Delivering high quality in silico estimates of human ADME/PK

Design with confidence

PROSILICO is a Swedish company focusing on the research and development of innovative technologies to provide high quality estimates of human ADME/PK (Absorption, Distribution, Metabolism, Excretion, PharmacoKinetics) directly from chemical structure.

PROSILICO’s unique data base of human clinical data provides the foundation to develop a wide scope of relevant prediction models for human ADME/PK. State of the art machine learning and AI is applied to extract the relevant information.

The PROSILICO platform has been validated by cross-validation, forward-looking predictions of new drugs on the market, and by blinded external validation.

Conformal prediction technology ensures that confidence intervals are adapted to the proper size according to the expected prediction errors for the compound chemical structure at hand.

In benchmarking studies PROSILICO outperforms in vitro methodologies in the prediction of human ADME/PK-parameters. Having significantly lower prediction errors, and in addition to that, a wider scope of applicability.

Favorable ADME/PK properties are required for drug candidates in order to obtain desirable pharmacological characteristics and minimize risks of failure in clinical studies. For this purpose reliable and validated human ADME/PK-prediction methods must be applied.

News and publications

Scientific publications

Evaluation of the reliability and applicability of human unbound brain-to-plasma concentration ratios

Fagerholm. BioRxiv November 21, 2022.https://www.biorxiv.org/content/10.1101/2022.11.14.516429v1
Scientific publications

Validation of predicted conformal intervals for prediction of human clinical pharmacokinetics

Fagerholm, Alvarsson, Hellberg, Spjuth. BioRxiv November 14, 2022. https://www.biorxiv.org/content/10.1101/2022.11.10.515917v1
News

New article and ANDROMEDA milestone- Successful validation

Validation of predicted conformal intervals for prediction of human clinical pharmacokinetics https://www.biorxiv.org/content/10.1101/2022.11.10.515917v1