Dataset Information

Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning.

ABSTRACT: The application of machine learning to predict materials properties measured by experiments are valuable yet difficult due to the limited amount of experimental data. In this work, we use a multifidelity random forest model to learn the experimental formation enthalpy of materials with prediction accuracy higher than the Perdew-Burke-Ernzerhof (PBE) functional with linear correction, PBEsol, and meta-generalized gradient approximation (meta-GGA) functionals (SCAN and r²SCAN), and it outperforms the hotly studied deep neural network-based representation learning and transfer learning. We then use the model to calibrate the DFT formation enthalpy in the Materials Project database and discover materials with underestimated stability. The multifidelity model is also used as a data-mining approach to find how DFT deviates from experiments by explaining the model output.

SUBMITTER: Gong S

PROVIDER: S-EPMC9516701 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning.

Gong Sheng S Wang Shuo S Xie Tian T Chae Woo Hyun WH Liu Runze R Shao-Horn Yang Y Grossman Jeffrey C JC

JACS Au 20220909 9

The application of machine learning to predict materials properties measured by experiments are valuable yet difficult due to the limited amount of experimental data. In this work, we use a multifidelity random forest model to learn the experimental formation enthalpy of materials with prediction accuracy higher than the Perdew-Burke-Ernzerhof (PBE) functional with linear correction, PBEsol, and meta-generalized gradient approximation (meta-GGA) functionals (SCAN and r<sup>2</sup>SCAN), and it o ...[more]

PMID: 36186569

Similar Datasets

Project description:High-throughput screening (HTS), as one of the key techniques in drug discovery, is frequently used to identify promising drug candidates in a largely automated and cost-effective way. One of the necessary conditions for successful HTS campaigns is a large and diverse compound library, enabling hundreds of thousands of activity measurements per project. Such collections of data hold great promise for computational and experimental drug discovery efforts, especially when leveraged in combination with modern deep learning techniques, and can potentially lead to improved drug activity predictions and cheaper and more effective experimental design. However, existing collections of machine-learning-ready public datasets do not exploit the multiple data modalities present in real-world HTS projects. Thus, the largest fraction of experimental measurements, corresponding to hundreds of thousands of "noisy" activity values from primary screening, are effectively ignored in the majority of machine learning models of HTS data. To address these limitations, we introduce Multifidelity PubChem BioAssay (MF-PCBA), a curated collection of 60 datasets that includes two data modalities for each dataset, corresponding to primary and confirmatory screening, an aspect that we call multifidelity. Multifidelity data accurately reflect real-world HTS conventions and present a new, challenging task for machine learning: the integration of low- and high-fidelity measurements through molecular representation learning, taking into account the orders-of-magnitude difference in size between the primary and confirmatory screens. Here we detail the steps taken to assemble MF-PCBA in terms of data acquisition from PubChem and the filtering steps required to curate the raw data. We also provide an evaluation of a recent deep-learning-based method for multifidelity integration across the introduced datasets, demonstrating the benefit of leveraging all HTS modalities, and a discussion in terms of the roughness of the molecular activity landscape. In total, MF-PCBA contains over 16.6 million unique molecule-protein interactions. The datasets can be easily assembled by using the source code available at https://github.com/davidbuterez/mf-pcba.

Project description:Thermodynamic properties, i.e., bond dissociation energies and enthalpy of formation, of chlorinated and brominated polycyclic aromatic hydrocarbons play a fundamental role in understanding their formation mechanisms and reactivity. Computational electronic structure calculations routinely used to predict thermodynamic properties of various species are limited for these compounds due to large computational cost to obtain accurate results by employing high-level wave function theory methods. In this work, a number of composite model chemistry methods (CBS-QB3, G3MP2, G3, and G4) are used to compute bond dissociation energies and enthalpies of formation of small to medium-size chlorinated and brominated polycyclic aromatic hydrocarbon compounds. The enthalpy of formation is derived via the atomization method and compared against the recommended values. Statistical analysis indicates that G4 is the best method. For comparison, three commonly used density functional theory (DFT) methods (M06-2X, ωB97X-D and B2PLYP-D3) with various basis sets including 6-311++G(d, p), cc-pVTZ, and cc-pVQZ in the prediction of bond dissociation energies and enthalpies of formation have been tested using the optimized geometries at the same M06-2X/6-311++G(d, p) level of theory. It is found that ωB97X-D/6-311++G(d, p) shows the best performance in computing the bond dissociation energies, while ωB97X-D/cc-pVTZ exhibits the best prediction in enthalpy of formation of the studied reaction systems. The structural effect on the bond dissociation energies and enthalpy of formation of chlorinated and brominated polycyclic aromatic hydrocarbons are then systematically analyzed. Based on comparisons of the various methods, reliable DFT methods are recommended for future theoretical studies on large chlorinated and brominated polycyclic aromatic hydrocarbons considering both accuracy and computational cost. This work, to the authors' knowledge, is the first to systematically benchmark theoretical methods for the accurate prediction of thermodynamic properties for chlorinated and brominated polycyclic aromatic hydrocarbons.

Project description:BACKGROUND:Physical activity (PA) level is associated with multiple health benefits during early childhood. However, inconsistency in the methods for quantification of PA levels among preschoolers remains a problem. OBJECTIVE:This study aimed to develop PA intensity cut points for wrist-worn accelerometers by using machine learning (ML) approaches to assess PA in preschoolers. METHODS:Wrist- and hip-derived acceleration data were collected simultaneously from 34 preschoolers on 3 consecutive preschool days. Two supervised ML models, receiver operating characteristic curve (ROC) and ordinal logistic regression (OLR), and one unsupervised ML model, k-means cluster analysis, were applied to establish wrist-worn accelerometer vector magnitude (VM) cut points to classify accelerometer counts into sedentary behavior, light PA (LPA), moderate PA (MPA), and vigorous PA (VPA). Physical activity intensity levels identified by hip-worn accelerometer VM cut points were used as reference to train the supervised ML models. Vector magnitude counts were classified by intensity based on three newly established wrist methods and the hip reference to examine classification accuracy. Daily estimates of PA were compared to the hip-reference criterion. RESULTS:In total, 3600 epochs with matched hip- and wrist-worn accelerometer VM counts were analyzed. All ML approaches performed differently on developing PA intensity cut points for wrist-worn accelerometers. Among the three ML models, k-means cluster analysis derived the following cut points: ?2556 counts per minute (cpm) for sedentary behavior, 2557-7064 cpm for LPA, 7065-14532 cpm for MPA, and ?14533 cpm for VPA; in addition, k-means cluster analysis had the highest classification accuracy, with more than 70% of the total epochs being classified into the correct PA categories, as examined by the hip reference. Additionally, k-means cut points exhibited the most accurate estimates on sedentary behavior, LPA, and VPA as the hip reference. None of the three wrist methods were able to accurately assess MPA. CONCLUSIONS:This study demonstrates the potential of ML approaches in establishing cut points for wrist-worn accelerometers to assess PA in preschoolers. However, the findings from this study warrant additional validation studies.

Dataset Information

Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning.

Publications

Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets