SpliceFinder: ab initio prediction of splice sites using convolutional neural network

Abstract

Background: Identifying splice sites is a necessary step to analyze the location and structure of genes. Two dinucleotides, GT and AG, are highly frequent on splice sites, and many other patterns are also on splice sites with important biological functions. Meanwhile, the dinucleotides occur frequently at the sequences without splice sites, which makes the prediction prone to generate false positives. Most existing tools select all the sequences with the two dimers and then focus on distinguishing the true splice sites from those pseudo ones. Such an approach will lead to a decrease in false positives; however, it will result in non-canonical splice sites missing. Result: We have designed SpliceFinder based on convolutional neural network (CNN) to predict splice sites. To achieve the ab initio prediction, we used human genomic data to train our neural network. An iterative approach is adopted to reconstruct the dataset, which tackles the data unbalance problem and forces the model to learn more features of splice sites. The proposed CNN obtains the classification accuracy of 90.25%, which is 10% higher than the existing algorithms. The method outperforms other existing methods in terms of area under receiver operating characteristics (AUC), recall, precision, and F1 score. Furthermore, SpliceFinder can find the exact position of splice sites on long genomic sequences with a sliding window. Compared with other state-of-the-art splice site prediction tools, SpliceFinder generates results in about half lower false positive while keeping recall higher than 0.8. Also, SpliceFinder captures the non-canonical splice sites. In addition, SpliceFinder performs well on the genomic sequences of Drosophila melanogaster, Mus musculus, Rattus, and Danio rerio without retraining. Conclusion: Based on CNN, we have proposed a new ab initio splice site prediction tool, SpliceFinder, which generates less false positives and can detect non-canonical splice sites. Additionally, SpliceFinder is transferable to other species without retraining. The source code and additional materials are available at https://gitlab.deepomics. org/wangruohan/SpliceFinder.

Prediction of Alzheimer’s disease-specific phospholipase c gamma-1 SNV by deep learning-based approach for high-throughput screening

“…Genetic variants arising due to RNA splicing are more frequently found in individuals having neurodevelopmental disorders, with variable mutation rates between the pre-messenger RNA (pre-mRNA) and mature RNA processing stages ( 3 , 4 ). These events in genetic mutation reflect marked differences in the balance of transcriptional regulation fidelity among neural networking models ( 5 ). A correlation between splicing-mediated mutation and the likelihood of response to neurodegenerative disorders (NDs), together with the identification of associations between gene mutations and clinical outcomes of NDs, can provide comprehensive information on AS for diagnosis.…”

DASSI: Differential Architecture Search for Splice Identification from DNA Sequences

“…The challenges involved in performing manual feature extraction and model training led to development of models using Artificial Neural Network (ANN) [31,32] that performed automated feature representation. Many DL architectures were used and developed for splice site prediction based on CNN [33,34,35,36,37], RNN [13,38], Restricted Boltzmann Machines (RBM) [39], Autoencoders [40,41] and Deep Belief Networks [39]. Although these DL architectures have removed the burden of manual feature extraction, they are still time consuming to train and a much deeper knowledge on SS associated functions and evolution has been strongly urged.…”

Learning Distance-Dependent Motif Interactions: An Explicitly Interpretable Neural Model of Genomic Events

“…Koo et al [2018] used a similar procedure to understand how motif number and spacing impacts prediction. Meanwhile, a back-propagation method called DeepLIFT [Shrikumar et al, 2019] identifies motifs by comparing the gradient for a sample-of-interest against a reference [Wang et al, 2019]. In contrast, our model takes inspiration from self-explanation, in which interpretability is built-in architecturally [Alvarez-Melis and Jaakkola, 2018].…”

“…Interest has gathered recently around how machine learning, especially deep convolutional neural networks (CNNs), could be used to predict genomic events like RNA splicing [Ching et al, 2018, Jaganathan et al, 2019, Wang et al, 2019, Albaradei et al, 2020. Although deep CNNs achieve good performance, they do not learn an explicit model of motif pairs or their distancedependent interactions.…”