@article{20816,
  abstract     = {Background: DNA methylation (DNAm) can regulate gene expression, and its genome-wide patterns (epigenetic scores or EpiScores) can act as biomarkers for complex traits. The relative stability of methylation profiles may enable better assessment of chronic exposures compared to single time-point protein measures. We present the first large-scale epigenetic study of the highly-abundant serum proteome measured via ultra-high throughput mass spectrometry in 14,671 samples from the Generation Scotland cohort. We further demonstrate the first large-scale comparison of protein EpiScores and their respective proteins as predictors of incident cardiovascular disease.

Results: Marginal epigenome-wide association models, adjusting for age, sex, measurement batch, estimated white cell proportions, BMI, smoking and methylation principal components, reveal 15,855 significant CpG – protein associations across 125 of 133 proteins PBonferroni < 2.71 × 10-10. Bayesian epigenome-wide association studies of the same 133 proteins reveal 697 CpG-Protein associations (posterior inclusion probability > 0.95). 112 protein EpiScores correlate significantly with their respective protein in a holdout test-set. Of these, sixteen associate significantly with incident all-cause cardiovascular disease (Nevents=191) compared to one measured protein.

Conclusions: We highlight a complex interplay between the blood-based methylome and proteome. Importantly, we show that protein EpiScores correlate with measured proteins and demonstrate that the, as-yet understudied, high-abundance proteome may yield clinically relevant biomarkers. The protein EpiScores demonstrate more significant associations with cardiovascular disease than directly measured proteins, suggesting their potential as clinical biomarkers for monitoring or predicting disease risk. We suggest that biomarker development could be enhanced by the consideration of protein EpiScores alongside measured proteins.},
  author       = {Robertson, Josephine A. and Bajzik, Jakub and Vernardis, Spyros and Chybowska, Aleksandra D. and Mccartney, Daniel L. and Grauslys, Arturas and Mur, Jure and Smith, Hannah M. and Campbell, Archie and Drake, Camilla and Grant, Hannah and Pearce, Jamie and Russ, Tom C. and Adkin, Poppy and White, Matthew and Brigden, Charles and Messner, Christoph B. and Porteous, David J. and Hayward, Caroline and Cox, Simon R. and Zelezniak, Aleksej and Ralser, Markus and Robinson, Matthew Richard and Marioni, Riccardo E.},
  issn         = {1474-760X},
  journal      = {Genome Biology},
  publisher    = {Springer Nature},
  title        = {{Methylome-wide association studies and epigenetic biomarker development for 133 mass spectrometry-assessed circulating proteins in 14,671 Generation Scotland participants}},
  doi          = {10.1186/s13059-025-03892-0},
  volume       = {26},
  year         = {2025},
}

@article{11587,
  abstract     = {Background: Accurate and comprehensive annotation of transcript sequences is essential for transcript quantification and differential gene and transcript expression analysis. Single-molecule long-read sequencing technologies provide improved integrity of transcript structures including alternative splicing, and transcription start and polyadenylation sites. However, accuracy is significantly affected by sequencing errors, mRNA degradation, or incomplete cDNA synthesis.
Results: We present a new and comprehensive Arabidopsis thaliana Reference Transcript Dataset 3 (AtRTD3). AtRTD3 contains over 169,000 transcripts—twice that of the best current Arabidopsis transcriptome and including over 1500 novel genes. Seventy-eight percent of transcripts are from Iso-seq with accurately defined splice junctions and transcription start and end sites. We develop novel methods to determine splice junctions and transcription start and end sites accurately. Mismatch profiles around splice junctions provide a powerful feature to distinguish correct splice junctions and remove false splice junctions. Stratified approaches identify high-confidence transcription start and end sites and remove fragmentary transcripts due to degradation. AtRTD3 is a major improvement over existing transcriptomes as demonstrated by analysis of an Arabidopsis cold response RNA-seq time-series. AtRTD3 provides higher resolution of transcript expression profiling and identifies cold-induced differential transcription start and polyadenylation site usage.
Conclusions: AtRTD3 is the most comprehensive Arabidopsis transcriptome currently. It improves the precision of differential gene and transcript expression, differential alternative splicing, and transcription start/end site usage analysis from RNA-seq data. The novel methods for identifying accurate splice junctions and transcription start/end sites are widely applicable and will improve single-molecule sequencing analysis from any species.},
  author       = {Zhang, Runxuan and Kuo, Richard and Coulter, Max and Calixto, Cristiane P.G. and Entizne, Juan Carlos and Guo, Wenbin and Marquez, Yamile and Milne, Linda and Riegler, Stefan and Matsui, Akihiro and Tanaka, Maho and Harvey, Sarah and Gao, Yubang and Wießner-Kroh, Theresa and Paniagua, Alejandro and Crespi, Martin and Denby, Katherine and Hur, Asa Ben and Huq, Enamul and Jantsch, Michael and Jarmolowski, Artur and Koester, Tino and Laubinger, Sascha and Li, Qingshun Quinn and Gu, Lianfeng and Seki, Motoaki and Staiger, Dorothee and Sunkar, Ramanjulu and Szweykowska-Kulinska, Zofia and Tu, Shih Long and Wachter, Andreas and Waugh, Robbie and Xiong, Liming and Zhang, Xiao Ning and Conesa, Ana and Reddy, Anireddy S.N. and Barta, Andrea and Kalyna, Maria and Brown, John W.S.},
  issn         = {1474-760X},
  journal      = {Genome Biology},
  publisher    = {BioMed Central},
  title        = {{A high-resolution single-molecule sequencing-based Arabidopsis transcriptome using novel methods of Iso-seq analysis}},
  doi          = {10.1186/s13059-022-02711-0},
  volume       = {23},
  year         = {2022},
}

@article{10702,
  abstract     = {Background: Blood-based markers of cognitive functioning might provide an accessible way to track neurodegeneration years prior to clinical manifestation of cognitive impairment and dementia. Results: Using blood-based epigenome-wide analyses of general cognitive function, we show that individual differences in DNA methylation (DNAm) explain 35.0% of the variance in general cognitive function (g). A DNAm predictor explains ~4% of the variance, independently of a polygenic score, in two external cohorts. It also associates with circulating levels of neurology- and inflammation-related proteins, global brain imaging metrics, and regional cortical volumes. Conclusions: As sample sizes increase, the ability to assess cognitive function from DNAm data may be informative in settings where cognitive testing is unreliable or unavailable.},
  author       = {McCartney, Daniel L. and Hillary, Robert F. and Conole, Eleanor L.S. and Banos, Daniel Trejo and Gadd, Danni A. and Walker, Rosie M. and Nangle, Cliff and Flaig, Robin and Campbell, Archie and Murray, Alison D. and Maniega, Susana Muñoz and Valdés-Hernández, María Del C. and Harris, Mathew A. and Bastin, Mark E. and Wardlaw, Joanna M. and Harris, Sarah E. and Porteous, David J. and Tucker-Drob, Elliot M. and McIntosh, Andrew M. and Evans, Kathryn L. and Deary, Ian J. and Cox, Simon R. and Robinson, Matthew Richard and Marioni, Riccardo E.},
  issn         = {1474-760X},
  journal      = {Genome Biology},
  number       = {1},
  publisher    = {Springer Nature},
  title        = {{Blood-based epigenome-wide analyses of cognitive abilities}},
  doi          = {10.1186/s13059-021-02596-5},
  volume       = {23},
  year         = {2022},
}