Biopolymer characterization method, device and equipment, and computer storage medium

Abstract

The embodiment of the invention discloses a biopolymer characterization method, device and equipment, and a computer storage medium, and the method comprises the steps: carrying out the local feature extraction and time sequence feature extraction of a first electric signal of a target biopolymer through a preset neural network model, and obtaining the combined feature information of a related local feature and time sequence feature; and characterizing the target biopolymer according to the combined feature information. In this way, in the biopolymer characterization process, through the preset neural network model, the combined feature information giving consideration to the local features and the time sequence features is obtained and used for recognizing the structural unit sequence or modification information of the target biopolymer, so that the characterization result is more accurate.

Description

Technical field [0001] The present disclosure belongs to the field of biotechnology, and more particularly to characterization methods, apparatus, apparatus, and computer storage medium of biopolymers. Background technique [0002] The biopolymer is characterized by using a biopolymer to characterize the membrane array nanopore or the like, collecting the electrical signal generated by the biopolymer in the process of passing through the aperture, and then by convoluming neural network according to the collected electrical signals (Convolutional Neural NetWorks, CNN) identifies the internal structure of the biopolymer. For example, gene sequencing is performed by nanopores, and the DNA double helix chain is subjected to a rotating velocked enzyme, and DNA is split into a single screw chain, and the electrical signal of the corresponding base in the nanopore is obtained. The characteristic information of the electrical signal between the base is extracted by CNN, and the base sequ...

AI Technical Summary

Problems solved by technology

[0003] However, due to the influence of factors such as nanopores and rate-controlling enzymes, the speeds of different biopolymers passing through the nanopores are different, resulting in a large difference in the step duration of the collected electrical signals. However, due to the limitations of its own network structure, the CNN network cannot Accurate and comprehensive extraction of characteristic information of biopolymers with different electrical signal step lengths, resulting in low accuracy of final characterization results

Images