iiinova — where your digital self keeps evolving

Charlie Harris @harrisbio.bsky.social · 14/04/2025

Small personal update: very pleased to be in Singapore next week to present 2 spotlight papers at ICLR 2025 on AI for molecular design!! 🇸🇬 DM me if you want to meet up and chat about AI for bio, drug discovery, science policy or just chat about aviation!!!

010

Charlie Harris @harrisbio.bsky.social · 23/01/2025

I’m very biased but great list of ML for Drug Discovery and resources and blogs by @wpwalters.bsky.social !

040

Charlie Harris @harrisbio.bsky.social · 13/01/2025

16/ What’s clear is that getting data and compute right is essential—not just for breakthroughs in science but for keeping the UK competitive globally. Here’s hoping this plan gets the funding, leadership, and focus it needs to succeed! Happy to chat about any of this. end

010

Charlie Harris @harrisbio.bsky.social · 13/01/2025

15/ Side note: UK universities could supercharge their AI teaching by embracing industry expertise (where the real knowledge is) I teach a course at Cambridge led by a DeepMind researcher, and it’s the most popular in the department.

110

Charlie Harris @harrisbio.bsky.social · 13/01/2025

14/ US universities do this well with CS minors, which foster computational literacy across disciplines. The UK could adopt similar models to produce scientists who are not only domain experts but also skilled at applying AI tools to their fields.

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

13/ The plan has solid ideas on AI skills, but it's not *just* about creating more "AI graduates." We need to train domain experts in the natural sciences to understand and use AI effectively. Almost all scientists should know neural networks as well as they know Excel and stats

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

12/ Another standout: the plan proposes an internal headhunting team within the UK Government to attract top global talent to AISI, the UK Sovereign AI Team, and UK-based companies. Will they also have the power to fast-track visas? From experience, i hope so....

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

11/ The UK Sovereign AI Team could be a great connector of -Public institutions creating scientific datasets -Industrial labs capable of training models on those datasets This sort of collaboration could really unlock breakthroughs in science

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

10/ The plan’s proposal to create a UK Sovereign AI Team is great. This unit will partner with private and academic sectors to back national champions and remove roadblocks in AI, with a strong focus on AI for science and robotics.

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

(Usual reminder that AlphaFold3 was trained for 120k+ GPU hours... this is multiple times more than the whole compute budget of my lab this year)

121

Charlie Harris @harrisbio.bsky.social · 13/01/2025

9/ Another question: who will the AIRR programme directors work for? UKRI? ARIA? Will they be empowered to deploy large amount of compute into highly productive groups at the cutting edge? There is no point in this if it means everyone only gets a few GPU hours each.

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

9/ One question: will these AIRR programme directors also decide how funding is allocated for data generation? For scientific initiatives, compute and data strategies are deeply interconnected. Ideally, the same person would oversee both to ensure alignment.

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

8/ Another standout is the creation of AIRR programme directors—mission-focused individuals with autonomy to strategically allocate compute to high-potential projects. A kind of "Compute Czar" role, this could significantly accelerate progress on big bets in AI for science.

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

7/ However, there’s a risk of duplicating efforts where existing world-class institutions, like the EBI managing the PDBe, are already doing excellent work. Not every problem needs to fit into a National Data Library-sized™ hole. Let’s build on what we already have!

110

Charlie Harris @harrisbio.bsky.social · 13/01/2025

6/ People often say, "Big Pharma has lots of data!"—but much of it is unstructured and sparse, making it unsuitable for deep learning. The plan acknowledges this challenge and recommends creating better infrastructure and incentives to make datasets AI-ready.

110

Charlie Harris @harrisbio.bsky.social · 13/01/2025

5/ That’s why I’m thrilled to see the plan emphasise strategic data initiatives: -Identifying high-impact datasets -Improving data quality -Incentivising researchers and companies to unlock and curate datasets These efforts will make sparse, unstructured datasets better for AI

110

Charlie Harris @harrisbio.bsky.social · 13/01/2025

4/ If we want breakthroughs beyond protein folding, we need to address data gaps across science. AlphaFold was made possible by sustained investment in protein structure data. Similar long term commitments are essential for other fields like materials and climate science.

141

Charlie Harris @harrisbio.bsky.social · 13/01/2025

3/ AI breakthroughs like AlphaFold wouldn’t be possible without decades of work on datasets. e.g., AlphaFold was trained on protein structures from the Protein Data Bank (PDB), which took 50+ years and ~$20 *billion* to create. This is the kind of foundational effort AI needs.

1185

Charlie Harris @harrisbio.bsky.social · 13/01/2025

2/ There’s a lot to like in this plan: - Expanding UK AI compute capacity by 20x - Establishing AI Growth Zones - Building up AI talent pipelines But as a scientist, what excites me most is the report’s focus on **data**—an area we really need to get right.

100

Charlie Harris @harrisbio.bsky.social · 13/01/2025

1/ Just read through the Matt Clifford 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: 🧵

151

Reposted by Charlie Harris

Austin Tripp @austinjtripp.bsky.social · 10/01/2025

A common issue I see in ML, both from ML "experts" and "users", is overly optimistic assumptions. "experts" (people designing algs) usually assume the data is very simple "users" (people using algs) usually assume that algorithms are more robust than they really are Conclusion: always be careful!

1194

Charlie Harris @harrisbio.bsky.social · 11/01/2025

Added NewCo Kerna Labs, a new AI-first mRNA payload design company founded by former Moderna CSO with $6M in seed. Also added new Cradle Bio series B worth $73M

030

Charlie Harris @harrisbio.bsky.social · 09/01/2025

Just added Graph Therapeutics, a new startup in Vienna focusing on precision medicine for inflammation and immunology Founded by former Allcyte team

020

Reposted by Charlie Harris

Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 13/12/2024

📣 Save the dates 📅 We are organizing a Benzon Symposium on "Protein structure prediction and design" with what I think is an amazing set of speakers Meeting will take place in Copenhagen 🇩🇰 on Sept. 1–4, 2025, and abstract submission will open in March (benzon-foundation.dk/benzon-sympo...)

Flyer for a Benzon Symposium on Protein structure prediction and design in biology and pharmacology (Sept. 1–4, 2025). Speakers include: Gabriel Rocklin, Birte Höcker, Amy Keating, Tanja Kortemme, Bruno Correia, Sarel Fleishman, Ashutosh Chilkoti, Minkyung Baek, Noelia Ferruz, James Fraser, Alan Moses, Susan Marqusee, Ben Lehner, Mohammed AlQuraishi, Dek Woolfson, Gustav Oberdorfer, Hannah Wayment-Steele, Ora Schueler-Furman, Jenifer Listgarten, Alexander Rives, & Max Bonomi.

19230

Charlie Harris @harrisbio.bsky.social · 10/12/2024

Extremely pleased to announce that after *checks notes* 2 years, our paper on Structure-based Drug Design with diffusion models has been published in Nature Computational Science (@natcomputsci.bsky.social)!! Thanks a lot to the great co-authors! Esp @rne.bsky.social & Yuanqi Du.

nature.com

Structure-based drug design with equivariant diffusion models - Nature Computational Science

This work applies diffusion models to conditional molecule generation and shows how they can be used to tackle various structure-based drug design problems

1393

Charlie Harris @harrisbio.bsky.social · 04/12/2024

How to come SOTA on protein-ligand binding…. Use Vina (and nothing better) on a single starting conformer Works every time;)

020

Charlie Harris @harrisbio.bsky.social · 04/12/2024

As always, please do reach out if you think any company should be added. :) And thanks to those who have already done do! (Too many to tag unfortunately.)

010

Charlie Harris @harrisbio.bsky.social · 04/12/2024

- 301.ai (Protein Design) - ReticularAI (Protein design) - @deepgenomics.bsky.social (RNA Therapies) -Scala Biodesign (Protein Design) -Protai (Protein design) - Immunai (Antibodies) -Mana Bio (Drug Delivery) -Converge Bio (SaaS) -@popvax.com (Vaccines) -TernaryTx (Glues)

110

Charlie Harris @harrisbio.bsky.social · 04/12/2024

🚨I have updated the TechBio Company Database with a bunch of new companies! Find it here: tinyurl.com/techbiodatabase New ones are: - Enveda Biosciences (Natural Products) - Cure_51 (Personalised Medicine) - Antiverse (Antibodies) - Tamarind Bio (SaaS) - Biorelate (Target ID) cont.

1120

Charlie Harris @harrisbio.bsky.social · 03/12/2024

Unless I missed something - they moved to an highly permissive license so you can?

110

Reposted by Charlie Harris

Arne Elofsson @handle.invalid · 03/12/2024

AF3 BEST METHOD followed by cluspro but also some conversion errors

22210

Charlie Harris @harrisbio.bsky.social · 03/12/2024

In other words, we are still really bad at structure prediction UNLESS we have very rich sequence information from which to infer spatial contacts (?) Same applies to ligand binding obviously

110

Charlie Harris @harrisbio.bsky.social · 03/12/2024

Was very fortunate to be invited to give a talk on AI for Drug Discovery at the (very nice) British Ambassador's Residence in Rome last week! Thanks to the Foreign Office for the invitation!

070

Reposted by Charlie Harris

Philippe Schwaller @pschwllr.bsky.social · 02/12/2024

We are hiring (resharing appreciated)! Given recent successful grant applications (I got my SNSF Starting Grant 🚀), we are extending the LIAC team with multiple openings (PhD/postdoc) for 2025. Apply now (deadline: December 20th) by filling in this form: forms.fillout.com/t/eq5ADAw3kkus. #ChemSky

610271

Reposted by Charlie Harris

Brady Johnston @bradyajohnston.bsky.social · 02/12/2024

More material tests, this time extra squishy. MD trajectory that shows an aspirin ligand coming out of hibernation for spring (undbinding) #b3d #MolecularNodes #GeometryNodes #SciArt

37410

Charlie Harris @harrisbio.bsky.social · 02/12/2024

Actually a bit sad that I have never, and probably will never, attend CASP:( (unless I get a lot of spare time and funding) So important for driving the revolution in AI for structural biology that’s still taking place right now!

020

Reposted by Charlie Harris

Torsten Schwede @torstenschwede.bsky.social · 02/12/2024

Assessors’ conclusions of the 3D category (individual protein chains) of #CASP16 🧪

Conclusions of assessment of 3D category

02511

Charlie Harris @harrisbio.bsky.social · 21/11/2024

You can also break down by geography - I'd had many people say this is really useful for when it comes to applying for jobs.

010

Charlie Harris @harrisbio.bsky.social · 21/11/2024

You can also break down all companies by nice. For example here are all the ones pursuing 'small molecules'

120

Charlie Harris @harrisbio.bsky.social · 21/11/2024

Please share to make more people aware and reach out for any feedback/additions (I have added many suggestions even if I haven't got around to replying to your email!) The database is in a Notion database to allow for easy visualisation and querying.

130

Charlie Harris @harrisbio.bsky.social · 21/11/2024

Now I can share external links without the posts being down regulated - I thought it would share this again!:) I have compiled a list of now 100+ companies in the 'TechBio' space into a fully open database for the community. Find here and please share if you like open.substack.com/pub/harrisbi...

2256

Reposted by Charlie Harris

Chaitanya K. Joshi @chaitjo.bsky.social · 21/11/2024

Random thought: Did the DL x proteins academic research community sort of move on from antibody design to enzyme design? Everyone following the trend? Some of the discourse around antibodies may make it seem like de novo design given any target is ‘solved’, but this is not true as far as I know…

2111