Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for predicting off-target effects of CRISPR based on deep learning

An off-target effect and deep learning technology, applied in the field of bioinformatics, can solve problems such as low efficiency and ineffective use of genomic prior information, and achieve the effect of improving accuracy.

Active Publication Date: 2022-05-03
HUNAN UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, the prediction of off-target effects of CRISPR mainly adopts artificial methods such as biological information and experimental experience, and the efficiency is very low.
On the other hand, the current automated methods cannot effectively use the prior information of the genome, nor can they deal with the problem of label imbalance in current experimental data.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for predicting off-target effects of CRISPR based on deep learning
  • A method for predicting off-target effects of CRISPR based on deep learning
  • A method for predicting off-target effects of CRISPR based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] like figure 1 As shown, the steps of the method are described in detail below with an example:

[0050] A deep learning-based CRISPR off-target effect prediction method, comprising the following steps:

[0051] The first step is to start filtering all the genes of the human genome hg19: In order to avoid the reduction of subsequent prediction accuracy caused by too large pre-training data, it is necessary to filter out the data that is not related to the task first, and specifically find out that all PAM sequences are NGG , and then predict the sequence pair whose PAM sequence is NGG;

[0052] The second step is to preprocess the original corpus, which is divided into the following four steps:

[0053] 1. First divide the sequence with spaces as an interval;

[0054] 2. Construct a sequence sample pair, and randomly combine the two sequences,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the field of bioinformatics, and discloses a method for predicting off-target effects of CRISPR based on deep learning. By using the BERT model to extract information from the human genome, the prior information of the genome is effectively used, and the data is effectively enhanced. , and finally input the acquired features into the LightGBM method for training and prediction. The invention solves the problem of less data and data imbalance, and realizes the effective prediction of CRISPR off-target effects, which has very important promotion and application value.

Description

technical field [0001] The invention relates to a method for predicting off-target effects of CRISPR based on deep learning, belonging to the field of bioinformatics. Background technique [0002] The gene editing technology mediated by the CRISPR / Cas9 system is the third-generation "genome fixed-site editing technology" after zinc finger nucleases and transcription activator-like effector nucleases, which can edit and modify DNA sequences at specific positions . In recent years, CRISPR / Cas9 technology has been mainly used in gene knockout, gene knockin, deletion of large DNA fragments, transcription regulation, gene detection, and gene marking. However, there are still many scientific problems to be studied in this technology. For example, CRISPR / Cas9 is a single-chain enzyme, which is inherently unstable and prone to mutations leading to off-target effects. Therefore, overcoming off-target effects and improving genome editing efficiency have become urgent problems for r...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G16B15/30G16B30/00G16B40/00
CPCG16B15/30G16B30/00G16B40/00
Inventor 彭绍亮陈东舒文杰李肯立骆嘉伟刘云浩刘凡刘阳辉刘浩
Owner HUNAN UNIV