Litcius/Paper detail

A systematic modeling methodology of deep neural network‐based structure‐property relationship for rapid and reliable prediction on flashpoints

Huaqiang Wen, Yang Su, Zihao Wang, Saimeng Jin, Jingzheng Ren, Weifeng Shen, Mario R. Eden

2021AIChE Journal49 citationsDOIOpen Access PDF

Abstract

Abstract Deep neural networks (DNNs) based quantitative structure–property relationship (QSPR) studies are receiving increasing attention due to their excellent performances. A systematic methodology coupling multiple machine learning technologies is proposed to systematically solve vital problems including applicability domain and prediction uncertainty in DNN‐based QSPR modeling. Key features are rapidly extracted from plentiful but chaotic descriptors by principal component analysis (PCA) and kernel PCA. Then, a detailed applicability domain (AD) is defined by K‐means algorithm to avoid unreliable predictions and discover its potential impact on prediction uncertainty. Moreover, prediction uncertainty is analyzed with dropout ‐embedded DNN by thousands of independent tests to assess the reliability of predictions. The prediction of flashpoint temperature is employed as a case study, demonstrating that the model accuracy is remarkably improved comparing with the referenced model. Furthermore, the proposed methodology breaks through difficulties in analyzing the uncertainty of DNN‐based QSPRs and presents an AD correlated with the uncertainty.

Topics & Concepts

Artificial neural networkPrincipal component analysisComputer scienceArtificial intelligenceReliability (semiconductor)Applicability domainMachine learningDomain (mathematical analysis)Quantitative structure–activity relationshipKey (lock)Data miningKernel (algebra)Dropout (neural networks)Component (thermodynamics)MathematicsPhysicsThermodynamicsMathematical analysisQuantum mechanicsPower (physics)CombinatoricsComputer securityComputational Drug Discovery MethodsMachine Learning in Materials ScienceThermal and Kinetic Analysis
A systematic modeling methodology of deep neural network‐based structure‐property relationship for rapid and reliable prediction on flashpoints | Litcius