
Staff Software Engineer @ Valence Labs | @valence_ai
Montréal, Québec
Joined May 2019
- Tweets184
- Following188
- Followers229
- Likes988
Huge milestone for Blank Bio, congrats @hsu_jonny and team!
Today, we are excited to introduce Ladon, a state-of-the-art biological foundation model that predicts disease trajectory and treatment response in patients. There is immense complexity in the individual biology of every patient. Two patients can have the same diagnosis and receive the same treatment, yet have very different outcomes: one responds well and lives for years, while the other’s disease continues to progress. Understanding and resolving this heterogeneity to predict outcomes is how we accelerate our delivery of medicines for patients and unlock clinical trial abundance.
Ladon is our first step towards this future: one where we can learn more from every patient enrolled so that we can run smaller, faster trials with higher success rates. We built it to give drug developers quantitative support on billion-dollar clinical trial decisions. Today we're excited to share Ladon's capabilities in our blog and technical report.
Ladon is a 3B parameter model trained on millions of RNA-seq samples spanning decades of technical and biological variation across tissues and species. Ladon beats gene expression baselines, established biomarkers, and existing RNA foundation models at predicting patient prognosis and therapeutic response in 140+ oncology tasks, including external validation on past clinical trials. This is significant because clinical trials are fundamentally generalization problems. We show that Ladon-derived predictions are robust across indications, treatments, and sequencing platforms.
Reach out if you’d like to get started with the model today!
Read more about Ladon in the blog: blank.bio/introducing-ladon
Find more technical details in the white paper: blank.bio/introducing-ladon
4
187
Michel Moreau retweeted
1/ Valence Labs is bringing together next generation of Montréal researchers and innovators in Bio-AI.
We are hosting a Bio-AI Show & Tell — a quick and fun showcase of ideas, demos and projects in ML.
RSVP here: luma.com/n47bshdx
Michel Moreau retweeted
🛡️ New Certified Dataset and Benchmark!
Did you know that high-dimensional data like cell images (i.e. phenomics) can help us understand the relationship between compounds and genes?
Now you’ll have a chance to work with a phenomics dataset and benchmark to predict which genes a given compound interacts with!
RxRx3-core is the latest certified dataset from @RecursionPharma that includes labeled images of 735 genetic knockouts and 1,674 small-molecule perturbations. The related benchmark evaluates the zero-shot prediction of compound-gene activity.
If you’re at NeurIPS, come talk to the Polaris and @RecursionPharma teams! We’ll be at the conference and workshops over the weekend.
Explore the dataset: polarishub.io/datasets/recur…
Explore the benchmark: polarishub.io/benchmarks/rec…
Chime in on the certification process: github.com/polaris-hub/polar…
Michel Moreau retweeted
Yay! @Polaris_HQ is now hosting the RxRx3-core phenomics dataset and introduced a new standard for benchmarking compound-gene activity!
🛡️ New Certified Dataset and Benchmark!
Did you know that high-dimensional data like cell images (i.e. phenomics) can help us understand the relationship between compounds and genes?
Now you’ll have a chance to work with a phenomics dataset and benchmark to predict which genes a given compound interacts with!
RxRx3-core is the latest certified dataset from @RecursionPharma that includes labeled images of 735 genetic knockouts and 1,674 small-molecule perturbations. The related benchmark evaluates the zero-shot prediction of compound-gene activity.
If you’re at NeurIPS, come talk to the Polaris and @RecursionPharma teams! We’ll be at the conference and workshops over the weekend.
Explore the dataset: polarishub.io/datasets/recur…
Explore the benchmark: polarishub.io/benchmarks/rec…
Chime in on the certification process: github.com/polaris-hub/polar…
Michel Moreau retweeted
Love the momentum behind @Polaris_HQ right now and super excited to see @leashbio's massive BELKA dataset up on the platform.
Curious to learn more about the work that went behind making BELKA accessible through Polaris? Learn more about Dataset v2.0 and how we’re helping scientists focus on research, not on data wrangling. 👇🧵
Read the blog: polarishub.io/blog/dataset-v…
Access BELKA: polarishub.io/datasets/leash…
Michel Moreau retweeted
We’ve released an improved version of SynFlowNet!
SynFlowNet can now handle large action spaces (up to 220k building blocks) and we experiment with training different GFlowNet backward policies. (1/3)
arXiv: arxiv.org/abs/2405.01155
code: github.com/mirunacrt/synflow…
Michel Moreau retweeted
Recursion is a company to watch. Arguably the strongest upstart in deep learning aided drug discovery.
Replying to @nathanbenaich
Over in the world of biotech, we’re seeing one of the first landmark AI deals.
@RecursionPharma, which is industrializing discovery in biology using high-throughput AI-first experimentation, is acquiring AI-first precision medicine company @exscientiaAI.
Get hyped for a full-stack discovery and design company with the largest GPU cluster in biopharma as seen on stateof.ai/compute
Michel Moreau retweeted
Introducing a small portion of proprietary phenomics data from @RecursionPharma into the training of MolGPS, our foundation model for molecular property prediction, led to massive performance increases on new & existing benchmarks.
Learn more about the impact of data & scale.
Michel Moreau retweeted
[1 of 7] Data is the differentiator. Today, we’re kicking off a series called Data Deep Dive – sharing how we collect, model & analyze #data in order to solve challenging biological problems and transform drug discovery. 🧵#datadeepdive
Michel Moreau retweeted
Did you see the big news? Want to know more?
Join us for our L(earnings) Call today, 8:30am ET/6:30am MT on Thursday, August 8, where we provide a real-time livestream of the Company’s latest business developments from Co-founder and CEO @RecursionChris , Chief R&D and Chief Commercial Officer Najat Khan, PhD, and Dave Hallett, Interim CEO of Exscientia and planned Chief Scientific Officer of Recursion.
Submit your questions for consideration here: lnkd.in/e6sfBBDw
Where to watch:
LinkedIn: linkedin.com/company/4990022…
Twitter: teapaw.org/recursionpharma
YouTube: youtube.com/channel/UCXZs32P…
Learn more: globenewswire.com/news-relea…
Michel Moreau retweeted
Huge milestone in our partnership with @Roche and
@genentech, with many more to come!
Announcing the 1st #neuroscience phenomap – “Neuromap” – optioned under our collaboration with @Roche and @Genentech for $30m. To build it, we produced over 1 trillion hiPSC-derived #neuronal cells – one of the largest such datasets – & scaled new genetic perturbation techniques. We’re combining this w/ Genentech’s #transcriptomics data to rapidly accelerate discovery of new treatments. @RecursionChris: “We look forward to initiating new programs and building more maps on the forefront of the field with our colleagues at Roche and Genentech.”
Michel Moreau retweeted
1/ 🚀Today, we’re excited to launch Polaris! 🚀
Polaris is a platform where the ML community working on drug discovery problems can easily share and access datasets and benchmarks.
Get started with just a few lines of code: polarishub.io/
Michel Moreau retweeted
Last year at #ICML, we launched @valence_ai – an #ML research lab in #Montreal to develop next gen cutting-edge methods & models for drug discovery, w/ a focus on #openscience & academic partnerships. This year, we’re helping to launch @Polaris_HQ - benchmarks for ML in drug discovery - & showcasing new discoveries that have emerged from these collaborations: 🧵
Michel Moreau retweeted
Today's benchmarking landscape for ML in drug discovery is complicated. We want to help the community develop methods that matter!🌟
Join us for our launch party at ICML on July 25th to learn more: lu.ma/wj1agv8o
Our London office is now officially open
A story in @thetimes looks at Recursion’s new #London #AI hub where, as @RecursionChris says: “there is a density of talent and people who are trained in both biology and computer science and data science.” The response has been immediate. “Within the first 24 hours...the business had received more than 300 applications. It is currently seeking to fill eight open roles, including software engineers and computational biologists.” #techbio #techjobs
3
237
Michel Moreau retweeted
Excited to be hosting the #Moml2024 where more than 250 people are gathered around 40+ posters @Mila_Quebec @hsu_jonny
Michel Moreau retweeted
What better way to close the conference than a presentation of AlphaFold3, probably one of the first public presentations about it.
From @maxjaderberg , @IsomorphicLabs
You can join @_portal_ to find out about our next events and newsletter
Excited to be hosting the #Moml2024 where more than 250 people are gathered around 40+ posters @Mila_Quebec @hsu_jonny
Michel Moreau retweeted
Thanks to everyone who came out and hope to see you again next year!
Sneak peek of the footage we got for the ML4DD summer school 👀
Today was the last day of the summer school. With 150+ participants, it was exciting to see the growing interest of TechBio. Thank you to all of our speakers!
See you tomorrow @Mila_Quebec for MoML 2024 👋
Michel Moreau retweeted
In a new paper, researchers from Recursion & @valence_ai reveal the next level of scaling #microscopy images for use in biological research – offering a significant improvement over weakly supervised learning (WSL). They are presenting their findings at CVPR June 18-19. 🧵
Michel Moreau retweeted
Today we opened our office in #London – the epicenter for #TechBio in Europe & home to one of the world’s best talent pools across #tech, #biology and #chemistry.
@RecursionChris @howarddawber @mmbronstein @nathanbenaich @zavaindar @valence_ai @KristinaUlicna @_danielcohen

























