Industry 6

Pharma & life sciences

Discovery chemistry, structural biology and formulation science: long-acting injectables and excipients.

Written for

Discovery chemistry, structural biology and formulation science: long-acting injectables and excipients.

The decision

Which pocket to target before the assay campaign; which carrier or excipient to take to the bench.

How it is done today

Assay campaigns per target; formulation screens by trial and error.

When it goes wrong An assay campaign per target takes months; a failed formulation screen costs a bench quarter.

Applications

ApplicationYou giveYou getStatus
Allosteric site prediction from the structure file

Proof: AUC 0.89; energetics within 1.4%

A PDB or mmCIF fileA ranked residue list from structure aloneLive on quantum hardware
Formulation and excipient candidate ranking

Proof: Live with a formulation partner on long-acting injectables

Candidate carriers or excipientsThe ordering and the smallest difference between neighbours it resolvesLive on quantum hardware
Drug-candidate and fragment energeticsCandidate fragments or active spacesBinding energetics, with the smallest difference it resolves statedReady · computed, hardware next
Protein–ligand interaction energeticsThe complexInteraction energetics, with the smallest difference it resolves statedReady · computed, hardware next
Clinical and hospital shift schedulingStaff, shifts and rulesA rotaDeployed through the platform network
Medical-imaging classificationLabelled imagesA classifier and its accuracyDeployed through the platform network

What changes for you

  • A ranked site list from structure alone, with no assay data.
  • Formulation candidates ranked before the bench.
  • The scope is stated: it does not rank drug candidates, and on the public benchmark the current best method still leads.

First engagement

You send One structure file, PDB or mmCIF.

You get back The ranked sites. Two weeks.

Proof · Allosteric site prediction

Research result

AUC 0.89

on an independent biological benchmark, for sites read from the structure file alone; site energetics within 1.4% of reference

Measured on quantum hardwareClassical computationPlatform quantum hardware plus simulation

Decision

Which pocket to target before the assay

What is modelled

Site energetics of the protein, from the structure file alone, with no assay data.

Operational outcome

  • Ranked candidate sites before the assay
  • Site energetics within 1.4% of reference
  • Fewer assays on sites that will not bind
Problem size
Whole-protein structure files · per-site energetics
Scope
A site-prediction method; it does not rank drug candidates, and on the public benchmark the current best method still leads.

Results, each with its baseline

  • Site energetics within 1.4% of the exact reference at the validated size.Measured on quantum hardwareClassical computationWhere quantum hardware plus simulation
  • AUC 0.89 on an independent biological benchmark, for sites read from the structure file alone.Classical computationWhere simulation

Benchmark

Pharma & life sciencesAllosteric site prediction

Published reference

Peptides of 14–16 residues folded on 46–61 trapped-ion qubits reach the classical reference energy on some instances.

Sources: arXiv:2604.26861

Merlin

AUC 0.89 on an independent biological benchmark · site energetics within 1.4% of reference

Measured on quantum hardwareClassical computation

Baseline

Exact references; an independent biological benchmark

Read the story

Your industry, next

Bring us the decision your industry has to make next.

A resist, a grid plan, a controller, a cipher: you get the answer, the method it was checked against, and its status. The free check runs in your browser.

No keyNo cardAn answer in about a second