Prediction method and device for potential BGC in genome sequence, equipment and medium

Abstract

The invention discloses a prediction method and device for potential BGC in a genome sequence, equipment and a medium, and relates to the field of artificial intelligence. The method comprises the following steps: performing structural domain prediction on each gene in a genome sequence to obtain a Pfam structural domain contained in each gene; determining a Pfam score of each Pfam structural domain, wherein the Pfam score is used for representing the probability that the Pfam structural domain belongs to the BGC; on the basis of the Pfam score of each Pfam structural domain, determining a candidate BGC in the genome sequence; and performing BGC category prediction on the candidate BGCs, and determining potential BGCs in the candidate BGCs based on a category prediction result. According to the embodiment of the invention, a dual serial prediction mechanism is adopted, the first-stage filtering of the BGC is realized according to the Pfam score, and then the second-stage filtering of the BGC is realized through category prediction on the basis of the first-stage filtering result, so that the false positive rate of the BGC prediction result is reduced.

Description

technical field [0001] The embodiments of the present application relate to the field of artificial intelligence, in particular to a method, device, equipment and medium for predicting potential BGCs in genome sequences. Background technique [0002] Biosynthetic Gene Clusters (BGC) refers to a group of genes with biosynthetic functions, which can encode and synthesize secondary metabolites (small molecular compounds), and microbial secondary metabolites are an important source of drug development. [0003] In related technologies, drug developers use machine learning methods to detect the genome sequences of bacteria or fungi, so as to discover potential BGCs related to small molecular compounds with novel structures. In the subsequent research and development process, targeted experiments can be carried out based on the discovered potential BGCs. [0004] However, when using machine learning methods for BGC prediction, the false positive rate of BGC prediction results is ...

AI Technical Summary

Problems solved by technology

[0004] However, when using machine learning methods for BGC prediction, the false positive rate of BGC prediction results is high, that is, the BGC prediction results contain a large number of non-BGCs, which is not conducive to subsequent drug development

Images