SpliceAI Based Analysis

Introduction of SpliceAI

In higher eukaryotes, genes mostly exist in the form of intron-exon alternation. When they are transcribed into pre-mRNA, a series of different transcripts can be produced through different splicing methods, which makes the transcriptome and proteome in organisms diverse. The splicing of pre-mRNAs into mature transcripts is remarkable for its precision, but the mechanisms by which the cellular machinery achieves such specificity are incompletely understood.

As an emerging field of machine learning, deep learning has made rapid progress in recent years with the advancement of algorithms, the accumulation of data and the improvement of computing hardware. Furthermore, it has been widely used in bioinformatics, chemistry, and biomedicine. The SpliceAI tool predicts the splicing changes caused by a single nucleotide variation based on deep learning, and accurately predicts the splicing site (location, abnormal splicing probability) from any mRNA precursor sequence. So as to identify the abnormal splicing caused by mutations in non-coding RNA regions. There are many alternative splicing caused by non-coding mutations that may cause rare diseases such as autism and intellectual disability. Therefore, the use of SpliceAI tools can assist in the research of related diseases.

Fig 1. SpliceAI: a deep neural network precisely models mRNA splicing from a genomic sequence and accurately predicts noncoding cryptic splice mutations in patients with rare genetic diseases. (Jaganathan K, et al. 2019.)

SpliceAI Analysis Process

SpliceAI, a deep residual neural network that predicts whether each position in a pre-mRNA transcript is a splice donor, splice acceptor, or neither using as input only the genomic sequence of the pre-mRNA transcript. In disease research, the analysis process of SpliceAI is as follows:

SpliceAI training.
Identify cryptic splice mutations.
De novo pathogenic mutations.

Advantages of SpliceAI

SpliceAI is based on a 32 convolutional deep neural network to accurately predict the splicing site from the mRNA precursor sequence.
SpliceAI can predict hidden splicing caused by mutations in non-coding RNA regions.
High accuracy: most of predicted cryptic splice variants validate on RNA-seq.

Application Filed

Alternative splicing analysis, especially splicing analysis of non-coding RNA regions.
Non-coding mutation related disease research.

CD ComputaBio provides splice junction analysis based on SpliceAI. With the help of artificial intelligence methods, SpliceAI uses deep neural networks to predict the location of splicing events in the genome with high accuracy. In addition to SpliceAI, we also provide other types of software for customers to analyze alternative splicing data. For splice junction analysis, we will provide you with an appropriate analysis plan based on your data. In addition, if necessary, we will provide you with the most cutting-edge analysis solutions to meet your needs. If you have any questions, please feel free to contact us, we will provide you with satisfactory data analysis services.

References

Jaganathan K, et al. Predicting Splicing from Primary Sequence with Deep Learning[J]. Cell, 2019. 176, 1–14.