Michaël Moret
@moret1788
Followers
264
Following
1K
Media
36
Statuses
292
Co-founder at Externa | Previously postdoc at @geochurch's lab | PhD @ETH | ML for small molecules and macromolecules | Il est où Kadoc?
Cambridge MA, USA
Joined July 2009
Our work has just been published in @NatureCatalysis! Check it out below👇
Want to efficiently create large-scale dynamic models of metabolism that fit experimental data and reliably predict metabolic responses to various perturbations? Our new method does just that! Check it out here: https://t.co/d757bhiFC8.
0
0
4
Excited to announce mBER, our fully open AI tool for de novo design of epitope-specific antibodies. To validate, we ran the largest de novo antibody experiment to date: >1M designs tested against 145 targets, measuring >100M interactions. We found specific binders for nearly half
14
135
612
📢 JOB ALERT 📢 My team @molecularML is searching for a #postdoc with a background in medicinal chemistry! 👩🔬👨🔬🧪 Do you have the experience? Are you eager to contribute to #AI for discovering new drugs? 👉Then DM me! Funded by @ERC_Research and located at @TUeindhoven 🚀
1
46
96
This has always been an incredibly unsafe, downright scary, segment of Memorial Drive in Cambridge for pedestrians and cyclists that's been largely ignored for far too long by @MassDCR. It shouldn't take loss of life to make our streets safer by design. https://t.co/UMXDs8mT4z
mass.streetsblog.org
The state's Department of Conservation and Recreation, which owns Memorial Drive, had previously received serious warnings about safety hazards at the site of the killing.
7
33
180
Excited to share our paper published in @NatureComms led by @rythei & @CichonskaAnna! By integrating diverse bioactivity datatypes, we built a best-in-class drug-target interaction model called Kanopy—achieving an experimentally confirmed prospective hit rate of 40% (at 1µM)!
1
5
10
The generative machine learning tool RENAISSANCE generates kinetic models that accurately characterize cellular metabolic states https://t.co/fQ6Ecwf9Yn
#NBThighlight
nature.com
Nature Catalysis - Despite the availability of large omics datasets, determining intracellular metabolic states is challenging. Now a generative machine learning framework called RENAISSANCE has...
1
26
84
Following this story as it happens has been truly fascinating! Check out the bioRxiv and @AnushChP 's thread👇—you won't regret it!
1/ 🚨 Excited to share my Postdoc research with @geochurchlab at @harvadmed! Dive into our discoveries on the central dogma of biology, antibiotic resistance, #compbio designs, and #synbio. 🧬🔬 Check our paper:
1
1
9
Highly recommend!
The world needs 10x more scientist-founders. 5050 helps scientists and engineers become great founders and start indispensable companies. Applications open! Startups are the best way to make a real impact with research, but where do you get started? How do you know if
0
0
8
New paper alert! Wondering how to address the bystander challenge in base editing? Check out this work spearheaded by Ramiro (@rmperrotta ), Svenja (@SvenjaVinke ), & Raphael (@ferreira_raph_ ) in the thread below 👇
🧬🔬 How can we address the bystander challenge in base editing? Happy to share my first paper from the @geochurch lab! Discover how we're making on-demand genome editing a reality with ultra-precise base editing enzymes coupled with our agRNAs. 🚀🧵👇 https://t.co/4SIazXAatW
0
2
14
We are very grateful for the support of Northpond Ventures—and for the continuous support of the Wyss Institute. We can’t wait to push forward the frontier of protein therapies with non-standard amino acids!
We're excited to announce that AminoX is the latest tech at the Wyss to be supported by @npv_vc through our alliance. AminoX is making it easier and cheaper to manufacture protein drugs with non-standard amino acids. https://t.co/8t1yrs6ZsA
0
0
12
Welcome @ETH_DCHAB ! Dr Nathalie M. Grob @NathalieGrob , currently Postdoctoral Researcher at Massachusetts Institute of Technology @MIT , is appointed as Assistant Professor of Peptide-based Drug Discovery . Learn more on: https://t.co/2wJNT1FcDQ
2
2
43
The 50Y team was such great help during the 5050 program—from building our first deck to learning tactics to hiring great talent. Fireside chats with scientific founders, who shared their journey on building great startups, helped me understand what it takes to build one too
The SaaS startup playbook doesn’t work in deep tech. “Move fast and break things” doesn’t apply when building nuclear reactors or bioengineering cell therapies. That’s why we built 5050, “a cheat code for starting a deep tech startup.” (quote from an alumni) Applications open!
0
3
13
Quadratic attention has been indispensable for information-dense modalities such as language... until now. Announcing Mamba: a new SSM arch. that has linear-time scaling, ultra long context, and most importantly--outperforms Transformers everywhere we've tried. With @tri_dao 1/
53
397
2K
Amazing that @SchmidhuberAI gave this talk back in 2012, months before AlexNet paper was published. In 2012, many things he discussed, people just considered to be funny and a joke, but the same talk now would be considered at the center of AI debate and controversy. Full talk:
26
180
1K
Awesome work, Geemi (@GWellawatte)! XAI 🤝 LLMs Check out Geemi's thread to know more.
Preprint alert !! Introducing 🙌XpertAI🙌 - a new framework that combines explainable AI (XAI) methods with large language models (LLMs) to generate natural language explanations of structure-property relationships from raw data. Link to the preprint: https://t.co/sp2E8FkSbR
0
2
24
Super thrilled about the work of @DerekvTilborg on active #deeplearning for drug discovery 💪🏻 We address a broad range of questions on how to use active learning to explore the chemical space.🚀 It turns out active deep learning is quite powerful, even with little data!👇
Stoked to share our preprint on active learning for drug discovery: "Traversing Chemical Space with Active Deep Learning" https://t.co/ub8A9u5Quo A small 🧵 on how to find new #drugs efficiently with #AI 👇 @fra_grisoni @molecularML
#drugdiscovery #MachineLearning #chemistry
1
13
67
New preprint: Cyanobacteria isolated from marine volcanic seeps display rapid sinking and robust, high density growth. Thanks to U Palermo and Two Frontiers Project, we got unique samples from Vulcano, Italy, where CO2 bubbles into the shallow ocean, 24-7! https://t.co/bYlrM2gukS
4
25
61
Introducing Neural Developmental Programs (NDPs)🧬🧠Instead of neural networks with fixed architectures, we allow neural networks to grow through a dynamic self-organizing process, inspired by how biological nervous systems develop👇 PDF: https://t.co/3YiByyKwph
27
263
1K
📢 Open postdoc position on protein representation learning for drug discovery! 📢 Funded by @ERC_Research 🇪🇺 Join our vibrant team @molecularML+@TUeindhoven to push the boundaries of #AI for #drugdiscovery. 💪🏻 Apply before October 31st!👇 https://t.co/FWbFMOGJ9n Please RT 🙂
1
54
110
2/ 👩🔬Are you a scientist working on a bio x climate solution? Manifest Climate is a fast grants program that awards $25K - $100K to scientists to accelerate their most ambitious bio x climate solutions. Apply below! https://t.co/2Bwqv4KhQW
fiftyyears.com
Part of our Manifest Grants program, Manifest Climate is a fast grants program that awards $25K - $100K to scientists to accelerate their most ambitious bio x climate ideas.
4
23
71