Accurate and efficient prediction of polymer properties is of great significance in polymer design. Conventionally, expensive and time-consuming experiments or simulations are required to evaluate polymer functions. Recently, Transformer models, equipped with self-attention mechanisms, have exhibited superior performance in natural language processing. However, such methods have not been investigated in polymer sciences. Herein, we report TransPolymer, a Transformer-based language model for polymer property prediction. Our proposed polymer tokenizer with chemical awareness enables learning representations from polymer sequences. Rigorous experiments on ten polymer property prediction benchmarks demonstrate the superior performance of TransPolymer. Moreover, we show that TransPolymer benefits from pretraining on large unlabeled dataset via Masked Language Modeling. Experimental results further manifest the important role of self-attention in modeling polymer sequences. We highlight this model as a promising computational tool for promoting rational polymer design and understanding structure-property relationships from a data science view.
Metal-Organic Frameworks (MOFs) are materials with a high degree of porosity that can be used for applications in energy storage, water desalination, gas storage, and gas separation. However, the chemical space of MOFs is close to an infinite size due to the large variety of possible combinations of building blocks and topology. Discovering the optimal MOFs for specific applications requires an efficient and accurate search over an enormous number of potential candidates. Previous high-throughput screening methods using computational simulations like DFT can be time-consuming. Such methods also require optimizing 3D atomic structure of MOFs, which adds one extra step when evaluating hypothetical MOFs. In this work, we propose a structure-agnostic deep learning method based on the Transformer model, named as MOFormer, for property predictions of MOFs. The MOFormer takes a text string representation of MOF (MOFid) as input, thus circumventing the need of obtaining the 3D structure of hypothetical MOF and accelerating the screening process. Furthermore, we introduce a self-supervised learning framework that pretrains the MOFormer via maximizing the cross-correlation between its structure-agnostic representations and structure-based representations of crystal graph convolutional neural network (CGCNN) on >400k publicly available MOF data. Using self-supervised learning allows the MOFormer to intrinsically learn 3D structural information though it is not included in the input. Experiments show that pretraining improved the prediction accuracy of both models on various downstream prediction tasks. Furthermore, we revealed that MOFormer can be more data-efficient on quantum-chemical property prediction than structure-based CGCNN when training data is limited. Overall, MOFormer provides a novel perspective on efficient MOF design using deep learning.
Yuyang Wang, Ahmed A. Elhag, Navdeep Jaitly et al.
We present a novel way to predict molecular conformers through a simple formulation that sidesteps many of the heuristics of prior works and achieves state of the art results by using the advantages of scale. By training a diffusion generative model directly on 3D atomic positions without making assumptions about the explicit structure of molecules (e.g. modeling torsional angles) we are able to radically simplify structure learning, and make it trivial to scale up the model sizes. This model, called Molecular Conformer Fields (MCF), works by parameterizing conformer structures as functions that map elements from a molecular graph directly to their 3D location in space. This formulation allows us to boil down the essence of structure prediction to learning a distribution over functions. Experimental results show that scaling up the model capacity leads to large gains in generalization performance without enforcing inductive biases like rotational equivariance. MCF represents an advance in extending diffusion models to handle complex scientific problems in a conceptually simple, scalable and effective manner.
Graph neural networks (GNNs), which are capable of learning representations from graphical data, are naturally suitable for modeling molecular systems. This review introduces GNNs and their various applications for small organic molecules. GNNs rely on message-passing operations, a generic yet powerful framework, to update node features iteratively. Many researches design GNN architectures to effectively learn topological information of 2D molecule graphs as well as geometric information of 3D molecular systems. GNNs have been implemented in a wide variety of molecular applications, including molecular property prediction, molecular scoring and docking, molecular optimization and de novo generation, molecular dynamics simulation, etc. Besides, the review also summarizes the recent development of self-supervised learning for molecules with GNNs.
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 is 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.
Rishikesh Magar, Yuyang Wang, Amir Barati Farimani
Machine learning (ML) models have been widely successful in the prediction of material properties. However, large labeled datasets required for training accurate ML models are elusive and computationally expensive to generate. Recent advances in Self-Supervised Learning (SSL) frameworks capable of training ML models on unlabeled data have mitigated this problem and demonstrated superior performance in computer vision and natural language processing tasks. Drawing inspiration from the developments in SSL, we introduce Crystal Twins (CT): an SSL method for crystalline materials property prediction. Using a large unlabeled dataset, we pre-train a Graph Neural Network (GNN) by applying the redundancy reduction principle to the graph latent embeddings of augmented instances obtained from the same crystalline system. By sharing the pre-trained weights when fine-tuning the GNN for regression tasks, we significantly improve the performance for 7 challenging material property prediction benchmarks
Ionic Liquids (ILs) provide a promising solution for CO$_2$ capture and storage to mitigate global warming. However, identifying and designing the high-capacity IL from the giant chemical space requires expensive, and exhaustive simulations and experiments. Machine learning (ML) can accelerate the process of searching for desirable ionic molecules through accurate and efficient property predictions in a data-driven manner. But existing descriptors and ML models for the ionic molecule suffer from the inefficient adaptation of molecular graph structure. Besides, few works have investigated the explainability of ML models to help understand the learned features that can guide the design of efficient ionic molecules. In this work, we develop both fingerprint-based ML models and Graph Neural Networks (GNNs) to predict the CO$_2$ absorption in ILs. Fingerprint works on graph structure at the feature extraction stage, while GNNs directly handle molecule structure in both the feature extraction and model prediction stage. We show that our method outperforms previous ML models by reaching a high accuracy (MAE of 0.0137, $R^2$ of 0.9884). Furthermore, we take the advantage of GNNs feature representation and develop a substructure-based explanation method that provides insight into how each chemical fragments within IL molecules contribute to the CO$_2$ absorption prediction of ML models. We also show that our explanation result agrees with some ground truth from the theoretical reaction mechanism of CO$_2$ absorption in ILs, which can advise on the design of novel and efficient functional ILs in the future.
Modeling the ion concentration profile in nanochannel plays an important role in understanding the electrical double layer and electroosmotic flow. Due to the non-negligible surface interaction and the effect of discrete solvent molecules, molecular dynamics (MD) simulation is often used as an essential tool to study the behavior of ions under nanoconfinement. Despite the accuracy of MD simulation in modeling nanoconfinement systems, it is computationally expensive. In this work, we propose neural network to predict ion concentration profiles in nanochannels with different configurations, including channel widths, ion molarity, and ion types. By modeling the ion concentration profile as a probability distribution, our neural network can serve as a much faster surrogate model for MD simulation with high accuracy. We further demonstrate the superior prediction accuracy of neural network over XGBoost. Lastly, we demonstrated that neural network is flexible in predicting ion concentration profiles with different bin sizes. Overall, our deep learning model is a fast, flexible, and accurate surrogate model to predict ion concentration profiles in nanoconfinement.
Rishikesh Magar, Yuyang Wang, Cooper Lorsung et al.
Machine learning (ML) has demonstrated the promise for accurate and efficient property prediction of molecules and crystalline materials. To develop highly accurate ML models for chemical structure property prediction, datasets with sufficient samples are required. However, obtaining clean and sufficient data of chemical properties can be expensive and time-consuming, which greatly limits the performance of ML models. Inspired by the success of data augmentations in computer vision and natural language processing, we developed AugLiChem: the data augmentation library for chemical structures. Augmentation methods for both crystalline systems and molecules are introduced, which can be utilized for fingerprint-based ML models and Graph Neural Networks(GNNs). We show that using our augmentation strategies significantly improves the performance of ML models, especially when using GNNs. In addition, the augmentations that we developed can be used as a direct plug-in module during training and have demonstrated the effectiveness when implemented with different GNN models through the AugliChem library. The Python-based package for our implementation of Auglichem: Data augmentation library for chemical structures, is publicly available at: https://github.com/BaratiLab/AugLiChem.
Tensor product function (TPF) approximations have been widely adopted in solving high-dimensional problems, such as partial differential equations and eigenvalue problems, achieving desirable accuracy with computational overhead that scales linearly with problem dimensions. However, recent studies have underscored the extraordinarily high computational cost of TPFs on quantum many-body problems, even for systems with as few as three particles. A key distinction in these problems is the antisymmetry requirement on the unknown functions. In the present work, we rigorously establish that the minimum number of involved terms for a class of TPFs to be exactly antisymmetric increases exponentially fast with the problem dimension. This class encompasses both traditionally discretized TPFs and the recent ones parameterized by neural networks. Our proof exploits the link between the antisymmetric TPFs in this class and the corresponding antisymmetric tensors and focuses on the Canonical Polyadic rank of the latter. As a result, our findings reveal that low-rank TPFs are fundamentally unsuitable for high-dimensional problems where antisymmetry is essential.
Protein folding models have achieved groundbreaking results typically via a combination of integrating domain knowledge into the architectural blocks and training pipelines. Nonetheless, given the success of generative models across different but related problems, it is natural to question whether these architectural designs are a necessary condition to build performant models. In this paper, we introduce SimpleFold, the first flow-matching based protein folding model that solely uses general purpose transformer blocks. Protein folding models typically employ computationally expensive modules involving triangular updates, explicit pair representations or multiple training objectives curated for this specific domain. Instead, SimpleFold employs standard transformer blocks with adaptive layers and is trained via a generative flow-matching objective with an additional structural term. We scale SimpleFold to 3B parameters and train it on approximately 9M distilled protein structures together with experimental PDB data. On standard folding benchmarks, SimpleFold-3B achieves competitive performance compared to state-of-the-art baselines, in addition SimpleFold demonstrates strong performance in ensemble prediction which is typically difficult for models trained via deterministic reconstruction objectives. Due to its general-purpose architecture, SimpleFold shows efficiency in deployment and inference on consumer-level hardware. SimpleFold challenges the reliance on complex domain-specific architectures designs in protein folding, opening up an alternative design space for future progress.
Deep learning has been a prevalence in computational chemistry and widely implemented in molecule property predictions. Recently, self-supervised learning (SSL), especially contrastive learning (CL), gathers growing attention for the potential to learn molecular representations that generalize to the gigantic chemical space. Unlike supervised learning, SSL can directly leverage large unlabeled data, which greatly reduces the effort to acquire molecular property labels through costly and time-consuming simulations or experiments. However, most molecular SSL methods borrow the insights from the machine learning community but neglect the unique cheminformatics (e.g., molecular fingerprints) and multi-level graphical structures (e.g., functional groups) of molecules. In this work, we propose iMolCLR: improvement of Molecular Contrastive Learning of Representations with graph neural networks (GNNs) in two aspects, (1) mitigating faulty negative contrastive instances via considering cheminformatics similarities between molecule pairs; (2) fragment-level contrasting between intra- and inter-molecule substructures decomposed from molecules. Experiments have shown that the proposed strategies significantly improve the performance of GNN models on various challenging molecular property predictions. In comparison to the previous CL framework, iMolCLR demonstrates an averaged 1.3% improvement of ROC-AUC on 7 classification benchmarks and an averaged 4.8% decrease of the error on 5 regression benchmarks. On most benchmarks, the generic GNN pre-trained by iMolCLR rivals or even surpasses supervised learning models with sophisticated architecture designs and engineered features. Further investigations demonstrate that representations learned through iMolCLR intrinsically embed scaffolds and functional groups that can reason molecule similarities.
Molecular Machine Learning (ML) bears promise for efficient molecule property prediction and drug discovery. However, labeled molecule data can be expensive and time-consuming to acquire. Due to the limited labeled data, it is a great challenge for supervised-learning ML models to generalize to the giant chemical space. In this work, we present MolCLR: Molecular Contrastive Learning of Representations via Graph Neural Networks (GNNs), a self-supervised learning framework that leverages large unlabeled data (~10M unique molecules). In MolCLR pre-training, we build molecule graphs and develop GNN encoders to learn differentiable representations. Three molecule graph augmentations are proposed: atom masking, bond deletion, and subgraph removal. A contrastive estimator maximizes the agreement of augmentations from the same molecule while minimizing the agreement of different molecules. Experiments show that our contrastive learning framework significantly improves the performance of GNNs on various molecular property benchmarks including both classification and regression tasks. Benefiting from pre-training on the large unlabeled database, MolCLR even achieves state-of-the-art on several challenging benchmarks after fine-tuning. Additionally, further investigations demonstrate that MolCLR learns to embed molecules into representations that can distinguish chemically reasonable molecular similarities.
Two-dimensional nanomaterials, such as graphene, have been extensively studied because of their outstanding physical properties. Structure and geometry optimization of nanopores on such materials is beneficial for their performances in real-world engineering applications, like water desalination. However, the optimization process often involves very large number of experiments or simulations which are expensive and time-consuming. In this work, we propose a graphene nanopore optimization framework via the combination of deep reinforcement learning (DRL) and convolutional neural network (CNN) for efficient water desalination. The DRL agent controls the growth of nanopore by determining the atom to be removed at each timestep, while the CNN predicts the performance of nanoporus graphene for water desalination: the water flux and ion rejection at a certain external pressure. With the synchronous feedback from CNN-accelerated desalination performance prediction, our DRL agent can optimize the nanoporous graphene efficiently in an online manner. Molecular dynamics (MD) simulations on promising DRL-designed graphene nanopores show that they have higher water flux while maintaining rival ion rejection rate compared to the normal circular nanopores. Semi-oval shape with rough edges geometry of DRL-designed pores is found to be the key factor for their high water desalination performance. Ultimately, this study shows that DRL can be a powerful tool for material design.
The current design of aerodynamic shapes, like airfoils, involves computationally intensive simulations to explore the possible design space. Usually, such design relies on the prior definition of design parameters and places restrictions on synthesizing novel shapes. In this work, we propose a data-driven shape encoding and generating method, which automatically learns representations from existing airfoils and uses the learned representations to generate new airfoils. The representations are then used in the optimization of synthesized airfoil shapes based on their aerodynamic performance. Our model is built upon VAEGAN, a neural network that combines Variational Autoencoder with Generative Adversarial Network and is trained by the gradient-based technique. Our model can (1) encode the existing airfoil into a latent vector and reconstruct the airfoil from that, (2) generate novel airfoils by randomly sampling the latent vectors and mapping the vectors to the airfoil coordinate domain, and (3) synthesize airfoils with desired aerodynamic properties by optimizing learned features via a genetic algorithm. Our experiments show that the learned features encode shape information thoroughly and comprehensively without predefined design parameters. By interpolating/extrapolating feature vectors or sampling from Gaussian noises, the model can automatically synthesize novel airfoil shapes, some of which possess competitive or even better aerodynamic properties comparing to airfoils used for model training purposes. By optimizing shapes on the learned latent domain via a genetic algorithm, synthesized airfoils can evolve to target aerodynamic properties. This demonstrates an efficient learning-based airfoil design framework, which encodes and optimizes the airfoil on the latent domain and synthesizes promising airfoil candidates for required aerodynamic performance.
Ali Caner Turkmen, Tim Januschowski, Yuyang Wang et al.
Intermittency is a common and challenging problem in demand forecasting. We introduce a new, unified framework for building intermittent demand forecasting models, which incorporates and allows to generalize existing methods in several directions. Our framework is based on extensions of well-established model-based methods to discrete-time renewal processes, which can parsimoniously account for patterns such as aging, clustering and quasi-periodicity in demand arrivals. The connection to discrete-time renewal processes allows not only for a principled extension of Croston-type models, but also for an natural inclusion of neural network based models---by replacing exponential smoothing with a recurrent neural network. We also demonstrate that modeling continuous-time demand arrivals, i.e., with a temporal point process, is possible via a trivial extension of our framework. This leads to more flexible modeling in scenarios where data of individual purchase orders are directly available with granular timestamps. Complementing this theoretical advancement, we demonstrate the efficacy of our framework for forecasting practice via an extensive empirical study on standard intermittent demand data sets, in which we report predictive accuracy in a variety of scenarios that compares favorably to the state of the art.