subseq.bio

protein computational services

[subseq.bio @subseqbio]

🎆 Subseq MCP Server now supports OAuth 🎆

Now you can connect subseq directly to ChatGPT, Claude, and improved support for Claude Code and many other chat clients.

For most apps, just copy the mcp address:
https://t.co/t79B8MyzY8

Full guide: https://t.co/gqumsJpaPp

[subseq.bio @subseqbio]

🧬Update: ESMFold2 is now available on Subseq

Run fast all-atom structure prediction for proteins, DNA/RNA, complexes, and noncanonical AAs
— at scale.

Available on the web, API, and MCP for AI agents.

[Alex Rives @alexrives]

Today we're announcing ESMFold2, an open scientific engine to power prediction, design, and discovery across protein biology.

The new model delivers state of the art performance on protein interactions, especially antibodies, a critical modality for therapeutics.

We have designed and validated miniprotein binders and single chain antibodies across five therapeutic targets that are important in cancer and immunology. We are seeing very high success rates, and affinities at levels consistent with therapeutic activity.

We’re also releasing an atlas of 6.8 billion proteins, and 1.1 billion predicted structures.

ESMFold2 is built on a state of the art language model that has been trained on billions of protein sequences.

A world model of protein biology emerges through language modeling.

We’ve used the techniques of mechanistic interpretability developed to understand large language models to understand the concepts ESM uses to represent proteins.

The model’s representation space has a compositional organization of features across scales, levels of complexity, and abstraction, that reflects and mirrors the understanding of protein biology developed through a century of empirical science.

This understanding emerges without prior knowledge, just from language modeling of protein sequences.

Language models are becoming a powerful substrate to understand and program biology.

The design of protein interactions is one of the most fundamental problems in biophysics, and has critical implications for the discovery of new medicines. A simple gradient based search with the model was able to discover high-affinity protein binders.

I'm excited by the potential this has to accelerate basic science and the understanding of proteins. And especially for the new avenues it opens up for therapeutic design and medicine.

[subseq.bio @subseqbio]

🪙x402 payments now accepted!
Payments straight over HTTP — no card needed.
Agents can top up their own credits mid-run and keep running biotech jobs autonomously.
Currently supported: USDC on Base

[Emin Bursa @0xCF88]

supercharged bio workflows, gpt-5.5 w/ @subseqbio MCP server

[subseq.bio @subseqbio]

Subseq currently hosts an expanded version of RFdiffusion3 with broader symmetry support. Symmetry design is an important step in developing protein nanotechnology.
Try it out on the web, api, or mcp server at https://t.co/KgJVoTiNQZ

[Emin Bursa @0xCF88]

Unlocked all-atom symmetries in RFdiffusion3, tetrahedral, octahedral, and icosahedral, 480aa.

[Emin Bursa @0xCF88]

Here's structure prediction comparing alphafold2, with openfold3 with and without msa. gpt-5.5 xhigh took over an hour to configure the jobs, and create the animation. OF3 clearly performs much better with msa's

[subseq.bio @subseqbio]

RT @0xCF88: realizing programmable matter, staring with proteins

[subseq.bio @subseqbio]

🪅Update: OpenFold-3 is now available on subseq!

"OpenFold3-preview is a biomolecular structure prediction model aiming to be a bitwise reproduction of DeepMind's AlphaFold3"

Source: https://t.co/JPp71iqxT0

This marks the 18th, and 5th structure prediction, program on subseq.

[subseq.bio @subseqbio]

🧩 Introducing: Templates!

Now you can save and load JSON templates for any number of complex job pipelines, including customizable variables.

This simplifies multi-step pipelines into a set of variables, making for easy re-usability. Here is a demo for a 5-step template.

[subseq.bio @subseqbio]

🔮BioEmu is now available!

BioEmu is a generative protein “dynamics” model that rapidly samples realistic conformational ensembles for a given protein.

source: https://t.co/nR3VrevqWj

Try it at https://t.co/KgJVoTiNQZ, with many other pre-configured protein design programs.

[subseq.bio @subseqbio]

🎊 Chai-1 is now available!
A fast, all-atom complex structure predictor, including restraint specification.
(Source: https://t.co/SEP2xSuP0N)
Try it out at https://t.co/KgJVoTiNQZ

[subseq.bio @subseqbio]

✍️ Update!
Now you can edit data directly in the browser.
Currently text-based files supported.

[subseq.bio @subseqbio]

New icons and collapsible nav bar give more space for protein design.

[subseq.bio @subseqbio]

end-to-end jobs*

[subseq.bio @subseqbio]

🏭Introducing Pipelines

Submit a series of end-to-end from a single spec.
Use the Pipeline Builder on the UI to construct multi-step jobs, with automatic data routing.

Save or upload pipeline JSON for reusing favorite job steps. Available on UI + API.

[subseq.bio @subseqbio]

🗞️New Project Viewer!

A new UI page lets you see all assets associated with a project for better organization.

[subseq.bio @subseqbio]

📰Introducing subseq Blog!
https://t.co/3TcdscZYI0

First blog post: Intro to GROMACS for Protein Design
https://t.co/C7lifeLdc6

[subseq.bio @subseqbio]

📃New MCP docs: https://t.co/gqumsJpIEX

[subseq.bio @subseqbio]

⚡️Subseq MCP Server is now live! ⚡️

Server: https://t.co/t79B8MyzY8

Requires: Authorization: Bearer <SUBSEQ_API_KEY>
or set SUBSEQ_API_KEY env var.

[subseq.bio @subseqbio]

🔗New: Pre-signed URL's allow for quick sharing of datasets, jobs, or any individual file within them.

Anyone with the links can download the data within the expiration window.

Available on Web, API, and MCP tools.

[Emin Bursa @0xCF88]

c7 symmetric diffusion in action, unconditional backbones. One-shotted with codex using @subseqbio
rfdiffusion -> pymol+