Gregory Minevich

Building AI agents for biomedical science @phylo_bio

[Phylo @phylo_bio]

5M+ researchers open GeneCards when they look up a gene.

Today we are excited to integrate it in the Biomni Lab.

Our agents are now grounded in one of the most comprehensive, expert-curated human gene knowledge bases - 200+ integrated data sources spanning genomic, transcriptomic, proteomic, clinical, and functional data.

Try it at: https://t.co/9ME5BcaND3

Learn more at: https://t.co/f4US9gNMKy

[Gregory Minevich @gm2123]

Bacterial system that builds DNA from a protein template!

https://t.co/Us8Hhv7hzp

[Kexin Huang @KexinHuang5]

Biomni Lab lets biologists collaborate with AI agents to finish complex tasks end-to-end. Here are 15 popular use cases, each link is a full replay so you can watch the agent work through every step:

1. Spatial transcriptomics analysis: map gene expression across tissue architecture from spatial transcriptomics data, with spatial clustering and neighborhood analysis. https://t.co/Oop24XftZC

2. Binder design: design de novo protein binders against a target structure using computational protein design tools. https://t.co/XGE4itLFrL

3. Biomarker panel design: identify and optimize a multi-marker diagnostic or prognostic panel from omics data. https://t.co/KH8jqbbofR

4. Clinical trial landscaping: search and summarize the trial landscape for a disease area, mapping phase, endpoints, and sponsor activity. https://t.co/kUI0NwFO0n

5. Survival analysis: pull clinical and expression data, fit Cox models, generate Kaplan-Meier curves, and identify prognostic markers. https://t.co/M6xgwrMKvt

6. scRNA-seq processing and annotation: from raw counts to UMAP clustering, marker gene detection, and automated cell type labeling. https://t.co/GNfcgomD0a

7. Cell-cell communication: infer ligand-receptor interactions between cell types from single-cell data and map intercellular signaling networks. https://t.co/diGDFk6rNi

8. Primer design for novel Cas13: analyze a putative Cas13 protein from a metagenomic screen—verify the ORF, identify HEPN domains, and design cloning primers with restriction sites and a FLAG https://t.co/Vc7GNrCOKo

9. Proteomics differential expression: normalize mass spec data, run statistical tests, and visualize differentially abundant proteins. https://t.co/79U4gC5aWK

10. Gene regulatory network inference: reconstruct transcription factor-target gene networks from expression data and identify key regulators. https://t.co/CYn1prUC3j

11. Gene co-expression network analysis: build weighted co-expression networks, identify gene modules, and correlate them with phenotypic traits. https://t.co/w2spMXYuhG

12. Microbiome analysis: process 16S/metagenomic sequencing data to profile microbial communities, diversity, and differential abundance. https://t.co/JHuevnEjuh

13. Polygenic risk scores: compute and evaluate PRS from GWAS summary statistics against a target cohort. https://t.co/7bOEE4GzsA

14. Variant annotation: annotate genetic variants with functional predictions, allele frequencies, and clinical significance. https://t.co/gnMZFvG5ia

15. Fine-mapping: narrow GWAS loci to credible causal variants using statistical fine-mapping methods. https://t.co/ga6eVvLMjb

Each of these would normally take days to weeks of scripting, debugging, and iteration. In Biomni Lab, the agent handles the full execution while you steer the science.

Learn more: https://t.co/3IQPmuBT3H

[Ulkar @ulkar_aghayeva]

viruses from various families have repeatedly converged on capsids with icosahedral symmetry in the course of evolution. i wrote about why it might be so
https://t.co/4iQ3zhMMie

[Phylo @phylo_bio]

We've been building nonstop since our public launch, and this week we're officially celebrating with the Biomni community! 🚀

On Thursday, join us virtually for a live demo of Biomni Lab by co-founders @KexinHuang5 and @YuanhaoQ, plus recent product updates and how we think about evaluating AI agents in biology.

On Friday, we'll feature demos + lightning talks from scientific co-founders @jure and @lecong, plus free swag, drinks, small bites, and plenty of time to mingle. We only have a few spots left, so RSVP soon.

• Virtual: https://t.co/NNKtsIBymk
• South SF: https://t.co/0JcPPvhGMo

We can't wait to see you there!

[Kexin Huang @KexinHuang5]

Excited to share one of the first examples of agents transforming clinical trial & EHR data analysis at scale. Biomni leverages 12M+ patient EHRs at Mount Sinai to scale complex trial emulation end-to-end:

[Kexin Huang @KexinHuang5]

https://t.co/Je2Ao8sCJ6

[Feng Zhang @zhangf]

Congratulations to the @phylo_bio team on launching a super useful and thoughtfully designed tool for life science!

[Kexin Huang @KexinHuang5]

Today we’re launching Phylo, a research lab studying agentic biology, backed by a $13.5M seed round co-led by @a16z and @MenloVentures / Anthology Fund @AnthropicAI.

We’re also introducing a research preview of Biomni Lab, the first Integrated Biology Environment (IBE), where we’re imagining a new way biologists work.

Biomni Lab uses agents to orchestrate hundreds of biological databases, software tools, molecular AI models, expert workflows, and even external research services in one workspace, supporting research end-to-end from question to experiment to result.

Agents handle the mechanics, while you define the question, then review, steer, and decide. Scientists end up spending more time on science: asking questions, understanding mechanisms, and eliminating diseases.

Phylo (@phylo_bio) is a spin-out of @ProjectBiomni, where we will maintain the open-source community and push open-science research. I’m grateful to continue building with my co-founders @YuanhaoQ @jure @lecong and the dream founding team @serena2z @TianweiShe @huangzixin20151 @gm2123 @margaretwhua @malayhgandhi.

We’re also fortunate to be advised by leading scientists @zhangf, Carolyn Bertozzi, and @fabian_theis, and supported by an amazing group of investors including @JorgeCondeBio @zakdoric Matt Kraning @ZettaVentures @dreidco @conviction @saranormous @svangel @valkyrie_vc and others.

Biomni Lab is available for free today: https://t.co/zYcXEjvIbb
Learn more in our launch post: https://t.co/O09cnwYeNg

We are also hosting launch events - join us at
South San Francisco: https://t.co/4Xm9DFf4cY
Virtual: https://t.co/Wf7ksnWkRy

We’re also hiring! https://t.co/PABaLLwmRx

[nature @Nature]

For decades, researchers have noted that cancer and Alzheimer’s disease are rarely found in the same person

https://t.co/rgYalgRdfi

[Gregory Minevich @gm2123]

Microbe with bizarrely tiny genome may be evolving into a virus.
With DNA focused almost entirely on replication, newly discovered organism blurs the line between cells and viruses

https://t.co/FQD8vFeB2D

[nature @Nature]

“The leaders of the Human Genome Project always knew they were just starting a conversation”

The human genome encodes potentially thousands of tiny proteins that were previously overlooked. The search is on to find out what they do

https://t.co/ItyjKAAbtq

[nature @Nature]

Not only does Bennu contain all 5 of the nucleobases that form DNA and RNA on Earth and 14 of the 20 amino acids found in known proteins, the asteroid’s amino acids hold a surprise

https://t.co/s99i6GFhEz

[Zane Koch @zanehkoch]

WHY DOES THE EPIGENETIC CLOCK TICK?

While money has been poured into developing therapies to reverse the epigenetic clock (@altos_labs 🤑), why the epigenome changes with age at all is unclear.

In @NatureAging today, we suggest a potential driver: somatic mutations.

[Gregory Minevich @gm2123]

The lives of cells, recorded
https://t.co/C1N78TiIRk

[Sam Rodriques @SGRodriques]

Excited to report that we have discovered a new, endogenous molecular clock in unmodified human cells and tissues. It is ticking away right now in almost every cell in your body.

Specifically, in a new paper on BioRxiv, we show that RNA editing by the near-ubiquitous ADAR1 in unmodified human cells is sufficient to allow us to infer the ages of thousands of species of RNA. This provides a new way to infer past transcriptional dynamics, without any metabolic labeling or genetic engineering, in anything from cultured cells to patient biopsies.

Work by @agreeb66, @JamesBa95200124, @AaronWagen, and many more, and funded by @LNuzhna's Impetus Grants, along with generous support from @ericschmidt and @wenschmidt.
1/

[Gregory Minevich @gm2123]

Cells Across the Tree of Life Exchange ‘Text Messages’ Using RNA

https://t.co/irjjRCh8l3

[Gregory Minevich @gm2123]

Microglia rescue neurons through protein removal and mitochondria donation
https://t.co/PHMJEpP2gP

[Will Chen @wchenomics]

Super excited to share that ENGRAM is out today! ENGRAM cells are programmed to write their histories into the genome, recording the intensity, duration, and order of biological events simultaneously.
https://t.co/whJgHAm3nO

[Veera Rajagopal  @doctorveera]

It's been 60 years since Epstein-Barr virus (EBV) was discovered. Still, still scientists are continuing to learn fascinating facts about this EBV. A new paper in @Nature by Sylvain Latour and colleagues from INSERM, Paris, report a remarkable human genetics discovery that reveals an important biology of EBV infection--the role of IL27 and its receptor in EBV infection.

Martin et al. Nature
https://t.co/Ax8omwL5ov

The authors found that individuals who were born with complete deficiency of a cytokine receptor, IL27RA, are highly susceptible to severe EBV infection. But the remarkable part of the discovery is that, despite severe EBV infection, none of these individuals developed cancer; they are protected from EBV-induced cancer risk.

If there is one virus that oncologists might know better than virologists, it's EBV. Discovered in 1964 based on microscopy examinations of tumor cells from cancer tissue biopsied from African children, EBV was the first ever known oncogenic virus (https://t.co/EhJuNc3GU5). If you are curious, listen to this 6 mins video where famous scientist/author Dorothy Crawford tells the story of EBV discovery (https://t.co/b4RjAxpOph).

EBV infection is extremely common. More than 95% of the population gets it at some point in their life. Once the virus enters the body, it permanently lives dormant in your B cells until you die. In some individuals, such as those immunocompromised, reactivation of this latent infection results in uncontrolled proliferation of B cells causing lymphoma. Not just lymphoma, EBV also cause stomach cancer and nasopharyngeal cancer.

Most of the knowledge on the immune pathways hijacked by EBV came to light through humans born with rare genetic mutations causing different types of immunodeficiency. All such known monogenic conditions leading to severe EBV infection almost always have led to cancer. This is the first time scientists are encountering a genetic defect which increases the risk of severe EBV infection but protects against cancer. The finding has perhaps revealed the Achilles' heel of EBV infection, which could be exploited to prevent cancer development in immunocompromised individuals with EBV infection.

The other fascinating part of the finding is one of the loss of functions has drifted to higher frequency (0.7%) in Finnish population. So, there are more than 200 individuals in Finland who are knockouts for IL27RA. In the Finngen biobank, the authors found 15 homozygotes, of which two were hospitalized for EBV infection (>50-fold enrichment). The Finnish variant is probably incompletely penetrance because the variant do not completely inactivates IL27R; it leaves behind some residual activity.

Just a couple of years ago, Bjornevik et al. demonstrated the strong association of EBV with multiple sclerosis (https://t.co/HPA4pNmMMr). Shortly after this report, Lanz et al showed that the reason for 32-fold increased risk of MS after EBV infection is because of the resemblance of a antigen protein in EBV with a glial cell protein in the CNS, resulting in collateral damage in the immune defense against EBV (https://t.co/M1B8XweoNu). Currently, mRNA vaccines are being trialed based on this finding.

With the recent discovery of IL27 and its receptor IL27RA in EBV, I wonder if these genes have links to MS risk. If so, targeting these genes might also help with treating MS. We will know soon.

Amazing discovery. Yet another incredible demonstration of the power of 'natural experiments' aka human genetics in understanding the fundamental biology.
Martin et al. Nature
https://t.co/Ax8omwL5ov