Alec Eames@alec_eames
 Boston, MA, USA
Joined March 2016
🧬 Our 2nd preprint today, MethylGPT: A foundation model for the DNA methylome! Our generative pretained transformer-based model: - Trained on 226,555 samples (154,063 after QC & deduplication) - 49,156 curated CpG sites - 7.6B training tokens - Spans 20+ tissue types from 5,281 datasets Key achievements: - Robust methylation prediction (Pearson R=0.929) - Maintains performance with up to 70% missing data - Superior age prediction accuracy vs existing methods - Disease risk prediction across 60 conditions The model captures both genomic and biological context without external supervision. Analysis reveals distinct methylation signatures between young & old samples, with developmental vs aging pathway enrichment. Big thanks to the team: @HAOTIANCUI1 @jinyeop_song @VadimGladyshev @BoWang87 @mahdi_moqri @jpoganik @alec_eames @MarioniGroup @gladyshev_lab @BrighamWomens @harvardmed Read full text here: biorxiv.org/content/10.1101/…
8
37
223
24,063
🧵 1/7 Co-authored by several Consortium members, and leveraging our open-source biomarkers of aging analysis tooling Biolearn, "multi-omic aging genes" were identified as potential biomarkers of aging and targets for epigenetic editing to facilitate cellular rejuvenation.
Multi-omics biomarkers of aging identify functional aging genes a. Correlation of gene expression levels with age at regions with the highest age-associated DNA gain in MESA1, MESA2 and PPMI cohorts b. Correlation of DNAm levels with age at promoter of most age-associated down-regulated genes in MESA1, MESA2, and PPMI cohorts c. DNAm and expression levels of genes with the highest age-associated DNAm (left) and age-associated expression (right) levels for young (<=45 years) and old (>=75 years) participants in MESA1, MESA2, and PPMI cohorts d. DNAm and expression levels of CD248 in MESA1, MESA1 and MESA2 for individuals with top 10% highest DNAm (age-adjusted) at promoter of CD248 in MESA1 compared to others e. Percentage of top “aging transcripts” (Peters et al 2015) that replicates in MESA1, MESA2 and PPMI cohorts compared to the percentage of aging transcripts with corresponding aging CpGs that replicate in each cohort. Read the full preprint for more info.

ALT Multi-omics biomarkers of aging identify functional aging genes a. Correlation of gene expression levels with age at regions with the highest age-associated DNA gain in MESA1, MESA2 and PPMI cohorts b. Correlation of DNAm levels with age at promoter of most age-associated down-regulated genes in MESA1, MESA2, and PPMI cohorts c. DNAm and expression levels of genes with the highest age-associated DNAm (left) and age-associated expression (right) levels for young (<=45 years) and old (>=75 years) participants in MESA1, MESA2, and PPMI cohorts d. DNAm and expression levels of CD248 in MESA1, MESA1 and MESA2 for individuals with top 10% highest DNAm (age-adjusted) at promoter of CD248 in MESA1 compared to others e. Percentage of top “aging transcripts” (Peters et al 2015) that replicates in MESA1, MESA2 and PPMI cohorts compared to the percentage of aging transcripts with corresponding aging CpGs that replicate in each cohort. Read the full preprint for more info.

1
9
29
2,641
Alec Eames retweeted
U-M BME@UMBME
26 Jan 2024
Now a U-M BME BSE alum, Alec Eames led a study on using artificial intelligence (AI) to study cell quiescence (cells that are sleeping or dormant). Eames conducted his undergrad research under Associate Professor Sriram Chandrasekaran. Read more: bme.umich.edu/recent-u-m-bme…

Recent U-M BME Graduate Recognized for Leading Quiescence Research using AI - Biomedical Engineer...

Quiescence has medical applications

bme.umich.edu
2
1
494
Load more