arXiv subjects

Renxiao Wang

Publications and source records attributed to Renxiao Wang.

4 recordsLinked to original sources

arXiv2026

ASTEROID: A Spatiotemporal Information Transformer for Forecasting Multi-Step Time Series of Molecular Dynamics

Molecular dynamics (MD) simulation is computationally demanding, particularly for large-scale systems requiring long-term analysis. Accurate forecast of the outcomes of a MD simulation is not only an attractive scientific challenge but also has substantial practical value. In this work, we developed a data-driven framework, termed ASTEROID (Advanced Spatiotemporal TransformER fOr Inferring Dynamics), that can directly predict multi-step atomic coordinates, avoiding conventional iterative integration. For this purpose, our ASTEROID reformulates MD trajectories as high-dimensional spatiotemporal sequences and integrates the Spatiotemporal Information (STI) Transformation equation into a Transformer architecture. The core innovation of ASTEROID lies in its ability to model multiscale spatiotemporal dependencies. In particular, for spatial dependencies, a local-global self-attention mechanism captures both short- and long-range interactions. For temporal dependencies, an encoder-decoder structure integrates global context with autoregressive forecasting. ASTEROID was evaluated on several quantum-mechanics derived molecular datasets. Our results indicate that ASTEROID achieved not only a higher level of accuracy in multi-step prediction than existing methods on various benchmarks, but also significantly reduced computational cost of conventional MD simulation. Moreover, the model supports iterative multi-step forecasting over an extended time scale. This work establishes a robust and generalizable data-driven paradigm for accelerating MD simulations.

cs.LG↗

arXiv2026

PLANET v2.0: A comprehensive Protein-Ligand Affinity Prediction Model Based on Mixture Density Network

Drug discovery represents a time-consuming and financially intensive process, and virtual screening can accelerate it. Scoring functions, as one of the tools guiding virtual screening, have their precision closely tied to screening efficiency. In our previous study, we developed a graph neural network model called PLANET (Protein-Ligand Affinity prediction NETwork), but it suffers from the defect in representing protein-ligand contact maps. Incorrect binding modes inevitably lead to poor affinity predictions, so accurate prediction of the protein-ligand contact map is desired to improve PLANET. In this study, we have proposed PLANET v2.0 as an upgraded version. The model is trained via multi-objective training strategy and incorporates the Mixture Density Network to predict binding modes. Except for the probability density distributions of non-covalent interactions, we innovatively employ another Gaussian mixture model to describe the relationship between distance and energy of each interaction pair and predict protein-ligand affinity like calculating the mathematical expectation. As on the CASF-2016 benchmark, PLANET v2.0 demonstrates excellent scoring power, ranking power, and docking power. The screening power of PLANET v2.0 gets notably improved compared to PLANET and Glide SP and it demonstrates robust validation on a commercial ultra-large-scale dataset. Given its efficiency and accuracy, PLANET v2.0 can hopefully become one of the practical tools for virtual screening workflows. PLANET v2.0 is freely available at https://www.pdbbind-plus.org.cn/planetv2.

cs.LG↗

arXiv2025

COMET:Combined Matrix for Elucidating Targets

Identifying the interaction targets of bioactive compounds is a foundational element for deciphering their pharmacological effects. Target prediction algorithms equip researchers with an effective tool to rapidly scope and explore potential targets. Here, we introduce the COMET, a multi-technological modular target prediction tool that provides comprehensive predictive insights, including similar active compounds, three-dimensional predicted binding modes, and probability scores, all within an average processing time of less than 10 minutes per task. With meticulously curated data, the COMET database encompasses 990,944 drug-target interaction pairs and 45,035 binding pockets, enabling predictions for 2,685 targets, which span confirmed and exploratory therapeutic targets for human diseases. In comparative testing using datasets from ChEMBL and BindingDB, COMET outperformed five other well-known algorithms, offering nearly an 80% probability of accurately identifying at least one true target within the top 15 predictions for a given compound. COMET also features a user-friendly web server, accessible freely at https://www.pdbbind-plus.org.cn/comet.

cs.LG↗

arXiv2017

TopP-S: Persistent homology based multi-task deep neural networks for simultaneous predictions of partition coefficient and aqueous solubility

Aqueous solubility and partition coefficient are important physical properties of small molecules. Accurate theoretical prediction of aqueous solubility and partition coefficient plays an important role in drug design and discovery. The prediction accuracy depends crucially on molecular descriptors which are typically derived from theoretical understanding of the chemistry and physics of small molecules. The present work introduces an algebraic topology based method, called element specific persistent homology (ESPH), as a new representation of small molecules that is entirely different from conventional chemical and/or physical representations. ESPH describes molecular properties in terms of multiscale and multicomponent topological invariants. Such topological representation is systematical, comprehensive, and scalable with respect to molecular size and composition variations. However, it cannot be literally translated into a physical interpretation. Fortunately, it is readily suitable for machine learning methods, rendering topological learning algorithms. Due to the inherent correlation between solubility and partition coefficient, a uniform ESPH representation is developed for both properties, which facilitates multi-task deep neural networks for their simultaneous predictions. This strategy leads to more accurate prediction of relatively small data sets. A total of six data sets is considered in the present work to validate the proposed topological and multi-task deep learning approaches. It is demonstrate that the proposed approaches achieve some of the most accurate predictions of aqueous solubility and partition coefficient. Our software is available online at {\url{http://weilab.math.msu.edu/TopP-S/}}

q-bio.QM↗