A comparative evaluation of the generalised predictive ability of eight machine learning algorithms across ten clinical metabolomics data sets for binary classification DOI Creative Commons
Kevin Mendez, Stacey N. Reinke, David Broadhurst

et al.

Metabolomics, Journal Year: 2019, Volume and Issue: 15(12)

Published: Nov. 15, 2019

Abstract Introduction Metabolomics is increasingly being used in the clinical setting for disease diagnosis, prognosis and risk prediction. Machine learning algorithms are particularly important construction of multivariate metabolite Historically, partial least squares (PLS) regression has been gold standard binary classification. Nonlinear machine methods such as random forests (RF), kernel support vector machines (SVM) artificial neural networks (ANN) may be more suited to modelling possible nonlinear covariance, thus provide better predictive models. Objectives We hypothesise that classification using metabolomics data, non-linear will superior generalised ability when compared linear alternatives, particular with current PLS discriminant analysis. Methods general performance eight archetypal across ten publicly available data sets. The were implemented Python programming language. All code results have made Jupyter notebooks. Results There was only marginal improvement SVM ANN over all RF comparatively poor. use out-of-bag bootstrap confidence intervals provided a measure uncertainty model prediction quality observed bigger influence on than choice. Conclusion size set, choice metric, had greater algorithm.

Language: Английский

A homoeostatic switch causing glycerol-3-phosphate and phosphoethanolamine accumulation triggers senescence by rewiring lipid metabolism DOI Creative Commons
Khaled Tighanimine, José Américo Nabuco Leva Ferreira de Freitas, Ivan Nemazanyy

et al.

Nature Metabolism, Journal Year: 2024, Volume and Issue: 6(2), P. 323 - 342

Published: Feb. 19, 2024

Abstract Cellular senescence affects many physiological and pathological processes is characterized by durable cell cycle arrest, an inflammatory secretory phenotype metabolic reprogramming. Here, using dynamic transcriptome metabolome profiling in human fibroblasts with different subtypes of senescence, we show that a homoeostatic switch results glycerol-3-phosphate (G3P) phosphoethanolamine (pEtN) accumulation links lipid metabolism to the gene expression programme. Mechanistically, p53-dependent glycerol kinase activation post-translational inactivation phosphate cytidylyltransferase 2, ethanolamine regulate this switch, which promotes triglyceride droplets induces Conversely, G3P phosphatase ethanolamine-phosphate phospho-lyase-based scavenging pEtN acts senomorphic way reducing accumulation. Collectively, our study ties controlling droplet biogenesis phospholipid flux senescent cells, providing potential therapeutic avenue for targeting related pathophysiology.

Language: Английский

Citations

30
Experimental warming accelerates positive soil priming in a temperate grassland ecosystem DOI Creative Commons
Xuanyu Tao, Zhifeng Yang, Jiajie Feng

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Feb. 8, 2024

Abstract Unravelling biosphere feedback mechanisms is crucial for predicting the impacts of global warming. Soil priming, an effect fresh plant-derived carbon (C) on native soil organic (SOC) decomposition, a key mechanism that could release large amounts C into atmosphere. However, climate warming priming remain elusive. Here, we show experimental accelerates by 12.7% in temperate grassland. Warming alters bacterial communities, with 38% unique active phylotypes detected under The functional genes essential decomposition are also stimulated, which be linked to effects. We incorporate lab-derived information ecosystem model showing parameter uncertainty can reduced 32–37%. Model simulations from 2010 2016 indicate increase warming, 9.1% rise priming-induced CO 2 emissions. If our findings generalized other ecosystems over extended period time, play important role terrestrial cycle feedbacks and change.

Language: Английский

Citations

24
Heart proteomic profiling discovers MYH6 and COX5B as biomarkers for sudden unexplained death DOI
Ziyan Song,

Wensi Bian,

Junyi Lin

et al.

Forensic Science International, Journal Year: 2024, Volume and Issue: 361, P. 112121 - 112121

Published: June 26, 2024

Language: Английский

Citations

19
Gaudichaudione H Enhances the Sensitivity of Hepatocellular Carcinoma Cells to Disulfidptosis via Regulating NRF2‐SLC7A11 Signaling Pathway DOI Creative Commons

Mengjiao Shi,

Xinyan Li,

Ying Guo

et al.

Advanced Science, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 22, 2025

Abstract Gaudichaudione H (GH) is a naturally occurring small molecular compound derived from Garcinia oligantha Merr . (Clusiaceae), but the full pharmacological functions remain unclear. Herein, potential of GH in disulfidptosis regulation, novel form programmed cell death induced by disulfide stress explored. The omics results indicated that NRF2 signaling could be significantly activated GH. targets are associated with hepatocarcinogenesis and death. Moreover, both glutathione (GSH) metabolism NADP + ‐NADPH affected GH, indicating regulation. It also observed enhanced sensitivity hepatocellular carcinoma (HCC) cells to disulfidptosis, which dependent on activation NRF2‐SLC7A11 pathway. increased levels promoted transcription target gene, SLC7A11, through autophagy‐mediated non‐canonical mechanism. Under condition glucose starvation, GH‐induced upregulation SLC7A11 aggravated uptake cysteine, disturbance GSH synthesis, depletion NADPH, accumulation molecules, ultimately leading formation bonds between different cytoskeleton proteins eventually. Collectively, findings underscore role promoting cancer thereby offering promising avenue for treatment drug‐resistant HCC clinical settings.

Language: Английский

Citations

2
A comparative evaluation of the generalised predictive ability of eight machine learning algorithms across ten clinical metabolomics data sets for binary classification DOI Creative Commons
Kevin Mendez, Stacey N. Reinke, David Broadhurst

et al.

Metabolomics, Journal Year: 2019, Volume and Issue: 15(12)

Published: Nov. 15, 2019

Abstract Introduction Metabolomics is increasingly being used in the clinical setting for disease diagnosis, prognosis and risk prediction. Machine learning algorithms are particularly important construction of multivariate metabolite Historically, partial least squares (PLS) regression has been gold standard binary classification. Nonlinear machine methods such as random forests (RF), kernel support vector machines (SVM) artificial neural networks (ANN) may be more suited to modelling possible nonlinear covariance, thus provide better predictive models. Objectives We hypothesise that classification using metabolomics data, non-linear will superior generalised ability when compared linear alternatives, particular with current PLS discriminant analysis. Methods general performance eight archetypal across ten publicly available data sets. The were implemented Python programming language. All code results have made Jupyter notebooks. Results There was only marginal improvement SVM ANN over all RF comparatively poor. use out-of-bag bootstrap confidence intervals provided a measure uncertainty model prediction quality observed bigger influence on than choice. Conclusion size set, choice metric, had greater algorithm.

Language: Английский

Citations

145