Representation learning applications in biological sequence analysis

Although remarkable advances have been reported in high-throughput sequencing, the ability to aptly analyze a substantial amount of rapidly generated biological (DNA/RNA/protein) sequencing data remains critical hurdle. To tackle this issue, application natural language processing (NLP) sequence analysis has received increased attention. In method, sequences are regarded as sentences while single nucleic acids/amino acids or k-mers these represent words. Embedding is an essential step NLP, which performs conversion words into vectors. Specifically, representation learning approach used for transformation process, can be applied sequences. Vectorized then function and structure estimation, input other probabilistic models. Considering importance growing trend research, present study, we reviewed existing knowledge analysis.