MOFormer: Self-Supervised Transformer Model for Metal-Organic Framework Property Prediction

Metal-Organic Framework Stability in Water and Harsh Environments from Data-Driven Models Trained on the Diverse WS24 Data Set

Metal-organic frameworks (MOFs) are porous materials with applications in gas separations and catalysis, but a lack of water stability often limits their practical use given the ubiquity of water. Consequently, it is useful to predict whether a MOF is water-stable before investing time and resources into synthesis. Existing heuristics for designing water-stable MOFs lack generality and limit the diversity of explored chemistry due to narrowly defined criteria. Machine learning (ML) models offer the promise to improve the generality of predictions but require data. In an improvement on previous efforts, we enlarge the available training data for MOF water stability prediction by over 400%, adding 911 MOFs with water stability labels assigned through semiautomated manuscript analysis to curate the new data set WS24. The additional data are shown to improve ML model performance (test ROC-AUC > 0.8) over diverse chemistry for the prediction of both water stability and stability in harsher acidic conditions. We illustrate how the expanded data set and models can be used with a previously developed activation stability model in combination with genetic algorithms to quickly screen ∼10,000 MOFs from a space of hundreds of thousands for candidates with multivariate stability (upon activation, in water, and in acid). We uncover metal- and geometry-specific design rules for robust MOFs. The data set and ML models developed in this work, which we disseminate through an easy-to-use web interface, are expected to contribute toward the accelerated discovery of novel, water-stable MOFs for applications such as direct air gas capture and water treatment.

Evaluation of Open-Source Large Language Models for Metal-Organic Frameworks Research

Along with the development of machine learning, deep learning, and large language models (LLMs) such as GPT-4 (GPT: Generative Pre-Trained Transformer), artificial intelligence (AI) tools have been playing an increasingly important role in chemical and material research to facilitate the material screening and design. Despite the exciting progress of GPT-4 based AI research assistance, open-source LLMs have not gained much attention from the scientific community. This work primarily focused on metal-organic frameworks (MOFs) as a subdomain of chemistry and evaluated six top-rated open-source LLMs with a comprehensive set of tasks including MOFs knowledge, basic chemistry knowledge, in-depth chemistry knowledge, knowledge extraction, database reading, predicting material property, experiment design, computational scripts generation, guiding experiment, data analysis, and paper polishing, which covers the basic units of MOFs research. In general, these LLMs were capable of most of the tasks. Especially, Llama2-7B and ChatGLM2-6B were found to perform particularly well with moderate computational resources. Additionally, the performance of different parameter versions of the same model was compared, which revealed the superior performance of higher parameter versions.

Classifying and Predicting the Thermal Expansion Properties of Metal-Organic Frameworks: A Data-Driven Approach

Metal-organic frameworks (MOFs) are versatile materials for a wide variety of potential applications. Tunable thermal expansion properties promote the application of MOFs in thermally sensitive composite materials; however, they are currently available only in a handful of structures. Herein, we report the first data set for thermal expansion properties of 33,131 diverse MOFs generated from molecular simulations and subsequently develop machine learning (ML) models to (1) classify different thermal expansion behaviors and (2) predict volumetric thermal expansion coefficients (αV). The random forest model trained on hybrid descriptors combining geometric, chemical, and topological features exhibits the best performance among different ML models. Based on feature importance analysis, linker chemistry and topological arrangement are revealed to have a dominant impact on thermal expansion. Furthermore, we identify common building blocks in MOFs with exceptional thermal expansion properties. This data-driven study is the first of its kind, not only constructing a useful data set to facilitate future studies on this important topic but also providing design guidelines for advancing new MOFs with desired thermal expansion properties.

PACMAN: A Robust Partial Atomic Charge Predicter for Nanoporous Materials Based on Crystal Graph Convolution Networks

We report a fast and easy method (PACMAN) to assign partial atomic charges on metal-organic framework (MOF) and covalent-organic framework (COF) crystal structures based on graph convolution networks (GCNs) trained on >1.8 million high-fidelity partial atomic charge data obtained from the Quantum Metal-Organic Framework (QMOF) database. The developed model shows outstanding performance, achieving a mean absolute error (MAE) of 0.0055 e (test set performance) while maintaining consistency with DDEC6, Bader, and CM5 charges across diverse chemistry and topologies of MOFs and COFs. We find that the new method accurately assigns partial atomic charges for ion-containing nanoporous materials, which has not been possible in previous machine learning (ML) models. Grand canonical Monte Carlo (GCMC) simulation results for CO2 and N2 uptakes and the Widom particle insertion calculation for Henry's law constant of water results based on PACMAN and the original DDEC6 charges show excellent agreements compared to other ML models reported in the literature. The runtime analysis of the new method demonstrates that the partial atomic charges of MOF and COF structures with up to 500 atoms can be obtained in less than 10 s. An easy-to-use web interface has been developed to facilitate the adoption of the developed model.

Application of Transformers in Cheminformatics

By accelerating time-consuming processes with high efficiency, computing has become an essential part of many modern chemical pipelines. Machine learning is a class of computing methods that can discover patterns within chemical data and utilize this knowledge for a wide variety of downstream tasks, such as property prediction or substance generation. The complex and diverse chemical space requires complex machine learning architectures with great learning power. Recently, learning models based on transformer architectures have revolutionized multiple domains of machine learning, including natural language processing and computer vision. Naturally, there have been ongoing endeavors in adopting these techniques to the chemical domain, resulting in a surge of publications within a short period. The diversity of chemical structures, use cases, and learning models necessitate a comprehensive summarization of existing works. In this paper, we review recent innovations in adapting transformers to solve learning problems in chemistry. Because chemical data is diverse and complex, we structure our discussion based on chemical representations. Specifically, we highlight the strengths and weaknesses of each representation, the current progress of adapting transformer architectures, and future directions.

Multiscale Modeling of Physical Properties of Nanoporous Frameworks: Predicting Mechanical, Thermal, and Adsorption Behavior

ConspectusNanoporous frameworks are a large and diverse family of supramolecular materials, whose chemical building units (organic, inorganic, or both) are assembled into a 3D architecture with well-defined connectivity and topology, featuring intrinsic porosity. These materials play a key role in various industrial processes and applications, such as energy production and conversion, fluid separation, gas storage, water harvesting, and many more. The performance and suitability of nanoporous materials for each specific application are directly related to both their physical and chemical properties, and their determination is crucial for process engineering and optimization of performances. In this Account, we focus on some recent developments in the multiscale modeling of physical properties of nanoporous frameworks, highlighting the latest advances in three specific areas: mechanical properties, thermal properties, and adsorption.In the study of the mechanical behavior of nanoporous materials, the past few years have seen a rapid acceleration of research. For example, computational resources have been pooled to create a public large-scale database of elastic constants as part of the Materials Project initiative to accelerate innovation in materials research: those can serve as a basis for data-based discovery of materials with targeted properties, as well as the training of machine learning predictor models.The large-scale prediction of thermal behavior, in comparison, is not yet routinely performed at such a large scale. Tentative databases have been assembled at the DFT level on specific families of materials, such as zeolites, but prediction at larger scale currently requires the use of transferable classical force fields, whose accuracy can be limited.Finally, adsorption is naturally one of the most studied physical properties of nanoporous frameworks, as fluid separation or storage is often the primary target for these materials. We highlight the recent achievements and open challenges for adsorption prediction at a large scale, focusing in particular on the accuracy of computational models and the reliability of comparisons with experimental data available. We detail some recent methodological improvements in the prediction of adsorption-related properties: in particular, we describe the recent research efforts to go beyond the study of thermodynamic quantities (uptake, adsorption enthalpy, and thermodynamic selectivity) and predict transport properties using data-based methods and high-throughput computational schemes. Finally, we stress the importance of data-based methods of addressing all sources of uncertainty.The Account concludes with some perspectives about the latest developments and open questions in data-based approaches and the integration of computational and experimental data together in the materials discovery loop.

Accelerating material property prediction using generically complete isometry invariants

Periodic material or crystal property prediction using machine learning has grown popular in recent years as it provides a computationally efficient replacement for classical simulation methods. A crucial first step for any of these algorithms is the representation used for a periodic crystal. While similar objects like molecules and proteins have a finite number of atoms and their representation can be built based upon a finite point cloud interpretation, periodic crystals are unbounded in size, making their representation more challenging. In the present work, we adapt the Pointwise Distance Distribution (PDD), a continuous and generically complete isometry invariant for periodic point sets, as a representation for our learning algorithm. The PDD distinguished all (more than 660 thousand) periodic crystals in the Cambridge Structural Database as purely periodic sets of points without atomic types. We develop a transformer model with a modified self-attention mechanism that combines PDD with compositional information via a spatial encoding method. This model is tested on the crystals of the Materials Project and Jarvis-DFT databases and shown to produce accuracy on par with state-of-the-art methods while being several times faster in both training and prediction time.

Large-Scale Pretraining Improves Sample Efficiency of Active Learning-Based Virtual Screening

Virtual screening of large compound libraries to identify potential hit candidates is one of the earliest steps in drug discovery. As the size of commercially available compound collections grows exponentially to the scale of billions, active learning and Bayesian optimization have recently been proven as effective methods of narrowing down the search space. An essential component of those methods is a surrogate machine learning model that predicts the desired properties of compounds. An accurate model can achieve high sample efficiency by finding hits with only a fraction of the entire library being virtually screened. In this study, we examined the performance of a pretrained transformer-based language model and graph neural network in a Bayesian optimization active learning framework. The best pretrained model identifies 58.97% of the top-50,000 compounds after screening only 0.6% of an ultralarge library containing 99.5 million compounds, improving 8% over the previous state-of-the-art baseline. Through extensive benchmarks, we show that the superior performance of pretrained models persists in both structure-based and ligand-based drug discovery. Pretrained models can serve as a boost to the accuracy and sample efficiency of active learning-based virtual screening.

Coarse-Grained Crystal Graph Neural Networks for Reticular Materials Design

Reticular materials, including metal-organic frameworks and covalent organic frameworks, combine the relative ease of synthesis and an impressive range of applications in various fields from gas storage to biomedicine. Diverse properties arise from the variation of building units─metal centers and organic linkers─in almost infinite chemical space. Such variation substantially complicates the experimental design and promotes the use of computational methods. In particular, the most successful artificial intelligence algorithms for predicting the properties of reticular materials are atomic-level graph neural networks, which optionally incorporate domain knowledge. Nonetheless, the data-driven inverse design involving these models suffers from the incorporation of irrelevant and redundant features such as a full atomistic graph and network topology. In this study, we propose a new way of representing materials, aiming to overcome the limitations of existing methods; the message passing is performed on a coarse-grained crystal graph that comprises molecular building units. To highlight the merits of our approach, we assessed the predictive performance and energy efficiency of neural networks built on different materials representations, including composition-based and crystal-structure-aware models. Coarse-grained crystal graph neural networks showed decent accuracy at low computational costs, making them a valuable alternative to omnipresent atomic-level algorithms. Moreover, the presented models can be successfully integrated into an inverse materials design pipeline as estimators of the objective function. Overall, the coarse-grained crystal graph framework is aimed at challenging the prevailing atom-centric perspective on reticular materials design.

Machine Learning in Membrane Design: From Property Prediction to AI-Guided Optimization

Porous membranes, either polymeric or two-dimensional materials, have been extensively studied because of their outstanding performance in many applications such as water filtration. Recently, inspired by the significant success of machine learning (ML) in many areas of scientific discovery, researchers have started to tackle the problem in the field of membrane design using data-driven ML tools. In this Mini Review, we summarize research efforts on three types of applications of machine learning in membrane design, including (1) membrane property prediction using ML, (2) gaining physical insight and drawing quantitative relationships between membrane properties and performance using explainable artificial intelligence, and (3) ML-guided design, optimization, or virtual screening of membranes. On top of the review of previous research, we discuss the challenges associated with applying ML for membrane design and potential future directions.

Informative Training Data for Efficient Property Prediction in Metal-Organic Frameworks by Active Learning

In recent data-driven approaches to material discovery, scenarios where target quantities are expensive to compute and measure are often overlooked. In such cases, it becomes imperative to construct a training set that includes the most diverse, representative, and informative samples. Here, a novel regression tree-based active learning algorithm is employed for such a purpose. It is applied to predict the band gap and adsorption properties of metal-organic frameworks (MOFs), a novel class of materials that results from the virtually infinite combinations of their building units. Simpler and low dimensional descriptors, such as those based on stoichiometric and geometric properties, are used to compute the feature space for this model owing to their ability to better represent MOFs in the low data regime. The partitions given by a regression tree constructed on the labeled part of the data set are used to select new samples to be added to the training set, thereby limiting its size while maximizing the prediction quality. Tests on the QMOF, hMOF, and dMOF data sets reveal that our method constructs small training data sets to learn regression models that predict the target properties more efficiently than existing active learning approaches, and with lower variance. Specifically, our active learning approach is highly beneficial when labels are unevenly distributed in the descriptor space and when the label distribution is imbalanced, which is often the case for real world data. The regions defined by the tree help in revealing patterns in the data, thereby offering a unique tool to efficiently analyze complex structure-property relationships in materials and accelerate materials discovery.

Physics-Guided Dual Self-Supervised Learning for Structure-Based Material Property Prediction

Deep learning models have been widely used for high-performance material property prediction. However, training such models usually requires a large amount of labeled data, which are usually unavailable. Self-supervised learning (SSL) methods have been proposed to address this data scarcity issue. Herein, we present DSSL, a physics-guided dual SSL framework, for graph neural network-based material property prediction, which combines node masking-based generative SSL with atomic coordinate perturbation-based contrastive SSL strategies to capture local and global information about input crystals. Moreover, we achieve physics-guided pretraining by using the macroproperty (e.g., elasticity)-related microproperty prediction of atomic stiffness as an additional pretext task. We pretrain our DSSL model on the Materials Project database and fine-tune it with 10 material property data sets. The experimental results demonstrate that teaching neural networks some physics using the SSL strategy can afford ≤26.89% performance improvement compared to that of the baseline models.

A comprehensive transformer-based approach for high-accuracy gas adsorption predictions in metal-organic frameworks

Gas separation is crucial for industrial production and environmental protection, with metal-organic frameworks (MOFs) offering a promising solution due to their tunable structural properties and chemical compositions. Traditional simulation approaches, such as molecular dynamics, are complex and computationally demanding. Although feature engineering-based machine learning methods perform better, they are susceptible to overfitting because of limited labeled data. Furthermore, these methods are typically designed for single tasks, such as predicting gas adsorption capacity under specific conditions, which restricts the utilization of comprehensive datasets including all adsorption capacities. To address these challenges, we propose Uni-MOF, an innovative framework for large-scale, three-dimensional MOF representation learning, designed for multi-purpose gas prediction. Specifically, Uni-MOF serves as a versatile gas adsorption estimator for MOF materials, employing pure three-dimensional representations learned from over 631,000 collected MOF and COF structures. Our experimental results show that Uni-MOF can automatically extract structural representations and predict adsorption capacities under various operating conditions using a single model. For simulated data, Uni-MOF exhibits remarkably high predictive accuracy across all datasets. Additionally, the values predicted by Uni-MOF correspond with the outcomes of adsorption experiments. Furthermore, Uni-MOF demonstrates considerable potential for broad applicability in predicting a wide array of other properties.

Pretraining Strategies for Structure Agnostic Material Property Prediction

In recent years, machine learning (ML), especially graph neural network (GNN) models, has been successfully used for fast and accurate prediction of material properties. However, most ML models rely on relaxed crystal structures to develop descriptors for accurate predictions. Generating these relaxed crystal structures can be expensive and time-consuming, thus requiring an additional processing step for models that rely on them. To address this challenge, structure-agnostic methods have been developed, which use fixed-length descriptors engineered based on human knowledge about the material. However, the fixed-length descriptors are often hand-engineered and require extensive domain knowledge and generally are not used in the context of learnable models which are known to have a superior performance. Recent advancements have proposed learnable frameworks that can construct representations based on stoichiometry alone, allowing the flexibility of using deep learning frameworks as well as leveraging structure-agnostic learning. In this work, we propose three different pretraining strategies that can be used to pretrain these structure-agnostic, learnable frameworks to further improve the downstream material property prediction performance. We incorporate strategies such as self-supervised learning (SSL), fingerprint learning (FL), and multimodal learning (ML) and demonstrate their efficacy on downstream tasks for the Roost architecture, a popular structure-agnostic framework. Our results show significant improvement in small data sets and data efficiency in the larger data sets, underscoring the potential of our pretrain strategies that effectively leverage unlabeled data for accurate material property prediction.

Gas adsorption meets deep learning: voxelizing the potential energy surface of metal-organic frameworks

Intrinsic properties of metal-organic frameworks (MOFs), such as their ultra porosity and high surface area, deem them promising solutions for problems involving gas adsorption. Nevertheless, due to their combinatorial nature, a huge number of structures is feasible which renders cumbersome the selection of the best candidates with traditional techniques. Recently, machine learning approaches have emerged as efficient tools to deal with this challenge, by allowing researchers to rapidly screen large databases of MOFs via predictive models. The performance of the latter is tightly tied to the mathematical representation of a material, thus necessitating the use of informative descriptors. In this work, a generalized framework to predict gaseous adsorption properties is presented, using as one and only descriptor the capstone of chemical information: the potential energy surface (PES). In order to be machine understandable, the PES is voxelized and subsequently a 3D convolutional neural network (CNN) is exploited to process this 3D energy image. As a proof of concept, the proposed pipeline is applied on predicting [Formula: see text] uptake in MOFs. The resulting model outperforms a conventional model built with geometric descriptors and requires two orders of magnitude less training data to reach a given level of performance. Moreover, the transferability of the approach to different host-guest systems is demonstrated, examining [Formula: see text] uptake in COFs. The generic character of the proposed methodology, inherited from the PES, renders it applicable to fields other than reticular chemistry.

PolyNC: a natural and chemical language model for the prediction of unified polymer properties

Language models exhibit a profound aptitude for addressing multimodal and multidomain challenges, a competency that eludes the majority of off-the-shelf machine learning models. Consequently, language models hold great potential for comprehending the intricate interplay between material compositions and diverse properties, thereby accelerating material design, particularly in the realm of polymers. While past limitations in polymer data hindered the use of data-intensive language models, the growing availability of standardized polymer data and effective data augmentation techniques now opens doors to previously uncharted territories. Here, we present a revolutionary model to enable rapid and precise prediction of Polymer properties via the power of Natural language and Chemical language (PolyNC). To showcase the efficacy of PolyNC, we have meticulously curated a labeled prompt-structure-property corpus encompassing 22 970 polymer data points on a series of essential polymer properties. Through the use of natural language prompts, PolyNC gains a comprehensive understanding of polymer properties, while employing chemical language (SMILES) to describe polymer structures. In a unified text-to-text manner, PolyNC consistently demonstrates exceptional performance on both regression tasks (such as property prediction) and the classification task (polymer classification). Simultaneous and interactive multitask learning enables PolyNC to holistically grasp the structure-property relationships of polymers. Through a combination of experiments and characterizations, the generalization ability of PolyNC has been demonstrated, with attention analysis further indicating that PolyNC effectively learns structural information about polymers from multimodal inputs. This work provides compelling evidence of the potential for deploying end-to-end language models in polymer research, representing a significant advancement in the AI community's dedicated pursuit of advancing polymer science.

MOF-GRU: A MOFid-Aided Deep Learning Model for Predicting the Gas Separation Performance of Metal-Organic Frameworks

The remarkable versatility of metal-organic frameworks (MOFs) stems from their rich chemical information, leading to numerous successful applications. However, identifying optimal MOFs for specific tasks necessitates a thorough assessment of their chemical attributes. Conventional machine learning approaches for MOF prediction have relied on intricate chemical and structural details, hampering rapid evaluations. Drawing inspiration from recent advancements exemplified by Snurr et al., wherein a text string was used to represent a MOF (MOFid), we introduce a MOFid-aided deep learning model, named the MOF-GRU model. This model, founded on natural language processing principles and utilizing the gated recurrent unit architecture, leverages the serialized text string representation of metal-organic frameworks (MOFs) to forecast gas separation performance. Through a focused study on CH4/N2 separation, we substantiate the efficacy of this approach. Comparative assessments against traditional machine learning techniques underscore our model's superior predictive accuracy and its capacity to handle extensive data sets adeptly. The MOF-GRU model remarkably uncovers latent structure-performance relationships with only MOF sequences, obviating the necessity for intricate three-dimensional (3D) structural information. Overall, this model's judicious design empowers efficient data utilization, thereby hastening the discovery of high-performance materials tailored for gas separation applications.

Leveraging Machine Learning for Metal-Organic Frameworks: A Perspective

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 brute-force 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.

Graph Transformer with Convolution Parallel Networks for Predicting Single and Binary Component Adsorption Performance of Metal-Organic Frameworks

Metal-organic frameworks (MOFs) are considered one of the most important materials for carbon capture and storage (CCS) due to the advantages of porosity, multifunction, diverse structure, and controllable chemical composition. With the continuous development of artificial intelligence (AI) technology, more and more machine learning models are used to identify MOFs with high performance within a massive search space. However, current works have yet to form a model that uses graph-structured data only, which can predict the adsorption properties of single and binary components. In this work, we proposed and developed a graph transformer, combined with convolution parallel networks, called GC-Trans. The model can accurately and efficiently predict the adsorption performance of MOFs under the single- and binary-component adsorption conditions using only the features of the crystal diagram as inputs. By extracting and fusing local and global feature information, the model has stronger expression and generalization abilities. Thus, we used it to screen the ARC-MOF database and analyze the MOF structures that meet the target requirements. Additionally, to demonstrate the transferability of the model, we applied transfer learning methods to predict the CO2/CH4 separations and CH4 uptake, both of which showed good predictive performance.

Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials

Recent advances in equivariant graph neural networks (GNNs) have made deep learning amenable to developing fast surrogate models to expensive ab initio quantum mechanics (QM) approaches for molecular potential predictions. However, building accurate and transferable potential models using GNNs remains challenging, as the data are greatly limited by the expensive computational costs and level of theory of QM methods, especially for large and complex molecular systems. In this work, we propose denoise pretraining on nonequilibrium molecular conformations to achieve more accurate and transferable GNN potential predictions. Specifically, atomic coordinates of sampled nonequilibrium conformations are perturbed by random noises, and GNNs are pretrained to denoise the perturbed molecular conformations which recovers the original coordinates. Rigorous experiments on multiple benchmarks reveal that pretraining significantly improves the accuracy of neural potentials. Furthermore, we show that the proposed pretraining approach is model-agnostic, as it improves the performance of different invariant and equivariant GNNs. Notably, our models pretrained on small molecules demonstrate remarkable transferability, improving performance when fine-tuned on diverse molecular systems, including different elements, charged molecules, biomolecules, and larger systems. These results highlight the potential for leveraging denoise pretraining approaches to build more generalizable neural potentials for complex molecular systems.

Predicting band gaps of MOFs on small data by deep transfer learning with data augmentation strategies

Porphyrin-based MOFs combine the unique photophysical and electrochemical properties of metalloporphyrins with the catalytic efficiency of MOF materials, making them an important candidate for light energy harvesting and conversion. However, accurate prediction of the band gap of porphyrin-based MOFs is hampered by their complex structure-function relationships. Although machine learning (ML) has performed well in predicting the properties of MOFs with large training datasets, such ML applications become challenging when the training data size of the materials is small. In this study, we first constructed a dataset of 202 porphyrin-based MOFs using DFT computations and increased the training data size using two data augmentation strategies. After that, four state-of-the-art neural network models were pre-trained with the recognized open-source database QMOF and fine-tuned with our augmented self-curated datasets. The GCN models predicted the band gaps of the porphyrin-based materials with the lowest RMSE of 0.2767 eV and MAE of 0.1463 eV. In addition, the data augmentation strategy rotation and mirroring effectively decreased the RMSE by 38.51% and MAE by 50.05%. This study demonstrates that, when proper transfer learning and data augmentation strategies are applied, machine learning models can predict the properties of MOFs using small training data.