DOI: 10.1101/508242Dec 31, 2018Paper

A new convolution model for effective bio-motif detection via rationally design the "black box"

BioRxiv : the Preprint Server for Biology
Shen JinGe Gao

Abstract

Bio-motif detection is one of essential computational tasks for bioinformatics and genomics. Based on a theoretical framework for quantitatively modeling the relationship of convolution kernel shape and the motif detection effective- ness, we design and propose a novel convolution-based model, VCNN (Variable CNN), for effective bio-motif detection via the adaptive kernel length at runtime. Empirical evaluations based on both simulated and real-world genomics data demonstrate VCNN's superior performance to classical CNN in both detection power and hyper-parameter robustness. All source code and data are available at https://github.com/gao-lab/VCNN/ freely for academic usage.

Related Concepts

Laboratory
Evaluation
Shapes
Adaptation
Immunoglobulin Variable Region
Genomics
Bio-Informatics
Detection
Protein Domain
CNN1

Related Feeds

Bioinformatics in Biomedicine (Preprints)

Bioinformatics in biomedicine incorporates computer science, biology, chemistry, medicine, mathematics and statistics. Discover the latest preprints on bioinformatics in biomedicine here.

BioRxiv & MedRxiv Preprints

BioRxiv and MedRxiv are the preprint servers for biology and health sciences respectively, operated by Cold Spring Harbor Laboratory. Here are the latest preprint articles (which are not peer-reviewed) from BioRxiv and MedRxiv.

Related Papers

IEEE Transactions on Neural Networks and Learning Systems
Heyuan ShiJiaguang Sun
IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
Henry Wing Fung YeungYuk Ying Chung
BioRxiv : the Preprint Server for Biology
Nicholas BokulichJ Gregory Caporaso
IEEE Transactions on Neural Networks and Learning Systems
Qing SongDanwei Wang
BMC Bioinformatics
Guido ZampieriGiorgio Valle
© 2021 Meta ULC. All rights reserved