motifNet: A Neural Network Approach for Learning Functional Sequence Patterns in mRNA

Abstract

We present a new approach for predicting functional sequence patterns in mRNA, known as motifs. These motifs play an important role in understanding the mechanisms of the cell life cycle in clinical research and drug discovery. However, many existing neural network models for mRNA event prediction only take the sequence as input, and do not consider the positional information of the sequence. In contrast, motifNet is a lightweight neural network that uses both the sequence and its positional information as input. This allows for the implicit neural representation of the various motif interaction patterns in human mRNA sequences. The model can then be used to interactively generate motif patterns and the positional effect score in mRNA activities. Additionally, motifNet can identify violations of motif patterns in real human mRNA variants that are associated with disease-related cell dysfunction.