RESUMO
The identification of novel drug-target interactions (DTI) is critical to drug discovery and drug repurposing to address contemporary medical and public health challenges presented by emergent diseases. Historically, computational methods have framed DTI prediction as a binary classification problem (indicating whether or not a drug physically interacts with a given protein target); however, framing the problem instead as a regression-based prediction of the physiochemical binding affinity is more meaningful. With growing databases of experimentally derived drug-target interactions (e.g. Davis, Binding-DB, and Kiba), deep learning-based DTI predictors can be effectively leveraged to achieve state-of-the-art (SOTA) performance. In this work, we formulated a DTI competition as part of the coursework for a senior undergraduate machine learning course and challenged students to generate component DTI models that might surpass SOTA models and effectively combine these component models as part of a meta-model using the Reciprocal Perspective (RP) multi-view learning framework. Following 6 weeks of concerted effort, 28 student-produced component deep-learning DTI models were leveraged in this work to produce a new SOTA RP-DTI model, denoted the Meta Undergraduate Student DTI (MUSDTI) model. Through a series of experiments we demonstrate that (1) RP can considerably improve SOTA DTI prediction, (2) our new double-cold experimental design is more appropriate for emergent DTI challenges, (3) that our novel MUSDTI meta-model outperforms SOTA models, (4) that RP can improve upon individual models as an ensembling method, and finally, (5) RP can be utilized for low computation transfer learning. This work introduces a number of important revelations for the field of DTI prediction and sequence-based, pairwise prediction in general.
Assuntos
Desenvolvimento de Medicamentos , Descoberta de Drogas , Simulação por Computador , Descoberta de Drogas/métodos , Interações Medicamentosas , Humanos , Aprendizado de MáquinaRESUMO
Human and animal studies have shown that the colonic concentrations of lipid peroxidation products, such as 4-hydroxynonenal (4-HNE), are elevated in inflammatory bowel disease (IBD). However, the actions and mechanisms of these compounds on the development of IBD are unknown. Here, we show that a systemic treatment of low-dose 4-HNE exacerbates dextran sulfate sodium (DSS)-induced IBD in C57BL/6 mice, suggesting its pro-IBD actions in vivo. Treatment with 4-HNE suppressed colonic expressions of tight-junction protein occludin, impaired intestinal barrier function, enhanced translocation of lipopolysaccharide (LPS) and bacterial products from the gut into systemic circulation, leading to increased activation of Toll-like receptor 4 (TLR4) signaling in vivo. Furthermore, 4-HNE failed to promote DSS-induced IBD in Tlr4-/- mice, supporting that TLR4 signaling contributes to the pro-IBD effects of 4-HNE. Together, these results suggest that 4-HNE exacerbates the progression of IBD through activation of TLR4 signaling, and therefore could contribute to the pathogenesis of IBD.