SoftAlign: End-to-end protein structures alignment - Introduce SoftAlign, an end-to-end deep learning framework to generate protein structure alignments directly from a pair of 3D coordinate sets - Generate feature embeddings for each residue by processing 3D coordinates and

The 3-decade-old competition that enabled the emergence and evaluate of AlphaFold has run out of NIH funding. The program will be terminated in weeks. This is terminating success. science.org/content/articl…

AI-enabled drug discovery reaches clinical milestone | Nature Medicine nature.com/articles/s4159…

🤝Excited to announce Biomni × Anthropic! AI agents are set to transform how biologists do everyday research. Thanks to this partnership, the platform is now free for scientists worldwide: biomni.stanford.edu Learn more: anthropic.com/customers/biom…

BioEmu generates protein conformational states at scale and predicts their equilibrium probabilities, providing insight into protein domain motions that could inform drug discovery science.org/doi/10.1126/sc… #NBThighlight

Campolina: A Deep Neural Framework for Accurate Segmentation of Nanopore Signals biorxiv.org/content/10.110…

All-Atom Protein Generation with Latent Diffusion Researchers have introduced PLAID, a new paradigm for multi-modal, controllable protein generation. Unlike many existing models that generate only protein backbones, PLAID focuses on creating complete all-atom protein structures,

I’m not sure the linked in crowd is getting my snark about Virtual Cells 😄🫣 linkedin.com/posts/annecarp…

ok so I have got into discussions with several people last month on the term ‘techbio’. My main reason for preferring this term is that it covers so much ground - a techbio can be a tech/AI-first therapeutics company, a platform company or even data management/analytics

Rowan is making molecular modeling actually usable, so I built an MCP server that lets you access their tools through natural conversation.

AlphaFlex: Accuracy Modeling Of Protein Multiple Conformations Via Predicted Flexible Residues A new computational framework, AlphaFlex, has been introduced to address the long-standing challenge of accurately and efficiently modeling multiple protein conformational states, a

We are co-hosting with BioBuilders in Bangalore on 26 July, come hang out!

In collaboration IKP EDEN, Dognosis and BioBuilders, TBT is hosting its first meetup in Bangalore (and India!) on 26 July. Founders, researchers, open-source enthusiasts, VCs this is for you Let’s connect, share, and build. Register here: lu.ma/cz1vbkrk

Bangalore-based 🧬 bio-founders 🛠️ open-source builders 🧪 researchers 🧠 thinkers, investors, and tinkerers . ... this is the event for you! Come hang out on 26 July! Reach out to Vaibhav sai for more details Sign up @ lu.ma/cz1vbkrk

Upcoming TBT events in July 2025: 📍Bengaluru, India: 26 July 530pm RSVP: lu.ma/cz1vbkrk 📍Berkeley, CA, USA: 22 July 530pm RSVP: lu.ma/n3boihud

TT-Boltz is more than 1 minute faster again. The blue protein structure in the image was computed in 3 minutes and 20 seconds on a single Tenstorrent Wormhole processor. At Dev Day, it took 15 minutes, and the goal of 2 minutes seemed so far away. I was hoping for a speedup of

I’d love to hear biologists weigh in on the fundamental question: can you predict the impact of cell perturbations better by studying the natural variation in a population of healthy cells (more data), or by studying cells that have been perturbed genetically or chemically?