A diagnostic model for sepsis using an integrated machine learning framework approach and its therapeutic drug discovery

BMC Infectious Diseases, Journal Year: 2025, Volume and Issue: 25(1)

Published: Feb. 14, 2025

Sepsis remains a life-threatening condition in intensive care units (ICU) with high morbidity and mortality rates. Some biomarkers commonly used clinic do not have the characteristics of rapid specific growth decline after effective treatment. Machine learning has shown great potential early diagnosis, subtype analysis, accurate treatment prognosis evaluation sepsis. Gene expression matrices from GSE13904 GSE26440 were combined into training model quality control standardization. Then, intersection genes obtained by crossing screened differentially expressed (DEGs) module strongest correlation WGCNA analysis. 113 machine algorithms to build diagnosis model. Then CIBERSORT algorithm is analyze relationship between change core gene immune response Construct nomogram, DCA CIC further verify reliability The molecular compounds interacting key searched Traditional Chinese Medicine Active Compound Library (TCMACL). We 405 DEGs, including 334 up-regulated 71 down-regulated genes. 308 MEturquoise analysis DEGs for subsequent GO KEGG enrichment showed that sepsis was mainly related bacterial infection. are applied construct screen 22 hub Four four (CD177, GNLY, ANKRD22, IFIT1) through PPI network constructed Subsequently, diagnostic proved good predictive value CIC. Finally, (Dieckol, Grosvenorine Tellimagrandin II) out as drugs. combinated can distinguish patients. At same time, therapeutic docking.

Language: Английский

Limitations of nomogram models in predicting survival outcomes for glioma patients

Frontiers in Immunology, Journal Year: 2025, Volume and Issue: 16

Published: March 18, 2025

Glioma represents a prevalent and malignant tumor of the central nervous system (CNS), it is essential to accurately predict survival glioma patients optimize their subsequent treatment plans. This review outlines most recent advancements viewpoints regarding application nomograms in prognosis research. With an emphasis on precision external applicability predictive models, we carried out comprehensive literature provided step-by-step guide for developing evaluating nomograms. A summary thirty-nine articles was produced. The majority nomogram-building research has used limited patient samples, disregarded proportional hazards (PH) assumption Cox regression some them have failed incorporate validation. Furthermore, capability influenced by selection incorporated risk factors. Overall, current accuracy moderately credible. development validation nomogram models ought adhere standardized set criteria, thereby augmenting worth clinical decision-making clinician-patient communication. Prior nomogram, imperative thoroughly scrutinize its statistical foundation, rigorously evaluate accuracy, and, whenever feasible, assess utilizing multicenter databases.

Language: Английский

Integrating ensemble machine learning and multi-omics approaches to identify Dp44mT as a novel anti-Candida albicans agent targeting cellular iron homeostasis

Frontiers in Pharmacology, Journal Year: 2025, Volume and Issue: 16

Published: April 24, 2025

Introduction Candidiasis, mainly caused by Candida albicans , poses a serious threat to human health. The escalating drug resistance in C. and the limited antifungal options highlight critical need for novel therapeutic strategies. Methods We evaluated 12 machine learning models on self-constructed dataset with known anti- activity. Based their performance, optimal model was selected screen our separate in-house compound library unknown activity potential agents. of compounds confirmed through vitro susceptibility assays, hyphal growth biofilm formation assays. Through transcriptomics, proteomics, iron rescue experiments, CTC staining, JC-1 DAPI molecular docking, dynamics simulations, we elucidated mechanism underlying compound. Result Among models, best predictive an ensemble constructed from Random Forests Categorical Boosting using soft voting. It predicts that Dp44mT exhibits potent tests further verified this finding can inhibit planktonic growth, formation, . Mechanistically, exerts disrupting cellular homeostasis, leading collapse mitochondrial membrane ultimately causing apoptosis. Conclusion This study presents practical approach predicting com-pounds provides new insights into development homeostasis

Language: Английский