Journal Club

In this talk, we discuss the paper "SVD-AE: An asymmetric autoencoder with SVD regularization for multivariate time series anomaly detection" by Yueyue Yao, et.al., Neural Networks, 2024.  Abstract  Anomaly detection in multivariate time series is of critical importance in many real-world applications, such as system maintenance and Internet monitoring. In this article, we propose a novel …

In this talk, we study and discuss the paper "Laplacian renormalization group for heterogeneous networks" by Pablo Villegas et.al, Nature Physics, 2023. Abstract  The renormalization group is the cornerstone of the modern theory of universality and phase transitions and it is a powerful tool to scrutinize symmetries and organizational scales in dynamical systems. However, its …

In this talk, we discuss the paper "cellFlow: a generative flow-based model for single-cell count data" by A. Palma et.al, ICLR, 2024. Abstract Generative modeling for single-cell RNA-seq has proven transformative in crucial fields such as learning single-cell representations and perturbation responses. However, despite their appeal in relevant applications involving data augmentation and unseen cell …

In this talk, we discuss the paper "Feature selection and dimension reduction for single-cell RNA-Seq based on a multinomial model" by F. W. Townes et.al., Genome Biology, 2019. Abstract  Single-cell RNA-Seq (scRNA-Seq) profiles gene expression of individual cells. Recent scRNA-Seq datasets have incorporated unique molecular identifiers (UMIs). Using negative controls, we show UMI counts follow …

In this talk, we discuss the paper "CARE as a wearable derived feature linking circadian amplitude to human cognitive functions" by Shuya Cui et.al., npj Digital Medicine, 2023. Abstract Circadian rhythms are crucial for regulating physiological and behavioral processes. Pineal hormone melatonin is often used to measure circadian amplitude but its collection is costly and …

In this talk, we discuss the paper "Plausible, robust biological oscillations through allelic buffering" by F-S. Hsieh et.al, Cell Systems, 2024. at the Journal Club.  Abstract Biological oscillators can specify time- and dose-dependent functions via dedicated control of their oscillatory dynamics. However, how biological oscillators, which recurrently activate noisy biochemical processes, achieve robust oscillations remains …

In this talk, we discuss the paper "Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality" by H. Yuan et.al, npj digital medicine, 2024, at the Journal Club. Abstract  Sleep is essential to life. Accurate measurement and classification of sleep/wake and sleep stages is important in clinical studies for …

In this talk, we discuss the paper "A cell atlas foundation model for scalable search of similar human cells" by Graham Heimberg et.al., Nature, 2024 at the Journal Club. Abstract Single-cell RNA sequencing has profiled hundreds of millions of human cells across organs, diseases, development and perturbations to date. Mining these growing atlases could reveal …

In this talk, we discuss the paper "Method for cycle detection in sparse, irregularly sampled, long-term neuro-behavioral timeseries: Basis pursuit denoising with polynomial detrending of long-term, inter-ictal epileptiform activity" by Irena Balzekas et.al., Plos Com., 2024. Abstract Numerous physiological processes are cyclical, but sampling these processes densely enough to perform frequency decomposition and subsequent analyses …

In this talk, we discuss the paper "Constraining nonlinear time series modeling with the metabolic theory of ecology" by S.B. Munch et.al., PNAS, 2023. Abstract Forecasting the response of ecological systems to environmental change is a critical challenge for sustainable management. The metabolic theory of ecology (MTE) posits scaling of biological rates with temperature, but …

In this talk, we discuss the paper "Quantifying information accumulation encoded in the dynamics of biochemical signaling" by Y. Tang, et.al, Nature Communications, 2021. Abstract Cellular responses to environmental changes are encoded in the complex temporal patterns of signaling proteins. However, quantifying the accumulation of information over time to direct cellular decision-making remains an unsolved …

In this talk, we discuss the paper "The Large Language Models on Biomedical Data Analysis: A Survey" by Wei Lan et.al, IEEE J. Biomedical and Health Informatics, 2025, at the Journal Club. Abstract  With the rapid development of Large Language Model (LLM) technology, it has become an indispensable force in biomedical data analysis research. However, …