Reproduce “Helix-mRNA: A Hybrid Foundation Model For Full Sequence mRNA Therapeutics” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Matthew Wood, Mathieu Klop, Maxime Allard
Helix-mRNA models whole mRNA sequences for prediction tasks by reading individual nucleotides and marking codon boundaries. It combines Mamba-2 state-space layers with attention, then refines broad pretraining on human-only data. It accepts up to 12,288 tokens. It leads on four of five coding-region tasks; for 5′-UTR MRL prediction in HepG2 replicate 1, it reports r² 0.845 versus Optimus 5-Prime’s 0.818.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.