Search the PDBthe way you think about biology

We distilled 240,000+ PDB entries into rich queryable texts, spanning protein structure, function, chemistry, and more.

01 / Disparate Data
240,000+ PDBs
UniProt & GO
Computed metrics
02 / Synthesis text
Structured Profile

Queryable text covering function, structure, and context.

FunctionChemistryBinding
Same record, different surface

What changes is not the data.It’s the text.

We synthesize metadata, annotations, and computed features into profiles optimized for search.

BeforeTraditional PDB entry
9PC9
Title
Structure of Synaptic Vesicle Protein 2A Bound to UCB7361
Identifiers / source
Homo sapiens · Electron microscopy, 2.91 Å
Protein family
PF00083
Ligands
A1CHN (Subject of Investigation/LOI)
What’s missing
  • Ligand appears as an internal code (A1CHN), not usable chemistry
  • No pocket information (size, hydrophobicity, accessibility)
  • No in-depth functional description
With ProtplexStructured profile
9PC9

Human synaptic vesicle protein 2A (SV2A) is a multi-pass membrane protein that facilitates regulated neurotransmitter release and selectively enhances low‑frequency synaptic transmission. The structure shows Major Facilitator Superfamily / sugar-transporter–like transmembrane domains and an inhibitor, UCB7361, bound in the transmembrane region.

Filled in
  • Ligand identified as inhibitor
  • Pocket characteristics described
  • Biological role detailed

Why semantic search wins here

Structural biology queries are multi-dimensional by nature. Keyword search forces you to flatten them.

Multi-dimensional queries

One query can cross every dimension of the deposited record — from molecular role to pocket shape to crystallization conditions. No need to chain field-based searches or browse ontology trees.

Concept-level search

Search by ideas — "intersubunit pocket," "intramembrane cavity," "post-hydrolysis conformation" — not only IDs, gene names, or controlled vocabulary.

Every entry, equally searchable

An AI chatbot returns a handful of well-known hits skewed by training frequency. Protplex lets you scroll through hundreds of results — including obscure depositions — because semantic search ranks every entry on the same footing.

What’s next

Expanding thesearch surface

Today you can search by molecular role, binding character, and assembly. We’re adding dimensions that matter most for experimental reuse — so you can find structures worth building on, not just structures that match a keyword.

Functional states
Search by biological state: apo vs inhibitor-bound, open vs closed, pre- vs post-cleavage.
Pocket geometry
Find proteins by the character of their binding sites: buried cavities, intersubunit pockets, membrane-embedded channels.
Experimental context
Match lab conditions that matter for replication: pH, cofactors, detergents, constructs, method, and resolution.

Get early access

Help shape this tool. leave your email and we’ll be in touch.

No spam. Unsubscribe anytime. We only email about Protplex.

Get in touch

Questions, feedback, or collaboration ideas. We welcome hearing from you.

Your email is used only for direct communication about Protplex. We do not share or sell contact information.