Biology subjects

Dylov, D. V.

Publications and source records attributed to Dylov, D. V..

4 recordsLinked to original sources

bioRxiv2024

ComputAgeBench: Epigenetic Aging Clocks Benchmark

The success of clinical trials of longevity drugs relies heavily on identifying integrative health and aging biomarkers, such as biological age. Epigenetic aging clocks predict the biological age of an individual using their DNA methylation profiles, commonly retrieved from blood samples. However, there is no standardized methodology to validate and compare epigenetic clock models as yet. We propose ComputAgeBench, a unifying framework that comprises such a methodology and a dataset for comprehensive benchmarking of different clinically relevant aging clocks. Our methodology exploits the core idea that reliable aging clocks must be able to distinguish between healthy individuals and those with aging-accelerating conditions. Specifically, we collected and harmonized 66 public datasets of blood DNA methylation, covering 19 such conditions across different ages, and tested 13 published clock models. Additionally, we compiled 46 separate datasets to facilitate the training of new aging clocks. We believe our work will bring the fields of aging biology and machine learning closer together for the research on reliable biomarkers of health and aging. Codehttps://github.com/ComputationalAgingLab/ComputAge Datasethttps://huggingface.co/datasets/computage/computage_bench

bioinformatics↗

bioRxiv2023

Epistemic uncertainty challenges aging clock reliability in predicting rejuvenation effects

Epigenetic aging clocks have been widely used to validate rejuvenation effects during cellular reprogramming. However, these predictions are unverifiable because the true biological age of reprogrammed cells remains unknown. We present an analytical framework to consider rejuvenation predictions from the uncertainty perspective. Our analysis reveals that the DNA methylation profiles across reprogramming are poorly represented in the aging data used to train clock models, thus introducing high epistemic uncertainty in age estimations. Moreover, predictions of different published clocks are inconsistent, with some even suggesting zero or negative rejuvenation. While not questioning the possibility of age reversal, we show that the high clock uncertainty challenges the reliability of rejuvenation effects observed during in vitro reprogramming before pluripotency and throughout embryogenesis. Conversely, our method reveals a significant age increase after in vivo reprogramming. We recommend including uncertainty estimation in future aging clock models to avoid the risk of misinterpreting the results of biological age prediction.

systems biology↗

bioRxiv2020

Deep Learning for Cortical Potential Imaging

Electroencephalography (EEG) is a well-established non-invasive technique to measure the brain activity, albeit with a limited spatial resolution. Variations in electric conductivity between different tissues distort the electric fields generated by cortical sources, resulting in smeared potential measurements on the scalp. One needs to solve an ill-posed inverse problem to recover the original neural activity. In this article, we present a generic method of recovering the cortical potentials from the EEG measurement by introducing a new inverse-problem solver based on deep Convolutional Neural Networks (CNN) in paired (U-Net) and unpaired (DualGAN) configurations. The solvers were trained on synthetic EEG-ECoG pairs that were generated using a head conductivity model computed using the Finite Element Method (FEM). These solvers are the first of their kind, that provide robust translation of EEG data to the cortex surface using deep learning. Providing a fast and accurate interpretation of the tracked EEG signal, our approach promises a boost to the spatial resolution of the future EEG devices.

neuroscience↗

bioRxiv2019

Spectroscopy and Machine Learning Based Rapid Point-of-Care Assessment of Core Needle Cancer Biopsies

Solid tumor needle biopsies are essential to confirm malignancy and assess for actionable characteristics or genetic alterations to guide treatment selection. Ensuring that sufficient and suitable material is acquired for tumor profiling, while minimizing patient risk, remains a critical unmet need. Here, we evaluated the performance characteristics of transmission optical spectroscopy for rapid identification of malignant tissue in core needle biopsies (CNB). Human kidney biopsy specimens (545 CNB from 102 patients, 5583 spectra for analysis) were analyzed directly on core biopsy needles with a custom-built optical spectroscopy instrument. Machine learning classifiers were trained to differentiate malignant from normal tissue spectra. Classifiers were compared using receiver operating characteristics analysis and sensitivity and specificity were calculated relative to a histopathologic gold standard. The best performing algorithm was the random forest (sensitivity 96% and 93%, specificity 90% and 93% at the level of individual spectra and full CNB, respectively). Ex-vivo spectroscopy paired with machine learning paves the way towards rapid and accurate characterization of CNB at the time of tissue acquisition and improving tumor biopsy quality.

bioinformatics↗