🚀 The PDBe Graph Server is built for power users.
Explore the PDBe-KB Neo4j schema with AI-assisted Cypher generation - including nodes, and edges
🔗 Graph DB:
https://t.co/3dsJzPpAEh
#Neo4j#KnowledgeGraph#PDBe#AI#Cypher
🧬 Claude isn't the only AI that can query PDBe.
PDBe MCP Servers work with other AI clients too, such as Google Antigravity.
You only need one protocol for any MCP-compatible AI.
🎥 Watch the install walkthrough 👇
📦 https://t.co/NcwR2h1ipu
#PDBe#MCP#GoogleAntigravity
🧬 New tutorial video drop from @EMBL_EBI!
"Similarity Metrics & Confidence Scores in Protein Structure Prediction" by Dr. Yonathan Goldtzvik- Essential for anyone using #AlphaFold 🎯
🎥 https://t.co/ZIgv9CXPLB
#StructuralBiology#Bioinformatics#ProteinStructure#pLDDT
Connect Claude to PDBe in 3 steps:
1️⃣ Install uv
2️⃣ Run:
uvx pdbe-mcp-server --server-type pdbe_api_server
3️⃣ Add config to Claude Desktop
Now ask:
“Find X-ray structures for UniProt P12345”
📦 https://t.co/NcwR2h1ipu
#PDBe#MCP#ClaudeAI#Bioinformatics
What’s inside the PDBe MCP package?
⚡ API Server
Live structural biology data via REST-powered MCP tools
🔍 Search Server
Schema-aware Solr search across PDBe
🌐 Graph Server
Neo4j schema exploration + Cypher generation
One install.
Three servers.
Unlimited workflows
#MCP
1/6🧪 Big news for structural biology and AI: PDBe is now AI-native.
We’ve built MCP Servers that connect the Protein Data Bank in Europe and the Alphafold Protein Structure Database directly to Claude and other MCP-compatible AI systems. Here’s what that unlocks 👇
5/6 What can you build with it?
→ Ask Claude about any PDB entry in plain English.
→ Generate Cypher queries with schema awareness.
→ Build structural biology copilots.
→ Create lab assistants powered by live PDBe data.
→ Explore protein structure graphs interactively.
PDBe-SIFTS is now open source 🎉
Developed in collaboration with @PDBeurope and @uniprot , it enables fast, accurate residue-level mapping between protein sequences and structures, achieving >93% agreement with curated mappings.
Get started: https://t.co/hxH79eWZsy
Our bioRxiv paper introduces ECIFP: a scalable interaction fingerprint that maps the landscape of ligand binding modes.
✅ Identified binding modes for 9k+ ligands
✅ Analysis of 48k+ binding sites from 21k+ proteins
✅ Open-source & interpretable
more:
https://t.co/abkDFOwMeD
🚨New Syntax for PDB DOIs for Entries Released After July 21, 2027
• New entries DOI will use extended ID (e.g. 10.2210/pdb_1000axyz/pdb)
• Older entries keep 4-character DOI format (e.g. 10.2210/pdb1abc/pdb)
🔗https://t.co/mhoFAHCwbX
#PDB
🚨July 21, 2027: PDB Beta Archive replaces current PDB archive.
Key updates:
• Extended IDs (1ABC → pdb_00001abc).
• Only 12-char IDs issued.
• Data in PDBx/mmCIF & PDBML only.
All PDB users must transition to extended IDs and PDBx/mmCIF.
🔗https://t.co/LpXTcAkYdi
#PDB
🚨Updated Validation Reports for Released PDB and EMDB Entries.
Key highlights:
• Recalculated percentiles for all entries.
• New stats reflecting PDB archive as of Dec 31, 2025.
• Added Q-score percentiles.
• Improved ligand validation.
🔗https://t.co/k9DPckqhWW
#PDB
@mitsenkov, Senior Bioinformatician at AlphaFold DB, will be giving a keynote talk for @EHA_Hematology Computational Biology Training in Hematology programme, speaking with haematologists about structural biology and practical AlphaFold DB use-cases.
#AlphaFold#EHA2026
An honour to participate with works from the PDBArt project in the exhibition "Habitar lo Invisible" (Inhabiting the Invisible), organised by BioScience-App in Ayacucho, Peru.
⬇️ more ⬇️
https://t.co/Njc7L2rRSs
https://t.co/s5hOvXJNIf
#science#artㅤ
🚨 Job alert 🚨: Every published #cryoEM structure is paired with access to its underlying data. Want to help make that possible? Join the OneDep biocuration team at EBI as an EMDB biocurator: https://t.co/c5aTSYCPlV