Song-Bin Guo

Large language models (LLMs) are gradually evolving from text generators into cognitive interfaces and decision-making infrastructure that can be...

Background: Distinctive heterogeneity characterizes diffuse large B‐cell lymphoma (DLBCL), one of the most frequent types of non‐Hodgkin's lymphoma. Mitochondria have been demonstrated to be closely involved in tumorigenesis and progression, particularly in DLBCL.Objective: The purposes of this study were to identify the prognostic mitochondria‐related genes (MRGs) in DLBCL, and to develop a risk model based on MRGs and machine learning algorithms.Methods: Transcriptome profiles and clinical information were obtained from the Gene Expression Omnibus (GEO) database. The risk model was defined using Least Absolute Shrinkage and Selection Operator (Lasso) regression algorithm, and its prognostic value was further examined in independent datasets. Patients were stratified into two clusters based on the risk scores, additionally a nomogram was generated based on the risk score and clinical characteristics. Gene pathway level, microenvironment, expression of targeted therapy‐associated genes, response to immunotherapy, drug sensitivity, and somatic mutation status were compared between clusters.Results: Eighteen prognostic MRGs (DNM1L, PUSL1, CHCHD4, COX7A1, CPT1A, CYP27A1, POLDIP2, PCK2, MRPL2, PDK3, PDK4, MARC2, ACSM3, COA7, THNSL1, ATAD3B, C15orf48, TOMM70A) were identified to construct the risk model. Remarkable discrepancies were observed between groups. The high‐risk group had shorter overall survival, less immune infiltration, lower CD20 and higher PD‐L1 expression than the low‐risk group. Distinct immune microenvironment, responses to immunotherapy and predictive drug IC50 values were found between groups.Conclusions: We established a novel prognostic mitochondria‐related signature by machine learning algorithm, which also demonstrated outstanding predictive value in tumor microenvironment and responses to therapies.

Liquid-liquid phase separation (LLPS) is a complex and subtle phenomenon whose formation and regulation take essential roles in cancer initiation, growth, progression, invasion, and metastasis. This domain holds a wealth of underutilized unstructured data that needs further excavation for potentially valuable information. Therefore, we retrospectively analyzed the global scientific knowledge in the field over the last decade by using informatics methods (such as hierarchical clustering, regression statistics, hotspot burst, and Walktrap algorithm analysis). Over the past decade, this area enjoyed a favorable development trend (Annual Growth Rate: 34.98%) and global collaboration (International Co-authorship: 27.31%). Through unsupervised hierarchical clustering based on machine learning, the global research hotspots were divided into five dominant research clusters: Cluster 1 (Effects and Mechanisms of Phase Separation in Drug Delivery), Cluster 2 (Phase Separation in Gene Expression Regulation), Cluster 3 (Phase Separation in RNA-Protein Interaction), Cluster 4 (Reference Value of Phase Separation in Neurodegenerative Diseases for Cancer Research), and Cluster 5 (Roles and Mechanisms of Phase Separation). And further time-series analysis revealed that Cluster 5 is the emerging research cluster. In addition, results from the regression curve and hotspot burst analysis point in unison to super-enhancer (a=0.5515, R²=0.6586, p=0.0044) and stress granule (a=0.8000, R²=0.6000, p=0.0085) as the most potential star molecule in this field. More interestingly, the Random-Walk-Strategy-based Walktrap algorithm further revealed that “phase separation, cancer, transcription, super-enhancer, epigenetics”(Relevance Percentage[RP]=100%, Development Percentage[DP]=29.2%), “stress granule, immunotherapy, tumor microenvironment, RNA binding protein”(RP=79.2%, DP=33.3%) and “nanoparticle, apoptosis”(RP=70.8%, DP=25.0%) are closely associated with this field, but are still under-developed and worthy of further exploration. In conclusion, this study profiled the global scientific landscape, discovered a crucial emerging research cluster, identified several pivotal research molecules, and predicted several crucial but still under-developed directions that deserve further research, providing an important reference value for subsequent basic and clinical research of phase separation in cancer.