Join us on the journey toward improving de novo protein sequencing. 👉Explore their progress in our latest blog post: bit.ly/4lircYB ⌨️ Explore our codebase here: bit.ly/43ExRGl 📝 See the paper on Nature Machine Intelligence: bit.ly/3XBeJFh

1/ 🚀 InstaNovo just got a major upgrade. Our Nature Machine Intelligence paper with InstaDeep presents v0.1—but while the paper was under review, we kept building. Now releasing InstaNovo v1.1, with major gains. Blog: bit.ly/4lircYB 🧵

As seen in Nature Machine Intelligence, our multimodal conversational agent, ChatNT, fuses biological sequences and natural language into a shared vocabulary. Hear from research scientist and lead author Bernardo Almeida on our first proof-of-concept for this generalist AI.

📖Learn from our blog: bit.ly/4dRlo5c 👉 Read more in Nature Machine Intelligence: go.nature.com/43ZKvPP

ChatNT can optimise multiple tasks simultaneously, in conversational English. Trained on a dataset spanning 27 biological functions and species, including 600 million DNA tokens and 273 million English tokens, ChatNT is designed to be a useful agent for scientists without coding

🆕 Just dropped: @InstaDeepAI's Alain-Sam Cohen on how DeepPCB uses RL to transform PCB layout featured in Emerj’s AI in Business podcast with Editorial Director Matthew DeMello ✅ Week-long designs done in a day ✅ Engineers freed from repetitive tasks ✅ Real-world enterprise

How can we bridge the gap between powerful biological sequence models and user-friendly conversational interfaces for genomics research?Nature Machine Intelligence InstaDeep "A multimodal conversational agent for DNA, RNA and protein tasks" • While conversational language models have

Introducing ChatNT: The first biological sequence-language model, published in Nature Machine Intelligence ! 🧬🎉 Inspired by vision-language models, ChatNT's architecture combines biological and language foundation models, using Nucleotide Transformer (NT) and Llama to answer questions

A multimodal conversational agent for DNA, RNA and protein tasks Nature Machine Intelligence １．ChatNT is a new conversational AI system that understands DNA, RNA and protein sequences, enabling biologists to solve complex genomics tasks simply by asking questions in English. ２．Unlike

Next Tues (6/17) at 4PM ET, we will have Bora Guloglu and Tom Barrett present "Flexible Antibody Design with Multimodal Bayesian Flow Networks" Paper: biorxiv.org/content/10.110… This will be followed by Brian Hie, who will give an early-career talk on Wed (6/18) at 4PM ET!

Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing １．RefineNovo introduces a curriculum learning framework for non-autoregressive (NAR) peptide sequencing models, tackling instability in CTC-based training. The model significantly

ChatNT has been featured on the front cover of Nature Machine Intelligence! This exciting opportunity allows us to share our proof-of-concept for a generalist genomics AI with a wider community of scientists and researchers around the world. 🎊

We made the cover of Nature Machine Intelligence! 🌱 ChatNT is a Conversational Agent analysing genomics sequences to answer key biological questions, assisting scientists in their work 👩‍🔬 Kudos to Bernardo Almeida, Thomas Pierrot & the InstaDeep research team for this huge milestone!✨

📆 Six months, four publications, one cover. We’re halfway through the year and InstaDeep research is powering ahead with multiple boundary-pushing papers published in the Nature Portfolio! Catch up on the highlights below 🔽

🧬 In March, we published our research for InstaNovo and InstaNovo+ in Nature Machine Intelligence, our diffusion-powered ‘de novo’ peptide sequencing models built to uncover the secrets of the human proteome. bit.ly/3XBeJFh

Going from our first Nature journal paper in late 2024 to four published in the first half of 2025, is mind-blowing! 🤯

New Post on Cancer Vaccines They've yet to become a systematic science despite decades of work, 200 trials + an exciting Moderna PII We Compound are excited about more comprehensive assays (full genome sequencing, more relevant readout, etc), novel target spaces & manuf leaps

HACKATHON ALERT!🔥 The excitement is building as we count down to Deep Learning Indaba𝕏🇿🇦'25, we're absolutely thrilled to officially unveil our highly anticipated Hackathon! Powered by our incredible partners – GroundUp, RadixTrie,Institute of Mine Seismology, InstaDeep & ZINDI

Thrilled to open-source the dataset behind our Nature Machine Intelligence cover paper! 🧬 The ChatNT training data is now open-source on Hugging Face. It's the first large-scale dataset for training conversational agents on biological sequences. A thread on what's inside 👇

✨ CELEBRATING OUR DEEP LEARNING INDABA𝕏🇿🇦 2025 PARTNERS! ✨ As we gear up for an unforgettable Deep Learning Indaba𝕏 South Africa 2025, the excitement is electric, and it’s all made possible by the phenomenal support of our visionary partners. #Indaba𝕏SA2025 #Indaba𝕏SA