I am a PhD candidate at Yale University and an expert in Computational Biomedical technologies with over a decade of experience embedding Data Science and Artificial Intelligence to the Biomedical space.

My current research focus is on human aging and on the side I advice venture capital funds on which longevity and geroscience companies to invest in while also consulting companies at the intersection of Bioinformatics and Longevity!

As a PhD student in Computational Biology and Bioinformatics at Yale University, I am passionate about solving the mysteries of aging and extending healthy lifespans. I am developing machine learning and deep learning tools to analyze multi-omic and multi-modal data, and to answer questions such as what biological systems drive aging, how can we measure them, and can we reverse them. I am also a Yale Cancer Biology Training program fellow, where I learn about the practical clinical issues of oncology and prepare to lead translational research on teams that include both basic scientists and clinicians.

In addition to my academic research, I am a Scientific Advisor and Venture Consultant at Longevitytech.fund, a venture capital firm that focuses on investing in companies that are innovating in the fields of AI, digital health, medical devices, and diagnostics. I provide expert advice on their potential investment opportunities, and also helped them raise their second fund by building strategies for future investments. Beyond this, I have 9 years of experience in applying data science and artificial intelligence to the biomedical space, as a scientist, engineer, product manager, team builder, academician, and entrepreneur. I have worked on projects ranging from cancer prediction to metabolic regulation, and have published in prestigious journals such as Nature. I have also received multiple honors and awards, such as the Gruber Science Fellowship, Impetus Aging Grant and more.

Experience

Aug 2020 – Present | New Haven, CT
Trainee under Dr. Morgan Levine and Dr. Albert Higgins Chen. Finding latent representations of human aging by building ML models on multi-omic data.
Developed Systems Age: ML model for predicting aging in 11 different organs of humans using multi-omic data from a single blood draw. Patent filed.
Developed geodesic clustering algorithm for integrating omics data for target discovery - Rotation with Dr. Smita Krishnaswamy.
Feb 2022 - Present | Remote

LTF focuses on investing in companies extending healthy lifespans at Pre-seed to Series A stage.
I provide expert advice on their potential investment opportunities in AI technologies, digital health, medical devices, and diagnostics. I am also helping them raise their second fund by building strategies for potential investments in the future.
Oct 2022 - May 2023 | Remote

Cambrian BioPharma is building therapeutics to lengthen healthspan, the period of life spent in good health. I advised them on their clinical trial biomarker strategy as well as consumer facing product biomarker strategy.
Aug 2021 - May 2022 | New Haven, CT

Yale Accelerator for Innovation Development (Y-AID) fellowship is offered by Yale Ventures formerly known as Yale Office of Cooperative Research (OCR). Fellows are involved in actively evaluating and enabling start-ups under OCR’s investment portfolio.
May 2015 – Aug 2019 | Delhi, India

• Product Manager for Polly, an AI driven target discovery platform.
– Responsible for managing and planning the algorithm development behind the product.
– Built over 20 different omic data analysis workflows for metabolomics, transcriptomics, genomics, integrative omics and more.
• Product Development Lead for El-MAVEN, an ML enabled metabolomics data processing engine.
– Added multiple new ML algorithms for better metabolomic data detection and quantification.
• Data Scientist for developing bioinformatics pipeline for CRISPR Tx containing 6 different applications of note two were:
– Guido: CRISPR guide RNA prediction based on hypothesized on-target and off-target activity. Data engineered the pipeline for cloud computation using 10 different AWS services.
– Tsunami, an application to mathematically detect the effectiveness of mutations induced by a CRISPR Cas9 and guide pair.
• Data Scientist for International Prostate Cancer Dream Challenge.
– Improved prediction results for survival, risk and discontinuation of a medication for patients in a lab trial through mathematical modeling & ML based predictive analysis on clinical data.
– Placed second globally.

Notable Projects

SYMPHONYAge

A single blood methylation test to quantify aging heterogeneity across 11 physiological systems

SYMPHONYAge has been patented and is currently being licensed out to multiple vendors who provide at-home aging tests

Key components of Systems Age:

Systems Age leverages a combination of supervised and unsupervised machine learning approaches to find latent dimensions of organ specific aging. Its 5 step process which uses a mixture of classical machine learning methods and more novel neural network approaches is able to model 11 different organ aging scores from 450K methylation features and 20K samples.
Systems age is a first of its kind epigentic biomarker which can untangle organ level aging from just one single blood draw. This allows systems age to not only give more insight into organ aging but also makes it a more precise biomarker than it whole body aging epigenetic biomarker counterparts
Having 11 different organ level scores from a single blood draw allows for categorisation of individuals into ageotypes that have increased pre-disposition to specific aging related diseases and conditions.

Publication

Talk

At-home test

Aging DB

Using publicly available data we built a platform to understand which anti-aging interventions were modifying aging biomarkers the most and in-turn which aging biomarkers were responding the most to interventions.

Publication

Talk

AIOmic and DMDB

AIOmic stands for AI enabled Integrative Omics pipeline and was specially built for Drug Metabolism Database (DMDB) to integrate and analyse data from 500 drugs in 50 cell lines over 5 years.

Very often “Integration of Omics data” refers to generation of multiple Omics data and viewing them in parallel. AIOmic on the other hand integrates all 4 of its Omic data to view on the same KEGG Network.
One of the biggest challenges in large multi-omic data sets is to find succinct biological insights by manually scavenging the data. AIOmic automates this by using publicly available information to find relevant insights.
DMDB with its 4 Omics datasets and integration gives a holistic and multi-pronged view of metabolism at different levels of the cellular processes.

Publication

Talk

Start-up pitch

Publications

2023

Geroscience-Centric Perspective for Geriatric Psychiatry: integrating aging biology with geriatric mental health research
Authors: Breno S Diniz, Johanna Seitz-Holland, Raghav Sehgal, Jessica Kasamoto, Albert T Higgins-Chen, Eric Lenze
More than bad luck: cancer and aging are linked to replication-driven changes to the epigenome.
Authors: Christopher J Minteer, Kyra Thrush, John Gonzalez, Peter Niimi, Mariya Rozenblit, Joel Rozowsky, Jason Liu, Mor Frank, Thomas McCabe, Raghav Sehgal...
Systems Age: A single blood methylation test to quantify aging heterogeneity across 11 physiological systems.
Authors: Raghav Sehgal, Yaroslav Markov, Chenxi Qin, Margarita Meer, Courtney Hadley, Aladdin H Shadyab, Ramon Casanova...

2022

System specific aging scores: a state of the art aging clock built using aging scores from different bodily functions
Authors: Raghav Sehgal, Albert Higgins-Chen, Margarita Meer, Morgan Levine
Pyruvate kinase M1 suppresses development and progression of prostate adenocarcinoma
Authors: Shawn M Davidson, Daniel R Schmidt, Julia E Heyman, James P O'Brien, Amy C Liu, William J Israelsen, Talya L Dayton, Raghav Sehgal, Roderick T Bronson...
Comprehensive analysis of metabolic isozyme targets in cancer
Authors: Michal Marczyk, Vignesh Gunasekharan, David Casadevall, Tao Qing, Julia Foldi, Raghav Sehgal, Naing Lin Shan
Abstract P5-17-01: Targeting Acetyl-CoA carboxylase in pre-clinical breast cancer models
Authors: Julia Foldi, Michal Marczyk, Vignesh Gunasekharan, Tao Qing, Raghav Sehgal, Naing Lin Shan...

2021

Aging Biomarkers for Clinical Trials and Drug Discovery
Authors: Margarita Meer, Raghav Sehgal, Morgan Levine
Deep Learning Methods Capture Non-Linear Brain Aging Patterns Underlying Alzheimer’s Disease and Resilience
Authors: Kyra Thrush, Albert Higgins-Chen, Yaroslav Markov, Raghav Sehgal, Morgan Levine
Systems aging clock: A novel epigenetic aging clock modeled from organ & bodily function based mortality indices
Authors: Raghav Sehgal, Morgan Levine

2020

Multi-tissue acceleration of the mitochondrial phosphoenolpyruvate cycle improves whole-body metabolic health
Authors: Abudukadier Abulizi, Rebecca L Cardone, Romana Stark, Sophie L Lewandowski, Xiaojian Zhao, Joelle Hillion, Lingjun Ma, Raghav Sehgal, Tiago C Alves...
L-Glutamine Mass Isotopomers Map Hepatic Mitochondrial Metabolism without Tracer Interference
Authors: Stephan Siebel, Rebecca L Cardone, Abudukadier Abulizi, Raaisa Raaisa, Richard M Williams, Raghav Sehgal, GINA BUTRICO, Gary Cline...

2019

El-MAVEN: a fast, robust, and user-friendly mass spectrometry data processing engine for metabolomics
Authors: Shubhra Agrawal, Sahil Kumar, Raghav Sehgal, Sabu George, Rishabh Gupta, Surbhi Poddar, Abhishek Jha, Swetabh Pathak
O‐GlcNAc signaling orchestrates metabolic adaptation to prolonged fasting
Authors: Mindian Li, Jiayu Liu, Raghav Sehgal, Jing Wu, Pei Zhang, Weiping Han, Abhishek Jha, Xiaoyong Yang

2018

Electrophilic properties of itaconate and derivatives regulate the IκBζ–ATF3 inflammatory axis
Authors: Monika Bambouskova, Laurent Gorvel, Vicky Lampropoulou, Alexey Sergushichev, Abdurrahman Keskin, Andrea Santeford, Rajendra S Apte, Raghav Sehgal...

2017

Prediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data
Authors: Justin Guinney, Tao Wang, Teemu D Laajala, Kimberly Kanigel Winner, J Christopher Bare, Gopal Peddinti, Antti Airola, Tapio Pahikkala, Raghav Sehgal, Fatemeh Seyednasrollah