ChemML: A Machine Learning and Informatics Program Package for the Analysis, Mining, and Modeling of Chemical and Materials Data

Haghighatlari, Mojtaba; Vishwakarma, Gaurav; Altarawy, Doaa; Subramanian, R.; Kota, Bhargava Urala; Sonpal, Aditya; Setlur, Srirangaraj; Hachmann, Johannes

doi:10.26434/chemrxiv.8323271

Cited by 6 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are, however, interdependent and often multiple iterations of each step are required to create a successful machine learning system. Specialized software frameworks [220][221][222] have been developed to aid the set-up and build and management of machine learning models.…”

Section: Specifics Of Machine Learning In Materials Sciencementioning

confidence: 99%

Data‐Driven Materials Science: Status, Challenges, and Perspectives

et al. 2019

View full text Add to dashboard Cite

Data‐driven science is heralded as a new paradigm in materials science. In this field, data is the new resource, and knowledge is extracted from materials datasets that are too big or complex for traditional human reasoning—typically with the intent to discover new or improved materials or materials phenomena. Multiple factors, including the open science movement, national funding, and progress in information technology, have fueled its development. Such related tools as materials databases, machine learning, and high‐throughput methods are now established as parts of the materials research toolset. However, there are a variety of challenges that impede progress in data‐driven materials science: data veracity, integration of experimental and computational data, data longevity, standardization, and the gap between industrial interests and academic efforts. In this perspective article, the historical development and current state of data‐driven materials science, building from the early evolution of open science to the rapid expansion of materials data infrastructures are discussed. Key successes and challenges so far are also reviewed, providing a perspective on the future development of the field.

show abstract

Section: Specifics Of Machine Learning In Materials Sciencementioning

confidence: 99%

Data‐Driven Materials Science: Status, Challenges, and Perspectives

et al. 2019

View full text Add to dashboard Cite

show abstract

“…It is an example of knowledge transfer from a smaller to a bigger system. ASE, ChemML, rdkit, and OpenBabel can be used to convert the SMILES strings for new species into 3D structures. DFT simulations of these structures would yield whether the generated species has a stable relaxed configuration.…”

Section: Methodsmentioning

confidence: 99%

Learning Chemistry of Complex Reaction Systems via a Python First-Principles Reaction Rule Stencil (pReSt) Generator

Gupta

Vlachos

2021

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Complex reaction networks can be generated with automated network generators from initial reactants and reaction rules. Reaction rule specification is central to network generation. These reaction rules are, at present, user-defined based on (intuitive) expert knowledge of chemistry and are often transferred from gas-phase to surface processes. The catalyst active site geometry is usually left out but is often responsible for selectivity. We propose a first-principles-based reaction mechanism generation framework using density functional theory (DFT) data of published reaction mechanisms. The framework "learns the chemistry" from published mechanisms. It can generate reaction networks not studied before, "flag" reactions not seen before for further DFT convergence tests, and easily reconcile differences between catalysts and reactants that may introduce new pathways never seen before. As such, it can be a diagnostic tool for data (mechanism) quality assessment and novel pathway discovery to new molecules. A software, the Python Reaction Stencil (pReSt), was developed for this purpose to wrap around automatic mechanism generation software. Multiple catalytic chemistries are considered to show the efficacy of the proposed framework.

show abstract

“…For this, we pursue a DNN approach within a feature space of molecular descriptors. We build the DNN model using ChemML, 46,50,51 our program suite for machine learning and informatics in chemical and materials research. In this work, ChemML employs the scikit-learn 0.18.2 library for the multilayer perceptron regressor 1.17.1 (ref.…”

Section: Neural Network Prediction Modelmentioning

confidence: 99%

A Deep Neural Network Model for Packing Density Predictions and its Application in the Study of 1.5 Million Organic Molecules

Afzal¹,

Sonpal²,

Haghighatlari³

et al. 2019

Preprint

View full text Add to dashboard Cite

<pre>The process of developing new compounds and materials is increasingly driven by computational modeling and simulation, which allow us to characterize candidates before pursuing them in the laboratory. One of the non-trivial properties of interest for organic materials is their packing in the bulk, which is highly dependent on their molecular structure. By controlling the latter, we can realize materials with a desired density (as well as other target properties). Molecular dynamics simulations are a popular and reasonably accurate way to compute the bulk density of molecules, however, since these calculations are computationally intensive, they are not a practically viable option for high-throughput screening studies that assess material candidates on a massive scale. In this work, we employ machine learning to develop a data-derived prediction model that is an alternative to physics-based simulations, and we utilize it for the hyperscreening of 1.5 million small organic molecules as well as to gain insights into the relationship between structural makeup and packing density.We also use this study to analyze the learning curve of the employed neural network approach and gain empirical data on the dependence of model performance and training data size, which will inform future investigations.</pre>

show abstract

ChemML: A Machine Learning and Informatics Program Package for the Analysis, Mining, and Modeling of Chemical and Materials Data

Cited by 6 publications

References 30 publications

Data‐Driven Materials Science: Status, Challenges, and Perspectives

Data‐Driven Materials Science: Status, Challenges, and Perspectives

Learning Chemistry of Complex Reaction Systems via a Python First-Principles Reaction Rule Stencil (pReSt) Generator

A Deep Neural Network Model for Packing Density Predictions and its Application in the Study of 1.5 Million Organic Molecules

Contact Info

Product

Resources

About