Jan Ludwiczak1,2, Aleksander Winski1, Krzysztof Szczepaniak1, Vikram Alva3, Stanislaw Dunin-Horkawicz1. 1. Laboratory of Structural Bioinformatics, Centre of New Technologies, University of Warsaw, Warsaw, Poland. 2. Laboratory of Bioinformatics, Nencki Institute of Experimental Biology, Warsaw, Poland. 3. Department of Protein Evolution, Max Planck Institute for Developmental Biology, Tübingen, Germany.
Abstract
MOTIVATION: Coiled coils are protein structural domains that mediate a plethora of biological interactions, and thus their reliable annotation is crucial for studies of protein structure and function. RESULTS: Here, we report DeepCoil, a new neural network-based tool for the detection of coiled-coil domains in protein sequences. In our benchmarks, DeepCoil significantly outperformed current state-of-the-art tools, such as PCOILS and Marcoil, both in the prediction of canonical and non-canonical coiled coils. Furthermore, in a scan of the human genome with DeepCoil, we detected many coiled-coil domains that remained undetected by other methods. This higher sensitivity of DeepCoil should make it a method of choice for accurate genome-wide detection of coiled-coil domains. AVAILABILITY AND IMPLEMENTATION: DeepCoil is written in Python and utilizes the Keras machine learning library. A web server is freely available at https://toolkit.tuebingen.mpg.de/#/tools/deepcoil and a standalone version can be downloaded at https://github.com/labstructbioinf/DeepCoil. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: Coiled coils are protein structural domains that mediate a plethora of biological interactions, and thus their reliable annotation is crucial for studies of protein structure and function. RESULTS: Here, we report DeepCoil, a new neural network-based tool for the detection of coiled-coil domains in protein sequences. In our benchmarks, DeepCoil significantly outperformed current state-of-the-art tools, such as PCOILS and Marcoil, both in the prediction of canonical and non-canonical coiled coils. Furthermore, in a scan of the human genome with DeepCoil, we detected many coiled-coil domains that remained undetected by other methods. This higher sensitivity of DeepCoil should make it a method of choice for accurate genome-wide detection of coiled-coil domains. AVAILABILITY AND IMPLEMENTATION: DeepCoil is written in Python and utilizes the Keras machine learning library. A web server is freely available at https://toolkit.tuebingen.mpg.de/#/tools/deepcoil and a standalone version can be downloaded at https://github.com/labstructbioinf/DeepCoil. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: Westley Heydeck; Brian A Bayless; Alexander J Stemm-Wolf; Eileen T O'Toole; Amy S Fabritius; Courtney Ozzello; Marina Nguyen; Mark Winey Journal: J Cell Sci Date: 2020-06-04 Impact factor: 5.285
Authors: Barry T DeRose; Robert S Kelley; Roshni Ravi; Bashkim Kokona; Joris Beld; Elias T Spiliotis; Shae B Padrick Journal: Cytoskeleton (Hoboken) Date: 2020-11-23
Authors: Sydney E Cason; Peter J Carman; Claire Van Duyne; Juliet Goldsmith; Roberto Dominguez; Erika L F Holzbaur Journal: J Cell Biol Date: 2021-05-20 Impact factor: 8.077
Authors: Stephen J Fuller; Nick S Edmunds; Liam J McGuffin; Michelle A Hardyman; Joshua J Cull; Hajed O Alharbi; Daniel N Meijles; Peter H Sugden; Angela Clerk Journal: Biochem J Date: 2021-06-11 Impact factor: 3.857
Authors: Roland S Kun; Sandra Garrigues; Marcos Di Falco; Adrian Tsang; Ronald P de Vries Journal: Appl Microbiol Biotechnol Date: 2021-07-08 Impact factor: 4.813
Authors: Joshua S MacCready; Lisa Tran; Joseph L Basalla; Pusparanee Hakim; Anthony G Vecchiarelli Journal: Mol Microbiol Date: 2021-03-08 Impact factor: 3.501