Special Issue on Deep Neural Networks for Precision Medicine
摘要截稿:
全文截稿: 2020-02-01
影响因子: 4.438
期刊难度:
CCF分类: C类
中科院JCR分区:
• 大类 : 计算机科学 - 2区
• 小类 : 计算机:人工智能 - 2区
Overview
Complex diseases are often classified into many subtypes that may require different treatment regiments. The precision medicine is an emerging approach for disease treatment and prevention that takes into account individual variability of patients. This approach assists medical doctors and technicians in accurate prediction of treatment, prevention and prognosis strategies that would work best for a particular disease, a specific patient or a group of patients. This is in contrast to more traditional approaches where the treatment and prevention strategies are developed for large and other heterogeneous populations of patients, with little attention to the differences between individuals.
Recent advances in the high throughput biotechnologies resulted in the creation of massive omics datasets (e.g., genomics, proteomics, transcriptomics, metabolomics), medical imaging datasets, clinical datasets, electronic medical records, and others. These data coming from patients having the same disease are often heterogeneous and provide unparalleled levels of insightful information that can be used to develop accurate methods for precision medicine. Moreover, integration of these multi-modal data is seen as a feasible approach to improve accuracy of these methods. However, the development of accurate methods for precision medicine is very challenging, as it requires design of novel and sophisticated computational tools. Recently deep neural networks have been showing promise as the tools that offer several advantages in this context. They are capable to extracting useful end-to-end data and knowledge representations, benefitting from the availability of the very large datasets. The deep neural networks integrate multiple network layers (e.g., convolution layer, maximum pooling layer, etc.) and/or network blocks (residual block, dense block, etc.) to provide accurate predictive performance when trained from big and multi-modal data. They were applied to develop numerous tools for precision medicine that span multiple application areas including processing of omics data, image analysis, and text classification.
This special issue calls for high quality, state-of-the-art research results related to the analysis and prediction of the precision medicine-related data that relies on deep neural networks. The specific topics include, but are not limited to:
Deep neural networks for next-generation sequencing data analysis
We encourage submission of articles that present novel methodologies as well as review/survey/vision papers on the above topics. The editors will actively seek to invite expert authors to submit the latter types of articles.