Lukas Oesinghaus

Postdoc @UW working on RNA design.

[Waggoner Lab @LabWaggoner]

@biorxivpreprint comprehensive cell type-resolved transcriptional screen of human cytokine responses
https://t.co/qMOVsyhC6j @fabian_theis
@HelmholtzMunich @LOesinghaus @UW @seeliglab 🇺🇸🇩🇪🇨🇭

[Lukas Oesinghaus @LOesinghaus]

@dwarkesh_sp @geochurch I'd be curious about his thoughts on Eroom's law. What are the major bottlenecks right now? How can we make sure that cell/gene/mRNA therapies actually help us break the trend?

[Jure Leskovec @jure]

Announcing Biomni — the first general-purpose biomedical AI agent. Biomni is a free web platform where biomedical scientists can immediately delegate their tasks to Biomni, starting today!

Biomni automates literature reviews, hypothesis generation, protocol design, bioinformatics analysis, clinical reasoning, and much more — scaling biomedical expertise for 100× the number of discoveries.

Key results:
➡️ Designed a cloning experiment with real-world wet-lab validation; on par with 5+ year expert in a blind test
➡️ Ran 458-file wearable bioinformatics analysis in 35 minutes vs. 3 weeks (800x faster) for human expert
➡️ Uncovered novel hypothesis: new TFs regulating skeletal lineages on a large scRNA+scATAC data
➡️ Human-level performance on LAB-bench DbQA and SeqQA, with SOTA at Humanity’s Last Exam and across 8 new biomedical tasks—ranging from GWAS and rare disease diagnosis to microbiology and drug repurposingPowered by:
➡️ Biomni-E1 – the first unified environment designed for a biomedical agent—encompassing 150 tools, 59 databases, 106 software—systematically curated from 2,500+ bioRxiv papers
➡️ Biomni-A1 – a generalist agent with retrieval, planning, and code as action

Biomni is an open-source initiative: we invite the community to build on it and advance biomedical research at scale.
- Try it now: https://t.co/GyZdCKEKYN
- Paper: https://t.co/lgtyUEGfEy
- Code: https://t.co/vqq9W6Zkv3
- Join the community: https://t.co/2C7rWOPp2z

Amazing team and collaborators @StanfordAILab @StanfordMed @StanfordCancer @genentech @arcinstitute @UCSF @UW @PrincetonAInews
@KexinHuang5 @serena2z @hcwww_ @YuanhaoQ @mintaylu @yusufroohani @RyanLi0802 @LinQiu0128 Gavin Junze Di Shruti Jennefer Xin Zhou @MWheelerMD Jon Bernstein @MengdiWang10 @PengHeAtlas @SnyderShot @lecong Aviv Regev

[Ross Rheingans-Yoo🔸 @rossry]

The way we develop new drugs is broken.

The process costs too much, takes too long, and far too often it simply doesn't work.

I sat down with five leaders in the field—from industry, VC, academia, and government—to hear their takes on how, and why, and what we can do about it.

[Sierra Lore @Sierra_Lore_]

What if the path to slowing aging wasn’t a drug, but replacing worn out parts?

Our new paper out today in @NatureAging shows how this could one day work. We map a unified framework—from scaffolds & bioprinted tissues to pacemakers, xenotransplants & brain machine interfaces—for extending healthy lifespan through replacement-based approaches. Read the thread to learn more about what replacement means for the aging field! https://t.co/eqWdJEPBU4 🧵👇(1/10)

[bioRxiv Synthetic Biology @bioRxiv_synbio]

Design of overlapping genes using deep generative models of protein sequences https://t.co/AgKREPIa5C #biorxiv_synbio

[Nature Biotechnology @NatureBiotech]

Nanocarrier imaging at single-cell resolution across entire mouse bodies with deep learning https://t.co/4RhnmhJ0PE

[bioRxiv Synthetic Biology @bioRxiv_synbio]

Quantitative design of cell type-specific mRNA stability from microRNA expression data https://t.co/dTJ2ZRUALe #biorxiv_synbio

[Lukas Oesinghaus @LOesinghaus]

Applying our results should be straightforward for anyone trying to use endogenous miRNA for SynBio applications, so I hope it proves useful to people (or maybe inspires someone to try or go back to using miRNA for SynBio?).

[Lukas Oesinghaus @LOesinghaus]

Just put my first postdoc publication on bioRxiv – designing cell type-specific gene and mRNA therapy from microRNA expression data! Good timing with the recent Nobel Prize, I guess. In essence: You have to use the right type of expression data. https://t.co/ZQlh2FK7IZ

[Lukas Oesinghaus @LOesinghaus]

Naturally, there’s more work to be done – better prediction of the impact of secondary structure and estimating miRNA-independent stability variation, for example.