Henry Kenlay (@hennesseeeeee) header
Henry Kenlay (@hennesseeeeee) profile picture

MTS @Latent_Labs. Previously @ExscientiaAi, @UniofOxford (@aims_oxford), @Cambridge_Uni. Machine Learning ∩ Biology 🤖🧬

Oxford, England
Joined August 2012
Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)Photo by Henry Kenlay (@hennesseeeeee)
Henry Kenlay retweeted
Today we're launching Latent-Y: the world's first autonomous agent for drug design, lab-validated end to end. Give it a research goal. Latent-Y reasons, designs, iterates, and delivers lab-ready antibodies, autonomously or collaboratively, with the biological reasoning of a PhD protein design expert. Technical report: tinyurl.com/latent-y-techrep… Blog post: latentlabs.com/latent-y Apply for access: platform.latentlabs.com
37
143
27
870
121,913
Henry Kenlay retweeted
I am looking for an intern to do a research project on RL posttraining of LLMs. If you are PhD student and would like to work with me for several months pushing the efficiency of RL systems, send me an email with the [efficient_rl_internship] subject. Friends, please, retweet.
11
45
2
417
45,604
Henry Kenlay retweeted
Introducing Latent-X2 — AI-generated antibodies with drug-like developability and low immunogenicity in human panels, zero-shot. Technical report: tinyurl.com/latent-X2-report Blog: latentlabs.com/latent-x2 Apply for access: [email protected]
19
59
10
302
54,875
Henry Kenlay retweeted
5 months from Latent-X1 to Latent-X2. AI-generated antibodies with drug-like developability and low immunogenicity in human panels — zero-shot. Available now for selected partners.
1
5
2
12
12,365
Henry Kenlay retweeted
Today at 11am I’ll present some of the exciting work in AI x Bio we’ve been up to at @Latent_Labs at the @RenPhilanthropy booth (Hall A/B, booth 1343 @NeurIPSConf - straight through the entrance at the back left). Come say hi!
5
8
2
51
3,869
I'm so happy to share that I’ll be joining @UofT as an Assistant Professor of Statistical Sciences and Computer Science, with an appointment at the @VectorInst, in 2026! I'm recruiting postdocs and PhD students: timrudner.com! Please help me spread the word! 🧵(1/5)
26
73
15
370
42,078
Henry Kenlay retweeted
Where are all the de novo designed therapeutics? In a guest post by @frdreyer, we break down what the actual bottlenecks, challenges, and opportunities are in building and deploying purely in silico drug discovery engines, with a focus on antibody structure. Link below 👇
5
29
2
161
14,289
Henry Kenlay retweeted
Introducing Latent-X — our all-atom frontier AI model for protein binder design. State-of-the-art lab performance, widely accessible via the Latent Labs Platform. Free tier: platform.latentlabs.com Blog: latentlabs.com/latent-x/ Technical report: tinyurl.com/latent-X
17
57
9
270
57,677
Henry Kenlay retweeted
We are out of stealth with $50M in funding. Join us on our moonshot mission of making biology programmable and reach out to work with us today.
Replying to @Latent_Labs
@Latent_Labs comes out of stealth today with $50M funding. Our goal? To push the frontiers of generative biology, giving partners instant access to tools capable of accelerating drug design. Every biotech or pharma company searching for the best therapeutic molecules understands the role AI can play - but not all are in a position to develop their own advanced models. That’s where @Latent_Labs comes in.
4
1
16
1,754
Henry Kenlay retweeted
Replying to @Latent_Labs
@Latent_Labs comes out of stealth today with $50M funding. Our goal? To push the frontiers of generative biology, giving partners instant access to tools capable of accelerating drug design. Every biotech or pharma company searching for the best therapeutic molecules understands the role AI can play - but not all are in a position to develop their own advanced models. That’s where @Latent_Labs comes in.
12
54
10
272
47,925
Computational design of developable therapeutic antibodies: efficient traversal of binder landscapes and rescue of escape mutations biorxiv.org/cgi/content/shor… #biorxiv_bioinfo
5
1
4
1,435
Henry Kenlay retweeted
Worth your reading time... An extraordinary Professor Nicholas J. Higham
"Obituary: Nicholas J. Higham" (by Desmond J. Higham and Françoise Tisseur, in @TheSIAMNews): sinews.siam.org/Details-Page…
1
4
2,591
My co-authors and I are pleased to share our latest work on paired antibody language models, where we trained the largest open-source antibody-specific models to date on over two billion sequences from the Observed Antibody Space.
2
7
29
3,809
We have released the weights, which can be accessed from our Hugging Face repo. We are grateful to NVIDIA for the compute resources. This was a great team effort by @frdreyer and myself, Charlotte Deane, Aleks Kovaltsuk, Dom Miketa, and @DrDouglasPires.
1
1
1
468
The DEGAS webinar series is back. The new season will begin on 6 Dec 3:00pm CET when @epomqo present "On the stability of spectral graph filters and beyond: A topological perspective". Check out dsiseminar.github.io for details. #graphsignalprocessing
7
26
3,929
Chefs kiss
[Cantor 1873]: The quadratic function P: ℕ x ℕ → ℕ (x,y) ↦ ½( (x+y)² + 3x + y ) is a bijection. [Fueter–Pólya 1923]: The only quadratic bijections ℕ x ℕ → ℕ are Cantor's P(x,y) and P(y,x).
2
1,063
Following the hand-in of my DPhil, I’m excited to have started a new role last week as an Immunoinformatics Research Scientist at @exscientiaAI. I’ll be working on machine learning for antibody design 🤖🧪
1
20
1,984
Henry Kenlay retweeted
Our paper on "learning on graphs with missing node features" has been accepted at the LoG conference! Impressed by the extremely high quality of the reviews, the monetary incentives seem to work! Paper: arxiv.org/abs/2111.12128 Blog post: towardsdatascience.com/learn…
We introduce Feature Propagation (FP), a new method to learn on graphs with partially missing node features. With 99% of features missing, FP loses only 4% rel. acc. compared to when all features are available. Bonus: It scales to graphs with >100M nodes arxiv.org/abs/2111.12128
3
30
131
I interned at Twitter last year and met and learnt from many welcoming, friendly and talented people. I'll always be grateful to them for the opportunity. I'm sad to hear about the situation they've been put in. Best of luck, tweeps 🫡
11