Drug discovery
Quantum Powered Protein DesignMaturity: concept
Machine learning has transformed structure prediction; design — going from a desired function to a sequence — is still much harder, and the gap between a predicted structure and a working protein is routinely surprising. We are looking at conformational search and interaction scoring where classical scoring functions are known to be weak. Nothing here counts without wet-lab validation, which is a field where computational and experimental results diverge often enough that nothing else does.
concept — An idea we find credible. Nothing has been built or measured.
What this is
The problem
Designing a protein to fold into a chosen structure and perform a chosen function is an enormous combinatorial search, with a scoring function that is itself approximate.
Where the current approach strains
Machine-learning methods have transformed structure prediction. Design — going from desired function to sequence — remains harder, and the gap between a predicted structure and a working protein is still routinely surprising.
What we are exploring
Conformational search and interaction scoring, in the regions where classical scoring functions are known to be weak.
What would have to be true
Wet-lab validation. Protein design is a field where computational results and experimental outcomes diverge often enough that nothing else counts.
Published as a case study on the legacy site with no experimental validation behind it, which is why it appears here as a concept.
Provenance
Published as a case study on the legacy site. It described an application concept rather than a delivered engagement with measured outcomes, so it lives here with a maturity label instead.
Previously published at https://quzones.com/case-studies/quantum-powered-protein-design/
Where it applies
Related
Accelerated Drug Screening
Virtual screening has to be cheap enough to run across a whole library and accurate enough not to throw away good molecules. Docking scores track binding affinity loosely, so shortlists carry false positives you can measure and false negatives nobody ever finds out about. We are working on scoring for the middle of the funnel, tested by whether it ranks known binders highly without being told.
Molecular Optimization
Conformation, energy, binding and molecular-property optimisation.
Targeted Drug Design
Binding affinity, selectivity and off-target risk concepts for targeted compounds.