SEARCH · Engineering Papers

Results for “SCORE”

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.

SourceResearch connectionFrom yearThrough year

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

At least 271 records · Page 15

All sources NASA NTRS DOE OSTI

DOE OSTI2023

When less is more: How increasing the complexity of machine learning strategies for geothermal energy assessments may not lead toward better estimates

Previous moderate- and high-temperature geothermal resource assessments of the western United States utilized data-driven methods and expert decisions to estimate resource favorability. Although expert decisions can add confidence to the modeling process by ensuring reasonable models are employed, expert decisions also introduce human and, thereby, model bias. This bias can present a source of error that reduces the predictive performance of the models and confidence in the resulting resource estimates. Our study aims to develop robust data-driven methods with the goals of reducing bias and improving predictive ability. We present and compare nine favorability maps for geothermal resources in the western United States using data from the U.S. Geological Survey's 2008 geothermal resource assessment. Two favorability maps are created using the expert decision-dependent methods from the 2008 assessment (i.e., weight-of-evidence and logistic regression). With the same data, we then create six different favorability maps using logistic regression (without underlying expert decisions), XGBoost, and support-vector machines paired with two training strategies. The training strategies are customized to address the inherent challenges of applying machine learning to the geothermal training data, which have no negative examples and severe class imbalance. We also create another favorability map using an artificial neural network. We demonstrate that modern machine learning approaches can improve upon systems built with expert decisions. We also find that XGBoost, a non-linear algorithm, produces greater agreement with the 2008 results than linear logistic regression without expert decisions, because the expert decisions in the 2008 assessment rendered the otherwise linear approaches non-linear despite the fact that the 2008 assessment used only linear methods. The F1 scores for all approaches appear low (F1 score < 0.10), do not improve with increasing model complexity, and, therefore, indicate the fundamental limitations of the input features (i.e., training data). Until improved feature data are incorporated into the assessment process, simple non-linear algorithms (e.g., XGBoost) perform equally well or better than more complex methods (e.g., artificial neural networks) and remain easier to interpret.

15 GEOTHERMAL ENERGY↗

DOE OSTI2023

Towards deep computer vision for in-line defect detection in polymer electrolyte membrane fuel cell materials

Polymer Electrolyte Membrane (PEM) fuel cells are a promising source of alternative energy. However, their production is limited by a lack of well-established methods for quality control of their constituent materials like the membrane-electrode assembly during roll-to-roll manufacturing. One potential solution is the implementation of deep learning methods to detect unwanted defects through their detection in scanned images. Here we explore the detection of defects like scratches, pinholes, and scuffs in a sample dataset of PEM optical images using two deep learning algorithms: Patch Distribution Modeling (PaDiM) for unsupervised anomaly detection and Faster-RCNN for supervised object detection. Both methods achieve scores on performance metrics (ROC-AUC and PRO-AUC for PaDiM and AP for Faster-RCNN) that are comparable to their scores on benchmark datasets. These methods also have the potential to detect a wider range of defects compared to IR thermography and previous optical inspection methods. Overall, deep learning shows promise at detecting relevant defects of interest and has the potential to achieve real-time defect detection.

30 DIRECT ENERGY CONVERSION↗

DOE OSTI2021

Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types

In the last decade, the widespread adoption of electronic health record documentation has created huge opportunities for information mining. Natural language processing (NLP) techniques using machine and deep learning are becoming increasingly widespread for information extraction tasks from unstructured clinical notes. Disparities in performance when deploying machine learning models in the real world have recently received considerable attention. In the clinical NLP domain, the robustness of convolutional neural networks (CNNs) for classifying cancer pathology reports under natural distribution shifts remains understudied. In this research, we aim to quantify and improve the performance of the CNN for text classification on out-of-distribution (OOD) datasets resulting from the natural evolution of clinical text in pathology reports. We identified class imbalance due to different prevalence of cancer types as one of the sources of performance drop and analyzed the impact of previous methods for addressing class imbalance when deploying models in real-world domains. Our results show that our novel class-specialized ensemble technique outperforms other methods for the classification of rare cancer types in terms of macro F1 scores. We also found that traditional ensemble methods perform better in top classes, leading to higher micro F1 scores. Based on our findings, we formulate a series of recommendations for other ML practitioners on how to build robust models with extremely imbalanced datasets in biomedical NLP applications.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2023

Understanding the trade-offs of national municipal solid waste estimation methods for circular economy policy

Policies embracing circular economy concepts have taken hold in national legislation around the world. As the number of governments and organizations adopting circular economy policies increases, so does the need for accurate and timely measurement of material resource flows. Since many countries do not have access to centrally reported municipal solid waste (MSW) data, estimation and modeling are critical in evaluating circular economy policy effectiveness. The purpose of this paper is to examine three modeling approaches estimating national MSW data in the United States, including industry-based material flow analysis, waste-extended input-output modeling, and aggregated regional waste reporting. We establish five criteria to guide the analysis through the context of policy monitoring (data quality, flow totality, update frequency, sensitivity to disruption, and product granularity) and use these criteria to analyze and score each model. We then use a literature search to identify five, internationally-implemented options for circular economy policy and determine the data and modeling components that are most helpful in evaluating policy effectiveness. Finally, we provide a crosswalk of the model scores and policy needs to inform the suitability of model selection by policy type. We found that data quality and update frequency are identified as critical components for evaluating circular economy policies within the models evaluated, and can both be fulfilled by aggregated regional waste reporting. Flow totality, sensitivity to disruption, and product granularity requirements vary by both model and policy types. While none of the evaluated models satisfy the combination of requirements for any of the five policies, industry-based material flow analysis offers flow totality for extended producer responsibility, landfill bans, and recycling rate target policies that typically require it. Here, the waste-extended input-output model can provide disruption sensitivity and product granularity as needed for policies like minimum recycled content and market restrictions. Policy developers in areas where strong centralized data collection is not an option should design policy action(s) with modeling tradeoffs in mind, including the potential hybridization of modeling approaches that may provide the most accurate national MSW estimates.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2021

Evaluation of Subseasonal-to-Seasonal (S2S) precipitation forecast from the North American Multi-Model ensemble phase II (NMME-2) over the contiguous U.S.

The second phase of the North America Multi-Model Ensemble (NMME-2) provides globally available Subseasonal-to-Seasonal (S2S) precipitation forecasts with a daily resolution. The S2S precipitation forecasts are getting increasing attention for their potentials in providing hydrometeorological forcing information for water resources planning at an extended range. However, the forecast skills of many existing S2S forecast products will significantly decrease when the lead time increases, hindering their applicability for watershed-scale hydrologic modeling. Therefore, forecast validation and large-scale evaluation are of great importance for water resources planning and hydrological applications. In this study, we comprehensively evaluate the S2S precipitation forecasts from the NMME-2 dataset over the contiguous United States (CONUS) and during the study period from 1982 to 2011. Three aspects of precipitation forecast capabilities are compared and analyzed: bias, skill scores, and the ability to predict extreme precipitation events. The Parameter-elevation Regressions on Independent Slopes Model (PRISM) is used as ground truth reference. Differs from other regional forecast validation study, we further examined and analyzed the dependences of NMME-2 precipitation forecast skills according to different seasonality, geographical locations, and lead times. Results show that the forecast biases are not sensitive to lead times but are seasonally dependent of all NMME-2 models. Overestimations are found in the Western U.S. in cooler seasons while underestimations are observed in the central regions of the U.S. in warmer seasons. The forecast skill of all individual NMME-2 models generally decreases as increases of lead times. The simple model averaging (SMA) of five NMME-2 models demonstrates a higher forecast skill than any individual NMME-2 models. Spatially, the highest forecast skill scores are observed at coastal areas in the Western U.S. with an one-week lead time. As compared to the historical resampled forecasts, NMME-2 also shows better performance in predicting extreme precipitation events above 99% percentiles and below 1% percentiles with higher probability of detections and lower false alarm ratios. Finally, the obtained results suggest the great potentials of NMME-2 precipitation forecasts in assisting ensemble hydrologic forecasts at the S2S scale over the CONUS.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

A novel conditional generative model for efficient ensemble forecasts of state variables in large-scale geological carbon storage

Integrating monitoring data to efficiently update reservoir pressure and CO 2 plume distribution forecasts presents a significant challenge in geological carbon storage (GCS) applications. Inverse modeling techniques are commonly used to fuse observational data and refine reservoir model parameters, thereby improving state variable forecasts. However, these techniques often rely on linear or Gaussian assumptions, which can limit their effectiveness in accurately predicting state variables. Moreover, simulating large-scale three-dimensional (3D) GCS problems is computationally expensive, making iterative runs in inverse problems prohibitive. To address these challenges, we propose a conditional generative model utilizing the score-based diffusion method for real-time 3D pressure and saturation field distribution predictions. Our approach involves solving the score function with a mini-batch-based Monte Carlo estimator to generate labeled data. This data is subsequently employed to train a fully connected neural network, enabling it to learn the conditional sample generator within a supervised learning framework. This method enables the rapid generation of a large ensemble of predictions, facilitating comprehensive uncertainty quantification of state variables. Here we applied our method to forecast the dynamic 3D distributions of pressure and saturation fields over a 30-year injection period. The statistical assessment with low root mean square error (RMSE) values demonstrates that our method can accurately predict the spatiotemporal distributions of both pressure and saturation fields. Moreover, the developed conditional generative model shows high computational efficiency by generating 100 ensemble forecasts of 3D state variables in less than 10 min. The consistency between ensemble averages and ground truth values further illustrates the model’s capability to capture state variable dynamics during the CO 2 plume injection process. Notably, the ground truth values fall within the ensemble forecasts, indicating that our uncertainty quantification effectively captures variability and potential noise in the observations. Thus, the developed conditional generative model proves to be a more efficient, accurate, and practical tool for GCS applications, facilitating timely risk analysis and informed decision-making.

58 GEOSCIENCES↗

DOE OSTI2022

Generalizability analysis of tool condition monitoring ensemble machine learning models

Tool condition monitoring (TCM) is an essential research area for the optimization and automation of metal machining processes, and could help manufacturers reduce costs, production time, machine downtime, energy use, and part scrappage. However, TCM systems developed in prior studies have struggled to reach the high level of generalizability which is necessary for industrial applications. This study addresses TCM system generalizability to new machining conditions, how variations in machining and environmental conditions may be used to improve model generalizability, and ensemble machine learning techniques for TCM. Further, milling tool life experiments were conducted using various machining conditions, and the processes' sound, spindle power, and axial load signals were collected. Different machine learning models were evaluated for the prediction of tool wear levels, including four individual models and five ensemble models. Changes in cutting speed were found to display a large effect on model performance, while the chip load showed some effect, and the feed rate had little effect. A simulated noise data augmentation technique for model improvement is applied within TCM for the first time, and resulted in increased model generalizability and reduced overfitting. Across several performance metrics the extremely randomized trees ensemble machine learning model generally performed the best for this application, achieving a leave-one-group-out cross validation accuracy score of 92.4 %, a 10-fold cross validation score of 98.9 %, and an averaged accuracy across 11 generalizability tests of 87.3 %.

42 ENGINEERING↗

DOE OSTI2025

Characterization and prediction of the electromechanical wear of contact tips during wire arc additive manufacturing of 316L stainless steel

Here, this study seeks to better understand the degradation of the contact tip with respect to WAAM for a 316L wire electrode as well as explore methods of monitoring the contact tip state from process data. The contact tip, a consumable component, positions the wire and serves as the electrical contact surface between the wire electrode and the welding power supply. The wear of the contact tip was characterized in terms of material loss and material contamination for a set of tips worn to discrete levels as measured by the amount of wire fed or arc time. Geometrical characterization found a 49% increase in the bore exit area at 180 meters of wire fed. Machine learning models were developed to predict the relative bore exit area of the contact tip from arc-based process data and a random forest classifier exhibited favorable performance with a cross-validated f1-score of 0.84. The regression architecture implemented a multi-layer perceptron with the ability to predict the relative exit area with an $R^2$ score of 0.75. Key features used in the prediction include the standard deviation of the voltage and the time between shorts.

Contact tip wear↗

DOE OSTI2022

Monitoring and prediction of porosity in laser powder bed fusion using physics-informed meltpool signatures and machine learning

In this work we accomplished the monitoring and prediction of porosity in laser powder bed fusion (LPBF) additive manufacturing process. This objective was realized by extracting physics-informed meltpool signatures from an in-situ dual-wavelength imaging pyrometer, and subsequently, analyzing these signatures via computationally tractable machine learning approaches. Porosity in LPBF occurs despite extensive optimization of processing conditions due to stochastic causes. Hence, it is essential to continually monitor the process with in-situ sensors for detecting and mitigating incipient pore formation. In this work a tall cuboid-shaped part (10 mm × 10 mm × 137 mm, material ATI 718Plus) was built with controlled porosity by varying laser power and scanning speed. This test caused various types of porosity, such as lack-of-fusion and keyhole formation, with varying degrees of severity in the part. The meltpool was continuously monitored using a dual-wavelength imaging pyrometer installed in the machine. Physically intuitive process signatures, such as meltpool length, temperature distribution, and ejecta (spatter) characteristics, were extracted from the meltpool images. Subsequently, relatively simple machine learning models, e.g., K-Nearest Neighbors, were trained to predict both the severity and type of porosity as a function of these physics-informed meltpool signatures. These models resulted in a prediction accuracy exceeding 95% (statistical F1-score). The same analysis was carried out with a complex, black-box deep learning convolutional neural network which directly used the meltpool images instead of physics-informed features. The convolutional neural network produced a comparable F1-score in the range of 89–97%. Finally, these results demonstrate that using pragmatic, physics-informed meltpool signatures within a simple machine learning model is as effective for flaw prediction in LPBF as using a complex and computationally demanding black-box deep learning model.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Comparison of Expert Vocabulary Usage Patterns Between Mental Health and Nonmental Health Clinicians When Diagnosing Pediatric Anxiety Disorders

Objective: To compare the utilization patterns of expert vocabulary (EVo) in diagnosing pediatric anxiety between mental health and non-mental health clinical notes from electronic health records to understand the role of Evo in informing classification and decision-making in anxiety diagnoses. Study design: We conducted a retrospective study using a cohort less than age 25 from Cincinnati Children's Hospital including 897 685 patients with 61 586 446 notes. We analyzed EVo, collected from mental health clinicians, in both mental and nonmental health notes. We compared classification accuracy using EVo-based patient-level embedding from all clinical notes, mental-health notes, and nonmental health notes for 2 tasks: 1) pre-vs postdiagnosis anxiety patients, and 2) prediagnosis anxiety vs nonanxiety patients. Results: EVo usage was highest in prediagnosis anxiety, lower in nonanxiety, and lowest in post-diagnosis. Classification models using EVo features from all, mental-health, and non-mental health notes showed similar F1 scores for prediagnosis anxiety (0.70 ± 0.2 for 2 categories). For anxiety vs nonanxiety classification, all clinical and nonmental health notes had better F1 scores than mental-health notes (above 0.90 for 3 categories). There was a notable difference in class-wise performance across both tasks. Conclusions: There are significant differences in anxiety EVo use between mental health and nonmental health clinicians. Despite less anxiety-specific terminology, non-mental health notes still captured key aspects of patient presentations, emphasizing the importance of including all clinicians' notes in analysis. EVo's utility for anxiety classification is most effective in prediagnostic phases, suggesting the need for a dedicated diagnostic lexicon and further study before incorporating EVo into classification models.

feature engineering↗

DOE OSTI2025

A hybrid numerical and machine learning framework for evaluating the performance of a 780 cm 2 aqueous organic redox flow battery

Aqueous organic redox flow battery (AORFB) is a promising cost-competitive technology for large-scale energy storage. Among existing work, the dihydroxyphenazine (DHP)-based AORFB has demonstrated high energy density and low capacity degradation in 10 cm2 cells during lab tests. However, its commercial-scale performance in more complex environments remains unknown, posing a barrier for commercialization. To address this gap, this work presents a comprehensive performance evaluation of a 780 cm 2 DHP-based AORFB by combining physics-based numerical model, machine learning (ML)-based surrogate models, and ML-derived sensitivity quantification. Specifically, we first select 12 key battery parameters that include 10 physicochemical quantities and 2 operation quantities, then select 6 performance metrics that include energy efficiency (EE), discharging capacity, charging energy, and power losses due to concentration, activation, and ohmic over-potentials. With such selection, 12800 combinations of the 12 parameters are subsequently generated using the Latin Hypercube Sampling method. These combinations, together with 38 pre-defined State of Charge, are then integrated to a validated AORFB model developed in COMSOL to compute the performance metrics. With both input parameters and performance metrics, 60 deep neural network (DNN) surrogate models are then trained to approximate the relationship between the 10 physicochemical quantities and 6 performance metrics at each flow rate and current density. Sensitivity scores are then calculated based on the DNN models. Two additional sensitivity analysis tools, i.e., MARS, and SHAP, are also used to cross-validate the sensitivity scores from the DNN. The results demonstrate that 1) the standard potential ranks the first in controlling EE and charging energy, 2) the membrane conductivity is most critical for power loss and EE, and 3) specific area and reaction rate control activation power loss.

25 ENERGY STORAGE↗

DOE OSTI2023

Evaluating the effectiveness of M-AMBI with other biotic indexes in a temperate estuary

Need for a scalable and widely applicable index has been increasingly important. This study evaluates the applicability of the M-AMBI, a potential comprehensive index, at small spatial scales. M-AMBI was compared to regional indices (EMAP-E and GOM B-IBI), assessing response to natural environmental gradients and low oxygen stress. Results indicate poor agreement between indices with M-AMBI and GOM B-IBI showing positive correlation but significant disagreement in habitat condition. EMAP-E had no agreement. Indices showed similar patterns of better habitat scores in higher salinities. M-AMBI also showed a negative relationship with sediment organic matter and total nitrogen. DO influenced all indices with M-AMBI the most sensitive. However, mismatches between DO and index score were observed further calibration may be needed before adoption into programs. Altogether, the M-AMBI demonstrates potential at smaller, local scales, but additional studies are needed to validate its performance in different coastal environments and under different conditions.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Combined effects of horizontal and vertical resolution on reliable turbulence prediction at tidal energy sites: A systematic study in the Salish Sea, WA

Predicting turbulence characteristics with coastal ocean models is essential for tidal energy converter deployment. While large eddy simulation provides a detailed turbulence representation, computational limitations restrict its use to smaller domains. We systematically evaluate whether well-configured coastal models can provide reliable turbulence prediction through progressive refinement of 3D model representation. We implemented four model configurations (Levels 1–4) using terrain-following coordinates, isolating the impacts of horizontal resolution, vertical resolution, and layer distribution. We validated all configurations against field measurements from the Salish Sea, WA. Results show that tidal current velocity predictions remain unchanged regarding model configuration, but turbulence properties are sensitive to resolution refinement. Increasing vertical resolution alone proved insufficient; even with vertical sigma-levels rising from 11 to 41, significant underprediction persisted until finer horizontal resolution better captured bathymetric variations. The Level 4 configuration, incorporating geometric sigma-levels distribution, achieved turbulence prediction skill scores exceeding 0.90. Turbulence closure comparison revealed Mellor- Yamada 2.5 outperformed k-epsilon in TKE prediction (skill scores 0.84–0.94 versus 0.72–0.81) due to better boundary layer parameterization. This study shows that well-configured coastal models effectively bridge the gap between simplified tools and costly high-fidelity modeling, offering the tidal energy industry practical and cost-effective turbulence data at commercially relevant scales.

Marine Energy↗

DOE OSTI2022

Evaluating wind speed and power forecasts for wind energy applications using an open-source and systematic validation framework

Building on the verification and validation work developed under the Second Wind Forecast Improvement Project, this work exhibits the value of a consistent procedure to evaluate wind power forecasts. We established an open-source Python code base tailored for wind speed and wind power forecast validation, WE-Validate. The code base can evaluate model forecasts with observations in a coherent manner. To demonstrate the systematic validation framework of WE-Validate, we designed and hosted a forecast evaluation benchmark exercise. We invited forecast providers in industry and academia to participate and submit forecasts for two case studies. We then evaluated the submissions with WE-Validate. Our findings suggest that ensemble means have reasonable skills in time series forecasting, whereas they are often inferior to single ensemble members in wind ramp forecasting. Adopting a voting scheme in ramp forecasting that allows ensemble members to detect ramps independently leads to satisfactory skill scores. Throughout this document, we also emphasize the importance of using statistically robust and resistant metrics as well as equitable skill scores in forecast evaluation.

17 WIND ENERGY↗

DOE OSTI2024

Learning From User Behavior: A Survey-Assist Algorithm for Longitudinal Mobility Data Collection

GPS-based travel surveys are widely used in mobility studies to gather crucial qualitative data, like purpose, transportation mode and replaced mode. However, survey response still poses a burden to users, especially in long-term mobility studies, leading to response fatigue. We explore a survey-assist strategy to ease this burden by a novel, user-level modeling approach that leverages past responses from each user to predict responses for new trips, without relying on external data sources like GIS data. We investigate three main algorithms for predicting responses: (i) clustering trips and extrapolating responses for similar trips, (ii) using random forest classification, and (iii) clustering that uses a hybrid algorithm to determine spatial structure, which is then fed as input to a classic random forest classifier. The clustering approach can flexibly predict responses for even complex qualitative survey questions; it achieved F-scores of 65%. The random forest pipeline uses architecture that restricts it to predicting three predetermined survey questions: trip purpose, mode, and replaced mode. However, it achieved F-scores of 78%. While the survey-assist approach has been implemented by several proprietary systems, to our knowledge, this is the first exploration in the academic literature. It follows that this is also the first rigorous evaluation of multiple algorithms that can implement the approach. The evaluation uses a large scale, publicly available, longitudinal dataset consisting of ~ 92k trips from 235 users over a period of roughly one and a half years. With this approach, travel surveys can be pre-filled with the predicted responses for each trip, thus streamlining the survey process for users. Combined with an active learning system that requests user input on low-confidence predictions, models can be updated and improved over time to better support the long-term collection of longitudinal qualitative data.

clustering↗

DOE OSTI2023

Analysis of the molecular determinants for furin cleavage of the spike protein S1/S2 site in defined strains of the prototype coronavirus murine hepatitis virus (MHV)

We analyzed the spike protein S1/S2 cleavage of selected strains of a prototype coronavirus, mouse hepatitis virus (MHV) by the cellular protease furin, in order to understand the structural requirements underlying the sequence selectivity of the scissile segment. The probability of cleavage of selected MHV strains was first evaluated from furin cleavage scores predicted by the ProP computer software, and then cleavage was measured experimentally with a fluorogenic peptide cleavage assay consisting of S1/S2 peptide mimics and purified furin. We found that in vitro cleavability varied across MHV strains in line with predicted results—but with the notable exception of MHV-A59, which was not cleaved despite a high score predicted for its sequence. Using the known X-Ray structure of furin in complex with a substrate-like inhibitor as an initial structural reference, we carried out molecular dynamics (MD) simulations to learn the modes of binding of the peptides in the furin active site, and the suitability of the complex for initiation of the enzymatic cleavage. We identified the 3D structural requirements of the furin active site configuration that enable bound peptides to undergo cleavage, and the way in which the various strains tested experimentally are fulfilling these requirements. We find that despite some flexibility in the organization of the peptide bound to the active site of the enzyme, the presence of a histidine at P2 of MHV-A59 fails to properly orient the sidechain of His194 of the furin catalytic triad and therefore produces a distortion that renders the peptide/complex structural configuration in the active site incompatible with requirements for cleavage initiation. The Ser/Thr in P1 of MHV-2 and MHV-S has a similar effect of distorting the conformation of the furin active site residues produced by the elimination of the canonical salt-bridge formed by arginine in P1 position. This work informs a study of coronavirus infection and pathogenesis with respect to the function of the viral spike protein, and suggests an important process of viral adaptation and evolution within the spike S1/S2 structural loop.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2020

Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19

In this work, we present a supercomputer-driven pipeline for in silico drug discovery using enhanced sampling molecular dynamics (MD) and ensemble docking. Ensemble docking makes use of MD results by docking compound databases into representative protein binding-site conformations, thus taking into account the dynamic properties of the binding sites. We also describe preliminary results obtained for 24 systems involving eight proteins of the proteome of SARS-CoV-2. The MD involves temperature replica exchange enhanced sampling, making use of massively parallel supercomputing to quickly sample the configurational space of protein drug targets. Using the Summit supercomputer at the Oak Ridge National Laboratory, more than 1 ms of enhanced sampling MD can be generated per day. We have ensemble docked repurposing databases to 10 configurations of each of the 24 SARS-CoV-2 systems using AutoDock Vina. Comparison to experiment demonstrates remarkably high hit rates for the top scoring tranches of compounds identified by our ensemble approach. We also demonstrate that, using Autodock-GPU on Summit, it is possible to perform exhaustive docking of one billion compounds in under 24 h. Finally, we discuss preliminary results and planned improvements to the pipeline, including the use of quantum mechanical (QM), machine learning, and artificial intelligence (AI) methods to cluster MD trajectories and rescore docking poses.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2021

CyProduct: A software tool for accurately predicting the byproducts of human cytochrome P450 metabolism

In silico metabolism prediction is a cheminformatic task of autonomously predicting the set of metabolic byproducts produced from a specified molecule and a set of enzymes or reactions. Here we describe a novel machine-learned in silico cytochrome P450 (CYP450) metabolism prediction suite, called CyProduct, that accurately predicts metabolic byproducts for a specified molecule and a human CYP450 isoform. It includes three modules: (1) CypReact, a tool that predicts if the query compound reacts with a given CYP450 enzyme; (2) CypBoM, a tool that accurately predicts the “bond site” of the reaction (i.e., which specific bonds within the query molecule react with the CYP isoform); and (3) MetaboGen, a tool that generates the metabolic byproducts based on CypBoM’s bond-site prediction. CyProduct predicts metabolic biotransformation products for each of the nine most important human CYP450 enzymes. CypBoM uses an important new concept called “Bond of Metabolism” (BoM), which extends the traditional “Site of Metabolism" (SoM) by specifying the information about the set of chemical bonds that is modified or formed in a metabolic reaction (rather than the specific atom). We created a BoM database for 3487 CYP450-mediated Phase I reactions, then used this to train the CypBoM Predictor to predict the reactive bond locations on substrate molecules. CypBoM Predictor’s cross-validated Jaccard score for reactive bond prediction ranged from 0.380 to 0.452 over the nine CYP450 enzymes. Over variants of a test set of 72 known CYP450 substrates and 30 non-reactants, CyProduct outperformed the other packages -- including ADMET Predictor, BioTransformer and GLORY -- by an average of 200% (wrt Jaccard score) in terms of predicting metabolites. The CyProduct suite and the datasets are freely available at https://bitbucket.org/wishartlab/cyproduct/src/master/.

Machine learning, Cytochrome P450, Metabolism pred↗