Background Interactions between microRNAs and RNA-binding proteins are crucial for microRNA-mediated gene regulation and sorting. The molecular mechanisms underlying these protein interactions with small RNAs remain largely under-studied, apart from sequence motifs identified on microRNAs. To date, only a limited number of microRNA-binding proteins have been confirmed, typically through labor-intensive experimental procedures. Advanced bioinformatics tools are urgently needed to facilitate this research.
Methods DeepMiRBP is a novel hybrid deep learning model designed to predict microRNA-binding proteins by modeling molecular interactions. This innovation approach is the first to target the interactions between small RNAs and proteins specifically. DeepMiRBP consists of two main components. The first component employs bidirectional long short-term memory (Bi-LSTM) neural networks to capture sequential dependencies and context within RNA sequences, attention mechanisms to enhance the model’s focus on the most relevant features and transfer learning to apply knowledge gained from a large dataset of RNA-protein binding sites to the specific task of predicting microRNA-protein interactions. Cosine similarity is applied to assess RNA similarities. The second component utilizes Convolutional Neural Networks (CNNs) to process the spatial data inherent in protein structures based on Position-Specific Scoring Matrices (PSSM) and contact maps to generate detailed and accurate representations of potential microRNA-binding sites and assess protein similarities.
Results Our DeepMiRBP method reported a prediction accuracy of 87.4 via training and 85.4 using testing, with an F score of 0.860. Additionally, we have applied three case studies to further validate the method using recently reported evidence on miRNA interactions, including miR-451, -19b, -23a, -21, -223, and -let-7d. Using DeepMiRBP, we accurately predict known microRNA interactions with recently discovered RNA binding proteins identified in different exosomes, including AGO, YBX1, and FXR2.
Conclusions Our proposed DeepMiRBP strategy represents the first of its kind designed for microRNA-protein interaction prediction. Its promising performance underscores the model’s potential to identify novel interactions involved in small RNA sorting and packaging and infer new RNA transporter proteins. The methodologies and insights from DeepMiRBP offer a scalable template for future small RNA research, from mechanistic discovery to modeling disease-related cell-to-cell communication, emphasizing its adaptability and potential for developing novel small RNA-centric therapeutic interventions and personalized medicine.