Genomic Intelligence

[Genomic Intelligence @GenomeLayer]

Enjoy! Let's know how it works for you!

https://t.co/Mpcjfv6WqI

[Julia Kiseleva @julia_kiseleva]

Apparently, people want to run genomic analyses from their phones. We honestly did not expect that. But enough of you asked, so we rebuilt the Genomic Intelligence platform for mobile. You can now analyze genomic sequences directly from your phone 📱🧬
Try it: https://t.co/94YWW200vm
@GenomeLayer #GenomicAI #Genomics #AIforScience #BioTech #PrecisionMedicine

[Genomic Intelligence @GenomeLayer]

One GLP-1 response variant became 229 new hypotheses worth testing

We analyzed 2,734 DNA changes around GLP1R and found hundreds predicted to have larger effects, including rare variants that population studies may miss

This is the opportunity for genomic AI: turning overlooked DNA into testable biology across drugs and diseases

https://t.co/oR7Po022B6

#GLP1 #GenomicAI #DrugDiscovery

[Genomic Intelligence @GenomeLayer]

Very exciting to see Marc Amil turn our genomic models into a working sequence-design loop. When we launched the Agentic Genomics Build Challenge, we invited people to build a practical genomics use case with our API, MCP server, or platform. We promised up to $1,000 for our favorite one (https://t.co/D69s7QmKdb).

Marc’s prototype generates candidate sequences, evaluates them with Genomic Intelligence, and iteratively improves them toward a specific biological objective.

This is exactly the direction we envisioned: moving beyond predicting what a DNA sequence does toward designing sequences for a specific purpose.

Great work, Marc, and thank you for building with us!

More challenges to come! What would you build with a genomic model? 🧬

[Marc Amil @AmilMarc]

Excited to share my submission to the GI Builder Challenge #genomics #AI #bioinformatics
@GenomeLayer

Turning a Genomic Model into a Sequence Designer: GI × Proto https://t.co/yjEwFKmvZr

[Genomic Intelligence @GenomeLayer]

Why does Ozempic work better for some people than others?

A Nature study linked a GLP1R variant to greater weight loss.

Our genomic models suggest a second mechanism: the variant may affect not only how the receptor works, but also how much of it the body produces.

We then screened rare variants that GWAS can miss��collectively carried by an estimated 527M people worldwide.

This is what genomic AI makes possible: moving from population-level association to individual, testable biological hypotheses.

Read the study and try the workflow on your own genome:
https://t.co/RWRxSadWPS

#Genomics #GLP1 #PrecisionMedicine #AIforScience

[Julia Kiseleva @julia_kiseleva]

Why do some people lose more weight on Ozempic than others?

A Nature study found a GLP1R variant linked to a better response. Our models suggest a second mechanism: it may also increase GLP1R expression.

We turned this into a workflow for Claude, OpenAI agents & Biomni.

https://t.co/r5hCZ1nCzj

Follow @GenomeLayer for the coming full rare-variant study

#GLP1 #Ozempic #Genomics #AIForScience

[Genomic Intelligence @GenomeLayer]

The genome is becoming programmable through natural language

We partnered with @PhyloBio to bring @GenomeLayer models into Biomni Lab so researchers can move from a biological question to regulatory DNA analysis, expression prediction, variant interpretation, and sequence optimization inside one agentic workflow

Try it yourself ↓

https://t.co/ajNNFVa02G

#AIForScience #Genomics #Biotech

[Julia Kiseleva @julia_kiseleva]

One step closer to making genomic analysis directly accessible through scientific agents.

@GenomeLayer partnered with @PhyloBio to bring genomic models into Biomni Lab.

You can now use natural language to analyze regulatory DNA, predict gene expression, interpret genetic variants, and optimize biological sequences in reproducible workflows.

Try it yourself:
https://t.co/2UPtNEbAeG

#AIForScience #Genomics #Biotech #AgenticAI #Bioinformatics

[Julia Kiseleva @julia_kiseleva]

Tomorrow, Genomic Intelligence @GenomeLayer is presenting at UPMC and the University of Pittsburgh on genomic foundation models, agentic workflows, and their applications in regulatory DNA analysis, gene expression prediction, splicing, and variant interpretation.

#Genomics #AIinHealthcare #PrecisionMedicine #Bioinformatics

[Julia Kiseleva @julia_kiseleva]

Inspired by Claude Science announcement AI for science is moving toward agents + tools + executable workflows? Here is our @GenomeLayer demo inspired by the Nature paper on synthetic super-enhancers for precision viral gene therapy in glioblastoma.

For the #ICML audience, the interesting question is not just AI for bio, but: How do general-purpose AI agents compose with specialized genomic foundation models to design, score, and prioritize experimentally testable regulatory DNA?

With our MCP, you can already try workflows around promoter/enhancer design, expression prediction, variant interpretation, and regulatory DNA analysis today: https://t.co/GGD61MPLZ7
#ICML #ICML2026 #AIforScience #Genomics #AgenticAI #MCP #ClaudeScience #BioAI

[minja @minjaf]

Claude for Science is here!

Q: “What is the expression level of this DNA in rabbit liver cells?”
A: “That can’t be read from sequence.”

Why?
We need specialized models that know biology.

With GI MCP we got: ~23K TPM

Try this MCP:
https://t.co/Xtm2xfbGyi

[Julia Kiseleva @julia_kiseleva]

Claude Science is a clear signal: scientific work is becoming agentic.

That is why we built the Genomic Intelligence MCP server.

Claude, Cursor, and other MCP-compatible agents can now call GI models directly to fetch genomic regions, predict promoters, enhancers, splice sites, expression, and compose genomic workflows.

General agents need domain-native scientific tools.

GI is building the genome-native prediction layer for AI-native biology.

https://t.co/GGD61MPLZ7

#ClaudeScience #MCP #AIforScience #Genomics #BioAI

[Julia Kiseleva @julia_kiseleva]

NIH’s All of Us program is now the world’s largest integrated genomics + health database

747K+ participants, 535K+ whole genomes, and clinical data linked at scale

This is an important step toward the next phase of medicine: not only reading genomes, but learning to predict what they mean

At @GenomeLayer this is the direction we are building toward

https://t.co/wFzMOufTkQ

#Genomics #PrecisionMedicine #AIForScience #AI #HealthTech #GenomicIntelligence

[Julia Kiseleva @julia_kiseleva]

Can you build something useful in genomics in 2 weeks? We’re launching a Genomic Intelligence builder challenge

Use our API, MCP server, or web platform to build a biology/genomics use case

Our favorite case gets up to $1,000
Post what you built
Tag @genomelayer

Watch the seminar recording to get started:
https://t.co/YmZa66taSi

Platform:
https://t.co/CVmm04l3qb
#Genomics #BioAI #AIforScience #ComputationalBiology #AgenticAI

[Julia Kiseleva @julia_kiseleva]

Missed today’s session? The recording is now live -- check it out and see what we’ve been building!

@ClawBio @GenomeLayer

https://t.co/1QC5QBW2G4

[Genomic Intelligence @GenomeLayer]

We are stating in 5 minutes! Still have time to join!

[Julia Kiseleva @julia_kiseleva]

222 people already registered for tomorrow’s Genomic Intelligence seminar 🚀

We’ll show how genomic models can plug into agentic biology workflows, helping interpret sequences, reason over regulatory logic, and design biological programs faster.

Join us: https://t.co/p5Nhd1bSYs

[Julia Kiseleva @julia_kiseleva]

222 people already registered for tomorrow’s Genomic Intelligence seminar 🚀

We’ll show how genomic models can plug into agentic biology workflows, helping interpret sequences, reason over regulatory logic, and design biological programs faster.

Join us: https://t.co/p5Nhd1bSYs

[Julia Kiseleva @julia_kiseleva]

Sequencing DNA is becoming easy.

Understanding what the DNA does is still hard.

In our new post, we show a ClawBio + Genomic Intelligence workflow that starts from raw genomic sequence and predicts genes, splice sites, coding regions, proteins, and function.

As a validation demo, it recovered MYC / c-Myc from a 120 kb “unknown” genomic region.

This is the future of genomics: sequence → function.

https://t.co/hMQ75NBAoH

#Genomics #AI #Bioinformatics #ComputationalBiology