Urban Fagerholm

This study compares five PK software tools for predicting fraction absorbed and unbound in humans, finding ANDROMEDA to be the most accurate with better quantitative and qualitative performance.

This paper evaluates simple allometry for predicting human clearance and oral clearance, finding it limited and showing improvements with in silico predictions and 2D PK-Space positioning.

The paper evaluates the accuracy of in silico, in vitro, and in vivo ADME/PK predictions for drug discovery, finding poor performance and highlighting the superiority of the ANDROMEDA software.

This paper compares Lipinski's Rule of 5 and machine learning predictions of fraction absorbed to assess oral absorption in humans, finding machine learning models more accurate.

This study evaluates in vitro assays for predicting human oral bioavailability and hepatic clearance, finding low predictive accuracy and significant inter-study variability.