🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Artificial intelligence and the shape of reality. psychologytoday.com/us/blog/the-di…

The most dangerous assumption in science is that data alone is enough. What we see defines what we understand.

The beauty of biology is in its messiness. The beauty of informatics is in helping us see patterns within that chaos —without flattening its complexity.

We're excited to launch a new Rowan workflow for subscribers today—macroscopic pKa prediction! We use a retrained Uni-pKa-based model ("Starling") to quickly predict per-microstate free energies, and use these values to compute pKa, pI, logD, & blood–brain-barrier permeability:

We teach machines to read petabytes. But we still haven’t figured out how to help humans read a figure.

I’ve always believed the most powerful tools in science are the ones that disappear. When interaction becomes intuition, and data becomes insight. That’s when we’re doing real work.

Agreed.

More use of AlphaFold2 ensembles: 557 peptides, 80 poses each, with ensemble RMSD < 2.5 Å, RMSF < 1.5 Å vs NMR. Interestingly, MSA depth? Largely irrelevant. Sequence alone is hinting at dynamics, not just shape.

95% of meaningful progress happens behind closed doors, long before it becomes visible to the world. The ones who stay consistent without applause end up defining the future.

35 teams, 10k structures later ... not one model could predict how a 6-aa linker positions two rigid domains. CASP16’s SAXS + RDC benchmark exposes the “dynamics gap” left by AlphaFold-era models — and calls for continuous SE(3) ensembles. Which next-gen BioAI will finally

Biology is messy, chaotic, unpredictable. AI brings structure, prediction, and possibility. The intersection between the two is where the next generation of medicine will be born.

An insightful day at our London office yesterday! We were thrilled to host Prof Sir Mene Pangalos FRS, a distinguished member of our Scientific Advisory Board. Our Chief Scientific Officer, Miles Congreve, led a fascinating fireside chat with Sir Mene, diving into crucial topics like selecting the

We’re not short on data. We’re short on systems that make complexity understandable. The next frontier isn’t scale. It’s clarity.

AI agents for autonomous discovery still surprise me. El Agente turns plain-English prompts into fully debugged ORCA workflows, auto-recovers from runtime errors, and exports an auditable Jupyter log. It scored 88%+ on six university-level tasks.

⚕️🧪Delighted to share extended lab validation results for our Google DeepMind Google AI AI co-scientist! Great work from our collaborators Stanford Medicine validating novel insights in liver fibrosis, a condition that affects millions with few effective therapies. More details from

One year ago today, we published the breakthrough AI model #AlphaFold 3 together with @GoogleDeepmind. AlphaFold 3 allows researchers to model the structures and interactions of all of life’s molecules with unprecedented accuracy. With the ability to model proteins, DNA, RNA, and

The future of medicine isn’t just in molecules it’s in models. As AI learns to reason through biological complexity, we shift from describing life to debugging it.

Most infrastructure isn’t flashy. It’s silent, robust, and thankless until something breaks. That’s when you realize who built carefully, and who just built.

The most important work feels boring to watch. It’s hard, slow, and rarely optimized for social media. But it’s the only work that lasts.

We’re entering an era where AI isn’t just reacting to data. It’s starting to navigate systems. From biology to markets it’s not a chatbot revolution. It’s a systems revolution.