New thesis offers dual frameworks for gene regulatory network inference

A new thesis introduces two frameworks for inferring gene regulatory networks (GRNs). The first, PMF-GRN, uses probabilistic graphical models and variational inference to provide uncertainty-aware estimates and principled model selection. The second, GLM-Prior, fine-tunes the Nucleotide Transformer to predict TF-target gene interactions directly from nucleotide sequences, generalizing across species. These methods aim to overcome limitations in current GRN reconstruction, such as heuristic model selection and the difficulty of transferring prior knowledge. AI

IMPACT Introduces novel computational frameworks for biological network inference, potentially advancing research in genomics and systems biology.

RANK_REASON The item is a research paper submitted to arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv stat.ML →

• arXiv
• Claudia Skok Gibbs
• GLM-Prior
• human
• Nucleotide Transformer
• PMF-GRN
• Saccharomyces cerevisiae

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →