Fedor Galkin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Fedor Galkin has a total of 93 co-authors. Here are the top co-authors by number of shared publications:
- Alex Zhavoronkov
Insilico Medicine
11 shared publications - Alex Aliper
Insilico
5 shared publications - Vadim N. Gladyshev
Division of Genetics, Department of Medicine, Brigham and Women's Hospital Harvard Medical School Boston Massachusetts USA
4 shared publications - Vladimir Naumov
Insilico Medicine AI
4 shared publications Alex Zhavoronkov
3 shared publications- Denis Sidorenko
Insilico Medicine
3 shared publications
Latest Publications
- Open Access
- 7 September 2026
- Published by Springer Nature in Nature Biotechnology
- p. 1-13
Integration of proteomic aging clocks in a phase 2a clinical trial supports simultaneous geroprotective assessment
Drugs for aging-related diseases may modulate aging itself, but standard clinical trial designs cannot detect such effects. Aging clocks could close this gap, but epigenetic models often yield inconsistent, hard-to-interpret results. In contrast, proteomic clocks, by tracking the immediate effectors of biological change, may excel in providing aging biomarkers or mechanistic insight. Here we compare six proteomic clocks (ProtAge, OrganAge mortality , OrganAge chrono , PAC, ipfP3GPT and PAOPAC) on serum proteomes from a published 12-week phase 2a trial of the candidate anti-fibrotic drug rentosertib in idiopathic pulmonary fibrosis. We measure the variance between the clocks and find that all six clocks consistently predicted lower biological age in treated arms. However, proteomic clocks alone cannot deconvolute aging- and disease-specific effects. We addressed this issue indirectly through pathway analyses that identified potential anti-aging shifts in senescence and metabolic processes alongside the anti-fibrotic activity of rentosertib. This work supports the goal of dual-purpose clinical trial designs that integrate aging endpoints into studies for specific disease indications.
- 7 September 2026
- Published by Springer Nature in Nature Biotechnology
- p. 1-13
Open AccessIntegration of proteomic aging clocks in a phase 2a clinical trial supports simultaneous geroprotective assessment
Drugs for aging-related diseases may modulate aging itself, but standard clinical trial designs cannot detect such effects. Aging clocks could close this gap, but epigenetic models often yield inconsistent, hard-to-interpret results. In contrast, proteomic clocks, by tracking the immediate effectors of biological change, may excel in providing aging biomarkers or mechanistic insight. Here we compare six proteomic clocks (ProtAge, OrganAge mortality , OrganAge chrono , PAC, ipfP3GPT and PAOPAC) on serum proteomes from a published 12-week phase 2a trial of the candidate anti-fibrotic drug rentosertib in idiopathic pulmonary fibrosis. We measure the variance between the clocks and find that all six clocks consistently predicted lower biological age in treated arms. However, proteomic clocks alone cannot deconvolute aging- and disease-specific effects. We addressed this issue indirectly through pathway analyses that identified potential anti-aging shifts in senescence and metabolic processes alongside the anti-fibrotic activity of rentosertib. This work supports the goal of dual-purpose clinical trial designs that integrate aging endpoints into studies for specific disease indications.
- Open Access
The End of Aging Clocks: Training Foundation Models to Reason in Aging and Longevity
The aging clock paradigm has yielded dozens of specialist models that can estimate chronological age or mortality from virtually any biodata type. Yet each such model operates within a fixed modality, relies on a predetermined feature set, and produces limited biological interpretation. Here, we report Longevity-LLM v0.1, a Qwen3-14B model fine-tuned through supervised and reinforcement learning regimes on DNA methylation, proteomics, clinical biomarker, and RNA expression data. Longevity-LLM achieves high ranks in the recently announced Longevity Bench, including such tasks as cancer survival and RNA- or proteome-based age prediction. After reinforcement fine-tuning, the model achieved a 4.34-year MAE in epigenetic age prediction, surpassing the Horvath multi-tissue clock. In addition to age prediction, Longevity-LLM can carry out numerous other tasks, including proteomic profile generation, for which it significantly outperforms all frontier LLMs. These results demonstrate that a single modestly sized LLM can match or replace purpose-built aging clocks across data modalities. This work constitutes an interim report from the initial sprint of our Multi-Modal AI Gym for Science (MMAI), an initiative dedicated to building foundation models for drug discovery and aging research.
Open AccessThe End of Aging Clocks: Training Foundation Models to Reason in Aging and Longevity
The aging clock paradigm has yielded dozens of specialist models that can estimate chronological age or mortality from virtually any biodata type. Yet each such model operates within a fixed modality, relies on a predetermined feature set, and produces limited biological interpretation. Here, we report Longevity-LLM v0.1, a Qwen3-14B model fine-tuned through supervised and reinforcement learning regimes on DNA methylation, proteomics, clinical biomarker, and RNA expression data. Longevity-LLM achieves high ranks in the recently announced Longevity Bench, including such tasks as cancer survival and RNA- or proteome-based age prediction. After reinforcement fine-tuning, the model achieved a 4.34-year MAE in epigenetic age prediction, surpassing the Horvath multi-tissue clock. In addition to age prediction, Longevity-LLM can carry out numerous other tasks, including proteomic profile generation, for which it significantly outperforms all frontier LLMs. These results demonstrate that a single modestly sized LLM can match or replace purpose-built aging clocks across data modalities. This work constitutes an interim report from the initial sprint of our Multi-Modal AI Gym for Science (MMAI), an initiative dedicated to building foundation models for drug discovery and aging research.
- Open Access
LongevityBench: Are SotA LLMs ready for aging research?
Aging is a core biological process observed in most species and tissues, which is studied with a vast array of technologies. We argue that the abilities of AI systems to emulate aging and to accurately interpret biodata in its context are the key criteria to judge an LLM’s utility in biomedical research. Here, we present LongevityBench — a collection of tasks designed to assess whether foundation models grasp the fundamental principles of aging biology and can use low-level biodata to arrive at phenotype-level conclusions. The benchmark covers a variety of prediction targets including human time-to-death, mutations’ effect on lifespan, and age-dependent omics patterns. It spans all common biodata types used in longevity research: transcriptomes, DNA methylation profiles, proteomes, genomes, clinical blood tests and biometrics, as well as natural language annotations. After ranking state-of-the-art foundation models using LongevityBench, we highlight their weaknesses and outline procedures to maximize their utility in aging research and life sciences.
Open AccessLongevityBench: Are SotA LLMs ready for aging research?
Aging is a core biological process observed in most species and tissues, which is studied with a vast array of technologies. We argue that the abilities of AI systems to emulate aging and to accurately interpret biodata in its context are the key criteria to judge an LLM’s utility in biomedical research. Here, we present LongevityBench — a collection of tasks designed to assess whether foundation models grasp the fundamental principles of aging biology and can use low-level biodata to arrive at phenotype-level conclusions. The benchmark covers a variety of prediction targets including human time-to-death, mutations’ effect on lifespan, and age-dependent omics patterns. It spans all common biodata types used in longevity research: transcriptomes, DNA methylation profiles, proteomes, genomes, clinical blood tests and biometrics, as well as natural language annotations. After ranking state-of-the-art foundation models using LongevityBench, we highlight their weaknesses and outline procedures to maximize their utility in aging research and life sciences.
- Open Access
Biometric aging clock for practical utility in clinical settings
Aging clocks are an essential tool for biogerontological research that enables a quick assessment of one’s pace of aging. In research settings, clocks trained on -omics data types are the most popular since they allow for an inspection of the most basic cellular processes of aging. In clinical settings, however, -omics biomarkers of aging are impractical since they are linked to extra logistical load and costs, and they require personnel training. In this article, we present a cost-efficient aging clock that can be implemented easily in most clinics and hospitals to measure patients’ aging rates. The clock requires only 22 biomarkers, including 17 blood test parameters, and four biometric measures (blood pressure, body mass index, and waist circumference). The clock predicts one’s chronological age with a mean average error of 7.35 years, and it reveals associations with hypertension, cancer, and obesity.
Open AccessBiometric aging clock for practical utility in clinical settings
Aging clocks are an essential tool for biogerontological research that enables a quick assessment of one’s pace of aging. In research settings, clocks trained on -omics data types are the most popular since they allow for an inspection of the most basic cellular processes of aging. In clinical settings, however, -omics biomarkers of aging are impractical since they are linked to extra logistical load and costs, and they require personnel training. In this article, we present a cost-efficient aging clock that can be implemented easily in most clinics and hospitals to measure patients’ aging rates. The clock requires only 22 biomarkers, including 17 blood test parameters, and four biometric measures (blood pressure, body mass index, and waist circumference). The clock predicts one’s chronological age with a mean average error of 7.35 years, and it reveals associations with hypertension, cancer, and obesity.
- Open Access
AI-Driven Toolset for IPF and Aging Research Associates Lung Fibrosis with Accelerated Aging
Idiopathic pulmonary fibrosis (IPF) is a condition predominantly affecting the elderly and leading to a decline in lung function. Our study investigates the aging-related mechanisms in IPF using artificial intelligence (AI) approaches. We developed a pathway-aware proteomic aging clock using UK Biobank data and applied it alongside a specialized version of Precious3GPT (ipf-P3GPT) to demonstrate an AI-driven mode of IPF research. The aging clock shows great performance in cross-validation (R2=0.84) and its utility is validated in an independent dataset to show that severe cases of COVID-19 are associated with an increased aging rate. Computational analysis using ipf-P3GPT revealed distinct but overlapping molecular signatures between aging and IPF, suggesting that IPF represents a dysregulation rather than mere acceleration of normal aging processes. Our findings establish novel connections between aging biology and IPF pathogenesis while demonstrating the potential of AI-guided approaches in therapeutic development for age-related diseases.
Open AccessAI-Driven Toolset for IPF and Aging Research Associates Lung Fibrosis with Accelerated Aging
Idiopathic pulmonary fibrosis (IPF) is a condition predominantly affecting the elderly and leading to a decline in lung function. Our study investigates the aging-related mechanisms in IPF using artificial intelligence (AI) approaches. We developed a pathway-aware proteomic aging clock using UK Biobank data and applied it alongside a specialized version of Precious3GPT (ipf-P3GPT) to demonstrate an AI-driven mode of IPF research. The aging clock shows great performance in cross-validation (R2=0.84) and its utility is validated in an independent dataset to show that severe cases of COVID-19 are associated with an increased aging rate. Computational analysis using ipf-P3GPT revealed distinct but overlapping molecular signatures between aging and IPF, suggesting that IPF represents a dysregulation rather than mere acceleration of normal aging processes. Our findings establish novel connections between aging biology and IPF pathogenesis while demonstrating the potential of AI-guided approaches in therapeutic development for age-related diseases.
- Open Access
Precious3GPT: Multimodal Multi-Species Multi-Omics Multi-Tissue Transformer for Aging Research and Drug Discovery
We present a multimodal multi-species multi-omics multi-tissue transformer for aging research and drug discovery capable of performing multiple tasks such as age prediction across species, target discovery, tissue, sex, and disease sample classification, drug sensitivity prediction, replication of omics response and prediction of biological and phenotypic response to compound treatment. This model combines textual, tabular, and knowledge graph-derived representations of biological experiments to provide insights into molecular-level biological processes. We demonstrate that P3GPT has developed an intuition for the interactions between compounds, pathologies, and gene regulation in the context of multiple species and tissues. In these areas, it outperforms existing LLMs and we highlight its utility in diverse case studies. P3GPT is a general model that may be used as a target identification tool, aging clock, digital laboratory, and scientific assistant. The model is intended as a community resource available open source as well as via a Discord server.
Open AccessPrecious3GPT: Multimodal Multi-Species Multi-Omics Multi-Tissue Transformer for Aging Research and Drug Discovery
We present a multimodal multi-species multi-omics multi-tissue transformer for aging research and drug discovery capable of performing multiple tasks such as age prediction across species, target discovery, tissue, sex, and disease sample classification, drug sensitivity prediction, replication of omics response and prediction of biological and phenotypic response to compound treatment. This model combines textual, tabular, and knowledge graph-derived representations of biological experiments to provide insights into molecular-level biological processes. We demonstrate that P3GPT has developed an intuition for the interactions between compounds, pathologies, and gene regulation in the context of multiple species and tissues. In these areas, it outperforms existing LLMs and we highlight its utility in diverse case studies. P3GPT is a general model that may be used as a target identification tool, aging clock, digital laboratory, and scientific assistant. The model is intended as a community resource available open source as well as via a Discord server.
- Open Access
- 30 May 2024
- Published by Springer Nature in Translational Psychiatry
- Vol. 14 (1) , 1-5
Psychogenic Aging: A Novel Prospect to Integrate Psychobiological Hallmarks of Aging
Psychological factors are amongst the most robust predictors of healthspan and longevity, yet are rarely incorporated into scientific and medical frameworks of aging. The prospect of characterizing and integrating the psychological influences of aging is therefore an unmet step for the advancement of geroscience. Psychogenic Aging research is an emerging branch of biogerontology that aims to address this gap by investigating the impact of psychological factors on human longevity. It is an interdisciplinary field that integrates complex psychological, neurological, and molecular relationships that can be best understood with precision medicine methodologies. This perspective argues that psychogenic aging should be considered an integral component of the Hallmarks of Aging framework, opening the doors for future biopsychosocial integration in longevity research. By providing a unique perspective on frequently overlooked aspects of organismal aging, psychogenic aging offers new insights and targets for anti-aging therapeutics on individual and societal levels that can significantly benefit the scientific and medical communities.
- 30 May 2024
- Published by Springer Nature in Translational Psychiatry
- Vol. 14 (1) , 1-5
Open AccessPsychogenic Aging: A Novel Prospect to Integrate Psychobiological Hallmarks of Aging
Psychological factors are amongst the most robust predictors of healthspan and longevity, yet are rarely incorporated into scientific and medical frameworks of aging. The prospect of characterizing and integrating the psychological influences of aging is therefore an unmet step for the advancement of geroscience. Psychogenic Aging research is an emerging branch of biogerontology that aims to address this gap by investigating the impact of psychological factors on human longevity. It is an interdisciplinary field that integrates complex psychological, neurological, and molecular relationships that can be best understood with precision medicine methodologies. This perspective argues that psychogenic aging should be considered an integral component of the Hallmarks of Aging framework, opening the doors for future biopsychosocial integration in longevity research. By providing a unique perspective on frequently overlooked aspects of organismal aging, psychogenic aging offers new insights and targets for anti-aging therapeutics on individual and societal levels that can significantly benefit the scientific and medical communities.
- Open Access
- 13 April 2024
- Published by Elsevier in Experimental Gerontology
- Vol. 190, 112421
Higher blood biochemistry-based biological age developed by advanced deep learning techniques is associated with frailty in geriatric rehabilitation inpatients: RESORT
- 13 April 2024
- Published by Elsevier in Experimental Gerontology
- Vol. 190, 112421
Open AccessHigher blood biochemistry-based biological age developed by advanced deep learning techniques is associated with frailty in geriatric rehabilitation inpatients: RESORT
- Open Access
- 19 May 2023
- Published by Elsevier in Ageing Research Reviews
- Vol. 88, 101956
Stress, diet, exercise: Common environmental factors and their impact on epigenetic age
- 19 May 2023
- Published by Elsevier in Ageing Research Reviews
- Vol. 88, 101956
Open AccessStress, diet, exercise: Common environmental factors and their impact on epigenetic age