Review
Environmental Sciences
Dafni Anastasiadi, Francesc Piferrer
Summary: Epigenetic clocks are accurate tools for age prediction in fish, and have great potential for fisheries management and conservation biology. This review discusses the computational steps and tools necessary to build an epigenetic clock in any fish species, with a focus on the recommended bisulfite conversion method for distinguishing methylated and unmethylated cytosines. Machine learning statistical procedures, particularly penalized regressions, are applied to identify a set of CpGs that can accurately predict age, and once validated, only a small number of CpGs are needed for age prediction. The implementation of this molecular resource is expected to increase in the future due to its accuracy and decreasing sequencing costs. Accurate age prediction will greatly contribute to fish population management and conservation efforts.
FRONTIERS IN MARINE SCIENCE
(2023)
Article
Clinical Neurology
Gabriel A. Marx, Justin Kauffman, Andrew T. McKenzie, Daniel G. Koenigsberg, Cory T. McMillan, Susan Morgello, Esma Karlovich, Ricardo Insausti, Timothy E. Richardson, Jamie M. Walker, Charles L. White III, Bergan M. Babrowicz, Li Shen, Ann C. McKee, Thor D. Stein, Kurt Farrell, John F. Crary
Summary: Understanding age acceleration in the brain can provide insights into normal physiology, age-related decline, and early disease changes. Using histopathological images, a deep learning model was developed to estimate brain age. The model accurately predicted brain age and identified vulnerable neuroanatomical regions.
ACTA NEUROPATHOLOGICA
(2023)
Article
Biochemistry & Molecular Biology
Isabel Fernandez-Perez, Joan Jimenez-Balado, Uxue Lazcano, Eva Giralt-Steinhauer, Lucia Rey alvarez, Elisa Cuadrado-Godia, Ana Rodriguez-Campello, Adria Macias-Gomez, Antoni Suarez-Perez, Anna Revert-Barbera, Isabel Estragues-Gazquez, Carolina Soriano-Tarraga, Jaume Roquer, Angel Ois, Jordi Jimenez-Conde
Summary: Age acceleration (Age-A) is a useful tool for predicting various health outcomes. This study aims to estimate the contribution of environmental, lifestyle, and vascular risk factors to Age-A in patients with cerebrovascular disease, and to find a more accessible model for predicting Age-A.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Psychiatry
Angela Lombardi, Alfonso Monaco, Giacinto Donvito, Nicola Amoroso, Roberto Bellotti, Sabina Tangaro
Summary: Morphological changes in the brain over the lifespan have been successfully characterized using structural magnetic resonance imaging (MRI) and machine learning (ML) algorithms. A predictive model based on deep neural networks (DNN) showed the best performance in brain age prediction, outperforming other ML strategies with a MAE of 4.6 on hold-out test data.
FRONTIERS IN PSYCHIATRY
(2021)
Review
Cell Biology
Maxim N. Shokhirev, Adiv A. Johnson
Summary: Alzheimer's disease, an incurable age-related brain disorder, was studied through the analysis of genes, proteins, and microRNAs. The results showed that factors such as cell death, cellular senescence, energy metabolism, genomic integrity, and glia were associated with the disease. These factors exhibited unique characteristics in different age groups.
AGEING RESEARCH REVIEWS
(2022)
Article
Neurosciences
Shammi More, Georgios Antonopoulos, Felix Hoffstaedter, Julian Caspers, Simon B. Eickhoff, Kaustubh R. Patil
Summary: The difference between predicted age based on brain scans and chronological age can be used as a proxy for atypical aging. Different data representations and machine learning algorithms have different effects on performance criteria such as accuracy, generalizability, reliability, and consistency. The choice of feature representation and machine learning algorithm both affect performance, and further evaluation and improvements are needed for real-world application.
Review
Cell Biology
Adiv A. Johnson, Bradley W. English, Maxim N. Shokhirev, David A. Sinclair, Trinna L. Cuellar
Summary: Although chronological age is related to age-related diseases and conditions, it does not fully reflect an individual's functional capacity, well-being, or mortality risk. In contrast, biological age provides information on overall health and the pace of aging. Research has shown that aging clocks, computational models using inputs like DNA methylation sites, can predict biological age. This predicted biological age is associated with age-related diseases, social factors, and mental health conditions. Age acceleration, indicated by an increase in predicted biological age relative to chronological age, is linked to higher premature mortality risk.
Article
Neurosciences
Melis Anaturk, Tobias Kaufmann, James H. Cole, Sana Suri, Ludovica Griffanti, Eniko Zsoldos, Nicola Filippini, Archana Singh-Manoux, Mika Kivimaki, Lars T. Westlye, Klaus P. Ebmeier, Ann-Marie G. de Lange
Summary: In this study, machine-learning methods were used to estimate brain and cognitive age, revealing a link between premorbid IQ and cognitive age. The study did not find strong evidence for associations between brain or cognitive age and lifestyle trajectories.
HUMAN BRAIN MAPPING
(2021)
Article
Cell Biology
Anika Mijakovac, Azra Frkatovic, Maja Hanic, Jelena Ivok, Marina Martinic Kavur, Maja Pucic-Bakovic, Tim Spector, Vlatka Zoldos, Massimo Mangino, Gordan Lauc
Summary: Through genetic analysis of the TwinsUK female cohorts, we found that genetic factors have a moderate contribution to the variation of the glycan clock, while unique environmental factors have a minor role and shared environmental factors have a larger contribution. The estimates of genetic factors and unique environmental factors increased when age was included as a covariate.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2022)
Article
Psychiatry
Taehyoung Kim, Ukeob Park, Seung Wan Kang
Summary: Depression is a common mental disorder in modern society and machine learning models trained on z-score values of quantitative EEG indicators reflecting sex and age can serve as reliable and objective biomarkers for early screening of potential depression.
FRONTIERS IN PSYCHIATRY
(2022)
Article
Environmental Sciences
Jin Zhang, Lu Ma, Boyan Li, Xiong Chen, Dapeng Wang, Aihua Zhang
Summary: This study identified metabolic biomarkers associated with arsenicosis using untargeted metabolomics and machine learning algorithms. A total of 143 metabolic biomarkers, mainly organic acids, were found to be closely associated with arsenicosis. The disrupted metabolisms of beta-alanine and arginine were the most significant in arsenicosis patients with different symptom severity. Metabolic biomarkers combined with machine learning algorithms can be efficient for risk assessment and early identification of arsenicosis.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Multidisciplinary Sciences
Shaun M. Kandathil, Joe G. Greener, Andy M. Lau, David T. Jones
Summary: The study presents a deep learning-based method for predicting protein structure, which reduces preprocessing time and directly outputs main chain coordinates. The approach is fast, easy to use, and produces accurate structural models. It enables large-scale modeling of proteins on minimal hardware.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Review
Cell Biology
Weicheng Fang, Shuxin Chen, Xuejiao Jin, Shenkui Liu, Xiuling Cao, Beidong Liu
Summary: Metabolism plays a crucial role in regulating aging, and metabolic reprogramming is the primary driving force behind aging. The relationship between changes in metabolite levels and aging is complex due to variations in metabolic needs and organ functions. However, not all changes in metabolite levels contribute to aging. The development of metabolomics research provides insights into the overall metabolic changes during the aging process, aiming to identify potential metabolic markers of aging. This information can be valuable for future diagnosis and clinical intervention of aging and age-related diseases.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2023)
Article
Cell Biology
Sascha Jung, Javier Arcos Hodar, Antonio del Sol
Summary: In this study, MultiTIMER, the first multi-tissue aging clock, is presented. It can measure the biological age of cells from their transcriptional profiles by evaluating key cellular processes, instead of the chronological age. The authors applied MultiTIMER to a large number of transcriptional profiles and demonstrated its accuracy in responding to cellular stressors, known interventions, and dysregulated cellular functions.
Article
Cardiac & Cardiovascular Systems
Mehrdad Samadishadlou, Reza Rahbarghazi, Zeynab Piryaei, Mahdad Esmaeili, cigir Biray Avci, Farhad Bani, Kaveh Kavousi
Summary: By integrating bioinformatics and machine learning analysis, we identified a set of miRNA biomarkers for cardiovascular diseases. The study demonstrates that miRNA signatures derived from peripheral blood mononuclear cells can serve as valuable novel biomarkers for cardiovascular diseases.
CARDIOVASCULAR DIABETOLOGY
(2023)
Article
Biochemistry & Molecular Biology
Benoit Lehallier, David Gate, Nicholas Schaum, Tibor Nanasi, Song Eun Lee, Hanadie Yousef, Patricia Moran Losada, Daniela Berdnik, Andreas Keller, Joe Verghese, Sanish Sathyan, Claudio Franceschi, Sofiya Milman, Nir Barzilai, Tony Wyss-Coray
Article
Neurosciences
Julia Marschallinger, Tal Iram, Macy Zardeneta, Song E. Lee, Benoit Lehallier, Michael S. Haney, John V. Pluvinage, Vidhu Mathur, Oliver Hahn, David W. Morgens, Justin Kim, Julia Tevini, Thomas K. Felder, Heimo Wolinski, Carolyn R. Bertozzi, Michael C. Bassik, Ludwig Aigner, Tony Wyss-Coray
NATURE NEUROSCIENCE
(2020)
Correction
Neurosciences
Julia Marschallinger, Tal Iram, Macy Zardeneta, Song E. Lee, Benoit Lehallier, Michael S. Haney, John V. Pluvinage, Vidhu Mathur, Oliver Hahn, David W. Morgens, Justin Kim, Julia Tevini, Thomas K. Felder, Heimo Wolinski, Carolyn R. Bertozzi, Michael C. Bassik, Ludwig Aigner, Tony Wyss-Coray
NATURE NEUROSCIENCE
(2020)
Article
Multidisciplinary Sciences
Nicholas Schaum, Benoit Lehallier, Oliver Hahn, Robert Palovics, Shayan Hosseinzadeh, Song E. Lee, Rene Sit, Davis P. Lee, Patricia Moran Losada, Macy E. Zardeneta, Tobias Fehlmann, James T. Webber, Aaron McGeever, Kruti Calcuttawala, Hui Zhang, Daniela Berdnik, Vidhu Mathur, Weilun Tan, Alexander Zee, Michelle Tan, Angela Oliveira Pisco, Jim Karkanias, Norma F. Neff, Andreas Keller, Spyros Darmanis, Stephen R. Quake, Tony Wyss-Coray
Correction
Neurosciences
Julia Marschallinger, Tal Iram, Macy Zardeneta, Song E. Lee, Benoit Lehallier, Michael S. Haney, John V. Pluvinage, Vidhu Mathur, Oliver Hahn, David W. Morgens, Justin Kim, Julia Tevini, Thomas K. Felder, Heimo Wolinski, Carolyn R. Bertozzi, Michael C. Bassik, Ludwig Aigner, Tony Wyss-Coray
NATURE NEUROSCIENCE
(2020)
Article
Cell Biology
Benoit Lehallier, Maxim N. Shokhirev, Tony Wyss-Coray, Adiv A. Johnson
Article
Multidisciplinary Sciences
Tobias Fehlmann, Benoit Lehallier, Nicholas Schaum, Oliver Hahn, Mustafa Kahraman, Yongping Li, Nadja Grammes, Lars Geffers, Christina Backes, Rudi Balling, Fabian Kern, Rejko Krueger, Frank Lammert, Nicole Ludwig, Benjamin Meder, Bastian Fromm, Walter Maetzler, Daniela Berg, Kathrin Brockmann, Christian Deuschle, Anna-Katharina von Thaler, Gerhard W. Eschweiler, Sofiya Milman, Nir Barziliai, Matthias Reichert, Tony Wyss-Coray, Eckart Meese, Andreas Keller
NATURE COMMUNICATIONS
(2020)
Article
Multidisciplinary Sciences
Zurine De Miguel, Nathalie Khoury, Michael J. Betley, Benoit Lehallier, Drew Willoughby, Niclas Olsson, Andrew C. Yang, Oliver Hahn, Nannan Lu, Ryan T. Vest, Liana N. Bonanno, Lakshmi Yerra, Lichao Zhang, Nay Lui Saw, J. Kaci Fairchild, Davis Lee, Hui Zhang, Patrick L. McAlpine, Kevin Contrepois, Mehrdad Shamloo, Joshua E. Elias, Thomas A. Rando, Tony Wyss-Coray
Summary: Research shows that physical exercise can lead to the production of anti-inflammatory factors in the blood plasma of mice, which can reduce neuroinflammation, particularly in the hippocampus, and also increase in patients with cognitive impairment.