Learning Chemotherapy Drug Action via Universal Physics-Informed Neural Networks
This work addresses the need for automated model construction in drug development, but it is incremental as it uses existing methods on synthetic data without real-world validation.
The authors tackled the problem of constructing quantitative systems pharmacology models for chemotherapy drug action by applying Universal Physics-Informed Neural Networks to learn unknown components from synthetic data, achieving parameter fitting for multiple datasets and learning net proliferation rates in doxorubicin models as toy examples.
Quantitative systems pharmacology (QSP) is widely used to assess drug effects and toxicity before the drug goes to clinical trial. However, significant manual distillation of the literature is needed in order to construct a QSP model. Parameters may need to be fit, and simplifying assumptions of the model need to be made. In this work, we apply Universal Physics-Informed Neural Networks (UPINNs) to learn unknown components of various differential equations that model chemotherapy pharmacodynamics. We learn three commonly employed chemotherapeutic drug actions (log-kill, Norton-Simon, and E_max) from synthetic data. Then, we use the UPINN method to fit the parameters for several synthetic datasets simultaneously. Finally, we learn the net proliferation rate in a model of doxorubicin (a chemotherapeutic) pharmacodynamics. As these are only toy examples, we highlight the usefulness of UPINNs in learning unknown terms in pharmacodynamic and pharmacokinetic models.