Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model 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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

The Enterprise , a massive transposon carrying Spok meiotic drive genes

The genomes of eukaryotes are full of parasitic sequences known as transposable elements (TEs). Here, we report the discovery of a putative giant tyrosine-recombinase-mobilized DNA transposon, Enterprise, from the model fungus Podospora anserina. Previously, we described a large genomic feature called the Spok block which is notable due to the presence of meiotic drive genes of the Spok gene family. The Spok block ranges from 110 kb to 247 kb and can be present in at least four different genomic locations within P. anserina, despite what is an otherwise highly conserved genome structure. We propose that the reason for its varying positions is that the Spok block is not only capable of meiotic drive but is also capable of transposition. More precisely, the Spok block represents a unique case where the Enterprise has captured the Spoks, thereby parasitizing a resident genomic parasite to become a genomic hyperparasite. Furthermore, we demonstrate that Enterprise (without the Spoks) is found in other fungal lineages, where it can be as large as 70 kb. Lastly, we provide experimental evidence that the Spok block is deleterious, with detrimental effects on spore production in strains which carry it. This union of meiotic drivers and a transposon has created a selfish element of impressive size in Podospora, challenging our perception of how TEs influence genome evolution and broadening the horizons in terms of what the upper limit of transposition may be.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Novel small molecule FGF 23 inhibitors increase serum phosphate and improve skeletal abnormalities in Hyp mice

We report that excess fibroblast growth factor 23 (FGF23) causes hereditary hypophosphatemic rickets, such as X-linked hypophosphatemia (XLH) and tumor induced osteomalacia (TIO). A small molecule that specifically binds to FGF23 to prevent activation of the FGFR/a-Klotho complex has potential advantages over the currently approved systemically administered FGF23 blocking antibody. Using structure-based drug design we previously identified ZINC13407541 (N-[[2-(2-phenylethenyl)cyclopenten-1-yl]methylidene]hydroxylamine) as a small molecule antagonist for FGF23. Additional structure-activity studies developed a series of ZINC13407541 analogues with enhanced drug-like properties. In this study, we tested in a pre-clinical Hyp mouse homologue of XLH a direct connect analogue (8n) [(E)-2-(4-(tert-butyl)phenyl)cyclopent-1-ene-1-carbaldehyde oxime] that exhibited the greatest stability in microsomal assays, and 13a [(E)-2-((E)-4-methylstyryl)benzaldehyde oxime] that exhibited increased in vitro potency. Using cryo-electron microscopy (Cryo-EM) structure and computational docking, we identified a key binding residue (Q156) of the FGF23 antagonists, ZINC13407541 and its analogues (8n and 13a) in the N-terminal domain of FGF23 protein. Site-directed mutagenesis and bimolecular fluorescence complementation (BiFC)-fluorescence resonance energy transfer (FRET) assay confirmed the binding site of these three antagonists. We found that pharmacological inhibition of FGF23 with either of these compounds blocked FGF23 signaling and increased serum phosphate and 1,25(OH)2D concentrations in Hyp mice. Long-term parenteral treatment with 8n or 13a also enhanced linear bone growth, increased mineralization of bone, and narrowed the growth plate in Hyp mice. The more potent 13a compound had greater therapeutic effects in Hyp mice. Further optimization of these FGF23 inhibitors may lead to versatile drugs to treat excess FGF23-mediated disorders.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Leverage modern artificial intelligence (AI) enabled systems for waste reduction

Manufacturing industries continue to face challenges in reducing waste, as upstream strategies such as source reduction and product redesign require a deeper understanding of processes compared to conventional recycling methods. Recent advancements in artificial intelligence (AI) and machine learning (ML) have opened new opportunities to integrate modern computational techniques with traditional waste minimization strategies. This paper explores AI-enabled approaches for product redesign, source reduction, and recycling that can significantly reduce waste generation while improving efficiency and sustainability. AI-driven material substitution and lightweighting in product design enable discovery of novel materials with optimized properties, reducing waste without compromising performance. Reinforcement learning models optimize process parameters, raw material specifications, and machine sequencing to minimize production losses, while Industrial Internet of Things (IIoT) systems paired with AI analytics enhance real-time waste tracking, predictive maintenance, and quality inspection. Furthermore, AI-based demand forecasting and production planning reduce overproduction and excess inventory, as demonstrated in industrial applications. In recycling, ML-powered pattern recognition and robotic sorting technologies achieve higher accuracy in waste segregation, directly improving recycling efficiency. Complementary solutions such as smart bins and AI-enabled waste pickup scheduling optimize collection logistics, reducing both costs and emissions. Although implementation requires upfront investment in infrastructure and training, the long-term benefits include higher material efficiency, reduced waste, improved product quality, and stronger sustainability outcomes across the supply chain. By leveraging AI-enabled systems, manufacturers can align waste minimization efforts with circular economy principles, creating scalable solutions for both industry and society.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody–Antigen Interactions

This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein–protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

DATA-DRIVEN DISCOVERY OF DYNAMICS FROM TIME-RESOLVED COHERENT SCATTERING

This software implements a data-driven framework to uncover mechanistic models of dynamics directly from time-resolved coherent X-ray scattering measurements. It employs neural differential equations to parameterize unknown real-space dynamics and incorporates a computational scattering forward model to relate real-space predictions to reciprocal-space observations.

Zhou, Tao↗
DOE OSTI2024

Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning

Recently, rainfall-runoff simulations in small headwater basins have been improved by methodological advances such as deep neural networks (NNs) and hybrid physics-NN models—particularly, a genre called differentiable modeling that intermingles NNs with physics to learn relationships between variables. However, hydrologic routing simulations, necessary for simulating floods in stem rivers downstream of large heterogeneous basins, had not yet benefited from these advances and it was unclear if the routing process could be improved via coupled NNs. We present a novel differentiable routing method (δMC-Juniata-hydroDL2) that mimics the classical Muskingum-Cunge routing model over a river network but embeds an NN to infer parameterizations for Manning's roughness (n) and channel geometries from raw reach-scale attributes like catchment areas and sinuosity. The NN was trained solely on downstream hydrographs. Synthetic experiments show that while the channel geometry parameter was unidentifiable, n can be identified with moderate precision. With real-world data, the trained differentiable routing model produced more accurate long-term routing results for both the training gage and untrained inner gages for larger subbasins (>2,000 km2) than either a machine learning model assuming homogeneity, or simply using the sum of runoff from subbasins. The n parameterization trained on short periods gave high performance in other periods, despite significant errors in runoff inputs. The learned n pattern was consistent with literature expectations, demonstrating the framework's potential for knowledge discovery, but the absolute values can vary depending on training periods. The trained n parameterization can be coupled with traditional models to improve national-scale hydrologic flood simulations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Interplay of freeze-in and freeze-out: Lepton-flavored dark matter and muon colliders

We study a lepton-flavored dark matter model and its signatures at a future muon collider. We focus on the less-explored regime of feeble dark matter interactions, which suppresses the dangerous lepton-flavor-violating processes, gives rise to dark matter freeze-in production, and leads to long-lived particle signatures at colliders. We find that the interplay of dark matter freeze-in and its mediator freeze-out gives rise to an upper bound of around TeV scales on the dark matter mass. The signatures of this model depend on the lifetime of the mediator and can range from generic prompt decays to more exotic long-lived particle signals. In the prompt region, we calculate the signal yield, study useful kinematics cuts, and report tolerable systematics that would allow for a 5 σ discovery. In the long-lived region, we calculate the number of charged tracks and displaced lepton signals of our model in different parts of the detector and uncover kinematic features that can be used for background rejection. We show that, unlike in hadron colliders, multiple production channels contribute significantly, which leads to sharply distinct kinematics for electroweakly charged long-lived particle signals. Ultimately, the collider signatures of this lepton-flavored dark matter model are common among models of electroweak-charged new physics, rendering this model a useful and broadly applicable benchmark model for future muon collider studies that can help inform work on detector design and studies of systematics. Published by the American Physical Society 2024

Astronomy & Astrophysics↗
DOE OSTI2025

Fostering a Guiding Multiscale Model for the Development of Advanced MgB 2 Hydrogen Storage Materials (Final Technical Report)

Project Goal and Objective. The demand for energy and for an upgraded energy infrastructure has steadily grown, as have the needs for energy independence and alternatives to our reliance on petroleum. Hydrogen is considered the most viable fuels for wide-scale implementation in the near future as it is less-polluting, non-toxic, and has more stored energy than petroleum. It is envisioned that hydrogen can eventually become the prime energy carrier, integrating the transportation, grid, and chemical sectors in a way that improves resiliency, diversifies feedstocks, and affords new economic opportunities. A key remaining challenge is the development materials with enhanced gravimetric and volumetric hydrogen storage capacities that offer a higher performance than compressed gas. These materials would eliminate the need for large-scale compression, thereby dramatically reducing the footprint and cost of gas storage. The high gravimetric and volumetric hydrogen capacities of complex hydrides has prompted an intensive investigation of the potential of this class of materials as hydrogen storage media over the past 25 years. Among the many complex hydrides that have been explored, magnesium borohydride, Mg(BH 4 ) 2 , has been found to possess the best combination of practical thermodynamic properties. These include a gravimetric H 2 density of 14.9 wt% H 2 and thermodynamics for the dehydrogenation of Mg(BH 4 ) 2 to MgB 2 (equation 1) (ΔH° = 39 kJ/mol H 2 , ΔS = 112 J/K mol H 2 ) which lie in the narrow window required Mg(BH 4 ) 2 $\Leftrightarrow$ MgB 2 + 4 H 2 (1) for reversibility under moderate pressure and temperature. However, overcoming the extremely slow kinetics of the reversible release of hydrogen by this material in the solid state is a daunting challenge. At temperatures greater than 400 °C, the borohydride releases up to 14 wt% hydrogen giving MgB 2 . We discovered that the direct re-hydrogenation of MgB 2 to Mg(BH 4 ) 2 can be accomplished under 950 bar H 2 at 400 °C. While this demonstrated that complete reversibility can be achieved, the conditions employed are far too extreme for commercial hydrogen storage applications. More recently, we found through US DOE funded research projects (EERE HyMARC and HySCOR), that hydrogen cycling, can be accomplish at much milder conditions upon modification of the borohydride or boride. Guided by these discoveries these discoveries, the objective of this research project was to obtain key information that will enable the development of a model of reversible hydrogenation of MgB 2 to Mg(BH 4 ) 2 . The ultimate goal of our efforts is to attain a model of this transformation that can be utilized to accelerate development further advanced materials. This project directly follows on discoveries that were made over the course of a US DOE, EERE HyMARC project that was focused on improvement of the hydrogen cycling kinetics of modified MgB 2 . We found that that mechanical milling with graphene results the desired, pronounced kinetic enhancement. The dramatic lowering of the conditions required for the hydrogenation of MgB 2 is a significant step towards overcoming its chemical inertness allowing its development as a practical onboard hydrogen storage material. However, the exact nature of the modification(s) of MgB 2 that is responsible for its activation towards hydrogenation is completely unknown. This situation is not unique, as efforts to develop hydrogen storage materials typically have a narrow focus rather than a comprehensive approach that takes atomic level bonding and structure; molecular dynamics; long range, nano- and mesoscale-structure and their interconnection all into account. The goal of this project was the development of a comprehensive, multi-scale computational model of reversible hydrogenation of MgB 2 to Mg(BH 4 ) 2 that can be utilized for development of higher performance versions of the modified material. Development of the model requires determination of: 1) the bulk, nano-scale, and meso-scale structural changes occurring at elevated pressure following mechano-chemical modification of MgB 2 ; 2) the reaction pathway of the reversible hydrogenation of MgB 2 to Mg(BH 4 ) 2 ; 3) the effect of elevated pressure and mechano-chemical modification on the chemical reaction pathways; 4) the interactions at solid-gas interfaces; and particle surfaces; and 5) the kinetics and thermodynamic parameters associated with each step of the hydrogenation reaction pathway. This investigation required advanced techniques as preliminary, standard XRD, 11 B NMR, and FTIR analysis showed no signs of material modification. In order to gain this level of understanding of modified MgB 2 , required the teaming of a diverse group of experts and state-of-the art experimental capabilities at the University of Hawaii at Manoa (UHM) and collaborating National Laboratories: Craig Jensen , Department of Chemistry (PI and Project Director), solid state, solution, and high pressure NMR spectroscopy; solid-state synthesis; and high pressure hydrogenation (collaboration with SNL); Godwin Severa , Hawaii Natural Energy Institute (co-PI) calorimetry; infrared and Raman spectroscopy (collaboration with NREL); Dera , high pressure X-ray diffraction including in situ experiments (collaboration with ANL); Hope Ishii , Hawaii Institute of Geophysics electron microscopy investigations (collaboration with LBNL); and Joe Brown , Mechanical Engineering , material electronic structure and electric field effects.

08 HYDROGEN↗
DOE OSTI2023

Materials characterization: Can artificial intelligence be used to address reproducibility challenges?

Material characterization techniques are widely used to characterize the physical and chemical properties of materials at the nanoscale and, thus, play central roles in material scientific discoveries. However, the large and complex datasets generated by these techniques often require significant human effort to interpret and extract meaningful physicochemical insights. Artificial intelligence (AI) techniques such as machine learning (ML) have the potential to improve the efficiency and accuracy of surface analysis by automating data analysis and interpretation. In this perspective paper, we review the current role of AI in surface analysis and discuss its future potential to accelerate discoveries in surface science, materials science, and interface science. We highlight several applications where AI has already been used to analyze surface analysis data, including the identification of crystal structures from XRD data, analysis of XPS spectra for surface composition, and the interpretation of TEM and SEM images for particle morphology and size. We also discuss the challenges and opportunities associated with the integration of AI into surface analysis workflows. These include the need for large and diverse datasets for training ML models, the importance of feature selection and representation, and the potential for ML to enable new insights and discoveries by identifying patterns and relationships in complex datasets. Most importantly, AI analyzed data must not just find the best mathematical description of the data, but it must find the most physical and chemically meaningful results. In addition, the need for reproducibility in scientific research has become increasingly important in recent years. The advancement of AI, including both conventional and the increasing popular deep learning, is showing promise in addressing those challenges by enabling the execution and verification of scientific progress. By training models on large experimental datasets and providing automated analysis and data interpretation, AI can help to ensure that scientific results are reproducible and reliable. Although integration of knowledge and AI models must be considered for the transparency and interpretability of models, the incorporation of AI into the data collection and processing workflow will significantly enhance the efficiency and accuracy of various surface analysis techniques and deepen our understanding at an accelerated pace.

Materials Science↗
DOE OSTI2020

Radiological Recovery Logistics Tool - 20161

Argonne is building and testing a tool, the Radiological Recovery Logistics Tool (RRLT), that can be used during the response and recovery from a radiological or nuclear incident to effectively allocate appropriate commercial and public works equipment to mitigate, remove, and contain radiological contamination. The requirements for this tool - as well as development of the resulting software - is overseen by a steering committee of stakeholders from DHS's National Urban Security Technology Laboratory (NUSTL), the Federal Emergency Management Agency (FEMA), and the Environmental Protection Agency (EPA). One essential requirement is for RRLT to support the efficient and appropriate allocation of resources for a radiological response. Subsequent discussions between ANL and stakeholders have solidified the nature of this support to include identification of the types of resources to be allocated. The study reported in this paper has both factored fundamental concepts and connections out of this identification process and created a Knowledge Base detailing support goals, response scenarios, and efficacy information on dozens of equipment types. In short, RRLT will dynamically apply these findings to situational conditions surrounding contamination incidents. RRLT's Domain, the model of elements, ideas and relationships with which the tool will work, draws concepts from technical reports and stakeholder vocabularies to connect response goals and scenarios to types of equipment that offer utility towards those goals in those scenarios. RRLT's Knowledge Base will contain details on dozens of equipment types and facilitate the operator's discovery and consumption of these details most pertinent to a dynamically selected subset of goals. The core of its Domain Model is based on a report authored by this team. This report [1] contains a comprehensive list of proposed equipment to accomplish various missions or scenarios that might arise after a large-scale radiological contamination incident in an urban environment or critical infrastructure. The report divides potential response and recovery efforts into five support goals: Survey and monitoring of the contaminated area; Mitigation of received dose to first responders: Decontamination (gross and final) of buildings, vehicles, roadways, parks, and other surfaces: Waste management of solid waste generated during recovery operations: and Containment of wastewater and other waste generated during the response and recovery phases. RRLT's development is driven by use cases. A use case is an intention with which a user approaches the software. Use cases are grouped into delivery increments to schedule development, testing, and presentation to stakeholders. This model partitions the system into seven increments: User Arrival and Authentication, Search and Navigation, Equipment Recommendation, Plan Management, Content Management, and Expanded Access. Once a user 15 authenticated, RRLT will present the user with a dashboard that allows them to explore or search RRLT's content. The dashboard will also include a 'Plan' panel for collecting decisions and relevant observations about an incident at hand to facilitate development of an equipment list. RRLT will offer three general modes of access to items in the knowledge base: - Keyword search for direct discovery of items, - Navigation along predetermined paths from recovery goal towards equipment types, and - Interactive guidance towards equipment types by an autonomous software agent: the Equipment Recommendation Wizard. This presentation will detail progress in the development of the RRLT and also discuss opportunities for those interested in providing feedback on its content and functionality. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

MINE: a new way to design genetics experiments for discovery

Abstract The Maximally Informative Next Experiment or MINE is a new experimental design approach for experiments, such as those in omics, in which the number of effects or parameters p greatly exceeds the number of samples n (p > n). Classical experimental design presumes n > p for inference about parameters and its application to p > n can lead to over-fitting. To overcome p > n, MINE is an ensemble method, which makes predictions about future experiments from an existing ensemble of models consistent with available data in order to select the most informative next experiment. Its advantages are in exploration of the data for new relationships with n < p and being able to integrate smaller and more tractable experiments to replace adaptively one large classic experiment as discoveries are made. Thus, using MINE is model-guided and adaptive over time in a large omics study. Here, MINE is illustrated in two distinct multiyear experiments, one involving genetic networks in Neurospora crassa and a second one involving a genome-wide association study in Sorghum bicolor as a comparison to classic experimental design in an agricultural setting.

Biochemistry & Molecular Biology↗
DOE OSTI2026

Livewire: A Model Platform for Data Quality Assessment and AI Readiness Across DOE Missions

High-quality, well-governed data is essential for accelerating discovery and achieving operational excellence across DOE and national laboratory missions. The Livewire Data Platform is a DOE-supported platform that offers automated assessments of data quality, standardization, provenance, and Artificial Intelligence (AI) readiness. It allows researchers and data practitioners to systematically and easily evaluate datasets against established governance criteria and prepare them for advanced analytics. Livewire addresses critical challenges in DOE's data ecosystem with integrated capabilities for metadata validation, provenance tracking, and schema alignment. This platform's automated workflows assist users in identifying data quality gaps, enhancing interoperability between datasets collected from various stakeholders, and ensuring compliance with DOE data standards, all while reducing manual curation efforts. Additionally, we will discuss its AI readiness framework, which is being developed to prepare datasets for training models, developing advanced analytic tools, and machine learning applications. Using some of the more than one hundred tabular datasets on Livewire, processed with this open-source methodology, we will demonstrate how Livewire can serve as a model for scalable, standards-driven data management. This approach provides a pathway to leverage existing and future datasets within the DOE, boosting innovation and efficiency across national laboratories.

33 - ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

Text Mining for Process–Structure–Properties Relationships in Metals

With the advent of large language models (LLMs), the vast unstructured text within millions of academic papers is increasingly accessible for materials discovery—although significant challenges remain. While LLMs offer promising few- and zero-shot learning capabilities, particularly valuable in the materials domain where expert annotations are scarce, general-purpose LLMs often fail to address key materials-specific queries without further adaptation. To bridge this gap, fine-tuning LLMs on human-labeled data is essential for effective structured knowledge extraction (Liu in The Importance of Human-Labeled Data in the Era of LLMs, 2023). Here, in this study, we introduce a novel annotation schema designed to extract generic process–structure–properties relationships from scientific literature. We demonstrate the utility of this approach using a dataset of 128 abstracts, with annotations drawn from two distinct domains: high-temperature materials (Domain I) and uncertainty quantification in simulating materials microstructure (Domain II). Initially, we developed a conditional random field (CRF) model based on MatBERT—a domain-specific BERT variant—and evaluated its performance on Domain I. Subsequently, we compared this model with a fine-tuned LLM (GPT-4o from OpenAI) under identical conditions. Our results indicate that fine-tuning LLMs can significantly improve entity extraction performance over the BERT-CRF baseline on Domain I. However, when additional examples from Domain II were incorporated, the performance of the BERT-CRF model became comparable to that of the GPT-4o model. These findings underscore the potential of our schema for structured knowledge extraction and highlight the complementary strengths of both modeling approaches.

Materials science↗
DOE OSTI2025

Hierarchical Gaussian process-based Bayesian optimization for materials discovery in high entropy alloy spaces

Bayesian optimization (BO) is a powerful and data-efficient method for iterative materials discovery and design, particularly valuable when prior knowledge is limited, underlying functional relationships are complex or unknown, and the cost of querying the materials space is significant. Traditional BO methodologies typically utilize conventional Gaussian Processes (cGPs) to model the relationships between material inputs and properties, as well as correlations within the input space. However, cGP-BO approaches often fall short in multi-objective optimization scenarios, where they are unable to fully exploit correlations between distinct material properties. Leveraging these correlations can significantly enhance the discovery process, as information about one property can inform and improve predictions about others. Here, this study addresses this limitation by employing advanced kernel structures to capture and model multi-dimensional property correlations through multi-task (MTGPs) or deep Gaussian Processes (DGPs), thus accelerating the discovery process. We demonstrate the effectiveness of MTGP-BO and DGP-BO in rapidly and robustly solving complex materials design challenges that occur within the context of complex multi-objective optimization over FCC FeCrNiCoCu high entropy alloy (HEA) spaces, where traditional cGP-BO approaches fail. Furthermore, we highlight how the differential costs associated with querying various material properties can be strategically leveraged to make the materials discovery process more cost-efficient.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Improving deep learning model performance under parametric constraints for materials informatics applications

Abstract Modern machine learning (ML) and deep learning (DL) techniques using high-dimensional data representations have helped accelerate the materials discovery process by efficiently detecting hidden patterns in existing datasets and linking input representations to output properties for a better understanding of the scientific phenomenon. While a deep neural network comprised of fully connected layers has been widely used for materials property prediction, simply creating a deeper model with a large number of layers often faces with vanishing gradient problem, causing a degradation in the performance, thereby limiting usage. In this paper, we study and propose architectural principles to address the question of improving the performance of model training and inference under fixed parametric constraints. Here, we present a general deep-learning framework based on branched residual learning (BRNet) with fully connected layers that can work with any numerical vector-based representation as input to build accurate models to predict materials properties. We perform model training for materials properties using numerical vectors representing different composition-based attributes of the respective materials and compare the performance of the proposed models against traditional ML and existing DL architectures. We find that the proposed models are significantly more accurate than the ML/DL models for all data sizes by using different composition-based attributes as input. Further, branched learning requires fewer parameters and results in faster model training due to better convergence during the training phase than existing neural networks, thereby efficiently building accurate models for predicting materials properties.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Gene-Metabolite Association Prediction with Interactive Knowledge Transfer Enhanced Graph for Metabolite Production

Identifying gene targets for enhancing metabolite production in metabolic engineering is challenging due to the vast research literature and the approximation in genome-scale metabolic model (GEM) simulations. Here, to address this, we propose the Gene-Metabolite Association Prediction task, which automates gene discovery for given metabolite-gene pairs, accompanied by a benchmark dataset of 2474 metabolites and 1947 genes for Saccharomyces cerevisiae (SC) and Issatchenkia orientalis (IO). This task is complicated by incomplete metabolic graphs and metabolic heterogeneity. We introduce an Interactive Knowledge Transfer mechanism based on Metabolism Graphs (IKT4Meta) to enhance prediction accuracy by integrating cross-metabolism knowledge. Using Pretrained Language Models (PLMs) to generate inter-graph links mitigates heterogeneity issues, while intra-graph links are propagated via these anchors. Gene-metabolite predictions are then performed on the enriched graphs integrating multiple microorganisms’ knowledge. Experiments show that IKT4Meta outperforms baselines by up to 12.3% in link prediction.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Electron g − 2 foreshadowing discoveries at FCC-ee

A future e + e − circular collider (FCC-ee) may provide a unique probe of the electron Yukawa coupling through Higgs boson production on resonance. Motivated by this exciting possibility, we examine a simple model which can result in O ( 10 ) modifications of the Higgs coupling to electrons. The model can also lead to deviations in the electron anomalous magnetic moment, g e − 2 , which at present shows a + 2.2 σ or − 3.7 σ deviation, implied by differing precision determinations of the electromagnetic fine structure constant. The electron g e − 2 can be a forerunner for FCC-ee discoveries which, as we elucidate, may not be accessible to the high-luminosity LHC measurements. A simple extension of our model can also account for the current deviation in the muon g μ − 2 . Published by the American Physical Society 2024

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

$t\overline{t}t\overline{t}$ signatures through the lens of color-octet scalars

We reinterpret two recent LHC searches for events containing four top quarks ($t\overline{t}t\overline{t}$) in the context of supersymmetric models with Dirac gauginos and color-octet scalars (sgluons). We explore whether sgluon contributions to the four-top production cross section σ ($pp$ → $t\overline{t}t\overline{t}$) can accommodate an excess of four-top events recently reported by the ATLAS collaboration. We also study constraints on these models from an ATLAS search for new phenomena with high jet multiplicity and significant missing transverse energy ($E^{miss}_{T}$) sensitive to signals with four top quarks. We find that these two analyses provide complementary constraints, with the jets + $E^{miss}_{T}$ search exceeding the four-top cross section measurement in sensitivity for sgluons heavier than about 800 GeV. We ultimately find that either a scalar or a pseudoscalar sgluon can currently fit the ATLAS excess in a range of reasonable benchmark scenarios, though a pseudoscalar in minimal Dirac gaugino models is ruled out. We finally offer sensitivity projections for these analyses at the HL-LHC, mapping the 5σ discovery potential in sgluon parameter space and computing exclusion limits at 95% CL in scenarios where no excess is found.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗