Artificial intelligence-assisted repurposing of lubiprostone alleviates tubulointerstitial fibrosis.

Tubulointerstitial fibrosis (TIF) is the most prominent cause which leads to chronic kidney disease (CKD) and end-stage renal failure. Despite extensive research, there have been many clinical trial failures, and there is currently no effective treatment to cure renal fibrosis. This demonstrates the necessity of more effective therapies and better preclinical models to screen potential drugs for TIF. In this study, we investigated the antifibrotic effect of the machine learning-based repurposed drug, lubiprostone, validated through an advanced proximal tubule on a chip system and in vivo UUO mice model. Lubiprostone significantly downregulated TIF biomarkers including connective tissue growth factor (CTGF), extracellular matrix deposition (Fibronectin and collagen), transforming growth factor (TGF-ß) downstream signaling markers especially, Smad-2/3, matrix metalloproteinase (MMP2/9), plasminogen activator inhibitor-1 (PAI-1), EMT and JAK/STAT-3 pathway expression in the proximal tubule on a chip model and UUO model compared to the conventional 2D culture. These findings suggest that the proximal tubule on a chip model is a more physiologically relevant model for studying and identifying potential biomarkers for fibrosis compared to conventional in vitro 2D culture and alternative of an animal model. In conclusion, the high throughput Proximal tubule-on-chip system shows improved in vivo-like function and indicates the potential utility for renal fibrosis drug screening. Additionally, repurposed Lubiprostone shows an effective potency to treat TIF via inhibiting 3 major profibrotic signaling pathways such as TGFß/Smad, JAK/STAT, and epithelial-mesenchymal transition (EMT), and restores kidney function.

Drug repurposing for viral cancers: A paradigm of machine learning, deep learning, and virtual screening-based approaches.

Cancer management is major concern of health organizations and viral cancers account for approximately 15.4% of all known human cancers. Due to large number of patients, efficient treatments for viral cancers are needed. De novo drug discovery is time consuming and expensive process with high failure rate in clinical stages. To address this problem and provide treatments to patients suffering from viral cancers faster, drug repurposing emerges as an effective alternative which aims to find the other indications of the Food and Drug Administration approved drugs. Applied to viral cancers, drug repurposing studies following the niche have tried to find if already existing drugs could be used to treat viral cancers. Multiple drug repurposing approaches till date have been introduced with successful results in viral cancers and many drugs have been successfully repurposed various viral cancers. Here in this study, a critical review of viral cancer related databases, tools, and different machine learning, deep learning and virtual screening-based drug repurposing studies focusing on viral cancers is provided. Additionally, the mechanism of viral cancers is presented along with drug repurposing case study specific to each viral cancer. Finally, the limitations and challenges of various approaches along with possible solutions are provided.

Drug repurposing in psoriasis, performed by reversal of disease-associated gene expression profiles.

Psoriasis is a skin disease which results in scales on the skin caused by flaky patches. Psoriasis is triggered by various conditions such as drug reactions, trauma, and skin infection etc. Globally, there are 125 million people affected by psoriasis and yet there is no effective treatment available, and it emphasizes the need for discovery of efficacious treatments. De-novo drug development takes 10-17 years and $2-$3 billion of investment with <10 % success rate to bring drug from concept to a market ready product. A possible alternative is drug repurposing, which aims at finding other indications of already approved drugs. In this study, a computational drug repurposing framework is developed and applied to differential gene expressions of Psoriasis targets obtained from the publicly available database (GEO). This strategy uses the gene expression signatures of the Psoriasis and compares it with perturbagen available in the CMap. Based on the connected signature drugs are ranked which could possibly reverse the signatures to stop the psoriasis. The drugs with most negative connectivity scores are ranked efficient and vice versa. The top hit drugs are verified using the literature survey of the peer reviewed journal, electronic health records, patents, and hospital database. As a result, 50/150 and 37/150 drugs are confirmed to have anti-psoriasis efficacy in two datasets. Top 10 drugs are suggested as potential repurposable drugs for psoriasis. This study offers, a powerful yet simple approach for rapid identification of potential drug repurposing candidates in Psoriasis and any disease of interest.