AstraUNFOLD
Topology, Disorder, and Aggregation — Per Residue
Before you can trust a construct, you need to know how it sits in a membrane, which stretches are disordered, and where it might aggregate. AstraUNFOLD reads all three from sequence, one residue at a time.
Three Structural Reads, One Pass
Membrane topology, intrinsic disorder, and amyloid-aggregation propensity — every residue, straight from sequence, with no MSA or experimental structure.
Real Structure · LacY Transporter (PDB 1PV6) · Membrane View
Read Through the Membrane, Residue by Residue
What It Reads
Three Structural Reads at Once
One model, three per-residue tracks — the signals that decide whether a target is even workable before any mutation is scored.
Membrane Topology
Which segments cross the membrane, their orientation inside vs. out, and any N-terminal signal peptide — the layout of a membrane protein.
Intrinsic Disorder
Per-residue disorder probability and the disordered regions it resolves into — the parts that won't hold a fixed fold.
Aggregation Propensity
Amyloidogenic, aggregation-prone stretches — the sequence liabilities that sink expression and stability.
In Context
The Membrane Layout, Resolved
Topology isn't a footnote for membrane proteins — it dictates loops, termini, and where the accessible surface is. AstraUNFOLD lays out the transmembrane spans and orientation directly from the sequence.
Where It's Tested
Benchmarked Across Membrane Families
Topology and binding behaviour are evaluated at scale in the open Model Performance whitepapers — the families where getting the membrane read right matters most.
Put Astra on Your Targets
Every Astra model runs inside the Orbion platform. Bring a sequence and get the full read-out — structure, function, modifications, binding, and stability.