Ernst Schmid รีทวีตแล้ว
If you're at #ADPD2026, don't miss Naveen Mehta’s talk on @ManifoldBio’s approach to one of the core challenges in treating neurodegenerative diseases: getting drugs across the blood-brain barrier.
English
Ernst Schmid
153 posts
Ernst Schmid
@ernstschmidd
@Harvard BBS and @UCLA alumnus. Full stack developer who sometimes wears a lab coat. Applied machine learning scientist at ManifoldBio.
เข้าร่วม Mart 2020
418 กำลังติดตาม316 ผู้ติดตาม
Ernst Schmid รีทวีตแล้ว
We made a dataset of three bacterial transcription factors with over 100,000 *functional* measurements. We capture loads of single insertions and deletions AND many functional TFs with 7+ random mutations!! Data can be found through the link below, or you can DM me.
The Align Foundation@Align_Bio
🚀 Public Data Release: GROQ-seq Transcription Factor Dataset We’re excited to announce the public release of The Align Foundation's first GROQ-seq dataset, one of the largest high-resolution transcription factor datasets of its kind.
English
Ernst Schmid รีทวีตแล้ว
Behold the power of massively parallel multiplexing @ManifoldBio brought to this study
Kieran Didi@DidiKieran
@ManifoldBio @viva_biotech @novonordisk @Cambridge_Uni @DukeU @LMU_Muenchen Massive campaign: ~1M designed candidates screened across 127 diverse/challenging targets with all-to-all binding readouts. We solve more than 2/3 of the targets given a very limited compute budget and often quite challenging hotspots and crops 11/n
English
Ernst Schmid รีทวีตแล้ว
@ManifoldBio and @NVIDIAHealth announce a joint study validating Proteina-Complexa, NVIDIA's latest BioNeMo model for protein binder design.
English
Ernst Schmid รีทวีตแล้ว
We're growing the AI team at @ManifoldBio, starting with a role to train protein foundation models on our proprietary data.
I believe Manifold is the most interesting place to work on protein design. We're designing and testing millions of binders per month, including in vivo, and accelerating. No one else has data like this.
If you have deep experience pretraining or fine-tuning protein models and want to work somewhere the data actually lets you push beyond what public datasets can enable, please reach out.
English
Ernst Schmid รีทวีตแล้ว
Don't worry if you missed the excellent seminar by Mike Nichols and Erik Swanson from @ManifoldBio this week because you can check out the recording 👇
youtu.be/u9dznMvcDs4
YouTube
English
Ernst Schmid รีทวีตแล้ว
I'm working on this little ribosome game. You have to build a peptide as fast as you can. Prokaryotes can incorporate 20 amino acids per second. Currently, only the tRNAs work; the amino acids are next.
English
Ernst Schmid รีทวีตแล้ว
Epic to have AWS support as we enter this phase of scaling our AI protein design + (already massively multiplexed) data gen capabilities.
AWS Startups@AWSstartups
🧬@ManifoldBio is on an “ambitious mission” & it’s getting there faster with the #AWS #GenAI Accelerator. 🎞The #startup’s Co-founder & CEO discusses how GAIA will fuel growth. 🚀Join us at AWS re:Invent & discover how to accelerate your company’s mission: go.aws/4oht3x4
English
Ernst Schmid รีทวีตแล้ว
This is unironically the solution to every "printers suck" conversation
I've been using the same Brother B&W laser printer since 2009
Mike Key@1337hero
A laser printer is like the best home/office investment you can make. Stop buying ink like a dummy. Have had the same Brother printer for 9yrs just printing page after page after page without issue.
English
Thanks to members of the @FrogWalterLab and our fantastic collaborators @alanbrownhms and @MaintainGenome, we experimentally verified several of these new PPIs. But don’t worry, there are plenty more waiting to be discovered. Come and explore the data and see what you find!
English
Thrilled to share that the final piece of my PhD work is now on bioRxiv! biorxiv.org/content/10.110… With support from @nvidia and the @NSF, we used AlphaFold to screen 1.6M+ protein pairs, revealing thousands of potential novel PPIs. All data can be viewed at predictomes.org/hp
English
Ernst Schmid รีทวีตแล้ว
Boltzgen is out, and once again, it's fully open-source! We experimentally validated the model on a wide array of targets and use cases with impressive results, including 67% success rate on nanobody design! Huge credit to @HannesStaerk for driving this in a way only he can.
Hannes Stark@HannesStaerk
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project has been collaborating with many leading biologists who tested BoltzGen at an unprecedented scale, showing success on many novel targets and pushing its limits! 🧵..
English
Ernst Schmid รีทวีตแล้ว
Ernst Schmid รีทวีตแล้ว
DNA mutagenesis driven by transcription factor competition with mismatch repair: Cell cell.com/cell/fulltext/…
English
Ernst Schmid รีทวีตแล้ว
Can an AI model predict perfectly and still have a terrible world model?
What would that even mean?
Our new ICML paper formalizes these questions
One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵
English
Ernst Schmid รีทวีตแล้ว
We're bringing NASA+ to @Netflix!
Starting this summer, Netflix audiences will be able to stream rocket launches, spacewalks, and other major live events on the platform. Read more about how we're working to bring NASA's work to a global audience: go.nasa.gov/40wCJdY
English
Ernst Schmid รีทวีตแล้ว
The SubtiWiki Paper of the month for June 2025 has been selected!
Congratulations, @apbrogan @ @harvardmed
@NatureMicrobiol
subtiwiki.uni-goettingen.de/wiki/index.php…
English
Our AlphaFold 3 analysis tool is now accepting the new version of the AlphaFold 3 server output files. Thanks to those who let me know and apologies for any inconvenience! predictomes.org/tools/af3/
English
Ernst Schmid รีทวีตแล้ว
Out Now! Cyclic-di-AMP modulates cellular turgor in response to defects in bacterial cell wall synthesis bit.ly/3FZ4jJY #CyclicDiAMP #BacterialCellWall #Microbiology
English