular docking can degrade the accuracy of the machine learning methods. We introduce a novel structure-based inference method utilizing multiple molecular docking poses for each complex entity. Our proposed method employs multi-instance learning with an attention network to predict binding affinity from a collection of docking poses. We validate our method using multiple datasets, including PDBbind and compounds targeting the main protease of SARS-CoV-2. The results demonstrate that our method leveraging docking poses is competitive with other state-of-the-art inference models that depend on co-crystal structures. This method offers binding affinity prediction without requiring co-crystal structures, thereby increasing its applicability to protein targets lacking such data.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2009

Life Science Research in Outer Space: New Platform Technologies for Low-Cost, Autonomous Small Satellite Missions

We develop integrated instruments and platforms suitable for economical, frequent space access for autonomous life science experiments and processes in outer space. The technologies represented by three of our recent free-flyer small-satellite missions are the basis of a rapidly growing toolbox of miniaturized biologically/biochemically-oriented instrumentation now enabling a new generation of in-situ space experiments. Autonomous small satellites (~ 1 50 kg) are less expensive to develop and build than fullsize spacecraft and not subject to the comparatively high costs and scheduling challenges of human-tended experimentation on the International Space Station, Space Shuttle, and comparable platforms. A growing number of commercial, government, military, and civilian space launches now carry small secondary science payloads at far lower cost than dedicated missions; the number of opportunities is particularly large for so-called cube-sat and multicube satellites in the 1 10 kg range. The recent explosion in nano-, micro-, and miniature technologies, spanning fields from telecommunications to materials to bio/chemical analysis, enables development of remarkably capable autonomous miniaturized instruments to accomplish remote biological experimentation. High-throughput drug discovery, point-of-care medical diagnostics, and genetic analysis are applications driving rapid progress in autonomous bioanalytical technology. Three of our recent missions exemplify the development of miniaturized analytical payload instrumentation: GeneSat-1 (launched: December 2006), PharmaSat (launched: May 2009), and O/OREOS (organism/organics exposure to orbital stresses; scheduled launch: May 2010). We will highlight the overall architecture and integration of fluidic, optical, sensor, thermal, and electronic technologies and subsystems to support and monitor the growth of microorganisms in culture in these small autonomous space satellites, including real-time tracking of their culture density, gene expression, and metabolic activity while in the space environment. Flight data and results will be presented from GeneSat-1, which tracked gene expression levels of GFP-labeled E. coli and from PharmaSat, which monitored the dose dependency of an antifungal agent against S. cerevisiae. The O/OREOS SESLO instrument, which will study the effects of radiation and microgravity upon the viability and growth characteristics of B. subtilis and the halophile Halorubrum chaoviatoris for periods of 0 - 6 months in space, will be described as well. The ongoing expansion of the small satellite toolbox of biological technologies will be summarized.

Ricco, Antonio J.↗
NASA NTRS2011

Mineralized three-dimensional bone constructs

The present disclosure provides ex vivo-derived mineralized three-dimensional bone constructs. The bone constructs are obtained by culturing osteoblasts and osteoclast precursors under randomized gravity vector conditions. Preferably, the randomized gravity vector conditions are obtained using a low shear stress rotating bioreactor, such as a High Aspect Ratio Vessel (HARV) culture system. The bone constructs of the disclosure have utility in physiological studies of bone formation and bone function, in drug discovery, and in orthopedics.

Clarke, Mark S. F.↗