Recommendation System to Predict Missing Adsorption Properties of Nanoporous Materials

Sturluson, Arni; Raza, Ali; McConachie, Grant D.; Siderius, Daniel W.; Fern, Xiaoli Z.; Simon, Cory

doi:10.1021/acs.chemmater.1c01201

Cited by 20 publications

(19 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, due to the capacities of interpolation and extrapolation, MOFNet can potentially be applied to missing data imputation of gas adsorption isotherms in databases. We found reports of related attempts, and our model may help to complete missing adsorption properties of nanoporous materials. In terms of the training data set, previous studies are mainly based on the hMOF data set, which has limited diversity in types of metal atoms and metallic corners.…”

Section: Discussionmentioning

confidence: 64%

Interpretable Graph Transformer Network for Predicting Adsorption Isotherms of Metal–Organic Frameworks

Chen

Jiao

Liu

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Predicting interactions between metal–organic frameworks (MOFs) and their adsorbates based on structures is critical to design high-performance porous materials. Many gas uptake prediction models have been proposed, but adsorption isotherm prediction is still challenging for most existing models. Here, we report a deep learning approach (MOFNet) that can predict adsorption isotherms for MOFs based on hierarchical representation and pressure adaptive mechanism. We elaborately design a hierarchical representation to encode the MOF structures. We adopt a graph transformer network to capture atomic-level information, which can help learn chemical features required under low-pressure conditions. A pressure adaptive mechanism is employed to interpolate and extrapolate the given limited data points by transfer learning, which can predict adsorption isotherms on a wider pressure range by only one model. We demonstrate that our predictor outperformed other traditional machine learning as well as graph neural network models on the challenging benchmarks and also achieves high performance on the real-world experimental observed adsorption isotherms. Finally, we interpret the models to discover and present potential structure–property relationships using the self-attention mechanism in the network. The proof-of-concept applications, such as disordered MOF predictions and missing data imputation of gas adsorption isotherms, showcase the generality and usability of our model to improve MOF material design.

show abstract

Section: Discussionmentioning

confidence: 64%

Interpretable Graph Transformer Network for Predicting Adsorption Isotherms of Metal–Organic Frameworks

Chen

Jiao

Liu

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…As illustrated in Figure 2c, the latent vectors of COFs (M) and gas-adsorption properties (P) were directly learned through decomposing the COF-property matrix (A); after projecting the latent vectors of COFs onto a 2D space, the proximity between COFs and similar adsorption properties was observed, thus revealing the similarity across different COFs. 33 Model Training. Many ML studies for MOFs aim to establish structure−property relationships via supervised learning, generally known as regression or classification (Figure 1c).…”

Section: ■ Introductionmentioning

confidence: 99%

“…36 By projecting the latent vectors of COFs into a 2D space based on PCA, Sturluson et al observed similar adsorption properties in clustered COFs, hence suggesting the physical robustness of such data-driven latent vectors. 33 Despite being computationally efficient, PCA is subject to a linear assumption across different features and hence inherently falls short in capturing nonlinear relationships. As an improvement over PCA, the nonlinear manifold learning technique assumes that the original high-dimensional feature space can be approximately embedded by low-dimensional manifolds.…”

Section: ■ Introductionmentioning

confidence: 99%

Leveraging Machine Learning for Metal–Organic Frameworks: A Perspective

Tang,

Duan,

Jiang

2023

Langmuir

View full text Add to dashboard Cite

Metal−organic frameworks (MOFs) have attracted tremendous interest because of their tunable structures, functionalities, and physiochemical properties. The nearly infinite combinations of metal nodes and organic linkers have led to the synthesis of over 100,000 experimental MOFs and the construction of millions of hypothetical counterparts. It is intractable to identify the best candidates in the immense chemical space of MOFs for applications via conventional trial-to-error experiments or bruteforce simulations. Over the past several years, machine learning (ML) has substantially transformed the way of MOF discovery, design, and synthesis. Driven by the abundant data from experiments or simulations, ML can not only efficiently and accurately predict MOF properties but also quantitatively derive structure−property relationships for rational design and screening. In this Perspective, we summarize recent achievements in leveraging ML for MOFs from the aspects of data acquisition, featurization, model training, and applications. Then, current challenges and new opportunities are discussed for the future exploration of ML to accelerate the development of new MOFs in this vibrant field.

show abstract

“…27,28 To learn the low-rank latent representation of the movies and users, MF needs a few example ratings; this requirement for a new movie or user is known as the "cold-start problem". 27 Matrix factorization approaches have been applied to a variety of chemical systems, e.g., to predict gas adsorption in nanoporous materials, 29,30 diffusion coefficients 31 and activity coefficients 32−35 of binary liquids, Henry's law coefficients, 36 the synthesis of metal oxides 37,38 and halide perovskites, 39 gas permeabilities in polymers, 40 and antiviral activities of molecules. 41 In these examples, the rows and columns represent different entities (e.g., gases and sorbents, elements, and reaction conditions) like the movie setting.…”

Section: ■ Introductionmentioning

confidence: 99%

Data-Driven Imputation of Miscibility of Aqueous Solutions via Graph-Regularized Logistic Matrix Factorization

Behnoudfar,

Simon,

Schrier

2023

J. Phys. Chem. B

Self Cite

View full text Add to dashboard Cite

Aqueous, two-phase systems (ATPSs) may form upon mixing two solutions of independently water-soluble compounds. Many separation, purification, and extraction processes rely on ATPSs. Predicting the miscibility of solutions can accelerate and reduce the cost of the discovery of new ATPSs for these applications. Whereas previous machine learning approaches to ATPS prediction used physicochemical properties of each solute as a descriptor, in this work, we show how to impute missing miscibility outcomes directly from an incomplete collection of pairwise miscibility experiments. We use graph-regularized logistic matrix factorization (GR-LMF) to learn a latent vector of each solution from (i) the observed entries in the pairwise miscibility matrix and (ii) a graph where each node is a solution and edges are relationships indicating the general category of the solute (i.e., polymer, surfactant, salt, protein). For an experimental data set of the pairwise miscibility of 68 solutions from Peacock et al. [ACS Appl. Mater. Interfaces 2021, 13, 11449–11460], we find that GR-LMF more accurately predicts missing (im)miscibility outcomes of pairs of solutions than ordinary logistic matrix factorization and random forest classifiers that use physicochemical features of the solutes. GR-LMF obviates the need for features of the solutions and solutions to impute missing miscibility outcomes, but it cannot predict the miscibility of a new solution without some observations of its miscibility with other solutions in the training data set.

show abstract

Recommendation System to Predict Missing Adsorption Properties of Nanoporous Materials

Cited by 20 publications

References 110 publications

Interpretable Graph Transformer Network for Predicting Adsorption Isotherms of Metal–Organic Frameworks

Interpretable Graph Transformer Network for Predicting Adsorption Isotherms of Metal–Organic Frameworks

Leveraging Machine Learning for Metal–Organic Frameworks: A Perspective

Data-Driven Imputation of Miscibility of Aqueous Solutions via Graph-Regularized Logistic Matrix Factorization

Contact Info

Product

Resources

About