arXiv subjects

Luonan Chen

Publications and source records attributed to Luonan Chen.

At least 19 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↗

arXiv2025

A Time-Series Foundation Model by Universal Delay Embedding

This study introduces Universal Delay Embedding (UDE), a pretrained foundation model designed to revolutionize time-series forecasting through principled integration of delay embedding representation and Koopman operator prediction. Leveraging Takens' embedding theorem, UDE as a dynamical representation of observed data constructs two-dimensional subspace patches from Hankel matrices, theoretically preserving dynamical and topological properties of underlying dynamical systems. Such patches are viewed as images, which can be efficiently processed by exploiting advanced deep learning technologies. Computationally, these patches further serve as tokens for learning a self-attention encoder, thus enabling accurate prediction of nonlinear time-series by a finite-dimensional Koopman operator in a linear manner in a latent space. Extensive evaluations across various benchmarks and real-world climate datasets demonstrate over 20% average reduction in mean squared error versus state-of-the-art foundation models, alongside superior generalization in fine-tuning scenarios. In particular, the learned dynamical representations and Koopman operator prediction forms from the patches exhibit exceptional interpretability, with consistent identification of topologically informative subspaces and robust encoding of domain-invariant dynamics, establishing UDE as a scalable, interpretable framework for universal time-series modeling and forecasting with broad scientific and industrial applicability.

cs.LG↗

arXiv2025

Delayformer: spatiotemporal transformation for predicting high-dimensional dynamics

Predicting time-series is of great importance in various scientific and engineering fields. However, in the context of limited and noisy data, accurately predicting dynamics of all variables in a high-dimensional system is a challenging task due to their nonlinearity and also complex interactions. Current methods including deep learning approaches often perform poorly for real-world systems under such circumstances. This study introduces the Delayformer framework for simultaneously predicting dynamics of all variables, by developing a novel multivariate spatiotemporal information (mvSTI) transformation that makes each observed variable into a delay-embedded state (vector) and further cross-learns those states from different variables. From dynamical systems viewpoint, Delayformer predicts system states rather than individual variables, thus theoretically and computationally overcoming such nonlinearity and cross-interaction problems. Specifically, it first utilizes a single shared Visual Transformer (ViT) encoder to cross-represent dynamical states from observed variables in a delay embedded form and then employs distinct linear decoders for predicting next states, i.e. equivalently predicting all original variables parallelly. By leveraging the theoretical foundations of delay embedding theory and the representational capabilities of Transformers, Delayformer outperforms current state-of-the-art methods in forecasting tasks on both synthetic and real-world datasets. Furthermore, the potential of Delayformer as a foundational time-series model is demonstrated through cross-domain forecasting tasks, highlighting its broad applicability across various scenarios.

cs.LG↗

arXiv2025

ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model

Recent advances in reasoning with large language models (LLMs)has shown remarkable reasoning capabilities in domains such as mathematics and coding, yet their application to clinical diagnosis remains underexplored. Here, we introduce ClinicalGPT-R1, a reasoning enhanced generalist large language model for disease diagnosis. Trained on a dataset of 20,000 real-world clinical records, ClinicalGPT-R1 leverages diverse training strategies to enhance diagnostic reasoning. To benchmark performance, we curated MedBench-Hard, a challenging dataset spanning seven major medical specialties and representative diseases. Experimental results demonstrate that ClinicalGPT-R1 outperforms GPT-4o in Chinese diagnostic tasks and achieves comparable performance to GPT-4 in English settings. This comparative study effectively validates the superior performance of ClinicalGPT-R1 in disease diagnosis tasks. Resources are available at https://github.com/medfound/medfound.

cs.CL↗

arXiv2025

Strategic priorities for transformative progress in advancing biology with proteomics and artificial intelligence

Artificial intelligence (AI) is transforming scientific research, including proteomics. Advances in mass spectrometry (MS)-based proteomics data quality, diversity, and scale, combined with groundbreaking AI techniques, are unlocking new challenges and opportunities in biological discovery. Here, we highlight key areas where AI is driving innovation, from data analysis to new biological insights. These include developing an AI-friendly ecosystem for proteomics data generation, sharing, and analysis; improving peptide and protein identification and quantification; characterizing protein-protein interactions and protein complexes; advancing spatial and perturbation proteomics; integrating multi-omics data; and ultimately enabling AI-empowered virtual cells.

q-bio.OT↗

arXiv2025

Ultralow-dimensionality reduction for identifying critical transitions by spatial-temporal PCA

Discovering dominant patterns and exploring dynamic behaviors especially critical state transitions and tipping points in high-dimensional time-series data are challenging tasks in study of real-world complex systems, which demand interpretable data representations to facilitate comprehension of both spatial and temporal information within the original data space. Here, we proposed a general and analytical ultralow-dimensionality reduction method for dynamical systems named spatial-temporal principal component analysis (stPCA) to fully represent the dynamics of a high-dimensional time-series by only a single latent variable without distortion, which transforms high-dimensional spatial information into one-dimensional temporal information based on nonlinear delay-embedding theory. The dynamics of this single variable is analytically solved and theoretically preserves the temporal property of original high-dimensional time-series, thereby accurately and reliably identifying the tipping point before an upcoming critical transition. Its applications to real-world datasets such as individual-specific heterogeneous ICU records demonstrated the effectiveness of stPCA, which quantitatively and robustly provides the early-warning signals of the critical/tipping state on each patient.

stat.ML↗

arXiv2024

Brain-inspired Chaotic Graph Backpropagation for Large-scale Combinatorial Optimization

Graph neural networks (GNNs) with unsupervised learning can solve large-scale combinatorial optimization problems (COPs) with efficient time complexity, making them versatile for various applications. However, since this method maps the combinatorial optimization problem to the training process of a graph neural network, and the current mainstream backpropagation-based training algorithms are prone to fall into local minima, the optimization performance is still inferior to the current state-of-the-art (SOTA) COP methods. To address this issue, inspired by possibly chaotic dynamics of real brain learning, we introduce a chaotic training algorithm, i.e. chaotic graph backpropagation (CGBP), which introduces a local loss function in GNN that makes the training process not only chaotic but also highly efficient. Different from existing methods, we show that the global ergodicity and pseudo-randomness of such chaotic dynamics enable CGBP to learn each optimal GNN effectively and globally, thus solving the COP efficiently. We have applied CGBP to solve various COPs, such as the maximum independent set, maximum cut, and graph coloring. Results on several large-scale benchmark datasets showcase that CGBP can outperform not only existing GNN algorithms but also SOTA methods. In addition to solving large-scale COPs, CGBP as a universal learning algorithm for GNNs, i.e. as a plug-in unit, can be easily integrated into any existing method for improving the performance.

cs.LG↗

arXiv2024

Dynamical causality under invisible confounders

Causality inference is prone to spurious causal interactions, due to the substantial confounders in a complex system. While many existing methods based on the statistical methods or dynamical methods attempt to address misidentification challenges, there remains a notable lack of effective methods to infer causality, in particular in the presence of invisible/unobservable confounders. As a result, accurately inferring causation with invisible confounders remains a largely unexplored and outstanding issue in data science and AI fields. In this work, we propose a method to overcome such challenges to infer dynamical causality under invisible confounders (CIC method) and further reconstruct the invisible confounders from time-series data by developing an orthogonal decomposition theorem in a delay embedding space. The core of our CIC method lies in its ability to decompose the observed variables not in their original space but in their delay embedding space into the common and private subspaces respectively, thereby quantifying causality between those variables both theoretically and computationally. This theoretical foundation ensures the causal detection for any high-dimensional system even with only two observed variables under many invisible confounders, which is actually a long-standing problem in the field. In addition to the invisible confounder problem, such a decomposition actually makes the intertwined variables separable in the embedding space, thus also solving the non-separability problem of causal inference. Extensive validation of the CIC method is carried out using various real datasets, and the experimental results demonstrates its effectiveness to reconstruct real biological networks even with unobserved confounders.

cs.LG↗

arXiv2024

CIDER: Counterfactual-Invariant Diffusion-based GNN Explainer for Causal Subgraph Inference

Inferring causal links or subgraphs corresponding to a specific phenotype or label based solely on measured data is an important yet challenging task, which is also different from inferring causal nodes. While Graph Neural Network (GNN) Explainers have shown potential in subgraph identification, existing methods with GNN often offer associative rather than causal insights. This lack of transparency and explainability hinders our understanding of their results and also underlying mechanisms. To address this issue, we propose a novel method of causal link/subgraph inference, called CIDER: Counterfactual-Invariant Diffusion-based GNN ExplaineR, by implementing both counterfactual and diffusion implementations. In other words, it is a model-agnostic and task-agnostic framework for generating causal explanations based on a counterfactual-invariant and diffusion process, which provides not only causal subgraphs due to counterfactual implementation but reliable causal links due to the diffusion process. Specifically, CIDER is first formulated as an inference task that generatively provides the two distributions of one causal subgraph and another spurious subgraph. Then, to enhance the reliability, we further model the CIDER framework as a diffusion process. Thus, using the causal subgraph distribution, we can explicitly quantify the contribution of each subgraph to a phenotype/label in a counterfactual manner, representing each subgraph's causal strength. From a causality perspective, CIDER is an interventional causal method, different from traditional association studies or observational causal approaches, and can also reduce the effects of unobserved confounders. We evaluate CIDER on both synthetic and real-world datasets, which all demonstrate the superiority of CIDER over state-of-the-art methods.

cs.CE↗

arXiv2024

Deciphering interventional dynamical causality from non-intervention complex systems

Detecting and quantifying causality is a focal topic in the fields of science, engineering, and interdisciplinary studies. However, causal studies on non-intervention systems attract much attention but remain extremely challenging. Delay-embedding technique provides a promising approach. In this study, we propose a framework named Interventional Dynamical Causality (IntDC) in contrast to the traditional Constructive Dynamical Causality (ConDC). ConDC, including Granger causality, transfer entropy and convergence of cross-mapping, measures the causality by constructing a dynamical model without considering interventions. A computational criterion, Interventional Embedding Entropy (IEE), is proposed to measure causal strengths in an interventional manner. IEE is an intervened causal information flow but in the delay-embedding space. Further, the IEE theoretically and numerically enables the deciphering of IntDC solely from observational (non-interventional) time-series data, without requiring any knowledge of dynamical models or real interventions in the considered system. In particular, IEE can be applied to rank causal effects according to their importance and construct causal networks from data. We conducted numerical experiments to demonstrate that IEE can find causal edges accurately, eliminate effects of confounding, and quantify causal strength robustly over traditional indices. We also applied IEE to real-world tasks. IEE performed as an accurate and robust tool for causal analyses solely from the observational data. The IntDC framework and IEE algorithm provide an efficient approach to the study of causality from time series in diverse non-intervention complex systems.

cs.LG↗

arXiv2023

Velde: constructing cell potential landscapes by RNA velocity vector field decomposition

The Waddington landscape serves as a metaphor illustrating the developmental process of cells, likening it to a small ball rolling down various trajectories into valleys. Constructing an epigenetic landscape of this nature aids in visualizing and gaining insights into cell differentiation. Development encompasses intricate processes involving both cell differentiation and cell cycles. However, current landscape methods solely focus on constructing a potential landscape for cell differentiation, neglecting the accompanying cell cycle. This paper introduces a novel method that simultaneously constructs two types of potential landscapes using single-cell RNA sequencing data. Specifically, it presents the natural Helmholtz-Hodge decomposition (nHHD) of a continuous vector field within a bounded domain in n-dimensional Euclidean space. This decomposition uniquely breaks down the vector field into a gradient field, a rotation field, and a harmonic field. Utilizing this approach, the RNA velocity vector field is separated into a curl-free component representing cell differentiation and a curl component representing the cell cycle. By calculating the corresponding potential functions, potential landscapes for both cell differentiation and the cell cycle are obtained. Finally, the efficacy of this method is demonstrated through its application to synthetic and real datasets.

q-bio.QM↗

arXiv2023

Spatiotemporal information conversion machine for time-series prediction

Making predictions in a robust way is a difficult task only based on the observed data of a nonlinear system. In this work, a neural network computing framework, the spatiotemporal information conversion machine (STICM), was developed to efficiently and accurately render a multistep-ahead prediction of a time series by employing a spatial-temporal information (STI) transformation. STICM combines the advantages of both the STI equation and the temporal convolutional network, which maps the high-dimensional/spatial data to the future temporal values of a target variable, thus naturally providing the prediction of the target variable. From the observed variables, the STICM also infers the causal factors of the target variable in the sense of Granger causality, which are in turn selected as effective spatial information to improve the prediction robustness of time-series. The STICM was successfully applied to both benchmark systems and real-world datasets, all of which show superior and robust performance in multistep-ahead prediction, even when the data were perturbed by noise. From both theoretical and computational viewpoints, the STICM has great potential in practical applications in artificial intelligence (AI) or as a model-free method based only on the observed data, and also opens a new way to explore the observed high-dimensional data in a dynamical manner for machine learning.

cs.LG↗

arXiv2022

Time Series Prediction by Multi-task GPR with Spatiotemporal Information Transformation

Making an accurate prediction of an unknown system only from a short-term time series is difficult due to the lack of sufficient information, especially in a multi-step-ahead manner. However, a high-dimensional short-term time series contains rich dynamical information, and also becomes increasingly available in many fields. In this work, by exploiting spatiotemporal information (STI) transformation scheme that transforms such high-dimensional/spatial information to temporal information, we developed a new method called MT-GPRMachine to achieve accurate prediction from a short-term time series. Specifically, we first construct a specific multi-task GPR which is multiple linked STI mappings to transform high dimensional/spatial information into temporal/dynamical information of any given target variable, and then makes multi step-ahead prediction of the target variable by solving those STI mappings. The multi-step-ahead prediction results on various synthetic and real-world datasets clearly validated that MT-GPRMachine outperformed other existing approaches.

cs.LG↗

arXiv2020

Ontology-based systematic classification and analysis of coronaviruses, hosts, and host-coronavirus interactions towards deep understanding of COVID-19

Given the existing COVID-19 pandemic worldwide, it is critical to systematically study the interactions between hosts and coronaviruses including SARS-Cov, MERS-Cov, and SARS-CoV-2 (cause of COVID-19). We first created four host-pathogen interaction (HPI)-Outcome postulates, and generated a HPI-Outcome model as the basis for understanding host-coronavirus interactions (HCI) and their relations with the disease outcomes. We hypothesized that ontology can be used as an integrative platform to classify and analyze HCI and disease outcomes. Accordingly, we annotated and categorized different coronaviruses, hosts, and phenotypes using ontologies and identified their relations. Various COVID-19 phenotypes are hypothesized to be caused by the backend HCI mechanisms. To further identify the causal HCI-outcome relations, we collected 35 experimentally-verified HCI protein-protein interactions (PPIs), and applied literature mining to identify additional host PPIs in response to coronavirus infections. The results were formulated in a logical ontology representation for integrative HCI-outcome understanding. Using known PPIs as baits, we also developed and applied a domain-inferred prediction method to predict new PPIs and identified their pathological targets on multiple organs. Overall, our proposed ontology-based integrative framework combined with computational predictions can be used to support fundamental understanding of the intricate interactions between human patients and coronaviruses (including SARS-CoV-2) and their association with various disease outcomes.

q-bio.OT↗

arXiv2017

Data-based prediction and causality inference of nonlinear dynamics

Natural systems are typically nonlinear and complex, and it is of great interest to be able to reconstruct a system in order to understand its mechanism, which can not only recover nonlinear behaviors but also predict future dynamics. Due to the advances of modern technology, big data becomes increasingly accessible and consequently the problem of reconstructing systems from measured data or time series plays a central role in many scientific disciplines. In recent decades, nonlinear methods rooted in state space reconstruction have been developed, and they do not assume any model equations but can recover the dynamics purely from the measured time series data. In this review, the development of state space reconstruction techniques will be introduced and the recent advances in systems prediction and causality inference using state space reconstruction will be presented. Particularly, the cutting-edge method to deal with short-term time series data will be focused. Finally, the advantages as well as the remaining problems in this field are discussed.

nlin.CD↗

arXiv2015

Identifying overlapping communities in social networks using multi-scale local information expansion

Most existing approaches for community detection require complete information of the graph in a specific scale, which is impractical for many social networks. We propose a novel algorithm that does not embrace the universal approach but instead of trying to focus on local social ties and modeling multi-scales of social interactions occurring in those networks. Our method for the first time optimizes the topological entropy of a network and uncovers communities through a novel dynamic system converging to a local minimum by simply updating the membership vector with very low computational complexity. It naturally supports overlapping communities through associating each node with a membership vector which describes node's involvement in each community. This way, in addition to uncover overlapping communities, we can also describe different multi-scale partitions by tuning the characteristic size of modules from the optimal partition. Because of the high efficiency and accuracy of the algorithm, it is feasible to be used for the accurate detection of community structure in real networks.

physics.soc-ph↗

arXiv2015

Measuring robustness of community structure in complex networks

The theory of community structure is a powerful tool for real networks, which can simplify their topological and functional analysis considerably. However, since community detection methods have random factors and real social networks obtained from complex systems always contain error edges, evaluating the robustness of community structure is an urgent and important task. In this letter, we employ the critical threshold of resolution parameter in Hamiltonian function, $γ_C$, to measure the robustness of a network. According to spectral theory, a rigorous proof shows that the index we proposed is inversely proportional to robustness of community structure. Furthermore, by utilizing the co-evolution model, we provides a new efficient method for computing the value of $γ_C$. The research can be applied to broad clustering problems in network analysis and data mining due to its solid mathematical basis and experimental effects.

physics.soc-ph↗

arXiv2007

Stochastic Synchronization of Genetic Oscillator Networks

The study of synchronization among genetic oscillators is essential for the understanding of the rhythmic phenomena of living organisms at both molecular and cellular levels. Genetic networks are intrinsically noisy due to natural random intra- and inter-cellular fluctuations. Therefore, it is important to study the effects of noise perturbation on the synchronous dynamics of genetic oscillators. From the synthetic biology viewpoint, it is also important to implement biological systems that minimizing the negative influence of the perturbations. In this paper, based on systems biology approach, we provide a general theoretical result on the synchronization of genetic oscillators with stochastic perturbations. By exploiting the specific properties of many genetic oscillator models, we provide an easy-verified sufficient condition for the stochastic synchronization of coupled genetic oscillators, based on the Lur'e system approach in control theory. A design principle for minimizing the influence of noise is also presented. To demonstrate the effectiveness of our theoretical results, a population of coupled repressillators is adopted as a numerical example. In summary, we present an efficient theoretical method for analyzing the synchronization of genetic oscillator networks, which is helpful for understanding and testing the synchronization phenomena in biological organisms. Besides, the results are actually applicable to general oscillator networks.

q-bio.MN↗