High-Dimensional Feature Selection for Genomic Datasets
Department of Computer Science, Memorial University of Newfoundland(纽芬兰纪念大学计算机科学系);Department of Mathematics and Statistics, Memorial University of Newfoundland(纽芬兰纪念大学数学与统计系);Memorial University of Newfoundland(纽芬兰纪念大学)
Majid Afshar, Hamid Usefi
发表信息:
August 2020, Knowledge-Based Systems 206(4):106370
A central problem in machine learning and pattern recognition is the process of recognizing the most important features. In this paper, we provide a new feature selection method (DRPT) that consists of first removing the irrelevant features and then detecting correlations between the remaining features. Let $D=[A\mid \mathbf{b}]$ be a dataset, where $\mathbf{b}$ is the class label and $A$ is a matrix whose columns are the features. We solve $A\mathbf{x} = \mathbf{b}$ using the least squares method and the pseudo-inverse of $A$. Each component of $\mathbf{x}$ can be viewed as an assigned weight to the corresponding column (feature). We define a threshold based on the local maxima of $\mathbf{x}$ and remove those features whose weights are smaller than the threshold.
To detect the correlations in the reduced matrix, which we still call $A$, we consider a perturbation $\tilde A$ of $A$. We prove that correlations are encoded in $Δ\mathbf{x}=\mid \mathbf{x} -\tilde{\mathbf{x}}\mid $, where $\tilde{\mathbf{x}}$ is the least quares solution of
$\tilde A\tilde{\mathbf{x}}=\mathbf{b}$. We cluster features first based on $Δ\mathbf{x}$ and then using the entropy of features. Finally, a feature is selected from each sub-cluster based on its weight and entropy. The effectiveness of DRPT has been verified by performing a series of comparisons with seven state-of-the-art feature selection methods over ten genetic datasets ranging up from 9,117 to 267,604 features. The results show that, over all, the performance of DRPT is favorable in several aspects compared to each feature selection algorithm.
\e
Robust Ultra-High-Dimensional Variable Selection With Correlated Structure Using Group Testing
University of Maryland Baltimore Marlene & Stewart Greenebaum Comprehensive Cancer Center(马里兰大学巴尔的摩分校马伦和斯蒂文·格林堡综合癌症中心);Case Western Reserve University(凯斯西储大学);University of Florida(佛罗里达大学)
An integrative sparse boosting analysis of cancer genomic commonality and difference
在癌症研究中,高通量分析已被广泛进行。在最近的研究中,对多个癌症患者组/亚组的数据进行了综合分析。这种分析有可能揭示基因组的共性以及组/亚组之间的差异。然而,在现有的文献中,特别关注基因组共性和差异的方法非常有限。在这项研究中,一种新的估计和标记选择方法的基础上稀疏增强技术,以解决共性/差异的问题。在技术创新方面,引入了新的惩罚和增量计算方法。该方法还可以有效地适应协变量的分组结构。仿真结果表明,它可以在广泛的设置下优于直接竞争对手。对两个TCGA(The Cancer Genome Atlas)数据集的分析表明,该方法能够识别出具有重要生物学意义的标记,并具有令人满意的预测性和稳定性。
An Embarrassingly Simple Approach to Enhance Transformer Performance in Genomic Selection for Crop Breeding
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);School of Computer Science, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);School of Computer Science and Artificial Intelligence, Wuhan University of Technology(武汉理工大学计算机科学与人工智能学院);School of Animal Science and Technology, Huazhong Agricultural University(华中农业大学动物科学技术学院)
Distance-Preserving Representations for Genomic Spatial Reconstruction
Heinz College of Information Systems and Public Policy and Machine Learning Department, Carnegie Mellon University(信息系统与公共政策学院及机器学习系,卡内基梅隆大学);Musketeers Foundation Institute of Data Science and the Department of Statistics and Actuarial Science, University of Hong Kong(数据科学研究所及统计与精算科学系,香港大学)
Fast, memory-efficient genomic interval tokenizers for modern machine learning
Department of Genome Sciences, School of Medicine, University of Virginia(基因组科学系,医学院,弗吉尼亚大学);Department of Biomedical Engineering, School of Medicine, University of Virginia(生物医学工程系,医学院,弗吉尼亚大学);Department of Biochemistry and Molecular Genetics, School of Medicine, University of Virginia(生物化学与分子遗传学系,医学院,弗吉尼亚大学);School of Data Science, University of Virginia(数据科学学院,弗吉尼亚大学)
Semantically Rich Local Dataset Generation for Explainable AI in Genomics
LASIGE, Faculdade de Ciências da Universidade de Lisboa(里斯本大学理学院LASIGE实验室);Instituto de Medicina Molecular João Lobo Antunes, Faculdade de Medicina da Universidade de Lisboa(里斯本大学医学院若昂·洛博·安图内斯分子医学研究所);Mondego Science(蒙德戈科学公司)
AGP: A Novel Arabidopsis thaliana Genomics-Phenomics Dataset and its HyperGraph Baseline Benchmarking
Department of Electrical Engineering and Computer Science(电气工程与计算机科学系);Department of Entomology and Plant Pathology(昆虫学与植物病理学系);Department of Animal Science(动物科学系);School of Plant Sciences(植物科学学院)