Mechanism-first drug design
Many drugs reach clinical trials with the wrong mechanism. InterAx Deep Signal™, the engine behind every candidate we design, determines the response a drug must trigger inside the cell to achieve therapeutic efficacy and tolerability, before any animal or clinical study. That response is its target signaling profile, and we design the chemistry to trigger it.
Traditional drug discovery misses what really drives disease.
It optimizes structure and chemistry.
It refines the molecule: how it binds its target and its drug-like properties. What the drug then triggers in the cell is left to screening.
It underrates the biology.
Conventional screening reduces the cell's response to potency and efficacy (EC50 and Emax) at a single time point. The desired signaling profile is inferred from precedent or copied from a competitor, then held fixed.
The result.
Unexpected biological effects, sub-optimal efficacy or safety, and a high clinical failure rate.
GPCRs are the most tunable drug targets, and the easiest to get wrong.
GPCRs are the sensory organs of our cells and the largest family of proteins in humans. Roughly 36% of approved drugs act on them, and about 280 GPCR targets remain undrugged (Hauser et al., 2017). Yet many GPCR drugs carry sub-optimal efficacy or tolerability.
A kinase behaves like a switch: a drug turns it off while a GPCR behaves like a dimmer. A drug can push its activity up or down from baseline, by any amount, and it does so on several pathways at once, each with its own kinetics. Each of those settings is a way to get the mechanism wrong, and the error shows up only in clinical trials (Bender, 2026).
Kinase: a switch
One response: the drug turns it off.
GPCR: a dimmer, on several pathways
Up or down from baseline, by any amount, and differently on each pathway.
We extend rational drug design to the cellular mechanism, where disease outcome is decided.
Conventional design models the ligand and the target. We add the third model, the cell's response, and optimize all three together in every design cycle.
Each era has made more of drug discovery something to rationally optimize: first a compound's properties, such as bioavailability, then its binding and affinity. Mechanism-first design takes the last part still found by trial and error, efficacy and in vivo behavior.
Mechanistic signaling parameters link chemistry to clinical outcome.
A molecule and a patient are nine orders of magnitude apart, nanometers to meters, too far to map chemistry straight to outcome. Deep Signal bridges them with a compact set of mechanistic parameters, the signaling fingerprint, measured and modeled in the cell. It serves both steps below: it sets the cellular profile to aim for, and it extends structure-activity relationships to downstream signaling. InterAx does both: the signaling assays and models, and the chemistry.
1 Identify the optimal cellular profile
What the drug must trigger inside the cell to achieve therapeutic efficacy and tolerability.
- Time-resolved, multi-pathway signaling assays: cAMP, calcium, β-arrestin and receptor internalization, in human-lineage cell lines at varying receptor densities.
- A mechanistic mathematical model of the receptor's signaling, fitted to those time courses, generates the InterAx mechanistic signaling fingerprint. Potency and efficacy (EC50 and Emax), the classical parameters of pharmacology, are extended with the kinetics of each pathway.
- The fingerprint separates the measured response into the biological processes behind it, as parameters that do not depend on the assay conditions or the cellular background. They predict the response in primary cells and in vivo better than EC50 and Emax alone and, linked to clinical outcomes, show which mechanism drives therapeutic efficacy and tolerability: what the drug must do.
- The mathematical model holds cellular complexity where intuition alone cannot; in signaling, what sounds right is often wrong.
2 Build the chemistry that triggers it
Structure-activity relationships are extended to downstream signaling with molecular dynamics, quantum chemistry and machine learning, so the optimal profile is the design target from the first compound.
- GPCR molecular dynamics, covering nearly every GPCR target, and quantum chemistry.
- Ultra-large virtual screens, physics-based affinity prediction and generative AI design.
- Machine-learning property prediction and medicinal chemistry, with synthesis at contract research organizations.
- Every design-make-test-analyze cycle runs through the signaling assays, so biology and chemistry are optimized together.
We make cell signaling data that AI can learn from.
Most AI effort in drug discovery goes into the molecule, and most drugs fail on the biology. The effort goes to chemistry because its data means the same thing everywhere, whichever laboratory measured it. Cell signaling does not: the same drug gives a different potency, efficacy or bias depending on the assay, the cell line and the time point, so a model trained on such readouts learns the assay as much as the drug. InterAx produces signaling data without that defect.
AI needs data with low conditionality: a value that means the same thing wherever it was measured.
Conditionality after Bender et al., Drug Discovery Today, 2021.
Deep Signal™ removes that conditionality. The mechanistic model separates the readout into parameters of the biology itself, the same whatever the assay, so they can be learned from and compared across receptors, chemical series and tissues. It also needs far less data: the model holds the structure of the biology, so each experiment leaves only a few parameters to fit, and a handful of time courses is enough.
AI then works on both sides of the loop: on the chemistry, where generative design, property prediction and ultra-large screens propose compounds for the target profile, and on the biology, where an AI pharmacologist built on the same mechanistic models analyzes and interprets every experiment.
Five differences from conventional design.
- We read the response over time, not an endpoint. Conventional assays reduce a drug's effect to potency and efficacy, EC50 and Emax; we measure the cell's response as it unfolds, over seconds to minutes, on several pathways at once. That readout is the design target for the chemistry.
- The parameters hold outside the assay. They quantify the biological processes themselves, how the drug binds, how the receptor responds and engages its signaling partners, so they carry over to other cells and in vivo.
- Bias is measured apart from kinetics. A drug's bias between pathways, as usually estimated, changes with the time point of the assay, because the estimate mixes how strongly the drug drives each pathway with how long it stays on the receptor (Klein Herenbrink et al., 2016). The fingerprint separates the two, so the bias we design to is the drug's own, and its effect on efficacy and tolerability can be read.
- Clinical outcome shows up early. For six GLP-1 compounds with clinical data, parameters measured in cells explain their gastrointestinal side effects (R² ≥ 0.8).
- The right combination of mathematical models and experimental assays took years to build and is not quickly rebuilt.
What the engine has already measured and modeled.
Built on internal programs and research collaborations, the engine has characterized small molecules, peptides and antibodies, agonists and antagonists, orthosteric and allosteric mechanisms, from hit identification to lead optimization, in metabolic, CNS, oncology, inflammation and cardiovascular indications.