Abstract Substrate inhibition in lactic acid bacteria (LAB) fermentation occurs when substrate concentration exceeds a critical value, leading to reduced cell growth and thus inefficient lactic acid production. Many efforts, including experimental and kinetic models, have been devoted to elucidate the possible mechanisms of substrate inhibition. However, the molecular and physiological basis of this phenomenon remains incompletely characterized. In this study, we propose a mechanistic two‐pathway model that integrates a substrate‐responsive molecular regulatory pathway into the typical substrate assimilation and microbial growth pathway. Our modeling analysis captures a global growth dynamics, including lag, exponential, and stationary phases over a wide range of initial substrate concentrations, with one set of parameters. Consequently, the results exhibit a significantly prolonged lag phase at high initial substrate concentrations. We test this model framework by combining the model results with the published experimental data of LAB batch fermentation such as Lactobacillus bulgaricus, Lactobacillus casei, and Lactiplantibacillus plantarum on lactose, demonstrating its universality beyond specific substrate‐strain systems. Furthermore, the model simulations show that an appropriate preculture treatment for modulating the inoculum’s physiological state of the population could be a possible approach to cope with the challenge of substrate inhibition at high‐substrate environments. Finally, the model predictions of optimal microbial growth dynamics are investigated from various inoculum sizes. The proposed modeling approach provides novel insights into the connection between microbial fermentation and substrate supply, facilitating efficient substrate utilization in bioprocess engineering.

Abstract With the rapid advancements in large language model technology and the emergence of bioinformatics‐specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide‐ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications.

Abstract The detection of drug–drug interaction (DDI) is crucial to the rational use of drug combinations. Experimentally, DDI detection is time‐consuming and laborious. Currently, researchers have developed a variety of computational methods to predict DDI. Although there are many reviews that summarized these computational methods, these reviews focused on supervised learning. In this review, we provide a comprehensive and systematic summary of unsupervised (i.e., clustering) methods for DDI network analysis. Unlike previous studies, we highlight the unique advantages of clustering methods DDI prediction and uncovering mechanisms of action. We first introduced common drug information and discussed how to calculate drug similarity using this drug information. Then, we introduced representative clustering algorithms (i.e., drug information‐based and network‐based methods) and described clustering evaluation metrics. Finally, we discussed the limitations and challenges in this field, and proposed potential research directions. This review aims to promote further exploration and application of clustering methods in drug combination discovery and DDI network analysis.

Abstract Cancer is a complex and heterogeneous disease characterized by various genetic and epigenetic alterations. Early diagnosis, accurate subtyping, and staging are essential for effective, personalized treatment and improved survival rates. Traditional diagnostic methods, such as biopsies, are invasive and carry operational risks that hinder repeated use, underscoring the need for noninvasive and personalized alternatives. In response, this study integrates transcriptomic data into human genome‐scale metabolic models (GSMMs) to derive patient‐specific flux distributions, which are then combined with genomic, proteomic, and fluxomic (JX) data to develop a robust multi‐omic classifier for lung cancer subtyping and early diagnosis. The JX classifier is further enhanced by analyzing heterogeneous datasets from RNA sequencing and microarray analyses derived from both tissue samples and cell culture experiments, thereby enabling the identification of key marker features and enriched pathways such as lipid metabolism and energy production. This integrated approach not only demonstrates high performance in distinguishing lung cancer subtypes and early‐stage disease but also proves robust when applied to limited pancreatic cancer data. By linking genotype to phenotype, GSMM‐driven flux analysis overcomes challenges related to metabolome data scarcity and platform variability by proposing marker processes and reactions for further investigation, ultimately facilitating noninvasive diagnostics and the identification of actionable biomarkers for targeted therapeutic intervention. These findings offer significant promise for streamlining clinical workflows and enabling personalized therapeutic strategies, and they highlight the potential of our versatile workflow for unveiling novel biomarker landscapes in less studied diseases.

Abstract Recent advancements in spatial transcriptomics (ST) technologies allow researchers to simultaneously measure RNA expression levels for hundreds to thousands of genes while preserving spatial information within tissues, providing critical insights into spatial gene expression patterns, tissue organization, and gene functionality. However, existing methods for clustering spatially variable genes (SVGs) into co‐expression modules often fail to detect rare or unique spatial expression patterns. To address this, we present spatial transcriptomics iterative hierarchical clustering (stIHC), a novel method for clustering SVGs into co‐expression modules, representing groups of genes with shared spatial expression patterns. Through three simulations and applications to ST datasets from technologies such as 10x Visium, 10x Xenium, and Spatial Transcriptomics, stIHC outperforms clustering approaches used by popular SVG detection methods, including SPARK, SPARK‐X, MERINGUE, and SpatialDE. Gene ontology enrichment analysis confirms that genes within each module share consistent biological functions, supporting the functional relevance of spatial co‐expression. Robust across technologies with varying gene numbers and spatial resolution, stIHC provides a powerful tool for decoding the spatial organization of gene expression and the functional structure of complex tissues.

Abstract Comorbidity, the co‐occurrence of multiple medical conditions in a single patient, profoundly impacts disease management and outcomes. Understanding these complex interconnections is crucial, especially in contexts where comorbidities exacerbate outcomes. Leveraging insights from the human interactome and advancements in graph‐based methodologies, this study introduces transformer with subgraph positional encoding (TSPE) for disease comorbidity prediction. Inspired by biologically supervised embedding, TSPE employs transformer’s attention mechanisms and subgraph positional encoding (SPE) to capture interactions between nodes and disease associations. Our proposed SPE proves more effective than Laplacian positional encoding, as used in Dwivedi et al.’s graph transformer, underscoring the importance of integrating clustering and disease‐specific information for improved predictive accuracy. Evaluated on real clinical benchmark datasets (RR0 and RR1), TSPE demonstrates substantial performance enhancements over the state‐of‐the‐art method, achieving up to 28.24% higher ROC AUC (receiver operating characteristic–area under the curve) and 4.93% higher accuracy. This method shows promise for adaptation to other complex graph‐based tasks and applications. The source code is available at GitHub website (xihan‐qin/TSPE‐GraphTransformer).

Abstract Do we need a foundation model (FM) for spatial transcriptomic analysis? To answer this question, we prepared this perspective as a primer. We first review the current progress of developing FMs for modeling spatial transcriptomic data and then discuss possible tasks that can be addressed by FMs. Finally, we explore future directions of developing such models for understanding spatial transcriptomics by describing both opportunities and challenges. In particular, we expect that a successful FM should boost research productivity, increase novel biological discoveries, and provide user‐friendly access.

Abstract In this study, we show an example of a numerical model based on the Keller–Segel system of equations to simulate angiogenesis in response to chemotaxis under Robin boundary conditions, which represent the presence of flux at the tumor. Different parameters of the model are modified to identify key biological factors relevant to the behavior of angiogenesis. The results show that in the presence of a stronger flux, angiogenesis occurs later owing to the chemical flux that creates a more uniform and homogeneous matrix, decreasing the pronunciation of the gradient and reducing the potential of chemotaxis.