Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “predicted”

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 1,441 records · Page 80
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

SU-C-204-01: A Fast Analytical Approach for Prompt Gamma and PET Predictions in a TPS for Proton Range Verification

Purpose: We describe and demonstrate a fast analytical tool for prompt-gamma emission prediction based on filter functions applied on the depth dose profile. We present the implementation in a treatment planning system (TPS) of the same algorithm for positron emitter distributions. Methods: The prediction of the desired observable is based on the convolution of filter functions with the depth dose profile. For both prompt-gammas and positron emitters, the results of Monte Carlo simulations (MC) are compared with those of the analytical tool. For prompt-gamma emission from inelastic proton-induced reactions, homogeneous and inhomogeneous phantoms alongside with patient data are used as irradiation targets of mono-energetic proton pencil beams. The accuracy of the tool is assessed in terms of the shape of the analytically calculated depth profiles and their absolute yields, compared to MC. For the positron emitters, the method is implemented in a research RayStation TPS and compared to MC predictions. Digital phantoms and patient data are used and positron emitter spatial density distributions are analyzed. Results: Calculated prompt-gamma profiles agree with MC within 3 % in terms of absolute yield and reproduce the correct shape. Based on an arbitrary reference material and by means of 6 filter functions (one per chemical element), profiles in any other material composed of those elements can be predicted. The TPS implemented algorithm is accurate enough to enable, via the analytically calculated positron emitters profiles, detection of range differences between the TPS and MC with errors of the order of 1–2 mm. Conclusion: The proposed analytical method predicts prompt-gamma and positron emitter profiles which generally agree with the distributions obtained by a full MC. The implementation of the tool in a TPS shows that reliable profiles can be obtained directly from the dose calculated by the TPS, without the need of full MC simulation.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

SU-E-J-256: Predicting Metastasis-Free Survival of Rectal Cancer Patients Treated with Neoadjuvant Chemo-Radiotherapy by Data-Mining of CT Texture Features of Primary Lesions

Purpose: The purpose of this study is to investigate the relationship between computed tomographic (CT) texture features of primary lesions and metastasis-free survival for rectal cancer patients; and to develop a datamining prediction model using texture features. Methods: A total of 220 rectal cancer patients treated with neoadjuvant chemo-radiotherapy (CRT) were enrolled in this study. All patients underwent CT scans before CRT. The primary lesions on the CT images were delineated by two experienced oncologists. The CT images were filtered by Laplacian of Gaussian (LoG) filters with different filter values (1.0–2.5: from fine to coarse). Both filtered and unfiltered images were analyzed using Gray-level Co-occurrence Matrix (GLCM) texture analysis with different directions (transversal, sagittal, and coronal). Totally, 270 texture features with different species, directions and filter values were extracted. Texture features were examined with Student’s t-test for selecting predictive features. Principal Component Analysis (PCA) was performed upon the selected features to reduce the feature collinearity. Artificial neural network (ANN) and logistic regression were applied to establish metastasis prediction models. Results: Forty-six of 220 patients developed metastasis with a follow-up time of more than 2 years. Sixtyseven texture features were significantly different in t-test (p<0.05) between patients with and without metastasis, and 12 of them were extremely significant (p<0.001). The Area-under-the-curve (AUC) of ANN was 0.72, and the concordance index (CI) of logistic regression was 0.71. The predictability of ANN was slightly better than logistic regression. Conclusion: CT texture features of primary lesions are related to metastasisfree survival of rectal cancer patients. Both ANN and logistic regression based models can be developed for prediction.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

SU-E-T-39: A Logistic Function-Based Model to Predict Organ-At-Risk (OAR) DVH in IMRT Treatment Planning

Purpose: To investigate the feasibility of a logistic function-based model to predict organ-at-risk (OAR) DVH for IMRT planning. The predicted DVHs are compared to achieved DVHs by expert treatment planners. Methods: A logistic function is used to model the OAR dose-gradient function. This function describes the percentage of the prescription dose as a function of the normal distance to PTV surface. The slope of dose-gradient function is function of relative spatial orientation of the PTV and OARs. The OAR DVH is calculated using the OAR dose-gradient function assuming that the dose is same for voxels with same normal distance to PTV. Ten previously planned prostate IMRT plans were selected to build the model, and the following plan parameters were calculated as possible features to the model: the PTV maximum/minimum dose, PTV volume, bladder/rectum volume in the radiation field, percentage of bladder/rectum overlapping with PTV, and the distance between the bladder/rectum centroid and PTV. The bladder/rectum dose-gradient function was modeled and applied on 10 additional test cases, and the predicted and achieved clinical bladder/rectum DVHs were compared: V70 (percentage of volume receiving 70Gy and above), V65, V60, V55, V50, V45, V40. Results: The following parameters were selected as model features: PTV volume, and distance of centroid of rectum/bladder to PTV. The model was tested with 10 additional patients. For bladder, the absolute difference (mean±standard deviation) between predicted and clinical DVHs is V70=−0.3±3.2, V65=−0.8±3.9, V60=1.5±4.3, V55=1.7±5.3, V50=−0.6±6.4, V45=0.6±6.5, and V40=0.9±5.7, the correlation coefficient is 0.96; for rectum, the difference is V70=1.5±3.8, V65=1.2±4.2, V60=−0.1±5.3, V55=1.0±6.6, V50=1.6±8.7, V45=1.9±9.8, and V40=1.5±10.1, and the correlation coefficient is 0.87. Conclusion: The OAR DVH can be accurately predicted using the OAR dose-gradient function in IMRT plans. This approach may be used as a quality control tool and aid less experienced planners determine benchmarks for plan quality.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

SU-E-T-802: Verification of Implanted Cardiac Pacemaker Doses in Intensity-Modulated Radiation Therapy: Dose Prediction Accuracy and Reduction Effect of a Lead Sheet

Purpose: To verify delivered doses on the implanted cardiac pacemaker, predicted doses with and without dose reduction method were verified using the MOSFET detectors in terms of beam delivery and dose calculation techniques in intensity-modulated radiation therapy (IMRT). Methods: The pacemaker doses for a patient with a tongue cancer were predicted according to the beam delivery methods [step-and-shoot (SS) and sliding window (SW)], intensity levels for dose optimization, and dose calculation algorithms. Dosimetric effects on the pacemaker were calculated three dose engines: pencil-beam convolution (PBC), analytical anisotropic algorithm (AAA), and Acuros-XB. A lead shield of 2 mm thickness was designed for minimizing irradiated doses to the pacemaker. Dose variations affected by the heterogeneous material properties of the pacemaker and effectiveness of the lead shield were predicted by the Acuros-XB. Dose prediction accuracy and the feasibility of the dose reduction strategy were verified based on the measured skin doses right above the pacemaker using mosfet detectors during the radiation treatment. Results: The Acuros-XB showed underestimated skin doses and overestimated doses by the lead-shield effect, even though the lower dose disagreement was observed. It led to improved dose prediction with higher intensity level of dose optimization in IMRT. The dedicated tertiary lead sheet effectively achieved reduction of pacemaker dose up to 60%. Conclusion: The current SS technique could deliver lower scattered doses than recommendation criteria, however, use of the lead sheet contributed to reduce scattered doses.Thin lead plate can be a useful tertiary shielder and it could not acuse malfunction or electrical damage of the implanted pacemaker in IMRT. It is required to estimate more accurate scattered doses of the patient with medical device to design proper dose reduction strategy.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

MO-AB-BRA-10: Cancer Therapy Outcome Prediction Based On Dempster-Shafer Theory and PET Imaging

Purpose: In cancer therapy, utilizing FDG-18 PET image-based features for accurate outcome prediction is challenging because of 1) limited discriminative information within a small number of PET image sets, and 2) fluctuant feature characteristics caused by the inferior spatial resolution and system noise of PET imaging. In this study, we proposed a new Dempster-Shafer theory (DST) based approach, evidential low-dimensional transformation with feature selection (ELT-FS), to accurately predict cancer therapy outcome with both PET imaging features and clinical characteristics. Methods: First, a specific loss function with sparse penalty was developed to learn an adaptive low-rank distance metric for representing the dissimilarity between different patients’ feature vectors. By minimizing this loss function, a linear low-dimensional transformation of input features was achieved. Also, imprecise features were excluded simultaneously by applying a l2,1-norm regularization of the learnt dissimilarity metric in the loss function. Finally, the learnt dissimilarity metric was applied in an evidential K-nearest-neighbor (EK- NN) classifier to predict treatment outcome. Results: Twenty-five patients with stage II–III non-small-cell lung cancer and thirty-six patients with esophageal squamous cell carcinomas treated with chemo-radiotherapy were collected. For the two groups of patients, 52 and 29 features, respectively, were utilized. The leave-one-out cross-validation (LOOCV) protocol was used for evaluation. Compared to three existing linear transformation methods (PCA, LDA, NCA), the proposed ELT-FS leads to higher prediction accuracy for the training and testing sets both for lung-cancer patients (100+/−0.0, 88.0+/−33.17) and for esophageal-cancer patients (97.46+/−1.64, 83.33+/−37.8). The ELT-FS also provides superior class separation in both test data sets. Conclusion: A novel DST- based approach has been proposed to predict cancer treatment outcome using PET image features and clinical characteristics. A specific loss function has been designed for robust accommodation of feature set incertitude and imprecision, facilitating adaptive learning of the dissimilarity metric for the EK-NN classifier.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

TU-CD-BRB-09: Prediction of Chemo-Radiation Outcome for Rectal Cancer Based On Radiomics of Tumor Clinical Characteristics and Multi-Parametric MRI

Purpose: To evaluate the tumor clinical characteristics and quantitative multi-parametric MR imaging features for prediction of response to chemo-radiation treatment (CRT) in locally advanced rectal cancer (LARC). Methods: Forty-three consecutive patients (59.7±6.9 years, from 09/2013 – 06/2014) receiving neoadjuvant CRT followed by surgery were enrolled. All underwent MRI including anatomical T1/T2, Dynamic Contrast Enhanced (DCE)-MRI and Diffusion-Weighted MRI (DWI) prior to the treatment. A total of 151 quantitative features, including morphology/Gray Level Co-occurrence Matrix (GLCM) texture from T1/T2, enhancement kinetics and the voxelized distribution from DCE-MRI, apparent diffusion coefficient (ADC) from DWI, along with clinical information (carcinoembryonic antigen CEA level, TNM staging etc.), were extracted for each patient. Response groups were separated based on down-staging, good response and pathological complete response (pCR) status. Logistic regression analysis (LRA) was used to select the best predictors to classify different groups and the predictive performance were calculated using receiver operating characteristic (ROC) analysis. Results: Individual imaging category or clinical charateristics might yield certain level of power in assessing the response. However, the combined model outperformed than any category alone in prediction. With selected features as Volume, GLCM AutoCorrelation (T2), MaxEnhancementProbability (DCE-MRI), and MeanADC (DWI), the down-staging prediciton accuracy (area under the ROC curve, AUC) could be 0.95, better than individual tumor metrics with AUC from 0.53–0.85. While for the pCR prediction, the best set included CEA (clinical charateristics), Homogeneity (DCE-MRI) and MeanADC (DWI) with an AUC of 0.89, more favorable compared to conventional tumor metrics with an AUC ranging from 0.511–0.79. Conclusion: Through a systematic analysis of multi-parametric MR imaging features, we are able to build models with improved predictive value over conventional imaging or clinical metrics. This is encouraging, suggesting the wealth of imaging radiomics should be further explored to help tailor the treatment into the era of personalized medicine. This work is supported by the National Science Foundation of China (NSFC Grant No. 81201091), National High Technology Research and Development Program of China (863 program, Grant No. 2015AA020917), and Fund Project for Excellent Abroad Scholar Personnel in Science and Technology.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

Collision prediction software for radiotherapy treatments

Purpose: This work presents a method of collision predictions for external beam radiotherapy using surface imaging. The present methodology focuses on collision prediction during treatment simulation to evaluate the clearance of a patient’s treatment position and allow for its modification if necessary. Methods: A Kinect camera (Microsoft, Redmond, WA) is used to scan the patient and immobilization devices in the treatment position at the simulator. The surface is reconstructed using the SKANECT software (Occipital, Inc., San Francisco, CA). The treatment isocenter is marked using simulated orthogonal lasers projected on the surface scan. The point cloud of this surface is then shifted to isocenter and converted from Cartesian to cylindrical coordinates. A slab models the treatment couch. A cylinder with a radius equal to the normal distance from isocenter to the collimator plate, and a height defined by the collimator diameter is used to estimate collisions. Points within the cylinder clear through a full gantry rotation with the treatment couch at 0° , while points outside of it collide. The angles of collision are reported. This methodology was experimentally verified using a mannequin positioned in an alpha cradle with both arms up. A planning CT scan of the mannequin was performed, two isocenters were marked in PINNACLE, and this information was exported to AlignRT (VisionRT, London, UK)—a surface imaging system for patient positioning. This was used to ensure accurate positioning of the mannequin in the treatment room, when available. Collision calculations were performed for the two treatment isocenters and the results compared to the collisions detected the room. The accuracy of the Kinect-Skanect surface was evaluated by comparing it to the external surface of the planning CT scan. Results: Experimental verification results showed that the predicted angles of collision matched those recorded in the room within 0.5°, in most cases (largest deviation −1.2°). The accuracy study for the Kinect-Skanect surface showed an average discrepancy between the CT external contour and the surface scan of 2.2 mm. Conclusions: This methodology provides fast and reliable collision predictions using surface imaging. The use of the Kinect-Skanect system allows for a comprehensive modeling of the patient topography including all the relevant anatomy and immobilization devices that may lead to collisions. The use of this tool at the treatment simulation stage may allow therapists to evaluate the clearance of a patient’s treatment position and optimize it before the planning CT scan is performed. This can allow for safer treatments for the patients due to better collision predictions and improved clinical workflow by minimizing replanning and resimulations due to unforeseen clearance issues.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

SU-F-J-199: Predictive Models for Cone Beam CT-Based Online Verification of Pencil Beam Scanning Proton Therapy

Purpose: To utilize online CBCT scans to develop models for predicting DVH metrics in proton therapy of head and neck tumors. Methods: Nine patients with locally advanced oropharyngeal cancer were retrospectively selected in this study. Deformable image registration was applied to the simulation CT, target volumes, and organs at risk (OARs) contours onto each weekly CBCT scan. Intensity modulated proton therapy (IMPT) treatment plans were created on the simulation CT and forward calculated onto each corrected CBCT scan. Thirty six potentially predictive metrics were extracted from each corrected CBCT. These features include minimum/maximum/mean over and under-ranges at the proximal and distal surface of PTV volumes, and geometrical and water equivalent distance between PTV and each OARs. Principal component analysis (PCA) was used to reduce the dimension of the extracted features. Three principal components were found to account for over 90% of variances in those features. Datasets from eight patients were used to train a machine learning model to fit these principal components with DVH metrics (dose to 95% and 5% of PTV, mean dose or max dose to OARs) from the forward calculated dose on each corrected CBCT. The accuracy of this model was verified on the datasets from the 9th patient. Results: The predicted changes of DVH metrics from the model were in good agreement with actual values calculated on corrected CBCT images. Median differences were within 1 Gy for most DVH metrics except for larynx and constrictor mean dose. However, a large spread of the differences was observed, indicating additional training datasets and predictive features are needed to improve the model. Conclusion: Intensity corrected CBCT scans hold the potential to be used for online verification of proton therapy and prediction of delivered dose distributions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

MO-DE-207B-05: Predicting Gene Mutations in Renal Cell Carcinoma Based On CT Imaging Features: Validation Using TCGA-TCIA Datasets

Purpose: The goal of this work is to investigate the use of contrast enhanced computed tomographic (CT) features for the prediction of mutations of BAP1, PBRM1, and VHL genes in renal cell carcinoma (RCC). Methods: For this study, we used two patient databases with renal cell carcinoma (RCC). The first one consisted of 33 patients from our institution (UT Southwestern Medical Center, UTSW). The second one consisted of 24 patients from the Cancer Imaging Archive (TCIA), where each patient is connected by a unique identi?er to the tissue samples from the Cancer Genome Atlas (TCGA). From the contrast enhanced CT image of each patient, tumor contour was first delineated by a physician. Geometry, intensity, and texture features were extracted from the delineated tumor. Based on UTSW dataset, we completed feature selection and trained a support vector machine (SVM) classifier to predict mutations of BAP1, PBRM1 and VHL genes. We then used TCIA-TCGA dataset to validate the predictive model build upon UTSW dataset. Results: The prediction accuracy of gene expression of TCIA-TCGA patients was 0.83 (20 of 24), 0.83 (20 of 24), and 0.75 (18 of 24) for BAP1, PBRM1, and VHL respectively. For BAP1 gene, texture feature was the most prominent feature type. For PBRM1 gene, intensity feature was the most prominent. For VHL gene, geometry, intensity, and texture features were all important. Conclusion: Using our feature selection strategy and models, we achieved predictive accuracy over 0.75 for all three genes under the condition of using patient data from one institution for training and data from other institutions for testing. These results suggest that radiogenomics can be used to aid in prognosis and used as convenient surrogates for expensive and time consuming gene assay procedures.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

TU-AB-202-03: Prediction of PET Transfer Uncertainty by DIR Error Estimating Software, AUTODIRECT

Purpose: Deformable image registration (DIR) is a powerful tool, but DIR errors can adversely affect its clinical applications. To estimate voxel-specific DIR uncertainty, a software tool, called AUTODIRECT (automated DIR evaluation of confidence tool), has been developed and validated. This work tests the ability of this software to predict uncertainty for the transfer of standard uptake values (SUV) from positron-emission tomography (PET) with DIR. Methods: Virtual phantoms are used for this study. Each phantom has a planning computed tomography (CT) image and a diagnostic PET-CT image set. A deformation was digitally applied to the diagnostic CT to create the planning CT image and establish a known deformation between the images. One lung and three rectum patient datasets were employed to create the virtual phantoms. Both of these sites have difficult deformation scenarios associated with them, which can affect DIR accuracy (lung tissue sliding and changes in rectal filling). The virtual phantoms were created to simulate these scenarios by introducing discontinuities in the deformation field at the lung rectum border. The DIR algorithm from Plastimatch software was applied to these phantoms. The SUV mapping errors from the DIR were then compared to that predicted by AUTODIRECT. Results: The SUV error distributions closely followed the AUTODIRECT predicted error distribution for the 4 test cases. The minimum and maximum PET SUVs were produced from AUTODIRECT at 95% confidence interval before applying gradient-based SUV segmentation for each of these volumes. Notably, 93.5% of the target volume warped by the true deformation was included within the AUTODIRECT-predicted maximum SUV volume after the segmentation, while 78.9% of the target volume was within the target volume warped by Plastimatch. Conclusion: The AUTODIRECT framework is able to predict PET transfer uncertainty caused by DIR, which enables an understanding of the associated target volume uncertainty.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2018

Uranium polyhydrides at moderate pressures: Prediction, synthesis, and expected superconductivity

Hydrogen-rich hydrides attract great attention due to recent theoretical (1) and then experimental discovery of record high-temperature superconductivity in H 3 S [T c = 203 K at 155 GPa (2)]. Here we search for stable uranium hydrides at pressures up to 500 GPa using ab initio evolutionary crystal structure prediction. Chemistry of the U-H system turned out to be extremely rich, with 14 new compounds, including hydrogen-rich UH 5 , UH 6 , U 2 H 13 , UH 7 , UH 8 , U 2 H 17 , and UH 9 . Their crystal structures are based on either common face-centered cubic or hexagonal close-packed uranium sublattice and unusual H 8 cubic clusters. Our high-pressure experiments at 1 to 103 GPa confirm the predicted UH 7 , UH 8 , and three different phases of UH 5 , raising confidence about predictions of the other phases. Many of the newly predicted phases are expected to be high-temperature superconductors. The highest-T c superconductor is UH 7 , predicted to be thermodynamically stable at pressures above 22 GPa (with T c = 44 to 54 K), and this phase remains dynamically stable upon decompression to zero pressure (where it has T c = 57 to 66 K).

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2023

Volcanic forcing degrades multiyear-to-decadal prediction skill in the tropical Pacific

Volcanic aerosol forcing can affect global climate, but its role in climate prediction remains poorly understood. We isolate the impact of volcanic eruptions on multiyear-to-decadal climate prediction skill by comparing two suites of initialized decadal hindcasts conducted with and without historical volcanic forcing. Unexpectedly, the inclusion of volcanic forcing in the prediction system significantly degrades the forecast skill of detrended multiyear-to-decadal sea surface temperature (SST) variability in the central-eastern tropical Pacific. The ensemble mean hindcasts produce multiyear-to-decadal tropical Pacific SST cooling in response to large tropical volcanic eruptions through thermodynamic and El Niño–Southern Oscillation (ENSO)–like dynamic processes. However, in observations, these eruptions coincided with tropical Pacific warming, which is well predicted by the no-volcano hindcasts and, hence, is likely related to internal climate variability. Improved model representation of volcanic response and its interaction with internal climate variability is required to advance prediction of tropical Pacific decadal variability and associated global impacts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Data-driven global ocean modeling for seasonal to decadal prediction

Accurate modeling of ocean dynamics is crucial for enhancing our understanding of complex ocean circulation processes, predicting climate variability, and tackling challenges posed by climate change. Although great efforts have been made to improve traditional numerical models, predicting global ocean variability over multiyear scales remains challenging. Here, we propose ORCA-DL (Oceanic Reliable foreCAst via Deep Learning), a data-driven three-dimensional ocean model for seasonal to decadal prediction of global ocean dynamics. ORCA-DL accurately simulates the three-dimensional structure of global ocean dynamics with high physical consistency and outperforms state-of-the-art numerical models in capturing extreme events, including El Niño–Southern Oscillation and upper ocean heat waves. Moreover, ORCA-DL stably emulates ocean dynamics at decadal timescales, demonstrating its potential even for skillful decadal predictions and climate projections. Our results demonstrate the high potential of data-driven models for providing efficient and accurate global ocean modeling and prediction.

Science & Technology - Other Topics↗
DOE OSTI2023

Predicting variable gene content in Escherichia coli using conserved genes

Having the ability to predict the protein-encoding gene content of an incomplete genome or metagenome-assembled genome is important for a variety of bioinformatic tasks. In this study, as a proof of concept, we built machine learning classifiers for predicting variable gene content in Escherichia coli genomes using only the nucleotide k-mers from a set of 100 conserved genes as features. Protein families were used to define orthologs, and a single classifier was built for predicting the presence or absence of each protein family occurring in 10%–90% of all E. coli genomes. The resulting set of 3,259 extreme gradient boosting classifiers had a per-genome average macro F1 score of 0.944 [0.943–0.945, 95% CI]. We show that the F1 scores are stable across multi-locus sequence types and that the trend can be recapitulated by sampling a smaller number of core genes or diverse input genomes. Surprisingly, the presence or absence of poorly annotated proteins, including “hypothetical proteins” was accurately predicted (F1 = 0.902 [0.898–0.906, 95% CI]). Models for proteins with horizontal gene transfer-related functions had slightly lower F1 scores but were still accurate (F1s = 0.895, 0.872, 0.824, and 0.841 for transposon, phage, plasmid, and antimicrobial resistance-related functions, respectively). Finally, using a holdout set of 419 diverse E. coli genomes that were isolated from freshwater environmental sources, we observed an average per-genome F1 score of 0.880 [0.876–0.883, 95% CI], demonstrating the extensibility of the models. Overall, this study provides a framework for predicting variable gene content using a limited amount of input sequence data.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Modeling protein structures from predicted contacts with modern molecular dynamics potentials: accuracy, sensitivity, and refinement

Protein structure prediction has become increasingly popular and successful in recent years. An essential step for fragment-free, template-free methods is the generation of a final three-dimensional protein model from a set of predicted amino acid contacts that are often described by interresidue pairwise atomic distances. Here we explore the use of modern, open-source molecular dynamics (MD) engines, which have been continually developed over the last three decades with all-atom Hamiltonians to model biomolecular structure and dynamics, to generate accurate protein structures starting from a set of inferred pairwise distances. Additionally, the ability of MD empirical physical potentials to correct inaccuracies in the predicted geometries is tested. We rigorously characterize the effect of modeling parameters on results, the effect of different amounts of error in the predicted distances on the final structures, and test the ability of post-processing analysis to sort the best models out of a set of statistical replicas. We find that with exact distances and with noisy distances, the method can produce excellent structural models, and that the molecular dynamics force field seems to help correct errors in distance predictions, resisting the effects of applied noise.

Davidson, Russ↗
DOE OSTI2024

A Deep Multimodal Representation Learning Framework for Accurate Molecular Properties Prediction

Drug discovery is a complex and challenging process, requiring the optimization of candidate compounds to identify those with the potential to become safe and effective drugs. Predicting molecular properties is an indispensable step in the drug discovery pipeline. Traditionally, this process is costly and time-intensive, involving multiple rounds of experiments and clinical trials, rendering it impractical for every candidate compound. Deep learning techniques have emerged as a promising approach to drug discovery to reduce the cost and time required to identify novel drugs. However, prevalent research in deep learning models focused on predicting molecular properties has primarily fixated on single-modal models, which utilize a single modality of data, neglecting the potential benefits of combining different data modalities. To overcome this limitation, we introduce MRL-Mol: a deep \textbf{M}ultimodal \textbf{R}epresentation \textbf{L}earning framework for accurate \textbf{Mol}ecular properties prediction. MRL-Mol harnesses three data modalities: sequence, graph, and image, augmenting the depth of comprehension. Leveraging a large-scale unlabeled dataset~($\sim$1M unique molecules), we pretrain MRL-Mol to extract inter- and intra-modal information. Our study demonstrates the superior performance of MRL-Mol in predicting molecular properties across six benchmark datasets, including both classification and regression tasks. Notably, MRL-Mol outperforms other state-of-the-art molecular properties prediction models. These findings suggest that by combining information from multiple data modalities, MRL-Mol can comprehend molecules better than single-modal deep learning models and identify molecular properties with better accuracy.

Yang, Yuxin↗
DOE OSTI2023

Comparing Experimentally-Measured Sand’s Times with Concentrated Solution Theory Predictions in a Polymer Electrolyte

We compare the electrochemically measured Sand’s time, the time required for the cell potential to diverge when the applied current density exceeds the limiting current, with theoretical predictions for a 0.47 M poly(ethylene oxide) (5 kg mol −1 )/LiTFSI electrolyte. The theoretical predictions are made using concentrated solution theory which accounts for both concentration polarization and polymer motion, using independently measured parameters that depend on concentration, c : conductivity ( κ ), salt diffusion coefficient ( D ), cationic transference number with respect to the solvent velocity ( t + 0 ), thermodynamic factor 1 + dln f ± dln c , and partial molar volume of the salt ( V ̅ ); f ± is the mean molar activity coefficient of the salt. We find quantitative agreement between experimental data and theoretical predictions. We derive a generalized analytical expression for Sand’s time for electrolytes based on dilute solution theory. This expression correctly predicts the divergence of the Sand’s time at the limiting current, in agreement with experimental data and concentrated solution theory predictions. When the applied current is large compared to the limiting current, the analytical expression approaches the standard expression for Sand’s time used in the literature.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

labquake_future_prediction

The labquake_future_prediction code is a collection of python modules and scripts that serves as supporting information for the article “Predicting future laboratory fault friction through deep learning” for publication in the journal of “Geophysical Research Letters”. It is designed to predict laboratory fault slips in the immediate future by scanning continuous acoustic emission (AE) waveforms recorded in laboratory biaxial shear experiments. The predictions are made with a deep learning model based on convolutional encoder-decoder (CED) models and the Transformer model primarily developed for Natural Language Processing (NLP). The deep learning model is trained with the tensorflow package using publicly available laboratory data sets in standard binary file format in numpy. The utility functions for reading data files, configuring model hyperparameters, constructing the CED and Transformer models, training and testing of the models are defined in python module files. The workflow of training the models for labquake future predictions and the multiple GPU’s rapid model hyperparameter optimization as described in the journal article, are demonstrated in accompanying python script files and Jupyter notebooks.

Wang, Kun↗