Phylo (@phylo_bio) / X

Phylo

53 posts

Phylo

@phylo_bio

A research lab studying agentic biology.

South San Francisco, CA

Joined January 2026

Phylo reposted
Yuanhao Qu
@YuanhaoQ
Jun 5
Great collaborating with @ScaleAILabs on pushing evaluations and benchmarks in drug discovery. One clear takeaway we get from this and many others: different frontier models show different strengths across biomedical task categories. Thanks @afeyzaakyurek, @TuXinming, and the
Afra Feyza Akyürek
@afeyzaakyurek
Jun 5
Excited to share a new @ScaleAILabs research in collaboration with @phylo_bio on coding agents for drug-discovery research! 💊 We ran Claude Code, Codex, and Gemini on 60+ expert-curated drug-discovery tasks inside a shared Biomni-powered biomedical research environment and the
Can Coding Agents Tackle Early-Stage Drug Discovery?
From labs.scale.com
3.3K
Phylo
@phylo_bio
May 27
Replying to @phylo_bio
2. SOD1: use ESMC-6B to prioritize ClinVar missense VUS by log-likelihood ratio and structural context
540
Phylo
@phylo_bio
May 27
Replying to @phylo_bio
We ran two example workflows in ALS biology: 1. PFN1: predict structure with ESMFold2-Fast and map known disease mutations
865
Phylo
@phylo_bio
May 27
ESMC-6B, ESMFold2, and ESMFold2-Fast are now live on Biomni Lab. Through our collaboration with @biohub, researchers can now ask Biomni to: → generate protein embeddings → run zero-shot variant effect prediction → predict structures from sequences → compare variants against
Phylo x Biohub: ESMC-6B and ESMFold2 are integrated in Biomni Lab!
From phylo.bio
13K
Phylo reposted
Yuanhao Qu
@YuanhaoQ
May 18
𝗖𝗮𝗻 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗽𝗲𝗿𝗳𝗼𝗿𝗺 𝗯𝗶𝗼𝗺𝗲𝗱𝗶𝗰𝗮𝗹 𝗱𝗮𝘁𝗮 𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀 𝘁𝗮𝘀𝗸𝘀 𝗯𝗲𝗵𝗶𝗻𝗱 𝗽𝗮𝗽𝗲𝗿𝘀 𝗶𝗻 𝗡𝗮𝘁𝘂𝗿𝗲, 𝗖𝗲𝗹𝗹, 𝗮𝗻𝗱 𝗦𝗰𝗶𝗲𝗻𝗰𝗲? To find out, we built 𝗕𝗶𝗼𝗺𝗻𝗶𝗕𝗲𝗻𝗰𝗵, a benchmark we co-developed with the original paper
35K
Phylo
@phylo_bio
May 13
Until now, AI agent ran on one machine, and one workflow at a time. A memory-heavy step crashed six hours in, and the run started over. Biomni agent now autonomously decides how many machines it needs, how much CPU and memory each task requires, spins them up, and distributes
00:00
9.7K
Phylo
@phylo_bio
May 7
Introducing the Genetic Target Hypothesis skill, co-developed with Prof. Manuel Rivas at Stanford, which transforms rare-variant burden statistics from UK Biobank into ranked therapeutic target hypotheses in minutes. In a BMI/obesity case study, the system rediscovered canonical
30K
Phylo
@phylo_bio
Apr 30
Article
Agent-managed sandboxes for scientific workloads
Since Biomni Lab launched three months ago, Biomni agent uses the standard single sandbox pattern to help researchers run diverse biomedical workloads. One piece of feedback we often receive is that...
111K
Phylo reposted
Xinming Tu
@TuXinming
Apr 29
1/9 Today, alongside the team at @phylo_bio, we are sharing our first step toward having AI build better AI benchmarks using privileged information—and there is much more to come 👀 Meet BenchGuard: an automated auditing framework for scientific agent benchmarks. 🔬👇
19K
Phylo
@phylo_bio
Apr 23
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,
9.8K
Phylo reposted
Kexin Huang
@KexinHuang5
Apr 16
I’ve spent the past decade building bio AI models—until now, training them meant years, huge cost, and teams spanning AI, biology, and infra. Not anymore. Introducing a new capability at Biomni Lab: now any scientist can create, fine-tune, pre-train, and optimize bio foundation
00:00
63K
Phylo reposted
Kexin Huang
@KexinHuang5
Apr 14
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
00:00
27K
Phylo
@phylo_bio
Apr 1
Excited to partner with @adaptyvbio! You can now design proteins, and then send them to the wet-lab - all within Biomni Lab. This pushes towards a fully close-loop integrated biology environment. Try it out today by specifying Adaptyv key in the settings page, and happy
Julian Englert
@julian_englert
Apr 1
We're officially releasing the Adaptyv API, which gives you and your AI agents access to our wet-lab to test your proteins experimentally! • Check out our demo and the docs here: agents.adaptyvbio.com • Check out how our partners @tamarindbio and @phylo_bio have
8.3K