Jun Cheng

AlphaGenome paper and models are out today! nature.com/articles/s4158…. We have seen great community engagement since we released the API. We hope to open more use cases with the model weights! github.com/google-deepmin… We updated the supplementary note with some very interesting case studies. I encourage everyone using AlphaGenome for non-coding variant interpretation to read it. It was a huge team effort, I’m very proud of all of our co-authors @googledeepmind!

@Nature's @ewencallaway writes about how hackathons using AlphaGenome are solving rare disease mysteries. "The event helped diagnose someone with a rare condition called Rothmund–Thomson syndrome... [which] affects eyes, skin and other organ systems." Discoveries like this are why we @GoogleDeepMind believe advancing science is one of the most meaningful motivations for developing AI. Read more: nature.com/articles/d4158…

@anshulkundaje Thanks Anshul, your insights moved the field forward!

@s6juncheng Congrats Jun! Amazing work

AlphaGenome paper and models are out today! nature.com/articles/s4158…. We have seen great community engagement since we released the API. We hope to open more use cases with the model weights! github.com/google-deepmin… We updated the supplementary note with some very interesting case studies. I encourage everyone using AlphaGenome for non-coding variant interpretation to read it. It was a huge team effort, I’m very proud of all of our co-authors @googledeepmind!

@pkoo562 Thanks Peter!

@s6juncheng Congrats Jun and team!

This is a great idea, congratulations!

@anshulkundaje Also the brilliant engineers who optimize data pipeline and TPU/GPU utilizations should not be underestimated.

Also worth noting that many of the brilliant scientists in this team & others have spent years building intuition with specialized lightweight models (on splicing, TF binding etc). 13/

I'm only partially kidding cuz he definitely is forcing me to modify some of my slides 😂. But I did want to express some thoughts on the lightweight specialized single task (ST) models vs kitchensink multi task (MT) model paradigms a bit. 2/

@deAlmeida_BP Thanks!

@s6juncheng Congrats @s6juncheng , great work! It was nice meeting you, keep it up

Excited to share #AlphaGenome, a start of our AlphaGenome named journey to decipher the regulatory genome! The model matches or exceeds top-performing external models on 24 out of 26 variant evaluations, across a wide range of biological modalities.1/6

AlphaGenome model architecture. follows a U-Net-like structure with an Encoder, a central Transformer Tower, and a Decoder. The architecture has inspiration from Borzoi and AlphaFold.

One of the most exciting parts of our #AlphaGenome work is the ability to directly predict splice junctions from sequence and also use it for variant effect prediction. This is enabled by modeling the competition between splice sites and junction supporting reads.4/6

@pkoo562 Thanks Peter, looking forward to seeing how you’d use it!

Congrats @s6juncheng! Looking forward to seeing what it has learned!

Excited to launch our AlphaGenome API goo.gle/3ZPUeFX along with the preprint goo.gle/45AkUyc describing and evaluating our latest DNA sequence model powering the API. Looking forward to seeing how scientists use it! @GoogleDeepMind

@anshulkundaje Thanks Anshul, glad you liked it!

@s6juncheng Congrats Jun! What a leap forward!! 🎉🎉🎉🎉

Happy to introduce AlphaGenome, @GoogleDeepMind's new AI model for genomics. AlphaGenome offers a comprehensive view of the human non-coding genome by predicting the impact of DNA variations. It will deepen our understanding of disease biology and open new avenues of research.

AlphaGenome API github.com/google-deepmin…. Share ideas and feedback in the community forum alphagenomecommunity.com, paper storage.googleapis.com/deepmind-media…. The model source code and weights will also be provided upon final publication.

Having worked on RNA splicing models for years, this is a significant milestone for me. It is a real privilege to work with an extremely talented team. With the new API, I’m excited to see what researchers can find with #AlphaGenome.6/6

We are looking a PhD Student Researcher at Google DeepMind for 2025 summer! Strong publication record and technical skills on machine learning and genomics preferred. Need to be 80% for a few months. Team in London. Looking forward to hear from you!