Transfer learning via multi-scale convolutional neural layers for human-virus protein-protein interaction prediction.
Reads0
Chats0
TLDR
In this article, a Siamese convolutional neural network (CNN) architecture and a multi-layer perceptron were used to predict human-virus protein-protein interactions.Abstract:
Motivation To complement experimental efforts, machine learning-based computational methods are playing an increasingly important role to predict human-virus protein-protein interactions (PPIs). Furthermore, transfer learning can effectively apply prior knowledge obtained from a large source dataset/task to a small target dataset/task, improving prediction performance. Results To predict interactions between human and viral proteins, we combine evolutionary sequence profile features with a Siamese convolutional neural network (CNN) architecture and a multi-layer perceptron. Our architecture outperforms various feature encodings-based machine learning and state-of-the-art prediction methods. As our main contribution, we introduce two transfer learning methods (i.e., 'frozen' type and 'fine-tuning' type) that reliably predict interactions in a target human-virus domain based on training in a source human-virus domain, by retraining CNN layers. Finally, we utilize the 'frozen' type transfer learning approach to predict human-SARS-CoV-2 PPIs, indicating that our predictions are topologically and functionally similar to experimentally known interactions. Supplementary information Supplementary data are available at Bioinformatics online.read more
Citations
More filters
Journal ArticleDOI
Deep learning frameworks for protein–protein interaction prediction
TL;DR: In this article , a comprehensive introduction of deep learning in protein-protein interactions (PPIs) prediction, including the diverse learning architectures, benchmarks and extended applications, is presented, and readers are referred to the references therein.
Journal ArticleDOI
MARPPI: boosting prediction of protein-protein interactions with multi-scale architecture residual network
TL;DR: In this paper , a multi-scale architecture residual network for protein-protein interactions (MARPPI) based on dual-channel and multi-feature was proposed to predict cross-species interactions.
Journal ArticleDOI
ProtInteract: A deep learning framework for predicting protein–protein interactions
TL;DR: ProtInteract as mentioned in this paper proposes an autoencoder-decoder architecture that encodes each protein's primary structure to a lower-dimensional vector while preserving its underlying sequence attributes.
Journal ArticleDOI
Recent developments of sequence-based prediction of protein–protein interactions
Yoichi Murakami,Kenji Mizuguchi +1 more
TL;DR: A brief review of sequence-based methods for protein-protein interactions (PPIs) can be found in this article , where the authors discuss key issues in this field and present future perspectives of the sequencebased PPPI predictions.
Journal ArticleDOI
Machine learning on protein-protein interaction prediction: models, challenges and trends
TL;DR: A comprehensive survey of machine learning-based methods for protein-protein interaction (PPI) detection can be found in this article , where the machine learning models applied in these methods and details of protein data representation are also outlined.
References
More filters
Journal ArticleDOI
An automated method for finding molecular complexes in large protein interaction networks.
TL;DR: A novel graph theoretic clustering algorithm, "Molecular Complex Detection" (MCODE), that detects densely connected regions in large protein-protein interaction networks that may represent molecular complexes is described.
Journal ArticleDOI
A SARS-CoV-2 protein interaction map reveals targets for drug repurposing.
David E. Gordon,Gwendolyn M. Jang,Mehdi Bouhaddou,Jiewei Xu,Kirsten Obernier,Kris M. White,Matthew J. O’Meara,Veronica V. Rezelj,Jeffrey Z. Guo,Danielle L. Swaney,Tia A. Tummino,Ruth Hüttenhain,Robyn M. Kaake,Alicia L. Richards,Beril Tutuncuoglu,Helene Foussard,Jyoti Batra,Kelsey M. Haas,Maya Modak,Minkyu Kim,Paige Haas,Benjamin J. Polacco,Hannes Braberg,Jacqueline M. Fabius,Manon Eckhardt,Margaret Soucheray,Melanie J. Bennett,Merve Cakir,Michael McGregor,Qiongyu Li,Bjoern Meyer,Ferdinand Roesch,Thomas Vallet,Alice Mac Kain,Lisa Miorin,Elena Moreno,Zun Zar Chi Naing,Yuan Zhou,Shiming Peng,Ying Shi,Ziyang Zhang,Wenqi Shen,Ilsa T Kirby,James E. Melnyk,John S. Chorba,Kevin Lou,Shizhong Dai,Inigo Barrio-Hernandez,Danish Memon,Claudia Hernandez-Armenta,Jiankun Lyu,Christopher J.P. Mathy,Tina Perica,Kala Bharath Pilla,Sai J. Ganesan,Daniel J. Saltzberg,Rakesh Ramachandran,Xi Liu,Sara Brin Rosenthal,Lorenzo Calviello,Srivats Venkataramanan,Jose Liboy-Lugo,Yizhu Lin,Xi Ping Huang,Yongfeng Liu,Stephanie A. Wankowicz,Markus Bohn,Maliheh Safari,Fatima S. Ugur,Cassandra Koh,Nastaran Sadat Savar,Quang Dinh Tran,Djoshkun Shengjuler,Sabrina J. Fletcher,Michael C. O’Neal,Yiming Cai,Jason C.J. Chang,David J. Broadhurst,Saker Klippsten,Phillip P. Sharp,Nicole A. Wenzell,Duygu Kuzuoğlu-Öztürk,Hao-Yuan Wang,Raphael Trenker,Janet M. Young,Devin A. Cavero,Devin A. Cavero,Joseph Hiatt,Joseph Hiatt,Theodore L. Roth,Ujjwal Rathore,Ujjwal Rathore,Advait Subramanian,Julia Noack,Mathieu Hubert,Robert M. Stroud,Alan D. Frankel,Oren S. Rosenberg,Kliment A. Verba,David A. Agard,Melanie Ott,Michael Emerman,Natalia Jura,Mark von Zastrow,Eric Verdin,Eric Verdin,Alan Ashworth,Olivier Schwartz,Christophe d'Enfert,Shaeri Mukherjee,Matthew P. Jacobson,Harmit S. Malik,Danica Galonić Fujimori,Trey Ideker,Charles S. Craik,Stephen N. Floor,James S. Fraser,John D. Gross,Andrej Sali,Bryan L. Roth,Davide Ruggero,Jack Taunton,Tanja Kortemme,Pedro Beltrao,Marco Vignuzzi,Adolfo García-Sastre,Kevan M. Shokat,Brian K. Shoichet,Nevan J. Krogan +128 more
TL;DR: A human–SARS-CoV-2 protein interaction map highlights cellular processes that are hijacked by the virus and that can be targeted by existing drugs, including inhibitors of mRNA translation and predicted regulators of the sigma receptors.
Journal ArticleDOI
UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches
TL;DR: The results support the use of UniRef clusters as a comprehensive and scalable alternative to native sequence databases for similarity searches and reinforces its reliability for use in functional annotation.
Journal ArticleDOI
Predicting protein-protein interactions based only on sequences information.
Juwen Shen,Jian Zhang,Xiaomin Luo,Weiliang Zhu,Kunqian Yu,Kaixian Chen,Yixue Li,Hualiang Jiang +7 more
TL;DR: Different types of PPI networks have been effectively mapped with the proposed method, suggesting that, even with only sequence information, this method could be applied to the exploration of networks for any newly discovered protein with unknown biological relativity.
Journal ArticleDOI
Transfer Learning for Visual Categorization: A Survey
Ling Shao,Fan Zhu,Xuelong Li +2 more
TL;DR: This paper surveys state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition, to find out if they can be efficiently solved.
Related Papers (5)
Machine-learning techniques for the prediction of protein–protein interactions
Debasree Sarkar,Sudipto Saha +1 more