Detecting of Multi-level Events in Nanopore Experiments Based on HSMM and K-means

This paper proposes a HSMM and K-means based hybrid algorithm for identifying the multi-level events in nanopore data.By means of K-means to analyze the detected blockade events,the number of current amplitude level of nanopore data can be identified,which will be taken as the input of the HSMM's number of hidden states.And then,HSMM is used to identify different level inside multi-level event and deceide the dwell times and amplitude of different levels.In the situation of third-level and fourth-level event,the simulation results show that HSMM is more accurate than Opennanopore software,and can classify the events accurately.