Machine learning is widely used to analyze biological sequence data. Non-sequential models such as SVMs or feed-forward neural networks are often used although they have no natural way of handling sequences of varying length. Recurrent neural networks such as the long short term memory (LSTM) model on the other hand are designed to handle sequences. In this study we demonstrate that LSTM networks predict the subcellular location of proteins given only the protein sequence with high accuracy (0.902) outperforming current state of the art algorithms. We further improve the performance by introducing convolutional filters and experiment with an attention mechanism which lets the LSTM focus on specific parts of the protein. Lastly we introduce new visualizations of both the convolutional filters and the attention mechanisms and show how they can be used to extract biological relevant knowledge from the LSTM networks.
Subcellular proteome niche discovery using semi-supervised functional clustering
University of California, Santa Cruz(加利福尼亚大学圣克鲁兹分校);Marine Chemistry and Geochemistry Department, Woods Hole Oceanographic Institution(伍兹霍尔海洋研究所);Department of Biology, Mount Allison University(蒙茅斯阿尔金大学)
DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning
Department of Computer Science ETH Zurich(计算机科学系 雪绒花大学);National Key Laboratory for Novel Software Technology, School of Computer Science Nanjing University(新型软件技术国家重点实验室 计算机科学学院 南京大学)
DeepProteomics: Protein family classification using Shallow and Deep Networks
Center for Computational Engineering and Networking (CEN)(计算工程与网络中心(CEN));Amrita School of Engineering(阿姆里塔工程学院);Amrita Vishwa Vidyapeetham(阿姆里塔维什瓦维迪亚佩瑟姆大学)
Deep Recurrent Neural Network for Protein Function Prediction from Sequence
Wyss Institute for Biologically Inspired Engineering(威斯生物启发工程研究所);School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院);Department of Systems Biology, Harvard Medical School(哈佛医学院系统生物学系)