raganelė mark raganelė
Full atlas
65 of 800+ modules shown
Hallmarks
Tumour types
Cardiovascular
Metabolic
Immune
CNS
Substrate
—

—

—

Variables tracked—
Direct edges (atlas view)—
Couplings in full body≫ shown — curated
00Coupled-physiology programs

Most blockbusters aren't new molecules. They're new schedules.

The whole organism, as one program. We discover dose schedules, drug combinations, and repurposing candidates against coupled human physiology — for pharma, biotech, and academic research.

NOT AN LLM. A composed system of ordinary differential equations, parameterised from peer-reviewed studies, solved end-to-end using proprietary computational techniques rooted in quantitative finance. Every output is a reproducible numerical solution — not generated text.

Start the tour ↓ Engage
01Dose & schedule design

The dose is the model output, not the model input.

Given a tumour model coupled to bone marrow, plasma drug kinetics, and hepatic clearance, we search the schedule — daily dose, holiday weeks, ramp-up, intermittent dosing — that maximises response under a marrow-toxicity constraint. The chain on the right is the minimum required to compute it.

$$ \begin{aligned} \frac{d\,\text{Prol}}{dt} &= k_{\text{prol}} \left(\frac{\text{Circ}_0}{\text{Circ}}\right)^{\!\gamma}\!\bigl(1 - E_{\text{drug}}(C)\bigr)\,\text{Prol} \;-\; k_{tr}\,\text{Prol} \\[4pt] E_{\text{drug}}(C) &= \frac{E_{\max}\, C^{h}}{EC_{50}^{\,h} + C^{h}} \\[4pt] \min_{D(t),\,\tau} &\; \int \Bigl[ -w_r \cdot \text{Tumour}(t) \;+\; w_{\text{tox}}\!\cdot\!\max\!\bigl(0,\, \text{ANC}_{\text{thr}} - \text{ANC}(t)\bigr) \Bigr]\, dt \end{aligned} $$
Anchor: Friberg L, Henningsson A, Maas H et al. J Clin Oncol 2002;20(24):4713–21.

We expose: daily dose, drug-holiday length, ramp profile, max cumulative dose. The optimiser balances tumour AUC vs neutrophil nadir vs hepatic enzyme rise. Wall-clock per schedule sweep: seconds, not days.

02Combinations & interactions

Two drugs, one body — predicted synergy and shared toxicity, in the same pass.

Combination response is rarely additive. Our composed body computes the cross product of approved drugs against a target indication, scoring each pair on response surface (Bliss / Loewe) and on shared toxicity routes — most commonly competitive CYP inhibition and overlapping marrow suppression.

$$ \begin{aligned} E_{A+B}^{\text{Bliss}} &= E_A + E_B - E_A\, E_B \\[3pt] \Delta E_{\text{syn}} &= E_{A+B}^{\text{obs}} \;-\; E_{A+B}^{\text{Bliss}} \\[3pt] v_{\text{CYP}} &= \frac{V_{\max}\,[S]}{K_m\!\left(1 + \dfrac{[I]}{K_i}\right) + [S]} \end{aligned} $$
Anchor: Bliss CI, Ann Appl Biol 1939;26:585; Segel IH, Enzyme Kinetics, Wiley 1975.

Surfaces a small set of high-synergy / low-shared-tox candidate pairs out of the 100-million-pair search space. Pre-filters before any wet-lab confirmation.

03Repurposing & rare disease

Look at the mechanism. Find drugs whose mechanism happens to hit it.

Pick an under-served indication. We score every approved compound by how its mechanism (target affinities, off-target hallmark profile, tissue penetration) matches the indication's hallmark signature, subtracting toxicity through shared substrates.

$$ \begin{aligned} \text{score}(d, I) &= \sum_{h}\, w_h\,\text{Hit}(d, h)\,\text{Need}(I, h) \;-\; \lambda \sum_{o}\, \text{Tox}(d, o) \\[4pt] \text{Hit}(d, h) &= \mathbb{1}\!\left[\, C_{\text{tissue}}(d) > EC_{50}\bigl(d,\, \text{target}_h\bigr) \right] \end{aligned} $$
Framework adapted from Hopkins AL, Nat Chem Biol 2008;4:682; Cheng F et al. Nat Commun 2019;10:1197.

Output: a ranked shortlist of plausible repurposing candidates with a defensible mechanism story, ready for a focused in-vitro panel.

04Trial replication & extension

Replicate the published trial. Then extend to the patients the original sponsor did not study.

For any published Phase II / III, we generate a virtual cohort matched to the trial's demographics, apply the same dosing protocol, and check that endpoint distributions land within the reported confidence intervals. Then we change the cohort and recompute.

$$ \begin{aligned} \theta_i &\sim \mathcal{N}\!\bigl(\mu_{\text{pop}}, \Sigma_{\text{pop}}\bigr), \quad i = 1,\ldots,N \\[2pt] Y_i(t) &= M\!\bigl(\theta_i,\, \text{dose}(t)\bigr) \\[2pt] \hat{P}\!\bigl(Y > \text{thr}\bigr) &= \frac{1}{N}\sum_i \mathbb{1}\!\bigl[Y_i > \text{thr}\bigr] \;\approx\; P^{\text{trial}} \\[4pt] \theta'_i &\sim \mathcal{N}(\mu', \Sigma') \;\Longrightarrow\; \hat{P}'\!\bigl(Y > \text{thr}\bigr) \end{aligned} $$
Anchor: Allen RJ, Rieger TR, Musante CJ, CPT Pharmacomet Syst Pharmacol 2016;5:140.

39 published trials replicated. Useful for label-extension scoping, off-label safety, sub-population dose adjustment.

05Adverse-event counterfactuals

What would the AE rate have looked like if drug A's CYP inhibition had been flagged at IND?

A drug-induced cardiac event in a real trial usually reflects an interaction — the indexed drug shifts hepatic CYP3A4 activity, a comedication's AUC rises, QTc prolongs, the patient flags TdP. Our model runs the counterfactual.

$$ \begin{aligned} \text{AUC}_{B \mid A} &= \text{AUC}_B^{(0)} \cdot \left(1 + \frac{[A]_p}{K_{i,\, A\to\text{CYP3A4}}}\right) \\[3pt] \Delta\text{QTc} &= \beta\,\bigl(C_{\max,\,B \mid A} - C_{\max,\,B}^{(0)}\bigr)^{\!\alpha} \\[3pt] \text{TdP}_{\text{rate}}^{\text{cf}} &= \frac{1}{N}\sum_i \mathbb{1}\!\bigl[\Delta\text{QTc}_i > 60\,\text{ms}\bigr] \end{aligned} $$
Anchor: O'Hara T, Rudy Y, PLoS Comput Biol 2011;7:e1002061; Roden DM, NEJM 2004;350:1013.

Used for retrospective AE attribution, prospective IND CYP-screen prioritisation, label-language scoping.

06Delivery & PK/PD

Formulation, route, depot — scored on what reaches the target.

Oral, SC, IV, IM, depot, inhaled, intranasal — every route lands on a different gut / hepatic / lymphatic / nasal substrate, and the bioavailability into the target organ depends on the chain.

$$ \begin{aligned} \frac{dC_p}{dt} &= \frac{F \cdot k_a \cdot D}{V_c}\, e^{-k_a t} \;-\; k_e\, C_p \\[3pt] F &= F_a\, F_g\, F_h, \quad F_h = 1 - E_h \\[3pt] C_{\text{target}}(t) &= k_{p,t}\, C_p(t) \end{aligned} $$
Anchor: Rowland M, Tozer TN, Clinical Pharmacokinetics & Pharmacodynamics, 5th ed., LWW 2019; Wilkinson GR, NEJM 2005;352:2211.

Surfaces formulation re-ranking, route trade-offs, depot-vs-daily, BBB-penetration likelihood.

07Engage

One body, one model, one conversation. Bring the question.

Pharma, biotech, academic research. We start with a worked example on your published case, then scale.

Engage → All programs