Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Training Analysis”

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 1,207 records · Page 67
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

TPCpp-10M: Simulated proton-proton collisions in a time projection chamber for AI foundation models

Scientific foundation models hold great promise for advancing nuclear and particle physics by improving analysis precision and accelerating discovery. Yet, progress in this field is often limited by the lack of openly available large scale datasets, as well as standardized evaluation tasks and metrics. Furthermore, the specialized knowledge and software typically required to process particle physics data pose significant barriers to interdisciplinary collaboration with the broader machine learning community. This work introduces a large, openly accessible dataset of 10 million simulated proton-proton collisions, designed to support self-supervised training of foundation models. To facilitate ease of use, the dataset is provided in a common NumPy format. In addition, it includes 70,000 labeled examples spanning three well defined downstream tasks: track finding, particle identification, and noise tagging, to enable systematic evaluation of the foundation model's adaptability. The simulated data are generated using the Pythia Monte Carlo event generator at a center of mass energy of $\sqrt{s}$ = 200 GeV and processed with Geant4 to include realistic detector conditions and signal emulation in the sPHENIX Time Projection Chamber at the Relativistic Heavy Ion Collider, located at Brookhaven National Laboratory. This dataset resource establishes a common ground for interdisciplinary research, enabling machine learning scientists and physicists alike to explore scaling behaviors, assess transferability, and accelerate progress toward foundation models in nuclear and high energy physics. The complete simulation and reconstruction chain is reproducible with the sPHENIX software stack. All data and code locations are provided under Data Accessibility.

Data Analysis, Statistics and Probability (physics↗
DOE OSTI2021

Deep learning-based segmentation of lithium-ion battery microstructures enhanced by artificially generated electrodes

Accurate 3D representations of lithium-ion battery electrodes, in which the active particles, binder and pore phases are distinguished and labeled, can assist in understanding and ultimately improving battery performance. Here, we demonstrate a methodology for using deep-learning tools to achieve reliable segmentations of volumetric images of electrodes on which standard segmentation approaches fail due to insufficient contrast. We implement the 3D U-Net architecture for segmentation, and, to overcome the limitations of training data obtained experimentally through imaging, we show how synthetic learning data, consisting of realistic artificial electrode structures and their tomographic reconstructions, can be generated and used to enhance network performance. We apply our method to segment x-ray tomographic microscopy images of graphite-silicon composite electrodes and show it is accurate across standard metrics. We then apply it to obtain a statistically meaningful analysis of the microstructural evolution of the carbon-black and binder domain during battery operation.

25 ENERGY STORAGE↗
DOE OSTI2022

Neural Network-Based Electric Vehicle Range Prediction for Smart Charging Optimization

Range prediction is a standard feature in most modern road vehicles, allowing drivers to make informed decisions about when to refuel. Most vehicles make range predictions through data- or model-driven means, monitoring the average fuel consumption rate or using a tuned vehicle model to predict fuel consumption. The uncertainty of future driving conditions makes the range prediction problem challenging, particularly for less pervasive battery electric vehicles (BEV). Most contemporary machine learning-based methods attempt to forecast the battery SOC discharge profile to predict vehicle range. In this work, we propose a novel approach using two recurrent neural networks (RNNs) to predict the remaining range of BEVs and the minimum charge required to safely complete a trip. Each RNN has two outputs that can be used for statistical analysis to account for uncertainties; the first loss function leads to mean and variance estimation (MVE), while the second results in bounded interval estimation (BIE). These outputs of the proposed RNNs are then used to predict the probability of a vehicle completing a given trip without charging, or if charging is needed, the remaining range and minimum charging required to finish the trip with high probability. Training data was generated using a low-order physics model to estimate vehicle energy consumption from historical drive cycle data collected from medium-duty last-mile delivery vehicles. Here, the proposed method demonstrated high accuracy in the presence of day-to-day route variability, with the root-mean-square error (RMSE) below 6% for both RNN models.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

UFNet: Joint U-Net and Fully Connected Neural Network to Bias Correct Precipitation Predictions from

Paper information. Shuang Yu, Indrasis Chakraborty, Gemma J. Anderson, Donald D. Lucas, Yannic Lops, and Daniel Galea. UFNet: Joint U-Net and fully connected neural network to bias correct precipitation predictions from climate models. Artificial Intelligence for the Earth Systems, 2024. Overview. This work develops the UFNet methodology to correct E3SM historical precipitation projection bias. The UFNet deep learning framework consists of a two-part architecture: a U-Net convolutional network to capture the spatiotemporal distribution of precipitation and a fully connected network to capture the distribution of higher-order statistics. The joint network, termed UFNet, can simultaneously improve the spatial structure of the modeled precipitation and capture the distribution of extreme precipitation values. Below we provide guidance for applying UFNet to correct the Energy Exascale Earth System Model (E3SM; Golaz et al. 2019) daily precipitation projection over the contiguous United States (CONUS). Getting started 1. Obtain the historical climate simulation and observation data. The E3SM historical simulation data are available through https://aims2.llnl.gov/search/cmip6/. The CPC unified gauge-based analysis of daily precipitation can be found through https://psl.noaa.gov/data/gridded/data.cpc.globalprecip.html. The ECMWF atmospheric reanalysis of the 20th century (ERA-20C) data are available through https://www.ecmwf.int/en/forecasts/datasets/reanalysis-datasets/era-20c. The spatial resolution of E3SM and observed datasets are both regridded to a common 1° resolution grid using conservative interpolation. The regridded E3SM, CPC and ERA-20C with 1° resolution can be found throught ./data/. 2. Train the fully connected network (DNN) Python train_dnn.py 3. Train the UFNet Python train_ufnet.py 4. Evaluation and compared with the baseline Python evaluation.py

Lucas, DonaldD↗
DOE OSTI2024

Evaluating Physics-Informed Neural Network Performance for Seismic Discrimination between Earthquakes and Explosions

In this article, we evaluate adding a weak physics constraint, that is, a physics‐based empirical relationship, to the loss function with a physics‐informed manner in local distance explosion discrimination in the hope of improving the generalization capability of the machine learning (ML) model. We compare the proposed model with the two‐branch model we previously developed, as well as with a pure data‐driven model. Unexpectedly, the proposed model did not consistently outperform the pure data‐driven model. By varying the level of inconsistency in the training data, we find this approach is modulated by the strength of the physics relationship. In conclusion, this result has important implications for how to best incorporate physical constraints in ML models.

58 GEOSCIENCES↗
DOE OSTI2024

Application of Partial Least Squares Approaches to Pyroprocessing ER Data

Multivariate approaches show promise for application to process monitoring for safeguards of pyroprocessing. Past MPACT work explored the application of Principal Component Analysis (PCA) to detect off-normal conditions in pyroprocessing electrorefiner (ER) data from in the Hot Fuel Examination Facility (HFEF) at Idaho National Laboratory (INL) known as the Scalable Pyrochemical Recycling testbed (SPyRe) ER. PCA, however, does not consider the output variables. In FY24, multivariate analysis was extended from PCA to Partial Least Squares (PLS) analysis. PLS maximizes the variance between both the input signals and output variables. In the case of this work, PLS was applied in two different manners: Predictive PLS and Discriminant PLS. Predictive PLS maximizes the covariance between the process variables of the ER and the measured U concentration from in-situ voltammetry. Discriminant PLS maximizes the covariance between the process variables and a set of training process “states” such as known off-normal conditions. By projecting into the latent variable space in PLS, the process variables can be regressed onto the outputs and predictions can be made for new data sets. In this work, by applying predictive PLS, a penalized non-linear PLS approach was able to make predictions of concentration based on test and training data and detect when operations were off-normal. However, the predictive PLS does not classify the signals to which off-normal operations are attributable. Discriminant PLS can be used to classify off-normal operations but is inadequate to properly classify specific off-normal classes like power supply faults when the Discriminant PLS model is only specifically trained to detect that off-normal class. When all faults are trained against the observation data, all three operational classes are accurately classified and distinguished. Thus, future application of latent variable techniques should not select any given method, but should use a mixture of PCA, Predictive PLS, and Discriminant PLS.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

Sensitivity-Informed Bayesian Inference for Home PLC Network Models with Unknown Parameters

Bayesian inference is used to calibrate a bottom-up home PLC network model with unknown loads and wires at frequencies up to 30 MHz. A network topology with over 50 parameters is calibrated using global sensitivity analysis and transitional Markov Chain Monte Carlo (TMCMC). The sensitivity-informed Bayesian inference computes Sobol indices for each network parameter and applies TMCMC to calibrate the most sensitive parameters for a given network topology. A greedy random search with TMCMC is used to refine the discrete random variables of the network. This results in a model that can accurately compute the transfer function despite noisy training data and a high dimensional parameter space. The model is able to infer some parameters of the network used to produce the training data, and accurately computes the transfer function under extrapolative scenarios.

42 ENGINEERING↗
DOE OSTI2022

Synthetic Data Generation Using Machine Learning

Robust machine learning techniques for image analysis require a substantial amount of data to yield confident results. In the nuclear domain, data scarcity is a substantial challenge because there are so few facilities worldwide. This research focuses on being able alleviate the data scarcity problem by generating synthetic data to bridge the gap between large and small datasets. This work achieves that goal using a Generative Adversarial Network (GAN) architectural approach, by training a model on real-world data and expands that small dataset through synthetic data amendments. Model performance is impacted by the size of the real-world dataset and the number of training epochs utilized. This means that 1) It is important to develop your GAN to be optimized with the specific data type, and 2) approaches taken when training the GAN should be specialized to encompass important aspects of the dataset that it is generating. By taking a step to improve dataset sizes in this way, the gap between models trained by parties with significant amount of data and those without access to large data, closes, allowing for robust analyses of satellite imagery for nuclear domain applications.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Methodology and Tool for the Physical Security Analysis of Micro and Advanced Reactors

This work proposes a dynamic evaluation methodology to relax the conservatism in physical security evaluation, by leveraging an ongoing work in the Light Water Reactor Sustainability pathway. This methodology is implemented in a dynamic risk assessment tool named Event Modeling Risk Assessment using Linked Diagrams (EMRALD). The work extends EMRALD’s capability to support a sandbox feature where analysts can easily create attack scenarios and modify advanced/small modular reactor (A/SMR) security and safety features using templates. This approach saves time and cost since the analysis does not require creating detailed computer-aided design models, as is commonly required in commercial force-on-force software tools. EMRALD is completely free to use at https://emraldapp.inl.gov. We have developed basic templates including physical barriers, intrusion sensors, physical areas, and safety actions, that can be downloaded from EMRALD’s GitHub site: https://github.com/idaholab/EMRALD. These templates use generic data commonly used for training purposes, which do not reflect any actual operating nuclear reactor. Users may adjust the data in the templates with their own dataset and/or create new templates in EMRALD. The proposed methodology combines security and safety by assessing sabotage effects up to the radiological consequence to the public instead of merely the core damage state. This practice follows the industry standard for advanced non-light-water reactors currently proposed for endorsement by the Nuclear Regulatory Commission. The combination of security and safety is expressed in an achievability-consequence chart. EMRALD can be used to generate data for this chart. A hypothetical case study using a representative sodium-cooled fast reactor (SFR) facility is presented in this report to demonstrate this methodology. This case study does not contain any actual nuclear plant information. This work will benefit A/SMR vendors and utilities to implement security by design during the reactor design iteration phase, such that they do not have to perform upgrades and retrofits to the reactor after it is installed to improve its physical protection system. The tool may also be used to analyze domestic or foreign reactor designs to support the International Nuclear Security Techniques for Advanced Reactors (INSTAR) bilateral missions. Future works are planned to implement the methodology on a reference SFR reactor and a reference high-temperature gas-cooled reactor to obtain insights and lessons-learned for the A/SMR community.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Integration of the Biot–Gassmann Fluid Substitution Method and Machine Learning-Based Velocity–Stress Relationship for Estimating In Situ Stresses

Recent advancements have shown that in situ stresses can be reliably estimated through an integrated machine/deep learning (ML/DL)-based framework, which relies on models trained and validated using true triaxial ultrasonic velocity (TUV) experimental data that involve measurements of ultrasonic velocity in saturated rocks under varying stress configurations. However, when the goal is to interpret lower frequency measurements, it may be more appropriate to run experiments on dry rocks and then obtain Biot–Gassmann-derived equivalent saturated velocities (low-frequency approximation) and employ these quantities for training ML/DL models to predict in situ stress. Whether the dispersion effect of frequency on the velocity–stress relationship substantially impacts in situ stress prediction is an important and unresolved question. This work presents an enhancement of ML/DL-based workflow by training and implementing ML/DL models using equivalent saturated acoustic velocities (low-frequency) obtained by applying Biot–Gassmann fluid substitution on the ultrasonic velocities of dry cores. The models were trained on TUV data sets derived from three subsurface cores extracted from the geothermal well 16B(78)-32 at the Utah FORGE site. Each core was subjected to 75 unique stress configurations for velocity measurement in the dry state. The ML/DL trained on the TUV data set with equivalent saturated velocities demonstrated promising performance to predict in situ stress in subsurface geological rocks using velocity–stress relationships with R 2 of 0.86, 0.971, and 0.975 and root mean squared error (RMSE) of 2.59, 1.92, and 1.80 for validation/testing phases of vertical, minimum horizontal, and maximum horizontal stress models, respectively. Additionally, interpretation and explanation by Shapley additive explanations (SHAP) analysis further improved scientific validation and model reliability for estimating in situ stresses.

colloids↗
DOE OSTI2021

A machine learning aided interpretable model for rupture strength prediction in Fe-based martensitic and austenitic alloys

Abstract The class of 9–12% Cr ferritic-martensitic alloys (FMA) and austenitic stainless steels have received considerable attention due to their numerous applications in high temperature power generation industries. To design high strength steels with prolonged service life requires a thorough understanding of the long-term properties, e.g., creep rupture strength, rupture life, etc., as a function of the chemical composition and processing parameters that govern the microstructural characteristics. In this article, the creep rupture strength of both 9–12% Cr FMA and austenitic stainless steel has been parameterized using curated experimental datasets with a gradient boosting machine. The trained model has been cross validated against unseen test data and achieved high predictive performance in terms of correlation coefficient ( $$R^{2} > 0.98 $$ R 2 > 0.98 for 9–12% Cr FMA and $$R^{2} > 0.95 $$ R 2 > 0.95 for austenitic stainless steel) thus bypassing the need for additional comprehensive tensile test campaigns or physical theoretical calculations. Furthermore, the feature importance has been computed using the Shapley value analysis to understand the complex interplay of different features.

36 MATERIALS SCIENCE↗
DOE OSTI2021

NENCI-2021. I. A large benchmark database of non-equilibrium non-covalent interactions emphasizing close intermolecular contacts

In this work, we present NENCI-2021, a benchmark database of ~8000 Non-Equilibirum Non-Covalent Interaction energies for a large and diverse selection of intermolecular complexes of biological and chemical relevance. To meet the growing demand for large and high-quality quantum mechanical data in the chemical sciences, NENCI-2021 starts with the 101 molecular dimers in the widely used S66 and S101 databases and extends the scope of these works by (i) including 40 cation–π and anion–π complexes, a fundamentally important class of non-covalent interactions that are found throughout nature and pose a substantial challenge to theory, and (ii) systematically sampling all 141 intermolecular potential energy surfaces (PESs) by simultaneously varying the intermolecular distance and intermolecular angle in each dimer. Designed with an emphasis on close contacts, the complexes in NENCI-2021 were generated by sampling seven intermolecular distances along each PES (ranging from 0.7× to 1.1× the equilibrium separation) and nine intermolecular angles per distance (five for each ion–π complex), yielding an extensive database of 7763 benchmark intermolecular interaction energies (E int ) obtained at the coupled-cluster with singles, doubles, and perturbative triples/complete basis set [CCSD(T)/CBS] level of theory. The E int values in NENCI-2021 span a total of 225.3 kcal/mol, ranging from -38.5 to +186.8 kcal/mol, with a mean (median) E int value of -1.06 kcal/mol (-2.39 kcal/mol). In addition, a wide range of intermolecular atom-pair distances are also present in NENCI-2021, where close intermolecular contacts involving atoms that are located within the so-called van der Waals envelope are prevalent—these interactions, in particular, pose an enormous challenge for molecular modeling and are observed in many important chemical and biological systems. A detailed symmetry-adapted perturbation theory (SAPT)- based energy decomposition analysis also confirms the diverse and comprehensive nature of the intermolecular binding motifs present in NENCI-2021, which now includes a significant number of primarily induction-bound dimers (e.g., cation–π complexes). NENCI-2021 thus spans all regions of the SAPT ternary diagram, thereby warranting a new four-category classification scheme that includes complexes primarily bound by electrostatics (3499), induction (700), dispersion (1372), or mixtures thereof (2192). A critical error analysis performed on a representative set of intermolecular complexes in NENCI-2021 demonstrates that the E int values provided herein have an average error of ±0.1 kcal/mol, even for complexes with strongly repulsive E int values, and maximum errors of ±0.2–0.3 kcal/mol (i.e., ~±1.0 kJ/mol) for the most challenging cases. For these reasons, we expect that NENCI-2021 will play an important role in the testing, training, and development of next-generation classical and polarizable force fields, density functional theory approximations, wavefunction theory methods, and machine learning based intra- and inter-molecular potentials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Deconvoluting thermomechanical effects in X-ray diffraction data using machine learning

X-ray diffraction is ideal for probing the sub-surface state during complex or rapid thermomechanical loading of crystalline materials. However, challenges arise as the size of diffraction volumes increases due to spatial broadening and because of the inability to deconvolute the effects of different lattice deformation mechanisms. Here, we present a novel approach that uses combinations of physics-based modeling and machine learning to deconvolve thermal and mechanical elastic strains for diffraction data analysis. The method builds on a previous effort to extract thermal strain distribution information from diffraction data. The new approach is applied to extract the evolution of the thermomechanical state during laser melting of an Inconel 625 wall specimen which produces significant residual stress upon cooling. A combination of heat transfer and fluid flow, elasto-plasticity and X-ray diffraction simulations is used to generate training data for machine-learning (Gaussian process regression, GPR) models that map diffracted intensity distributions to underlying thermomechanical strain fields. First-principles density functional theory is used to determine accurate temperature-dependent thermal expansion and elastic stiffness used for elasto-plasticity modeling. The trained GPR models are found to be capable of deconvoluting the effects of thermal and mechanical strains, in addition to providing information about underlying strain distributions, even from complex diffraction patterns with irregularly shaped peaks.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques

Using multiple geophysical methods has become a prevailing approach in numerous geophysical applications to investigate subsurface structures and parameters. These multimethod-based exploration strategies have the potential to greatly diminish uncertainties and ambiguities encountered during geophysical data analysis and interpretation. One of the applications is the cooperative inversion of airborne magnetic and gravity gradient data for the interpretation of data obtained in mineral, oil and gas, and geothermal explorations. In this paper, a unified cooperative inversion framework is designed by combining the standard separate inversions with a deep neural network (DNN), which serves as the link between different types of data. A well-trained DNN takes the separately inverted susceptibility and density models as the inputs and provides improved models that will be used as the initial models of deterministic inversions. A two-round iteration strategy is adopted to guarantee the reasonability of the recovered models and overall efficiency of the inversion. In addition, this deep-learning (DL)-based framework demonstrates excellent generalization abilities when tested on models that are entirely distinct from the training data sets. The framework can easily incorporate multiphysics without necessitating any structural changes to the network. Synthetic experiments validate that our DL-based method outperforms conventional separate inversions and cross-gradient-based joint inversion in view of the accuracy of the recovered models and inversion efficiency. Successful application to field data further verifies the effectiveness of our DL-based method.

Geochemistry & Geophysics↗
DOE OSTI2020

Artificial neural network based isotopic analysis of airborne radioactivity measurement for radiological incident detection

Responders need tools to rapidly detect and identify airborne alpha radioactivity during consequence management scenarios. Traditional continuous air monitor systems used for this purpose compute the net counts in various energy windows to determine the presence of specified isotopes, such as 235U, 239Pu, and 241Am. These calculations rely on having a well-calibrated detector, which is challenging in low-background environments. Here an alternative approach of using artificial neural networks to classify alpha spectra is presented. Two network architectures, fully connected and convolutional networks, were trained to classify alpha spectra into four categories: background and background plus the three isotopes above. Sources were injected into measured background at various fractions of the derived response level (DRL) corresponding to early-phase Protective Action Guides. The convolutional network identifies all sources at 1% of the DRL with average probability of detection of 95% and false alarm probability of 1%. Further, the network identifies sources ranging between 0.25% and 1% of the DRL with higher than 80% probability of detection and lower than 7% false alarm probability. Most significantly, the network performance improves in low-count background conditions, increasing its minimum probability of detection to 93% and reducing the false alarm probabilities to lower than 0.25%. These results show that, once trained on datasets representing a range of detection scenarios, artificial neural networks can accurately identify alpha isotopes of interest without the need for detector calibration.

Woldegiorgis, Surafel F.↗
DOE OSTI2021

Utilizing computer vision and artificial intelligence algorithms to predict and design the mechanical compression response of direct ink write 3D printed foam replacement structures

Additive Manufacturing (AM) of porous polymeric materials, such as foams, recently became a topic of intensive research due their unique combination of low density, impressive mechanical properties, and stress dissipation capabilities. Conventional methods for fabricating foams rely on complex and stochastic processes, making it challenging to achieve precise architectural control of structured porosity. In contrast, AM provides access to a wide range of printable materials, where precise spatial control over structured porosity can be modulated during the fabrication process enabling the production of foam replacement structures (FRS). Current approaches for designing FRS are based on intuitive understanding of their properties or an extensive number of finite element method (FEM) simulations. These approaches, however, are computationally expensive and time consuming. As such, in this work, we present a novel methodology for determining the mechanical compression response of direct ink write (DIW) 3D printed FRS using a simple cross-sectional image. By obtaining measurement data for a relatively small number of samples, an artificial neural network (ANN) was trained, and a computer vision algorithm was used to make inferences about foam compression characteristics from a single cross-sectional image. Finally, a genetic algorithm (GA) was used to solve the inverse design problem, generating the AM printing parameters that an engineer should use to achieve a desired compression response from a DIW printed FRS. The methods developed herein present an avenue for entirely autonomous design and analysis of additively manufactured structures using artificial intelligence.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Effects of input gradient regularization on neural networks time-series forecasting of thermal power systems

This study proposes using neural networks, specifically gated recurrent unit (GRU), long-short-term memory (LSTM), and transformer networks, to improve control strategies in a 450 MW coal-fired power plant. However, neural networks face issues of becoming overly dependent on just a few variables to make predictions, which negatively impacts control decisions that rely on the model to determine the value of all manipulated variables. The paper introduces regularization techniques, including noise injection and input gradient regularization, during the training phase. Here, the work presents novel contributions in adapting neural networks to control industrial systems and applying regularization techniques from computer vision to industrial process control. Results demonstrate the effectiveness of input gradient regularization in reducing model dependence on subsets of variables, emphasizing the balance between fidelity and controllability. Further exploration is recommended, including the development of recurrent transformers, closed-loop control testing, and a sensitivity analysis on computer models to provide further insight.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2020

Clinically applicable 53-Gene prognostic assay predicts chemotherapy benefit in gastric cancer: A multicenter study

BACKGROUND:We previously established a 53-gene prognostic signature for overall survival (OS) of gastric cancer patients. This retrospective multi-center study aimed to develop a clinically applicable gene expression detection assay and to investigate the prognostic value of this signature. METHODS:A TCGA gastric adenocarcinoma cohort (TCGA-STAD) was used for comparing 53-gene signature with other gene signatures. A high-throughput mRNA hybridization gene expression assay was developed to quantify the expression of 53-genes in formalin-fixed paraffin-embedded tissues of 540 patients enrolled from three hospitals. 180 patents were randomly selected from two hospitals to build a prognostic prediction model based on the 53-gene signature using leave-p-out (one-third out) cross-validation method together with Cox regression and Kaplan-Meier analysis, and the model was assessed on three validation cohorts. FINDINGS:In the evaluation phase, studies based on TCGA-STAD showed that the 53-gene signature was significantly superior to other three prognostic signatures and was independent of TCGA molecular subtypes and clinical factors. For clinical validation and utility, the prognostic scores were generated using the newly developed assay, which was reliable and sensitive, in 100 sampling training sets and were significantly associated with OS in 100 sampling validation sets. The scores were significantly associated with OS in three independent and combined validation cohorts, and in patients with stages II and III/IV. The multivariate Cox regression demonstrated that the prognostic power of the score was independent of clinical factors, consistent with those findings in the TCGA dataset. Finally, patients with good prognostic scores exhibited significantly a better 5-year OS rate from adjuvant FOLFOX chemotherapy after surgery than from other chemotherapies. INTERPRETATION:The 53-gene prognostic score system is clinically applicable for predicting the OS of patients independent of clinical factors in gastric cancers, which could also be a promising predictive biomarker for FOLFOX regimen. FUNDING:Chinese National Science and Technology, National Natural Science Foundation and Natural Science Foundation of Jiangsu Province.

60 APPLIED LIFE SCIENCES↗