Dipan Shaw1, Hao Chen1, Tao Jiang1,2. 1. Department of Computer Science and Engineering, University of California, Riverside, CA, USA. 2. Bioinformatics Division, BNRIST/Department of Computer Science and Technology, Tsinghua University, Beijing, China.
Abstract
MOTIVATION: Isoforms are mRNAs produced from the same gene locus by alternative splicing and may have different functions. Although gene functions have been studied extensively, little is known about the specific functions of isoforms. Recently, some computational approaches based on multiple instance learning have been proposed to predict isoform functions from annotated gene functions and expression data, but their performance is far from being desirable primarily due to the lack of labeled training data. To improve the performance on this problem, we propose a novel deep learning method, DeepIsoFun, that combines multiple instance learning with domain adaptation. The latter technique helps to transfer the knowledge of gene functions to the prediction of isoform functions and provides additional labeled training data. Our model is trained on a deep neural network architecture so that it can adapt to different expression distributions associated with different gene ontology terms. RESULTS: We evaluated the performance of DeepIsoFun on three expression datasets of human and mouse collected from SRA studies at different times. On each dataset, DeepIsoFun performed significantly better than the existing methods. In terms of area under the receiver operating characteristics curve, our method acquired at least 26% improvement and in terms of area under the precision-recall curve, it acquired at least 10% improvement over the state-of-the-art methods. In addition, we also study the divergence of the functions predicted by our method for isoforms from the same gene and the overall correlation between expression similarity and the similarity of predicted functions. AVAILABILITY AND IMPLEMENTATION: https://github.com/dls03/DeepIsoFun/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: Isoforms are mRNAs produced from the same gene locus by alternative splicing and may have different functions. Although gene functions have been studied extensively, little is known about the specific functions of isoforms. Recently, some computational approaches based on multiple instance learning have been proposed to predict isoform functions from annotated gene functions and expression data, but their performance is far from being desirable primarily due to the lack of labeled training data. To improve the performance on this problem, we propose a novel deep learning method, DeepIsoFun, that combines multiple instance learning with domain adaptation. The latter technique helps to transfer the knowledge of gene functions to the prediction of isoform functions and provides additional labeled training data. Our model is trained on a deep neural network architecture so that it can adapt to different expression distributions associated with different gene ontology terms. RESULTS: We evaluated the performance of DeepIsoFun on three expression datasets of human and mouse collected from SRA studies at different times. On each dataset, DeepIsoFun performed significantly better than the existing methods. In terms of area under the receiver operating characteristics curve, our method acquired at least 26% improvement and in terms of area under the precision-recall curve, it acquired at least 10% improvement over the state-of-the-art methods. In addition, we also study the divergence of the functions predicted by our method for isoforms from the same gene and the overall correlation between expression similarity and the similarity of predicted functions. AVAILABILITY AND IMPLEMENTATION: https://github.com/dls03/DeepIsoFun/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: L M Gallego-Paez; M C Bordone; A C Leote; N Saraiva-Agostinho; M Ascensão-Ferreira; N L Barbosa-Morais Journal: Hum Genet Date: 2017-04-03 Impact factor: 4.132
Authors: Eric T Wang; Rickard Sandberg; Shujun Luo; Irina Khrebtukova; Lu Zhang; Christine Mayr; Stephen F Kingsmore; Gary P Schroth; Christopher B Burge Journal: Nature Date: 2008-11-27 Impact factor: 49.962
Authors: Fernando Pozo; Laura Martinez-Gomez; Thomas A Walsh; José Manuel Rodriguez; Tomas Di Domenico; Federico Abascal; Jesús Vazquez; Michael L Tress Journal: NAR Genom Bioinform Date: 2021-05-22