DeepModeling

On August 19, 2024, Linlin Hou, Hongxin Xiang, and Xiangxiang Zeng from Hunan University, in collaboration with Li Zeng from the Shanghai Institute of Materia Medica, published a research article titled "Attribute-guided Prototype Network for Few-shot Molecular Property Prediction" in Briefings in Bioinformatics. This study introduced an Attribute-guided Prototype Network (APN), which innovatively combines high-level molecular fingerprints with deep learning algorithms, significantly improving the accuracy of molecular property prediction in limited-sample scenarios. This breakthrough opens a new direction for few-shot learning in drug development.

The third highlight of DeePMD-kit v3 is its model plugin mechanism. This article introduces the feature from three perspectives: background and principles, development tutorial, and usage tutorial.

The second highlight of DeePMD-kit v3 is the DPA model and training strategies such as multi-task training and fine-tuning. This article introduces these features from two aspects: background and principles and usage tutorials.

One of the highlights of DeePMD-kit v3 is its multi-backend framework. This article introduces it from three aspects: background and principles, usage tutorial, and development tutorial.

1. Multi-backend framework: Powered by TensorFlow, PyTorch, and JAX

Recently, doctoral student Liang Sun and researcher Mohan Chen from the Center for Applied Physics and Technology at Peking University implemented a machine learning-based kinetic energy density functional (multi-channel ML-based Physically-constrained Non-local KEDF, or CPN KEDF) in the domestically developed open-source density functional theory software ABACUS (Atomic-based Ab initio Computation at UStc). This functional employs a multi-channel architecture, extending the previously developed MPN KEDF (ML-based Physical-constrained Non-local KEDF) [1], which was designed for simple metallic systems, to semiconductors. The method achieved promising results in tests on ground-state energy and ground-state charge density, laying the groundwork for the development of machine learning-based kinetic energy density functionals with broader applicability. The article, titled “Multi-channel machine learning-based nonlocal kinetic energy density functional for semiconductors,” has been published in the journal Electronic Structure (DOI: 10.1088/2516-1075/ad8b8c) [2].

DFTIO, initiated by the DeePTB team at the Beijing Institute of Science and Intelligence, is an efficient electronic structure data processing tool designed to convert electronic structure output information from various first-principles/quantum computation software into data formats that are easy for machine learning models to read.

In recent years, machine learning-based first-principles electronic structure models have developed rapidly, including but not limited to machine learning tight-binding models, Hamiltonian models, electronic density models, and functional models. With the advancement of these models, we have increasingly realized that the post-processing of output data from different electronic structure calculation software has become a common challenge for both developers and users.

Recently, Professor Han Ye's research team from the School of Materials Science and Engineering at Shandong University of Science and Technology utilized the Deep Potential (DP) model for molecular dynamics simulations. They conducted an in-depth analysis of the phonon dispersion relations, energy-volume curves, solid-liquid interfacial structures, and mechanical properties of Cu-Sn alloys. The results were validated against density functional theory (DFT) calculations, demonstrating excellent consistency.

The radial distribution function (RDF) results computed using the DP model revealed that the disordered atomic arrangements of Cu₁₀Sn₃ and CuSn structures at 1100 K are attributed to the broadening and shortening of RDF peaks at high temperatures, indicating reduced atomic coherence.

The findings were published in Computational Materials Science under the title "Research on Cu-Sn Machine Learning Interatomic Potential with Active Learning Strategy". Master's students Liu Jinyan and Zhang Guanghao were the co-first authors, with Professor Han Ye serving as the corresponding author.

On the journey toward developing a Large Atomic Model (LAM), the core Deep Potential development team has launched the OpenLAM initiative for the community. OpenLAM’s slogan is "Conquer the Periodic Table!" The project aims to create an open-source ecosystem centered on microscale large models, providing new infrastructure for microscopic scientific research and driving transformative advancements in microscale industrial design across fields such as materials, energy, and biopharmaceuticals.

Recently, Dr. Mei Jia from Shangqiu Normal University, Dr. Yongbin Zhuang from École Polytechnique Fédérale de Lausanne (EPFL), and Prof. Jun Cheng from Xiamen University conducted an in-depth study on the proton transfer mechanism at the SnO₂(110)/H₂O interface by combining ab initio molecular dynamics (AIMD) with the Deep Potential (DP) method. The team used AIMD to obtain the electronic structure of the interface system and applied the Deep Potential Molecular Dynamics (DPMD) model to accelerate molecular dynamics simulations, enabling larger-scale and longer-timescale simulations. This combination of methods allowed the researchers to analyze the free energy distributions of different proton transfer pathways in detail and to reveal the influence of the solvation environment on the proton transfer process.

The related findings have been published in the high-impact journal Precision Chemistry, under the title “Water-Mediated Proton Hopping Mechanisms at the SnO₂(110)/H₂O Interface from Ab Initio Deep Potential Molecular Dynamics.” Dr. Mei Jia and Dr. Yongbin Zhuang are the co-first authors, and Prof. Jun Cheng is the corresponding author.