Samuel Callisto, Ph.D.

Senior Scientist II

Samuel joined MetrumRG in 2019 after earning his PhD in Experimental and Clinical Pharmacology with an emphasis in Pharmacometrics from the University of Minnesota College of Pharmacy. His thesis work focused on modeling cognitive side effects of the anti-epileptic drug topiramate using a combination of pharmacokinetic-pharmacodynamic models and unsupervised machine learning algorithms. While in graduate school he also researched the impact of pharmacogenomics on the pharmacokinetics and pharmacodynamics of multiple drug classes.

Recent publications by this scientist

Simulated efficacy of nerandomilast on forced vital capacity decline in idiopathic pulmonary fibrosis and progressive pulmonary fibrosis across background antifibrotic therapies

March 18, 2026

Presented at the ASCPT 2026 Annual Meeting. An exposure-response model was developed to evaluate the effect of nerandomilast on forced vital capacity (FVC) in patients with idiopathic pulmonary fibrosis (IPF) and progressive pulmonary fibrosis (PPF) , capturing both an initial “offset effect” and a long-term “disease-modifying effect” on the rate of FVC decline. The analysis confirmed a positive exposure-response relationship that is maintained regardless of the underlying diagnosis. Furthermore, simulations support using an 18 mg twice-daily dose to mitigate the reduced drug exposure associated with background pirfenidone use, ensuring a robust treatment response for patients on multi-drug regimens.

Simulated efficacy of nerandomilast on forced vital capacity decline in idiopathic pulmonary fibrosis and progressive pulmonary fibrosis across background antifibrotic therapies Samuel P. Callisto1, Kyle Baron1, Elias Clark1, Curtis Johnston1∗, Nikolas Onufrak2∗, Sonja Hartmann2∗, Steve Choy2 1Metrum Research Group, Boston, MA, U.S.A., 2Boehringer Ingelheim Pharmaceuticals, Inc., Ridgefield, CT, U.S.A. ∗Affiliation during time of analysis Introduction.   

Download PDF

Pharmacometric Machine Learning: Integrating Neural Networks for Flexible, Advanced Covariate Analysis

June 13, 2025

Presented at ASCPT 2025 Annual Meeting. Neural networks can be integrated with traditional pharmacometric models using several free open-source programming languages. Both Julia and R environments are suitable platforms, but there are tradeoffs regarding development speed, built-in capabilities, and documentation. DCM simplifies the covariate modeling process and uncovers complex, non-linear relationships in computationally efficient workflows.

Download PDF

Reinforcement Learning for Pharmacometrics: A Proof of Concept and Future Directions.

December 6, 2024

Presented at ACoP 2024. A proof-of-concept was conducted using deep reinforcement learning to optimize vancomycin dosing based on predicted PK profiles. The reinforcement learner was able to produce dose recommendations that (on average) exceeded the standard-of-care recommended dose, and future opportunities for using reinforcement learning within pharmacometrics are vast with a large potential for impact through personalized dosing.

Download PDF