Search NASA⌕ Search

SEARCH · Search NASA

Results for “predict”

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

Validation of the Web-Based IBTR! 2.0 Nomogram to Predict for Ipsilateral Breast Tumor Recurrence After Breast-Conserving Therapy

Purpose: To evaluate the IBTR! 2.0 nomogram, which predicts 10-year ipsilateral breast tumor recurrence (IBTR) after breast-conserving therapy with and without radiation therapy for breast cancer, by using a large, external, and independent cancer center database. Methods and Materials: We retrospectively identified 1898 breast cancer cases, treated with breast-conserving therapy and radiation therapy at the University Hospital Leuven from 2000 to 2007, with requisite data for the nomogram variables. Clinicopathologic factors were assessed. Two definitions of IBTR were considered where simultaneous regional or distant recurrence were either censored (conform IBTR! 2.0) or included as event. Validity of the prediction algorithm was tested in terms of discrimination and calibration. Discrimination was assessed by the concordance probability estimate and Harrell's concordance index. The mean predicted and observed 10-year estimates were compared for the entire cohort and for 4 risk groups predefined by nomogram-predicted IBTR risks, and a calibration plot was drawn. Results: Median follow-up was 10.9 years. The 10-year IBTR rates were 1.3% and 2.1%, according to the 2 definitions of IBTR. The validation cohort differed from the development cohort with respect to the administration of hormonal therapy, surgical section margins, lymphovascular invasion, and tumor size. In univariable analysis, younger age (P=.002) and a positive nodal status (P=.048) were significantly associated with IBTR, with a trend for the omission of hormonal therapy (P=.061). The concordance probability estimate and concordance index varied between 0.57 and 0.67 for the 2 definitions of IBTR. In all 4 risk groups the model overestimated the IBTR risk. In particular, between the lowest-risk groups a limited differentiation was suggested by the calibration plot. Conclusions: The IBTR! 2.0 predictive model for IBTR in breast cancer patients shows substandard discriminative ability, with an overestimation of the risk in all subgroups.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

{sup 18}F-Fluorodeoxyglucose Positron Emission Tomography Can Quantify and Predict Esophageal Injury During Radiation Therapy

Purpose: We sought to investigate the ability of mid-treatment {sup 18}F-fluorodeoxyglucose positron emission tomography (PET) studies to objectively and spatially quantify esophageal injury in vivo from radiation therapy for non-small cell lung cancer. Methods and Materials: This retrospective study was approved by the local institutional review board, with written informed consent obtained before enrollment. We normalized {sup 18}F-fluorodeoxyglucose PET uptake to each patient's low-irradiated region (<5 Gy) of the esophagus, as a radiation response measure. Spatially localized metrics of normalized uptake (normalized standard uptake value [nSUV]) were derived for 79 patients undergoing concurrent chemoradiation therapy for non-small cell lung cancer. We used nSUV metrics to classify esophagitis grade at the time of the PET study, as well as maximum severity by treatment completion, according to National Cancer Institute Common Terminology Criteria for Adverse Events, using multivariate least absolute shrinkage and selection operator (LASSO) logistic regression and repeated 3-fold cross validation (training, validation, and test folds). This 3-fold cross-validation LASSO model procedure was used to predict toxicity progression from 43 asymptomatic patients during the PET study. Dose-volume metrics were also tested in both the multivariate classification and the symptom progression prediction analyses. Classification performance was quantified with the area under the curve (AUC) from receiver operating characteristic analysis on the test set from the 3-fold analyses. Results: Statistical analysis showed increasing nSUV is related to esophagitis severity. Axial-averaged maximum nSUV for 1 esophageal slice and esophageal length with at least 40% of axial-averaged nSUV both had AUCs of 0.85 for classifying grade 2 or higher esophagitis at the time of the PET study and AUCs of 0.91 and 0.92, respectively, for maximum grade 2 or higher by treatment completion. Symptom progression was predicted with an AUC of 0.75. Dose metrics performed poorly at classifying esophagitis (AUC of 0.52, grade 2 or higher mid treatment) or predicting symptom progression (AUC of 0.67). Conclusions: Normalized uptake can objectively, locally, and noninvasively quantify esophagitis during radiation therapy and predict eventual symptoms from asymptomatic patients. Normalized uptake may provide patient-specific dose-response information not discernible from dose.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Best practices for predictions of radionuclide activity concentrations and total absorbed dose rates to freshwater organisms exposed to uranium mining/milling

Predictions of radionuclide dose rates to freshwater organisms can be used to evaluate the radiological environmental impacts of releases from uranium mining and milling projects. These predictions help inform decisions on the implementation of mitigation measures. The objective of this study was to identify how dose rate modelling could be improved to reduce uncertainty in predictions to non-human biota. For this purpose, we modelled the activity concentrations of 210 Pb, 210 Po, 226 Ra, 230 Th, and 238 U downstream of uranium mines and mills in northern Saskatchewan, Canada, together with associated weighted absorbed dose rates for a freshwater food chain using measured activity concentrations in water and sediments. Differences in predictions of radionuclide activity concentrations occurred mainly from the different default partition coefficient and concentration ratio values from one model to another and including all or only some 238 U decay daughters in the dose rate assessments. Consequently, we recommend a standardized best-practice approach to calculate weighted absorbed dose rates to freshwater biota whether a facility is at the planning, operating or decommissioned stage. At the initial planning stage, the best-practice approach recommend using conservative site-specific baseline activity concentrations in water, sediments and organisms and predict conservative incremental activity concentrations in these media by selecting concentration ratios based on species similarity and similar water quality conditions to reduce the uncertainty in dose rate calculations. At the operating and decommissioned stages, the best-practice approach recommends relying on measured activity concentrations in water, sediment, fish tissue and wholebody of small organisms to further reduce uncertainty in dose rate estimates. This approach would allow for more realistic but still conservative dose assessments when evaluating impacts from uranium mining projects and making decision on adequate controls of releases.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗

Comparison of four learning-based methods for predicting groundwater redox status

Knowing the location where groundwater denitrification occurs, or by proxy the groundwater redox status (oxic, mixed, and anoxic), is valuable information for assessing and managing potential agricultural land-use impacts on freshwater quality. We compare the efficacy of supervised (Linear Discriminant Analysis LDA; Boosted Regression Trees, BRT; and Random Forest, RF) and unsupervised (Modified Self-Organizing Map, MSOM) learning-based methods to predict groundwater redox status in the agriculturally dominated Tasman, Waikato, and Wellington regions of New Zealand. Thresholds applied to regional groundwater-quality samples provide redox status variables and learn heuristics constrained by these variables and applied to spatial factors (climate, elevation, geologic, hydrology soils, and well depth) identify optimal sets of regional predictor variables. A split-sample approach is used to train and test the learning methods ability to predict redox status using the optimal predictor variables. Overall, the supervised methods demonstrate a prediction bias toward oxic conditions and inability to perform statistically well when using independent regional data; for example, consider kappa statistics for BRT (Tasman: 0.42, Waikato: 0.38, Wellington: 0.17), RF (Tasman: 0.42, Waikato: 0.47, Wellington: 0.17 and LDA (Tasman: 0.46, Waikato: 0.32, Wellington: 0.17). By contrast, the unsupervised method performs statistically well when predicting oxic, mixed, and anoxic conditions and corresponding depths when using independent regional data; for example, consider MSOM kappa statistics for Tasman: 0.78, Waikato: 0.80, Wellington: 0.76. The unsupervised learning method provides the added benefits of being (1) able to combine predictions into 3D regional anoxic probability plots for interpreting the spatial influence of paleosols and groundwater flowpaths on redox status, and (2) readily extended to map 3D redox status across New Zealand and other countries despite data bias and sparsity.

machine learning algorithms, Random Forest, booste↗

BIPSPI+: Mining Type-Specific Datasets of Protein Complexes to Improve Protein Binding Site Prediction

Computational approaches for predicting protein-protein interfaces are extremely useful for understanding and modelling the quaternary structure of protein assemblies. In particular, partner-specific binding site prediction methods allow delineating the specific residues that compose the interface of protein complexes. In recent years, new machine learning and other algorithmic approaches have been proposed to solve this problem. However, little effort has been made in finding better training datasets to improve the performance of these methods. With the aim of vindicating the importance of the training set compilation procedure, in this work we present BIPSPI+, a new version of our original server trained on carefully curated datasets that outperforms our original predictor. We show how prediction performance can be improved by selecting specific datasets that better describe particular types of protein interactions and interfaces (e.g. homo/hetero). In addition, our upgraded web server offers a new set of functionalities such as the sequence-structure prediction mode, hetero- or homo-complex specialization and the guided docking tool that allows to compute 3D quaternary structure poses using the predicted interfaces. BIPSPI+ is freely available at https://bipspi.cnb.csic.es.

59 BASIC BIOLOGICAL SCIENCES↗

Prediction of shock initiation thresholds and ignition probability of polymer-bonded explosives using mesoscale simulations

The design of new materials requires establishment of macroscopic measures of material performance as functions of microstructure. Traditionally, this process has been an empirical endeavor. In this paper, an approach to computationally predict the probabilistic ignition thresholds of polymer-bonded explosives (PBXs) using mesoscale simulations is developed. The simulations explicitly account for microstructure, constituent properties, and interfacial responses and capture processes responsible for the development of hotspots and damage. The specific mechanisms tracked include viscoelasticity, viscoplasticity, fracture, post-fracture contact, frictional heating, and heat conduction. The probabilistic analysis uses sets of statistically similar microstructure samples to directly mimic relevant experiments for quantification of statistical variations of material behavior due to inherent material heterogeneities. The particular thresholds and ignition probabilities predicted are expressed in James type and Walker–Wasley type relations, leading to the establishment of explicit analytical expressions for the ignition probability as function of loading. Specifically, the ignition thresholds corresponding to any given level of ignition probability and ignition probability maps are predicted for PBX 9404 for the loading regime of U p = 200–1200 m/s where U p is the particle speed. The predicted results are in good agreement with available experimental measurements. A parametric study also shows that binder properties can significantly affect the macroscopic ignition behavior of PBXs. Finally, the capability to computationally predict the macroscopic engineering material response relations out of material microstructures and basic constituent and interfacial properties lends itself to the design of new materials as well as the analysis of existing materials.

36 MATERIALS SCIENCE↗

Measurements and predictions of wind turbine tower shadow and fairing effects

Downwind two-bladed rotor configurations can have advantages in reducing rotor mass for wind turbines, compared with three-bladed upwind designs. However, the tower shadow adds an aerodynamic complication that can be difficult to quantify and predict. This study presents and analyzes a previously unpublished subset of data collected during an extensive wind tunnel campaign, the Unsteady Aerodynamic Experiment (UAE). At high tip speed ratios, the tower shadow is a dominating contributor to bending moment oscillations but can be mitigated by the use of a tower fairing when such a fairing is aligned with the flow. At lower tip speed ratios where the blades can undergo aerodynamic stall and hysteresis, tower shadow was only a secondary contributor to bending moments and the tower fairing did not significantly impact bending moments. The aeroelastic simulation code called FAST was used to predict the same experimental conditions. In general, simulations reasonably predicted most of the cycle-averaged aspects, but only qualitatively predicted the unsteady variations due to tower shadow. To improve simulation predictions inside the tower wake, it is suggested that future work model the unsteady wake component associated with cylinder shedding and to consider a wake model for tower fairings at various wind incidence angles.

17 WIND ENERGY↗

Prediction of Output Factor, Range, and Spread-Out Bragg Peak for Proton Therapy

In proton therapy, patient quality assurance (QA) requires measuring the beam range, spread-out Bragg peak (SOBP), and output factor. If these values can be predicted by using sampling measurements or previous QA data to find the correlation between beam setup parameters and measured data, efforts expended on patient QA can be reduced. Using sampling data, we predicted the range, SOBP, and output factor of the proton beam. To obtain sampling data, we measured the range, SOBP, and output factor for 14 data points at each of 24-beam range options, from 4-28 cm. Prediction conformity was evaluated by the difference between predicted and measured patient QA data. Results indicated that for 60% of patients, the values could be predicted within 3% of dose uncertainty.

61 RADIATION PROTECTION AND DOSIMETRY↗

Prediction of softening kinetics and recrystallization texture in non-isothermally annealed bulged tubes using CPFEM and CA models

A hierarchically coupled cellular automata (CA) model, crystal plasticity finite element method (CPFEM), and thermal finite element (FE) model is developed to predict the softening kinetics of the bulged steel tube during non-isothermal annealing. Through the developed model, the kinetics of softening mechanisms including static recovery (SRV) and static recrystallization (SRX), as well as the recrystallization texture are predicted. Later, the Johnson-Mehl-Avrami-Kohnogorov (JMAK) model based on the predicted SRX data is developed to interpret the recrystallization behavior of the material. To perform this study, diverse experimental tests including tube hydroforming (THF), annealing, uniaxial tensile test, hardness test, as well as microstructure observations through optical microscopy and Electron Backscatter Diffraction (EBSD) tests on steel tube are performed. The obtained experimental data are utilized to calibrate and verify the implemented CPFEM model for simulation of THF process, thermal FE model for prediction of the local temperature over annealing time, and CA algorithm for modeling of the softening kinetics and texture evolution throughout the annealing process. The study shows that the predicted deformation characteristics, softening kinetics, recrystallization texture and temperature profile during non-isothermal annealing are in good agreement with experimental data. During the annealing process, a total of four stages for the kinetics of softening mechanisms is observed: No softening; SRV only; SRV dominant; and SRX dominant. During the progress of SRX, the behavior of recrystallization is abruptly changed, confirming that two different mechanisms are controlling the kinetics of transformation.

36 MATERIALS SCIENCE↗

Prediction of dislocation - grain boundary interactions in FCC aluminum bicrystals using a modified continuum criterion and machine learning methods

Mechanical properties of metals such as strength and toughness are strongly correlated to complex interactions between various defects in the crystalline structure. While elementary interactions between these defects have been investigated using recent micro- and nano-characterization techniques, understanding of the detailed interaction mechanisms has hardly been obtained. To understand defect-driven plasticity at various time and length scales, it is necessary to formulate a general guideline to predict both the interaction type (transmission or reflection) and the dislocation's subsequent slip system after the interaction. Many criteria based on the geometric alignment of the defects have been developed to predict this phenomenon, but these have yet to be found to be accurate when applied to general data sets of grain boundaries (GBs). With this motivation, we conduct a systematic study using molecular dynamics (MD) models of bicrystals to analyze defect interaction process between a prismatic dislocation loop and eleven different grain boundaries of the following character: three tilt, three twist, and five mixed. Based on the MD observations, two new prediction methods are developed: the first is a new data-driven parametric score function based on the classical geometric criteria, and the second is by applying Gaussian process machine learning methods to find the probability distribution of a hidden function. In conclusion, the proposed data-driven prediction methods could pave a new way to predict the unit interaction of dislocations with various GBs, which could show much higher accuracy compared to pre-existing geometric criteria.

36 MATERIALS SCIENCE↗

Comparison of URANS and LES predictions for the open phase of the OECD NEA CSNI fluid structure interaction CFD benchmark

The OECD NEA CSNI WGAMA CFD Task Group ran a benchmark in 2020 and 2021 to assess the predictive capabilities of coupled fluid structure interaction (FSI) CFD analysis methods. This paper presents the predictions made for the open phase of the benchmark using URANS and LES turbulence modelling approaches, and a comparison of the results to the experimental data. The benchmark comprised a channel containing two inline cylinders in cross-flow. The cylinders were fixed at one end, free at the other, and had measured resonant frequencies and damping properties. The URANS modelling used ANSYS Fluent 2-way coupled to ANSYS Mechanical. The LES modelling used Nek5000, 1-way coupled to Diablo. Comparisons with cross-channel velocity profiles are presented, both for the mean flow and its RMS. Comparisons are also made to the frequency spectra for point measurements of fluid velocity and pressure, and for the accelerations of the free end of each cylinder. URANS predicts the average velocity profiles relatively well, and is able to predict the velocity and acceleration spectra at the shedding frequency. However, the frequency content at the 4th harmonic of the shedding frequency is low in the URANS flow fields, and so does not excite accelerations at the resonant frequency of the cylinders. LES makes better predictions of the average profiles, and the velocity spectra agree well at both the shedding frequency and at higher frequencies. In conclusion, the 1-way coupled LES results show good agreement for acceleration spectra.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

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↗

Predicting the superconducting critical temperature in transition metal carbides and nitrides using machine learning

Transition metal carbides and nitrides have unique mechanical and chemical characteristics. At low temperatures many of them also exhibit superconductivity, which can be controlled by substitutions into both the transition metal and carbon/nitrogen sites. To investigate the factors governing the superconducting state, we apply machine learning methods. Here we collected a dataset containing 147 materials, which was used to create a pipeline for predicting their superconducting critical temperature. When this pipeline is applied to a randomly selected test set, it shows a good performance, with of 0.82 and RMSE of 1.9 K. To explore the limits of the machine learning approach, we also use it to predict entire substitution series within the dataset. This represents a realistic test for the predictive models, which can be extremely useful when applied to new substitutions in materials systems. The performance of the pipeline in this case is much more uneven, with good predictions for some series, while for others the model shows minimal predictive power. We discuss possible reasons for these results, as well as methods to estimate the performance of machine learning on new substitution series.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Review of polymer oxidation and its relationship with materials performance and lifetime prediction

All polymers are intrinsically susceptible to oxidation, which is the underlying process for thermally driven materials degradation and of concern in various applications. There are many approaches for predicting oxidative polymer degradation. Aging studies usually are meant to accelerate oxidation chemistry for predictive purposes. Kinetic models attempt to describe reaction mechanisms and derive rate constants, whereas rapid qualification tests should provide confidence for extended performance during application, and similarly TGA tests are meant to provide rapid guidance for thermal degradation features. What are the underlying commonalities or diverging trends and complications when we approach thermo-oxidative aging of polymers in such different ways? This review presents a brief status report on the important aspects of polymer oxidation and focuses on the complexity of thermally accelerated polymer aging phenomena. Thermal aging and lifetime prediction, the importance of DLO, property correlations, kinetic models, TGA approaches, and a framework for predictive aging models are briefly discussed. An overall perspective is provided showing the challenges associated with our understanding of polymer oxidation as it relates to lifetime prediction requirements.

36 MATERIALS SCIENCE↗

Physics-informed graph neural networks for predicting cetane number with systematic data quality analysis

Designing alternative fuels for advanced compression ignition engines necessitates a predictive model for cetane number (CN). In this study, the physics-informed graph neural networks are introduced for a reliable CN prediction by considering molecular features pertinent to the physical properties of molecules that affect CN. The reliability of measured data is another key factor to consider for improving the predictive model. Various experimental instruments for measuring CN exist, including standard and non-standard methods. In this regard, a systematic data quality analysis was carried out for the total 630 CNs collected from literature and new measurements in this study using Advanced Fuel Ignition Delay Analyzer (AFIDA). The results from this data curation process were reflected in the model by imposing lower sample weights on the data coming from less reliable measurement techniques. This approach effectively maximized the prediction accuracy while incorporating data from all available sources. Using the sample weights decreased the mean absolute error (MAE) up to 0.8 CN units. The accuracy was also improved by introducing the CN-related physical properties (the number of hydrogen bond donors and acceptors); the test set MAE is 5.74 and 7.01 for the model with and without such properties, respectively. Investigating molecular structural effects on CN was also carried out to gain chemical insights into factors used to design new fuel candidates. The dimensionality reduction analysis of feature vectors showed a clear clustering in terms of functional groups and CN and the structural effect derived from the model was consistent with the physicochemical insights. Finally, this physics-informed model and data curation would be helpful for accurate CN prediction and inform rational fuel design.

97 MATHEMATICS AND COMPUTING↗

A validated methodology for the prediction of heating and cooling energy demand for buildings within the Urban Heat Island: Case-study of London

This paper describes a method for predicting air temperatures within the Urban Heat Island at discreet locations based on input data from one meteorological station for the time the prediction is required and historic measured air temperatures within the city. It uses London as a case-study to describe the method and its applications. The prediction model is based on Artificial Neural Network (ANN) modelling and it is termed the London Site Specific Air Temperature (LSSAT) predictor. The temporal and spatial validity of the model was tested using data measured 8 years later from the original dataset; it was found that site specific hourly air temperature prediction provides acceptable accuracy and improves considerably for average monthly values. It thus is a very reliable tool for use as part of the process of predicting heating and cooling loads for urban buildings. This is illustrated by the computation of Heating Degree Days (HDD) and Cooling Degree Hours (CDH) for a West-East Transect within London. The described method could be used for any city for which historic hourly air temperatures are available for a number of locations; for example air pollution measuring sites, common in many cities, typically measure air temperature on an hourly basis. (author)

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A unified algorithm for predicting partition coefficients for PBPK modeling of drugs and environmental chemicals

The algorithms in the literature focusing to predict tissue:blood PC (P{sub tb}) for environmental chemicals and tissue:plasma PC based on total (K{sub p}) or unbound concentration (K{sub pu}) for drugs differ in their consideration of binding to hemoglobin, plasma proteins and charged phospholipids. The objective of the present study was to develop a unified algorithm such that P{sub tb}, K{sub p} and K{sub pu} for both drugs and environmental chemicals could be predicted. The development of the unified algorithm was accomplished by integrating all mechanistic algorithms previously published to compute the PCs. Furthermore, the algorithm was structured in such a way as to facilitate predictions of the distribution of organic compounds at the macro (i.e. whole tissue) and micro (i.e. cells and fluids) levels. The resulting unified algorithm was applied to compute the rat P{sub tb}, K{sub p} or K{sub pu} of muscle (n = 174), liver (n = 139) and adipose tissue (n = 141) for acidic, neutral, zwitterionic and basic drugs as well as ketones, acetate esters, alcohols, aliphatic hydrocarbons, aromatic hydrocarbons and ethers. The unified algorithm reproduced adequately the values predicted previously by the published algorithms for a total of 142 drugs and chemicals. The sensitivity analysis demonstrated the relative importance of the various compound properties reflective of specific mechanistic determinants relevant to prediction of PC values of drugs and environmental chemicals. Overall, the present unified algorithm uniquely facilitates the computation of macro and micro level PCs for developing organ and cellular-level PBPK models for both chemicals and drugs.

60 APPLIED LIFE SCIENCES↗

Prediction model of potential hepatocarcinogenicity of rat hepatocarcinogens using a large-scale toxicogenomics database

The present study was performed to develop a robust gene-based prediction model for early assessment of potential hepatocarcinogenicity of chemicals in rats by using our toxicogenomics database, TG-GATEs (Genomics-Assisted Toxicity Evaluation System developed by the Toxicogenomics Project in Japan). The positive training set consisted of high- or middle-dose groups that received 6 different non-genotoxic hepatocarcinogens during a 28-day period. The negative training set consisted of high- or middle-dose groups of 54 non-carcinogens. Support vector machine combined with wrapper-type gene selection algorithms was used for modeling. Consequently, our best classifier yielded prediction accuracies for hepatocarcinogenicity of 99% sensitivity and 97% specificity in the training data set, and false positive prediction was almost completely eliminated. Pathway analysis of feature genes revealed that the mitogen-activated protein kinase p38- and phosphatidylinositol-3-kinase-centered interactome and the v-myc myelocytomatosis viral oncogene homolog-centered interactome were the 2 most significant networks. The usefulness and robustness of our predictor were further confirmed in an independent validation data set obtained from the public database. Interestingly, similar positive predictions were obtained in several genotoxic hepatocarcinogens as well as non-genotoxic hepatocarcinogens. These results indicate that the expression profiles of our newly selected candidate biomarker genes might be common characteristics in the early stage of carcinogenesis for both genotoxic and non-genotoxic carcinogens in the rat liver. Our toxicogenomic model might be useful for the prospective screening of hepatocarcinogenicity of compounds and prioritization of compounds for carcinogenicity testing. - Highlights: >We developed a toxicogenomic model to predict hepatocarcinogenicity of chemicals. >The optimized model consisting of 9 probes had 99% sensitivity and 97% specificity. >This model enables us to detect genotoxic as well as non-genotoxic hepatocarcinogens.

60 APPLIED LIFE SCIENCES↗