A Transfer Learning Exploited for Indexing Protein Structures from 3D Point Clouds

@inproceedings{Benhabiles2018ATL,
  title={A Transfer Learning Exploited for Indexing Protein Structures from 3D Point Clouds},
  author={Halim Benhabiles and Karim Hammoudi and F{\'e}ryal Windal and Mahmoud Melkemi and Adnane Cabani},
  booktitle={SaMBa@MICCAI},
  year={2018},
  url={https://api.semanticscholar.org/CorpusID:84182210}
}
Comparative study and performance evaluation show the efficiency and the potential of the proposed transfer learning-based methodology for indexing protein structures from associated 3D point clouds.
View via Publisher
7 Citations
Background Citations
1
Methods Citations
1

7 Citations

Predicting protein functional sites through deep graph convolutional neural networks on atomic point-clouds

A novel protein functional site predictor that avoids this expensive representation and instead leverages point-clouds as protein embeddings and is a state-of-the-art graph convolutional neural network (GCNN), which has been shown to be effective when analyzing spatial information.

SHREC 2020: Multi-domain protein shape retrieval challenge

Surface-based protein domains retrieval methods from a SHREC2021 challenge.

Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey

SHREC 2021: Surface-based Protein Domains Retrieval

This work assesses the ability of five methods to retrieve similar protein surfaces, using either their shape only (3D meshes), or their shape and the electrostatic potential at their surface, an important surface property.

BioS2Net: Holistic Structural and Sequential Analysis of Biomolecules Using a Deep Neural Network

The accuracy of BioS2Net obtained on the eDD dataset was comparable to results achieved by previously published methods, confirming that the algorithm described in this article is a top-class solution for protein fold recognition.

Deep Learning based Detection of Hair Loss Levels from Facial Images

This paper investigates deep learning methods for detecting hairs loss levels by men from face images with the potential and the efficiency for medical, security and commercial applications.

13 References

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

A Machine Learning Approach for Hot-Spot Detection at Protein-Protein Interfaces

This work describes a more accurate methodology to predict Hot-Spots in protein-protein interfaces from their native complex structure compared to previous published Machine Learning (ML) techniques.

PDB-Explorer: a web-based interactive map of the protein data bank in shape space

The essentially instantaneous 3DP-similarity search with the PDB-Explorer provides results comparable to those of much slower 3D-alignment algorithms, and automatically clusters proteins from the same superfamilies in tight groups.

Protein Shape Retrieval

Fast simplification with sharp feature preserving for 3D point clouds

This paper presents a fast point cloud simplification method that allows to preserve sharp edge points preserving and is much faster than the last proposed simplification algorithm, and still produces similar results.

The Princeton Shape Benchmark

It is concluded that no single descriptor is best for all classifications, and thus the main contribution of this paper is to provide a framework to determine the conditions under which each descriptor performs best.

SCOPe: Manual Curation and Artifact Removal in the Structural Classification of Proteins - extended Database.

A metric for distributions with applications to image databases

This paper uses the Earth Mover's Distance to exhibit the structure of color-distribution and texture spaces by means of Multi-Dimensional Scaling displays, and proposes a novel approach to the problem of navigating through a collection of color images, which leads to a new paradigm for image database search.

Electronic Reprint Biological Crystallography the Protein Data Bank Biological Crystallography the Protein Data Bank

The goals of the PDB are described, the systems in place for data deposition and access, how to obtain further information and plans for the future development of the resource are described.

The relationship between protein structure and function: a comprehensive survey with application to the yeast genome.

It is found that the major SCOP fold classes have different propensities to carry out certain broad categories of functions, and that the functions of the most ancient proteins are more evenly distributed among different structural classes than those of more modern ones.