A Transfer Learning Exploited for Indexing Protein Structures from 3D Point Clouds
In this paper, we propose a transfer learning-based methodology that can be exploited for indexing protein structures from associated 3D point clouds. Such a methodology can be particularly useful for biologists that are searching automated solutions to find family members of a query protein or even to label new structures by directly using input raw 3D point clouds. Comparative study and performance evaluation show the efficiency and the potential of the proposed methodology.
KeywordsTransfer learning Protein structure analysis Indexing 3D point clouds PDB Biomedical imaging
The authors particularly thank F. Langenfeld, organizing member of the SCHREC 2018 challenge for his assistance and the double-check of the performance rates for our method presented in Table 1. They thank F. Malbranque, V. Tondeux, A. Jaffrezic and J. Xu for deploying the processing pipeline.
- 1.Benhabiles, H., Aubreton, O., Barki, H., Tabia, H.: Fast simplification with sharp feature preserving for 3D point clouds. In: 2013 11th International Symposium on Programming and Systems (ISPS), pp. 47–52, April 2013. https://doi.org/10.1109/ISPS.2013.6581492
- 6.Langenfeld, F., et al.: SHREC 2018 protein shape retrieval. In: Eurographics Workshop on 3D Object Retrieval, pp. 53–61, April 2018. https://doi.org/10.2312/3dor.20181053
- 8.Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the Computer Vision and Pattern Recognition (CVPR). IEEE (2017)Google Scholar
- 9.Ritter, J.: An efficient bounding sphere. In: Graphics Gems, pp. 301–303. Academic Press Professional Inc., San Diego (1990)Google Scholar
- 10.Rubner, Y., Tomasi, C., Guibas, L.J.: A metric for distributions with applications to image databases. In: IEEE International Conference on Computer Vision, pp. 59–66, Bombay, India, 9–13 May 1998Google Scholar
- 11.Rusu, R.B., Cousins, S.: 3D is here: point cloud library (PCL). In: IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, 9–13 May 2011Google Scholar
- 12.Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The Princeton shape benchmark. In: Proceedings Shape Modeling Applications, pp. 167–178 (2004). https://doi.org/10.1109/SMI.2004.1314504
- 14.Yang, H.: Protein surface analysis by dimension reduction with applications in functional annotation and drug target prediction. Ph.D. thesis, Drexel University (2015)Google Scholar