Functional microRNA-Targeting Drug Discovery by Graph-Based Deep Learning

Abstract

MicroRNAs are recognized as key drivers in many cancers, but targeting them with small molecules remains a challenge. We present RiboStrike, a deep learning framework that identifies small molecules against specific microRNAs. To demonstrate its capabilities, we applied it to microRNA-21 (miR-21), a known driver of breast cancer. To ensure the selected molecules only targeted miR-21 and not other microRNAs, we also performed a counter-screen against DICER, an enzyme involved in microRNA biogenesis. Additionally, we used auxiliary models to evaluate toxicity and select the best candidates. Using datasets from various sources, we screened a pool of nine million molecules and identified eight, three of which showed anti-miR-21 activity in both reporter assays and RNA sequencing experiments. One of these was also tested in mouse models of breast cancer, resulting in a significant reduction of lung metastases. These results demonstrate RiboStrike's ability to effectively screen for microRNA-targeting compounds in cancer.

Accelerated simulation methodologies for computational vascular flow modelling

“…Operator learning techniques, such as DeepONets, are other powerful simulation techniques that have demonstrated strong generalisation capabilities, the ability to accelerate by two to five orders of magnitude, and the ability to overcome the curse of dimensionality [40,187,188]. However, operator learning is an emerging technique that has only seen a small number of applications to vascular flow problems to date [192,206].…”

“…Recent work has also investigated using physics-informed DeepONets for long-time integration of parametric partial differential equations [205]. Applications of operator learning to vascular flow problems are limited, but two examples are by Yin et al [192] and Arzani et al [206]. Yin et al [192] applied DeepONets to simulation of aortic dissection, a complex fluid–structure interaction problem.…”

“…The DeepONet was able to make predictions in less than 1 s, whereas the FEM used to produce training data took approximately 12 h to run using 20 processors. Arzani et al [206] applied an operator learning surrogate model to 2D cardiovascular flow applications, but the focus of this work was on the interpretability and generalisation rather than acceleration.…”

Analysis and Application of Antibacterial Drug Resistance Based on Deep Learning

“…The continuous development of deep learning algorithms has led to the application of more and more technologies in the medical field, promoting the continuous updating and progress of drug resistance testing methods in the medical field. At the same time, thanks to the application of deep learning technology in drug research and development, people have also made many beneficial explorations and attempts [13][14][15]. The study of gene expression and protein structure, compound screening, and the design and analysis of clinical trials for drug design are all influenced by artificial technology.…”