癌症组学数据的低维表示(79)

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:ty_142857
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
  癌症组学数据是典型的高维数据,即使在经过预处理后,特征数量通常也在数千或数万的量级。虽然特征众多,但生物分子并不是独立的,它们之间存在大量相互作用,形成网络结构,并自组织为若干生物过程。研究表明,癌症的生物学与临床特性主要由少数起驱动作用的生物过程决定,找到组学数据的低维特征表示、并建立其与癌症生物过程的对应关系,是揭示癌症生物学机制与调控规律的重要途径。我们提出了多个组学数据低维表示的方法,并将其应用于癌症高维组学数据的可视化、癌症分型与聚类分析:1)找到多层次组学数据共享的低维子空间,对发现起主要调控作用的生物过程具有重要意义。
其他文献
Defining informative features from complex and high dimensional biological data is of great importance in disease study,drug development,etc.Support vector machine-recursive feature elimination(SVM-RF
会议
Practical live-cell super-resolution(SR)techniques are long-desired in many routine biological labs to image biomolecule dynamics.However,the current methods either require sophisticated optical setup
会议
Graph canonization is a fundamental problem both in theoretical and practical computer science.However,it is still an open problem to study in graph theory.In this paper,we propose a new graph canoniz
会议
图聚类算法可以用于发现社会网络中的社区结构、蛋白质互作用网络的功能模块等,是当前复杂网络研究的热点之一。合理度量网络中节点的相似性是设计有效图聚类算法的核心问题。针对此问题,本文提出了一种基于两点间短路径的节点相似性度量方法,并在此基础上给出了一种面向复杂网络的图聚类算法(A Graph Clustering Algorithm Based on Pathsbetween Nodes in Com
会议
Big data,cloud computing and HPC are at the verge of convergence.Cloud computing is already playing an active part in big data processing with the help of big data frameworks like Hadoop and Spark.Rec
会议
The automatic detection of the diabetic retinopathy is of importance,as it is the main cause of irreversible vision lost in the working-age population in the developed world.Early detection of diabeti
会议
序列是一种重要的数据类型,在诸多应用领域广泛存在。基于序列的特征选择具有广阔的现实应用场景。交互特征是指一组整体具有显著强于单独个体与目标相关性的特征集合。从大规模序列中挖掘交互特征面临着位点的“组合爆炸”问题,计算挑战性极大。针对该问题,以生物领域高通量测序数据为背景,提出了一种新的基于并行处理和演化计算的高阶交互特征挖掘算法。位点数是制约互作挖掘效率的根本因素。本研究摈弃了现有方法基于序列分块
会议
Electron tomography(ET)is a widely applicable method for obtaining three-dimensional information by their projections.A major challenge for reconstruction is the limited sample angles(the "missing wed
会议
Many biological networks have been accumulated with various conditions due to the advances in high-throughput technologies.And,discovering the condition-specific modules in multiple networks has a gre
会议
Functional networks are extracted from resting state functional magnetic resonance imaging data to explore biomarkers for distinguishing brain disorder in disease diagnosis.Previous works have primari
会议