Team:Phystech Moscow/Implementation



Our lncRNA interaction predicting model will help researchers from all over the world to understand better the molecular mechanisms of small molecule interactions. It specifies the way the molecules interact as well as the way researchers can narrow down the number of potential candidates. It optimizes the work with RNA both in terms of saving money and time and increasing awareness. Cells produce thousands of non-coding RNAs that are involved in genome transcription and control gene expression at different levels. Non-coding RNAs play a crucial role in many diseases. Biological experiments with lncRNA are a high cost and labour-consuming process. Although the number of interactions between miRNA and lncRNA is increasing, it is still insufficient. Bioinformatics researchers can use computational methods to create a deep learning-based prediction model which effectively predicts large-scale lncRNA-miRNA interactions.

While the regulatory functions of lncRNA play an important role in the development and treatment of many human diseases, the algorithms explaining the interaction between lncRNA and miRNA become more attractive for the biopharmaceutical industry. New drug discovery design is a complicated, expensive, time-consuming process. Many biopharmaceutical facilities are seeking the way to reduce the cost and speed up the development process. One of the drug development optimization solutions is the incorporation of computer-aided drug design methods. For the best user experience, our team plans to build a useful online service based on a developed prediction model. Additionally, the model will have open-source project status to enable researchers to customise and improve it.