Identification of key circadian rhythm genes in skin aging based on bioinformatics and machine learning

Xiao, Xiao; Feng, Hao; Liao, Yangying; Tang, Hua; Li, Lan; Li, Ke; Hu, Feng

doi:10.18632/aging.205155

Cited by 4 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms, through leveraging large datasets and advanced algorithms, possess powerful data analysis capabilities. They are increasingly being applied to the field of medicine, demonstrating excellent performance in many studies 34 - 36 . To enhance the accuracy and stability of our newly developed diagnostic model, and to expedite the efficiency of image automation in personalised medicine, we chose the best model through machine learning algorithms to achieve optimal diagnostic performance.…”

Section: Methodsmentioning

confidence: 99%

Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework

Guan,

Yuan,

et al. 2024

J. Cancer

View full text Add to dashboard Cite

This study has used machine learning algorithms to develop a predictive model for differentiating between dermoscopic images of basal cell carcinoma (BCC) and actinic keratosis (AK). We compiled a total of 904 dermoscopic images from two sources -the public dataset (HAM10000) and our proprietary dataset from the First Affiliated Hospital of Dalian Medical University (DAYISET 1) -and subsequently categorised these images into four distinct cohorts. The study developed a deep learning model for quantitative analysis of image features and integrated 15 machine learning algorithms, generating 207 algorithmic combinations through random combinations and cross-validation. The final predictive model, formed by integrating XGBoost with Lasso regression, exhibited effective performance in the differential diagnosis of BCC and AK. The model demonstrated high sensitivity in the training set and maintained stable performance in three validation sets. The area under the curve (AUC) value reached 1.000 in the training set and an average of 0.695 in the validation sets. The study concludes that the constructed discriminative diagnostic model based on machine learning algorithms has excellent predictive capabilities that could enhance clinical decision-making efficiency, reduce unnecessary biopsies, and provide valuable guidance for further treatment.

show abstract

Section: Methodsmentioning

confidence: 99%

Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework

Guan,

Yuan,

et al. 2024

J. Cancer

View full text Add to dashboard Cite

show abstract

Characterizing the rhythmic oscillations of gut bacterial and fungal communities and their rhythmic interactions in male cynomolgus monkeys

Yang,

Yu,

et al. 2024

Microbiol Spectr

View full text Add to dashboard Cite

The circadian oscillation of gut microbiota plays vital roles in the normal physiology and health of the host. Although the diurnal oscillation of intestinal bacteria has been extensively studied, little relevant work has been done on intestinal fungi. Besides, the rhythmic correlations between bacterial and fungal microbes are also scarcely reported. Here, we investigated the diurnal oscillations of bacterial and fungal communities in male cynomolgus monkeys by performing 16S rRNA and ITS amplicon sequencing. As for bacterial genera, we found that the relative abundance of Prevotella , norank_f_Eubacterium_coprostanoligenes_group, and Peptococcus underwent significant changes at ZT12 (19:00) and exhibited obvious rhythmic oscillations. Consequently, most of the bacterial functions varied at ZT12 and were positively correlated with the bacterial genera norank_f_Eubacterium_coprostanoligenes_group and Prevotella . Among the fungal genera, the relative abundance of Aspergillus and Talaromyces decreased at ZT18 (1:00) and showed slight rhythmic oscillations. As for the fungal function, the undefined saprotroph showed slight rhythmic oscillation and was positively correlated with the fungal genus Aspergillus . Notably, we characterized the correlations between intestinal bacteria and fungi every 6 h over the course of a day and found that the bacterial and fungal microbes interacted closely, with the most bacteria–fungi interactions occurring at ZT12. Our study contributed to a more comprehensive understanding of the diurnal oscillation patterns of bacterial and fungal microbes in male cynomolgus monkeys and uncovered their correlations during a diurnal cycle. IMPORTANCE The rhythmic oscillation of gut microbiota can impact the physiology activity and disease susceptibility of the host. Until now, most of the studies are focused on bacterial microbes, ignoring other components of gut microbes, such as fungal microbes (mycobiota). Besides, only few studies have addressed the rhythmic correlations between gut bacteria and fungi. Here, we analyzed the rhythmic oscillations of bacterial and fungal communities in male cynomolgus monkeys by performing 16S rRNA and ITS amplicon sequencing. Apart from identifying the rhythmically oscillated bacterial and fungal microbes, we conducted the correlation analysis between these two microbial communities and found that the intestinal bacteria and fungi exhibited close interactions rhythmically, with the most interactions occurring at ZT12. Thus, our study not only investigated the rhythmic oscillations of gut bacterial and fungal communities in male cynomolgus monkeys but also uncovered their rhythmic interactions.

show abstract

Diabetes mellitus and glymphatic dysfunction: Roles for oxidative stress, mitochondria, circadian rhythm, artificial intelligence, and imaging

Maiese

2025

World J Diabetes

View full text Add to dashboard Cite

Diabetes mellitus (DM) is a debilitating disorder that impacts all systems of the body and has been increasing in prevalence throughout the globe. DM represents a significant clinical challenge to care for individuals and prevent the onset of chronic disability and ultimately death. Underlying cellular mechanisms for the onset and development of DM are multi-factorial in origin and involve pathways associated with the production of reactive oxygen species and the generation of oxidative stress as well as the dysfunction of mitochondrial cellular organelles, programmed cell death, and circadian rhythm impairments. These pathways can ultimately involve failure in the glymphatic pathway of the brain that is linked to circadian rhythms disorders during the loss of metabolic homeostasis. New studies incorporate a number of promising techniques to examine patients with metabolic disorders that can include machine learning and artificial intelligence pathways to potentially predict the onset of metabolic dysfunction.

show abstract

Identification of key circadian rhythm genes in skin aging based on bioinformatics and machine learning

Cited by 4 publications

References 37 publications

Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework

Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework

Characterizing the rhythmic oscillations of gut bacterial and fungal communities and their rhythmic interactions in male cynomolgus monkeys

Diabetes mellitus and glymphatic dysfunction: Roles for oxidative stress, mitochondria, circadian rhythm, artificial intelligence, and imaging

Contact Info

Product

Resources

About