Biohub Platform: ESM Protein Models, Atlas, and API for Biomolecular Research
Summary
This article presents the Biohub Platform, which offers a suite of tools built on the ESM family of protein language models. It highlights three main offerings: ESMFold2 for biomolecular complex structure prediction, ESMC for functional analysis and protein design, and the ESM Atlas — an open database containing functional annotations for over 6.8 billion proteins with 1.1 billion paired high-resolution predicted structures. The platform invites users to explore these tools and apply for additional credits.
Source
Twitter / XBiohub Platform: ESM Protein Models, Atlas, and API for Biomolecular Researchbiohub.aiKey quotes
· 5 pulledWelcome to the Biohub Platform — Build on the world model of protein biology.
ESMFold2 — A state-of-the-art model for biomolecular complex structure prediction.
ESMCA — A state-of-the-art protein language model powering functional analysis, structure prediction, and protein design.
ESM Atlas — An open database of functional annotations for over 6.8 billion proteins and 1.1 billion paired high-resolution predicted structures.
Apply for additional credits to power your discoveries.
You might also wanna read
ESMFold2 AI generates open-source atlas of over one billion predicted protein structures
A new open-source AI tool called ESMFold2 has generated the ESM Atlas, a database containing over one billion predicted protein structures a
flip.it·29d ago
ESMFold2 AI generates atlas of over 1 billion predicted protein structures, expanding known protein universe
A new open-source AI tool called ESMFold2 has generated the ESM Atlas, a database of over one billion predicted protein structures and billi
scientificamerican.com·1mo ago
xBind: An LLM-powered webserver for cross-molecular protein binding site prediction
xBind is a freely accessible webserver that uses large language model (LLM) embeddings from ESM-2 combined with sequence- and structure-deri
doi.org·20d ago
Build a conversational protein research assistant with Amazon Bedrock AgentCore
This article from Amazon Web Services provides a technical guide on building a conversational protein research copilot using Amazon Bedrock
aws.amazon.com·6d ago
Large-scale discovery, analysis and design of protein energy landscapes
POPSICLE: A Benchmark Suite for Machine Learning in Cryo-Electron Tomography
This article introduces POPSICLE, a benchmark suite for cryo-electron tomography (cryoET) segmentation and macromolecular localization. Buil
arxiv.org·5d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.