Biomedical subjects

Nilah M Ioannidis

Publications and source records attributed to Nilah M Ioannidis.

3 recordsLinked to original sources

PubMed2026

Base-pair resolution conservation data improves cell type specific sequence-to-expression prediction.

MOTIVATION: Genomic sequence-to-activity models can decipher gene regulatory mechanisms and predict the functional impact of regulatory variants. However, current models struggle to integrate information from sequences outside promoters, especially information from cell type specific regulatory elements. RESULTS: Here, we propose incorporating base-pair resolution evolutionary conservation data into genomic sequence-to-expression predictors. We explore two training strategies-training from scratch or fine-tuning an existing sequence-only model with additional conservation input. We find that in both cases, base-pair resolution conservation data improves cell type specific sequence-to-expression prediction, with training from scratch yielding the greatest benefit. The improvement in cell type specific expression prediction can be attributed in part to the fact that models trained on sequence and conservation data learn to better recognize cell type specific regulatory elements than models trained on sequence alone. AVAILABILITY: Code is available at https://github.com/ni-lab/basenji-phyloP.

Conserved Sequence↗

PubMed2026

Host Genetic Regulation of NLRP3 Inflammasome Cytokines Reveals Immune and Vascular Pathways in HIV.

People with HIV exhibit elevated inflammation and cardiovascular risk despite antiretroviral therapy. To define the genetic architecture of inflammasome-associated inflammation, we performed whole-genome sequencing and quantified plasma IL-6, IL-1β, and IL-18 in 1,000 ART-suppressed PWH from the U.S. Military HIV Natural History Study. Genome-wide analyses identified 14 loci implicating antiviral defense (DDX17, DDX41, EEA1, BCL11A), lipid metabolism (ABCA1, ABCA12, ABCC1, AGMO), and vascular remodeling (KLHL29, RNF213, ETV1). Transcriptome-wide analyses across cardiovascular and immune tissues identified regulatory programs linking interferon signaling, immune activation, and vascular biology to circulating cytokine levels. Mendelian randomization analyses supported causal relationships between inflammasome-associated cytokines and vascular events. Functional integration with genome-wide CRISPR perturbation datasets in primary CD4+ T cells linked cytokine-associated loci to HIV antiviral pathways and cytokine regulatory networks. External validation in cohorts without HIV demonstrated pathway-level convergence despite limited variant-level overlap. These findings define genetic mechanisms linking inflammasome signaling, antiviral defense, and cardiovascular risk.

HIV↗

PubMed2026

GUANinE v1.1 reveals complementarity of supervised and genomic language models.

There has been much debate about the benefits of supervised versus unsupervised learning on genomes. Determining which is better in what contexts requires developing comprehensive benchmarks spanning functional and evolutionary tasks. Importantly, such benchmarks need large sample sizes to enable well-powered ranking of models. Having developed and applied such a benchmark here (GUANinE v1.1), we conclusively demonstrate each paradigm offers key advantages and outperforms on certain tasks. In accordance with training, supervised sequence-to-function models exhibit strong performance when annotating functional states characterized by chromatin accessibility or histone marks, while self-supervised language models outperform on evolutionary conservation. Our hundreds of new evaluations in this v1.1 expansion provide evidence for a tradeoff between input context size and model parameter count for a fixed compute budget, which we depict with new metrics such as kiloparameters/base pair. We also construct two new large-scale variant interpretation tasks in v1.1: cadd-snv measuring deleteriousness, and clinvar-snv measuring clinical pathogenicity. We find that conservation scores, and by extension, genomic language models, predict deleteriousness well, but successfully translating deleteriousness predictions to pathogenicity remains challenging. GUANinE v1.1 newly evaluates dozens of pretrained genomic models, and we conclude that moderate-context hybrid or post-trained language models may define the next era of machine learning in genomics.

Genomics↗