Search

The evolution of AI and high-throughput technologies has boosted a rapid increase in the number of new materials, challenging our computational ability to comprehensively analyze their properties. Relaxed crystal structures often serve as the foundational basis for further property calculations. However, determining equilibrium structures traditionally involves computationally expensive iterative calculations. Here, we develop DeepRelax, an efficient deep generative model designed for rapid structural relaxation without any iterative process. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed counterparts. The ability to perform structural relaxation in just a few hundred milliseconds per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. To demonstrate the universality of DeepRelax, we benchmark it against three different databases of X-Mn-O oxides, Materials Project, and Computational 2D Materials Database with various types of materials. In these tests, DeepRelax exhibits both high accuracy and efficiency in structural relaxation, as further validated by DFT calculations. Finally, we integrate DeepRelax with an implementation of uncertainty quantification, enhancing its reliability and trustworthiness in material discovery. This work provides an efficient and trustworthy method to significantly accelerate large-scale computations, offering substantial advancements in the field of computational materials science.

Large Language Models (LLMs) have achieved remarkable performance in multiple Natural Language Processing (NLP) tasks. Under the premise that protein sequences constitute the protein language, Protein Language Models(PLMs) have advanced the field of protein engineering. However, as of now, unlike LLMs in NLP, PLMs cannot handle the protein understanding task and the protein generation task simultaneously in the Protein Language Processing (PLP) field. This prompts us to delineate the inherent limitations in current PLMs: (i) the lack of natural language capabilities, (ii) insufficient instruction understanding, and (iii) high training resource demands. To address these challenges, we introduce a training framework to transform any general LLM into a PLM capable of handling multiple PLP tasks. To improve training efficiency, we propose Protein Vocabulary Pruning (PVP) for general LLMs. We construct a multi-task instruction dataset containing 13 million samples with superfamily information, facilitating better modeling of protein sequence-function landscapes. Through these methods, we develop the ProLLaMA model, the first known PLM to handle multiple PLP tasks simultaneously. Experiments show that ProLLaMA achieves state-of-the-art results in the unconditional protein sequence generation task. In the controllable protein sequence generation task, ProLLaMA can design novel proteins with desired functionalities. As for the protein understanding task, ProLLaMA achieves a 62\% exact match rate in superfamily prediction. Codes, model weights, and datasets are available at \url{https://github.com/PKU-YuanGroup/ProLLaMA} and \url{https://huggingface.co/GreatCaptainNemo}.

In modern computational materials science, deep learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional simulations. However, existing models typically sacrifice either accuracy or efficiency. Moreover, lightweight models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs. A century ago, Felix Bloch demonstrated how leveraging the equivariance of the translation operation on a crystal lattice (with geometric symmetry) could significantly reduce the computational cost of determining wavefunctions and accurately calculate material properties. Here, we introduce a lightweight equivariant interaction graph neural network (LEIGNN) that can enable accurate and efficient interatomic potential and force predictions in crystals. Rather than relying on higher-order representations, LEIGNN employs a scalar-vector dual representation to encode equivariant features. By extracting both local and global structures from vector representations and learning geometric symmetry information, our model remains lightweight while ensuring prediction accuracy and robustness through the equivariance. Our results show that LEIGNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets, which include catalysts, molecules, and organic isomers. Finally, to further validate the predicted interatomic potentials from our model, we conduct classical molecular dynamics (MD) and ab initio MD simulation across various systems, including solid, liquid, and gas. It is found that LEIGNN can achieve the accuracy of ab initio MD and retain the computational efficiency of classical MD across all examined systems, demonstrating its accuracy, efficiency, and universality.

Alzheimer's disease is a progressive neurological disorder characterized by cognitive impairment and memory loss. With the increasing aging population, the incidence of AD is continuously rising, making early diagnosis and intervention an urgent need. In recent years, a considerable number of teams have applied computer-aided diagnostic techniques to early classification research of AD. Most studies have utilized imaging modalities such as magnetic resonance imaging (MRI), positron emission tomography (PET), and electroencephalogram (EEG). However, there have also been studies that attempted to use other modalities as input features for the models, such as sound, posture, biomarkers, cognitive assessment scores, and their fusion. Experimental results have shown that the combination of multiple modalities often leads to better performance compared to a single modality. Therefore, this paper will focus on different modalities and their fusion, thoroughly elucidate the mechanisms of various modalities, explore which methods should be combined to better harness their utility, analyze and summarize the literature in the field of early classification of AD in recent years, in order to explore more possibilities of modality combinations.