David Miller
@dmmiller597
machine learning on proteins @UCL + @TheCrick + @Vant_AI previously physics and CAR T-cells @Penn looking for the noumena
🚨 Delighted to share a new preprint: Mapping the aetiological foundations of the heart failure spectrum using human genetics medrxiv.org/content/10.110… A massive collaboration from the @HERMESgenetics Consortium, coordinated by @tomlumbers 🧵A thread on 10 highlights:
Come and join me, @_judewells, @_barneyhill, @jakublala and others in London on July 31st to hear some great flash talks on what’s next in comp bio + drug discovery lu.ma/dw9ijcrm
Presenting La-Proteina! A new model for scalable, all-atom protein design 🧬 Backbone + sequence + side-chains, indexed and unindexed atomistic motif scaffolding, scalable up to 800 residues, and more… A thread 🧵
🚨 Excited to share the first major project of my PhD: BAGEL, a modular, model-agnostic, fully customizable Python framework for programmable protein design 🧬🥯 Code (BAGEL) 💻: github.com/softnanolab/ba… Code (boileroom) ⚙️: github.com/softnanolab/bo… Preprint 📜:…
🚨CALL FOR HELP🚨 Want to help shape the UK Gov’s understanding of how AI is impacting bio? My colleagues in the EngBio team in @SciTechgovuk are conducting a survey to answer exactly that! Only 15 mins to shape UK AI policy + £200 goes to Cancer Research UK/100 replies. Link👇
very exciting!
Really pleased to share what I have been working on for 2 months: 🇬🇧 UK SovAI are today announcing our £8m seed investment into OpenBind - A consortium that will actually make AI for drug discovery great by generating 500k experiment protein-ligand complexes!! Explainer 🧵 (1/n)
Excited to see this announcement from the Government’s SovereignAI unit: funding for the world’s largest dataset of protein interactions, led by a truly world-class group of researchers As @demishassabis says, “This is a brilliant initiative for UK science”
Just published my live map of the london underground! (link below)
1/ Just read through the @matthewclifford AI Action Plan now. Tl;dr: it's great but here are a few things that stood out to me as someone interested in AI for Science and sovereign compute and data capability. A thread: 🧵
1/ Today the Prime Minister published my AI Opportunities Action Plan for the UK and committed to implement all its recommendations. A quick thread on why this is important, what we need to do now - and how you can help
🧬 Out today - our DCM GWAS in @NatureGenet 📍nature.com/articles/s4158… All made possible with friends and collaborators from @HERMESgenetics @AH_AlbertHenry @tomlumbers @drjamesware @MRC_LMS @BHFCoREImperial @ImperialNHLI See 🧵 for the cool science
Delighted to share our dilated cardiomyopathy GWAS from HERMES Consortium as a preprint. A massive team effort involving >1.2m participants from 16 studies, and 100+ colleagues. @AlbertHenry @TomLumbers @JamesWare doi.org/10.1101/2023.0… 🧵below 1/5
Excited to report that we have discovered a new, endogenous molecular clock in unmodified human cells and tissues. It is ticking away right now in almost every cell in your body. Specifically, in a new paper on BioRxiv, we show that RNA editing by the near-ubiquitous ADAR1 in…
Just submitted some designed proteins to @adaptyvbio EGFR binder competition. My strategy was Chai1 optimization on a diverse set of known EGFR binders shown below. Lower 2 are antibody FABs (necitumumab and panitumumab) which are too large for the competition requirements so...
Imagine a dataset where it's the whole of the AlphaFold Database but you can pull-out the domain-like structures avoiding random spaghetti, or get all the domain-domain interactions, or check whether domains match a known structural super-family. That's TED:
TED: The Encyclopedia of Domains now published in @ScienceMagazine discovering and annotating 314 MILLION protein domains in the AlphaFold database. joint work of @CATH_Gene3D and @psipred here at UCL.
📢 Exciting News! 📢 We're launching a monthly lecture series on Generative AI in Drug Discovery hosted by Prof. Michael Bronstein & Prof. Bruno Correia, where researchers will present their latest work. Our inaugural session is 📅 next Friday 📅, by @befcorreia and…
This was a lot of fun, hope it happens again soon!
We hosted an AI in Bio hackathon last weekend in London!! BioHack London was devised to bring together computer scientists, biologists and everyone in between to build at the crossroads of AI and Biology. 🧵 1/9
😶
Here's a 1-minute video showing--in the words of visualization hero @EdwardTufte--the "compared to what" factor for today's amazing @NASAWebb image. Thanks to the @WWTelescope for making this possible, and @ADavidWeigel. I only wish @NASA and @POTUS had shown the image this way!
Happy 10-year anniversary to the greatest fireworks show in history, when San Diego accidentally shot off 7,000 fireworks at once. 🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸
This is the future. Happening now. Sequencing the genome of critically ill patients at the point of care with the diagnosis made as rapidly as <8 hours nejm.org/doi/full/10.10… @NEJM @nanopore @Johngorzynski and colleagues @stanfordmed @stanfordeng @BenedictPaten @ucscgenomics
Therapeutic mRNA for heart failure?! Our own Joel Rurik (@DevBioAcademic) teamed up with @WeissmanLab to make CAR T cells entirely in the body to treat heart disease. Published today on the cover of Science! science.org/doi/10.1126/sc… @CAMBUpenn @PennBGS @ScienceMagazine 1/6
Beautiful piece @erikphoel! erikhoel.substack.com/p/baldwin-in-b…