Machine Learning and Graph Analytics in Computational Biomedicine

  in Special Issue   Posted on July 20, 2016

Information for the Special Issue

Special Issue Call for Papers:

Aims and Scope:

In recent years, computational methods have been broadly and extensively employed in the biomedicine researches, including medical image analysis, healthcare informatics, and cancer genomics. In particular, many computational problems can be formulated as the prediction task on the biomedical data, such as tumor images, electronic medical records, micro-array, and GWAS data. Therefore, a growing number of machine learning and graph analytics algorithms were employed in the prediction tasks of computational biomedicine.

Machine learning and graph analytics techniques have advanced quickly over the past few years. Several high-impact novel methods were reported in the top journals and conferences. For example, affinity propagation was published in Science as a novel clustering algorithm, and deep learning has become a hot topic in the predictions and classifications which is capable of processing big data. Parallel mechanisms, such as Spark and Mahout, are also developed by the scholar and industry researchers to speed up the algorithm. Computer scientists have been devoting themselves to the advanced large scale machine learning and graph analytics techniques. However, the applications on biomedicine are limited and fall far behind the techniques.

This special issue will target the recent large-scale machine learning and graph analytics techniques in biomedical applications. We especially welcome the novel machine learning algorithms and integrative network modeling approaches, such as strategies for large and imbalanced learning, strategies for learning with multiple views, strategies for various semi-supervised learning, strategies for multiple kernels learning, integrative network analysis of multi-scale data, random walk and shortest path analysis on heterogeneous network, etc. Applications on medical and biological large-scale data are strongly encouraged. However, machine learning or graph theory without biomedical application will not be accepted. We also encourage authors to contribute their codes and experimental data available to the public, which would make our special issue more infusive and attractive. Please do not test your algorithms only on UCI or benchmark medical datasets.

The editors expect to collect a set of recent advances in the related topics and provide a platform for researchers to exchange their innovative ideas and biomedical data.

Topics of Interest:

l Large scale classification algorithms with applications on biomedicine

l Large scale clustering algorithms with applications on biomedicine

l Imbalanced learning algorithms for biomedical data

l Learning with multiple views for medical image classification

l Semi-supervised learning strategies for biomedical data

l Ensemble learning strategies for biomedical data

l Parallel learning techniques for ultra large biomedical data

l Multiple kernel learning with applications on biomedicine

l Multiple label classification algorithms with applications on biomedicine

l Construction and analysis of multi-scale integrative network

l Oncogene identification based on protein-protein interaction network

l Drug discovery based on protein-chemical, chemical-chemical and protein-protein network

l Predictive modeling of complex diseases

Important Dates

l Paper Submission: Oct. 1, 2016

l First Round Notification: Dec. 1, 2016

l Revision: Jan. 1, 2017

l Final Decision: Feb. 1, 2017

l Publication Date: Apr. 1, 2017

Guest Editors

Quan Zou
School of Computer Science and Technology
Tianjin University, Tianjin 300072, China,

Lei Chen
Associate Professor
College of Information Engineering
Shanghai Maritime University, Shanghai 201306, China,

Tao Huang
Associate Professor and Director of Bioinformatics Core Facility
Institute of Health Sciences, Shanghai Institutes for Biological Sciences
Chinese Academy of Sciences, Shanghai 200031, China,

Zhenguo Zhang
Postdoctoral Research Associate
Department of Biology, University of Rochester
River Campus Box 270211, University of Rochester, Rochester, New York, USA,

Yungang Xu
Postdoctoral Research Scientist
Wake forest Baptist Medical Center, School of Medicine at Wake Forest University
Medical Center Boulevard, Winston-Salem, NC 27157-1088, USA,

Closed Special Issues