A Unified Framework for Systematic Curation and Evaluation of Aging Biomarkers

Abstract

Identifying and validating biomarkers of aging is pivotal for understanding the aging process and testing longevity interventions. Despite the development of numerous aging biomarkers, their clinical validation remains elusive, largely due to the lack of cross-population validation, which is hampered by disparate biomarker designs and inconsistencies in dataset structures. To bridge this gap, we introduce Biolearn, an innovative open-source library dedicated to the implementation and application of aging biomarkers. Biolearn facilitates (1) harmonization of existing aging biomarkers, while presenting a structured framework for novel biomarkers in standardized formats; (2) unification of public datasets, ensuring coherent structuring and formatting, thus simplifying cross-population validation studies; and (3) provision of computational methodologies to assess any harmonized biomarker against unified datasets. By furnishing a community-driven platform, Biolearn significantly augments the development, assessment, and validation trajectories of aging biomarkers, paving the way toward more rigorous clinical validation and, ultimately, application in clinical trials targeting healthy longevity. The Biolearn package is open-source and freely available athttps://Bio-Learn.github.io/

pyaging: a Python-based compendium of GPU-optimized aging clocks

“…Fourth, one of the main advantages of the package is speed. I compared with ( Ying et al 2023 ), a preliminary CPU-based biomarker package. To compare their performance, I predicted the ages of the AltumAge data with two linear models, Horvath2013 and DNAmPhenoAge ( Levine et al 2018 )—more complex clocks that would benefit the most from GPU acceleration, such as AltumAge, were not available on at the time of writing.…”

“…The notebook for the example analyses in this manuscript is available in the Supplementary Data . The packages used are pandas v2.1.3 ( McKinney et al 2011 ), numpy v1.26.2 ( Harris et al 2020 ), seaborn v0.12.2 ( Waskom 2021 ), matplotlib v3.7.1 ( Hunter 2007 ), umap-learn v0.5.5 ( McInnes et al 2018 ), scikit-learn v1.3.2 ( Pedregosa et al 2011 ), pyaging v0.1.6 (this manuscript), and biolearn v0.3.4 ( Ying et al 2023 ). The code was run on an M1 MacBook Pro.…”

Causality-Enriched Epigenetic Age Uncouples Damage and Adaptation

“…Custom code used are available in Supplementary Information. Algorithm of CausAge, DamAge, and AdaptAge are available in Supplementary information, as well as ClockBase (www.clockbase.org) and bio-learn python package (https://bio-learn.github.io/) 62,63 .…”