Drug–target interaction (DTI) prediction is a challenging albeit essential task in drug repurposing. Learning on graph models has drawn special attention as they can substantially reduce drug repurposing costs and time commitment. However, many current approaches require high-demand additional information besides DTIs that complicates their evaluation process and usability. Additionally, structural differences in the learning architecture of current models hinder their fair benchmarking. In this work, we first perform an in-depth evaluation of current DTI datasets and prediction models through a robust benchmarking process and show that DTI methods based on transductive models lack generalization and lead to inflated performance when traditionally evaluated, making them unsuitable for drug repurposing. We then propose a biologically driven strategy for negative-edge subsampling and uncovered previously unknown interactions via in vitro validation, missed by traditional subsampling. Finally, we provide a toolbox from all generated resources, crucial for fair benchmarking and robust model design.

The lung epithelium is constantly exposed to harmful agents present in the air that we breathe making it highly susceptible to damage. However, in instances of injury to the lung, it exhibits a remarkable capacity to regenerate injured tissue thanks to the presence of distinct stem and progenitor cell populations along the airway and alveolar epithelium. Mechanisms of repair are affected in chronic lung diseases such as idiopathic pulmonary fibrosis (IPF), a progressive life-threatening disorder characterized by the loss of alveolar structures, wherein excessive deposition of extracellular matrix components cause the distortion of tissue architecture that limits lung function and impairs tissue repair. Here, we review the most recent findings of a study of epithelial cells with progenitor behavior that contribute to tissue repair as well as the mechanisms involved in mouse and human lung regeneration. In addition, we describe therapeutic strategies to promote or induce lung regeneration and the cell-based strategies tested in clinical trials for the treatment of IPF. Finally, we discuss the challenges, concerns and limitations of applying these therapies of cell transplantation in IPF patients. Further research is still required to develop successful strategies focused on cell-based therapies to promote lung regeneration to restore lung architecture and function.