Skip to main content
recep.adiyaman
back_to_home
//Research Vision

From Static Snapshots to Dynamic Ensembles

Transforming protein structure prediction from static snapshots to dynamic ensembles for de novo design and drug discovery.

> simulation.run()

The Breathing Protein

Proteins are not static statues - they vibrate, shift, and breathe. Hover the visualization to trigger a conformational shift from a closed (inactive) to an open (active) state.

Ensemble State A
Ensemble State B
STATE A · CLOSED
STATE B · OPEN
STATIC STRUCTURE
STERIC CLASH
01

Limitations of rigid-body assumptions

Conventional algorithms rely on static crystal structures, ignoring thermodynamic fluctuations.

This leads to false negatives in mutation-impact analysis, as steric clashes and entropy changes are overlooked.

02

Enhanced sampling & ensemble generation

We integrate deep-learning potentials with molecular dynamics to sample the conformational landscape.

Boltzmann-weighted ensembles capture transient states critical for function - not just the lowest-energy snapshot.

POCKET CLOSED
POCKET OPEN · BOUND
03

Cryptic pocket identification & ligand docking

We identify cryptic allosteric sites that only open in specific conformational states.

This enables rational small-molecule design for 'undruggable' targets and de novo enzyme engineering.

//Proven Track Record

CASP blind prediction results

Consistent top performance at the most rigorous international benchmarks in structural bioinformatics.

ReFOLD3 CASP13

Top-5 refinement method

CASP13 refinement category

ReFOLD4 CASP14

Best Server award

Lifts models beyond AlphaFold2 accuracy

FunFOLD5 CASP16

2nd place · ligand-pose

Surpasses AlphaFold3 server

MultiFOLD3 CAMEO

Outperforms AlphaFold3

Quaternary structure prediction

IntFOLD Server Live

30,000+ users

400,000+ jobs processed per year

ModFOLDdock2Q QA

16,000+ engineered features

Protein binder quality assessment

//Current Research · InstaDeep / BioNTech

From research to cancer vaccines

Currently building a TCR-pMHC structural prediction pipeline for the personalised cancer vaccine programme at InstaDeep (BioNTech Group), integrating AlphaFold2, Boltz-2, and Chai-1 to inform neoantigen targeting.

BS HF DK