We are excited to share that Nanil will be attending the Alzheimer’s Association International Conference (AAIC) 2025 in Toronto this July. As the world’s largest forum for dementia research, AAIC is an incredible opportunity to connect with leading scientists, clinicians, and innovators who share our passion for advancing dementia research and care. We are especially looking forward to engaging with new discoveries in biomarker science and therapeutic development, areas close to our mission at Nanil. It’s always inspiring to be part of a community pushing the boundaries of what's possible in neurodegeneration, and we can’t wait to be there in person this year. See you in Toronto!

Emerging generative models for biology focus on DNA, non-coding RNA, or proteins, ignoring information hidden in mRNA. Additionally, in protein engineering and mRNA therapeutics the design of mRNA sequences is still a challenge, lacking a clear framework. Here, we introduce and rigorously evaluate two novel methods: a foundational model for mRNA and a reinforcement learning mRNA design framework built on such a model. codonGPT is the first generative foundational language model trained directly on coding mRNA sequences. To solve the problem of synonymous constraints that are only unique to mRNA, we introduce a novel method of inference-time masking, along with house-keeping genes evaluation. For the first time, we also rigorously demonstrate, that for precise mRNA therapeutics design, reinforcement learning on such a model provides a clear framework for biological optimization. Our study introduces a novel foundational model for mRNA and a new reinforcement learning based paradigm for mRNA sequence design.

• Problem: CNS delivery of biologics is hindered by the BBB. Only a few peptides (e.g., Angiopep-2, TAT) are known to mediate transport, and they suffer from issues like off-target effects, instability, and poor tunability.
  
  

• Gap: Current BBB models focus on small molecules. No model exists for systematically discovering or screening BBB-penetrant peptides/domains in proteins or biologics.
  
  

• Contribution: We present the first transformer-based BBB embedding and scoring model, capable of discovering novel shuttle domains and guiding CNS biologic design.

• 1. The model offers a first-in-class in silico screening tool for BBB shuttle peptides and protein domains

• 2. Uncovers both known and novel motifs associated with transcytosis

• 3. Interpretability reveals biophysically meaningful features (e.g., basic patching, structural motifs)

• 4. Bridges the gap between sequence-level design and CNS-targeted biologics

• 5. Extensible to multi-objective optimization (e.g., stability, immunogenicity)

Nanil Therapeutics was invited to the  Goodwin + KPMG 6th Annual Symposium at the 2025 JP Morgan Healthcare Conference in San Francisco. We had a fantastic time attending the event and learning from our more established peers. The event brought together an inspiring mix of healthcare leaders, innovators, and investors, and offered valuable insights into the future of biotech, medtech, and digital health. From thought-provoking panels to meaningful conversations during the networking sessions, the Symposium was a highlight of the week. We're grateful to Goodwin and KPMG for hosting such a thoughtful and energizing gathering, and we look forward to staying connected with the incredible community that came together in San Francisco.