High-performance ADMET prediction and PK/PD simulation — built for computational chemists, priced for real teams.
ML is the solvent.
The Platform
Dis-Solved combines stereo-aware graph neural networks with validated pharmacological rules to predict BBB permeability, transporter kinetics, cardiotoxicity, metabolism, and abuse liability — all from a single SMILES input.
Input
SMILES string
Dis-Solved Engine
GNN + pharmacological rules
ADMET Profile
Screen / advance / flag
BBB Predictor
The stereo-aware GNN model encodes 3D molecular geometry directly into the prediction, capturing chiral and conformational effects that descriptor-based methods miss. Validated on external holdout data with state-of-the-art performance.
ADMET Toolkit
Screen for transporter activity, cardiac safety, metabolic liabilities, and abuse potential in one pass.
DAT/NET/SERT substrate & blocker prediction with kinetic profiling
0.968 AUCHIGH/MODERATE/LOW scoring based on MAT profile + structural patterns
Multi-classhERG channel blocking prediction for cardiac safety screening
0.91 AUCDrug-drug interaction risk across major CYP isoforms
0.88 AUCPK/PD Simulation
Mechanistic pharmacokinetic simulation for lisdexamfetamine
Log a dose. See the curve.
Validated against 3 published datasets — paediatric to Swiss adult, 30–100 mg.
Coming soon — DoseTrack Full
Extended model: exercise, sleep, co-medications, and bodyweight-adjusted clearance. A curve personalised to your entire physiology.
Notify MeCustom PK/PD simulation
Need a bespoke simulation for a different compound, population, or dosing regimen? We build mechanistic PK/PD models to your specification.
Request Custom SimulationSocial Proof
"The BBB predictor flagged permeability issues in our lead series that we'd missed with descriptor-based methods. Genuinely useful at the screening stage."
Dr. J. Smith
Computational Chemist
"DoseTrack's PK simulations matched our clinical data remarkably well. We used it to justify dose selection in our IND filing."
Dr. A. Patel
Pharmacokineticist
Dr. R. Chen
Team
CEO & ML Research Engineer
Computational pharmacologist specialising in CNS drug discovery, GNN-based molecular property prediction, and mechanistic PK/PD modelling.
We're growing.
Hiring across computational chemistry, ML engineering, and pharmacometrics.
Get in touch →Pricing
Free for individual researchers. Usage-based pricing for teams.
Free
Full access to the web-based prediction tools — no sign-up required.
Usage-based pricing
Full programmatic access and dedicated support for production screening workflows.
Contact
Questions about the platform, custom simulations, or enterprise access?