Prediction of Pt, Ir, Ru, and Rh complexes light absorption in the therapeutic window for phototherapy using machine
V Vigna1, T F G G Cova2, A A C C Pais2
1PROMOCS Laboratory, Department of Chemistry and Chemical Technologies, University of Calabria, Arcavacata di Rende (CS), Italy. vincenzo.vigna@unical.it.
Abstract:
Effective light-based cancer treatments, such as photodynamic therapy (PDT) and photoactivated chemotherapy (PACT), rely on compounds that are activated by light efficiently, and absorb within the therapeutic window (600-850 nm). Traditional prediction methods for these light absorption properties, including Time-Dependent Density Functional Theory (TDDFT), are often computationally intensive and time-consuming. In this study, we explore a machine learning (ML) approach to predict the light absorption in the region of the therapeutic window of platinum, iridium, ruthenium, and rhodium complexes, aiming at streamlining the screening of potential photoactivatable prodrugs. By compiling a dataset of 9775 complexes from the Reaxys database, we trained six classification models, including random forests, support vector machines, and neural networks, utilizing various molecular descriptors. Our findings indicate that the Extreme Gradient Boosting Classifier (XGBC) paired with AtomPairs2D descriptors delivers the highest predictive accuracy and robustness. This ML-based method significantly accelerates the identification of suitable compounds, providing a valuable tool for the early-stage design and development of phototherapy drugs. The method also allows to change relevant structural characteristics of a base molecule using information from the supervised approach.Scientific Contribution: The proposed machine learning (ML) approach predicts the ability of transition metal-based complexes to absorb light in the UV-vis therapeutic window, a key trait for phototherapeutic agents. While ML models have been used to predict UV-vis properties of organic molecules, applying this to metal complexes is novel. The model is efficient, fast, and resource-light, using decision tree-based algorithms that provide interpretable results. This interpretability helps to understand classification rules and facilitates targeted structural modifications to convert inactive complexes into potentially active ones.
