Training mRNA Language Models Across 25 Species for $165

Training mRNA Language Models Across 25 Species for $165 Training mRNA Language Models Across 25 Species for $165 Team Article Published March 31, 2026 Upvote 30 Maziyar Panahi MaziyarPanahi OpenMed Part II: Building the Pipeline, From Structure Prediction to Codon Optimization By OpenMed, Open-Source Agentic AI for Healthcare & Life Sciences TL;DR : We built an end-to-end protein AI pipeline covering structure prediction, sequence design, and codon optimization. After comparing multiple transformer architectures for codon-level language modeling, CodonRoBERTa-large-v2 emerged as the clear winner with a perplexity of 4.10 and a Spearman CAI correlation of 0.40, significantly outperforming ModernBERT.

This ModelRelease is relevant to the technology intelligence record because it involves Perplexity, Meta. The source article should remain the factual reference for follow-up coverage.

• Training mRNA Language Models Across 25 Species for $165 Team Article Published March 31, 2026 Upvote 30 Maziyar Panahi MaziyarPanahi OpenMed Part II: Building the Pipeline, From Structure Prediction to Codon Optimization By OpenMed, Open-Source Agentic AI for Healthcare & Life Sciences TL;DR : We built an end-to-end protein AI pipeline covering structure prediction, sequence design, and codon optimization.
• After comparing multiple transformer architectures for codon-level language modeling, CodonRoBERTa-large-v2 emerged as the clear winner with a perplexity of 4.10 and a Spearman CAI correlation of 0.40, significantly outperforming ModernBERT.
• We then scaled to 25 species, trained 4 production models in 55 GPU-hours, and built a species-conditioned system that no other open-source project offers.
• Complete results, architectural decisions, and runnable code below.
• Contents What We Built The Architecture Exploration The Pipeline 3.1 Protein Folding 3.2 Sequence Design 3.3 mRNA Optimization Scaling to Multi-Species The End-to-End Workflow Where This Stands and What's Next References Imagine going from a therapeutic protein concept to a synthesis-ready, codon-optimized DNA sequence in an afternoon.
• That is the pipeline OpenMed set out to build, and this post documents the process from start to finish.