Identification of Cancer Subtypes by Integrating Multiple Types of Transcriptomics Data with Deep Le

来源 :第二届中国计算机学会生物信息学会议 | 被引量 : 0次 | 上传用户:TNicholas
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  Many cancers are composed of multiple subtypes in terms of distinct pathogeneses and clinical therapeutics.Identification of cancer subtypes is vital to advance the precision of disease diagnosis and therapy.In recent years,the advance of the high-throughput sequencing techniques produced huge and multiple types of genomics data,and provided good opportunities to comprehensively understand the mechanism of cancer progress.Over the past few years,numerous approaches have been proposed to integrate multiple types of genomics data,such as gene expression,DNA methylation and miRNA,etc.,to investigate cancer subtypes.However,on the one hand,few of them particularly considered the intrinsic correlations among genetic elements in each type of genomics data; on the other hand,to the best of our knowledge,none of them considered the alternative splicing regulations in data integrations.Nevertheless,it has been demonstrated that many cancers occurrences are related to abnormal alternative splicing regulations in recent years.
其他文献
In this talk,the following effective computational models developed by Chen Group for the Bioinformatics research will be introduced: 1)PBMDA(PLOS Computational Biology,2017,13(3): e1005455,cited 11 t
会议
In this talk,we will briefly introduce sevearl cases recently developed in our research group to use artificial intelligence and machine learning models for the analysis of pharmaceutical data and gen
会议
Nonnegative matrix factorization(NMF)is a powerful technique for dimension reduction and pattern recognition.In this talk,I will survey the recent applications of NMF and its variants joint NMF in bio
会议
Driver mutation provides fitness advantage to cancer cells,while the accumulation of driver mutations increases the fitness of cancer cells and accelerates cancer progression.The work seeks to extract
会议
Motivation: The growth and survival of cancer cells are greatly affected by their surrounding microenvironment.To understand the regulation under the influence of anti-cancer drugs and the synergistic
会议
N6-methyladenosine(m6A),as one of the most well-studied RNA modifications,has been found to be involved with a wide range of biological processes.Recently,diverse computational methods have been devel
会议
Neuropeptides(NPs)are short secreted peptides produced mainly in the nervous system and digestive system.It activates signaling cascades to control a wide range of biological functions,such as metabol
会议
The frequency of small subtrees in biological,social,and other types of networks could shed light into the structure,function,and evolution of such networks.However,counting all possible subtrees of a
会议
DNA N6-methyladenine(6mA)is associated with a wide range of biological processes.Accurate identification of 6mA site will be helpful for revealing its biological functions.Although experimental method
会议
With advances in next-generation sequencing(NGS)technologies,large number of multiple types of high-throughput genomics data are available.A highly challenge for cancer genomics is to identify the dri
会议