关键词： HEC1   选择性抑制剂   机器学习方法   支持向量机   随机森林   虚拟筛选  

摘要： HEC1(癌症高表达蛋白)是纺锤体检查点控制、着丝粒功能、细胞存活的关键的有丝分裂调节器,与原发性乳腺癌的不良预后有关.筛选具有高亲和力的HEC1新型抑制剂对探索乳腺癌的靶向治疗具有重要意义.本文从结构多样性的化合物库中筛选HEC1抑制剂.通过对分子描述符的特征筛选,采用支持向量机(SVM)和随机森林(RF)方法分别对HEC1抑制剂和非抑制剂建立了分类模型.经对比,RF模型显示了更好的预测精度.我们采用RF模型对HEC1抑制剂进行了虚拟筛选,从"in-house"实体库筛选得到2个潜在的HEC1抑制剂分子.随后对筛出的化合物进行了体外活性实验,发现对乳腺癌细胞株MDA-MB-468和MDA-MB-231均有一定程度的抗肿瘤活性.研究结果表明,机器学习方法对于设计和虚拟筛选HEC1抑制剂有良好的效果.

关键词： 病理图像标注   病理特性识别   多示例多标签学习   标准分割   图像特征提取  

摘要： 病理图像能够揭示疾病的原因及严重程度,在临床诊断中有重要应用.病理图像中局部区域与病理特性之间不明确的对应关系为建立计算机辅助诊断模型带来了困难.基于全局图像特征表达和等分小块等方法难以有效表达病理特性的局部性.提出一种基于多示例多标签学习的活检病理图像自动标注框架,对病理特性的局部性进行表达.通过带区域约束条件的分割算法把病理图像划分为若干视觉上不连续的区域,对区域进行基于纹理和内部结构的特征提取,把病理图像转化为多示例样本,在此基础上提出一种基于贝叶斯学习的多示例多标签稀疏集成算法.在本地大型三甲医院的皮肤科活检样本数据集上进行方法有效性评估,结果表明该方法能得到医学上可接受的标注准确率,从而说明其有效性.

关键词： Machine learning   multimodal neuroimaging   data fusion   review   EEG   MEG   fMRI   fNIRS  

摘要： Multimodal data are ubiquitous in engineering, communications, robotics, computer vision, or more generally speaking in industry and the sciences. All disciplines have developed their respective sets of analytic tools to fuse the information that is available in all measured modalities. In this paper, we provide a review of classical as well as recent machine learning methods (specifically factor models) for fusing information from functional neuroimaging techniques such as: LFP, EEG, MEG, fNIRS, and fMRI. Early and late fusion scenarios are distinguished, and appropriate factor models for the respective scenarios are presented along with example applications from selected multimodal neuroimaging studies. Further emphasis is given to the interpretability of the resulting model parameters, in particular by highlighting how factor models relate to physical models needed for source localization. The methods we discuss allow for the extraction of information from neural data, which ultimately contributes to 1) better neuroscientific understanding;2) enhance diagnostic performance;and 3) discover neural signals of interest that correlate maximally with a given cognitive paradigm. While we clearly study the multimodal functional neuroimaging challenge, the discussed machine learning techniques have a wide applicability, i.e., in general data fusion, and may thus be informative to the general interested reader.

关键词： Machine Learning   Quantitative structure-property relationships   Greedy ensembles   Linear ensembles  

摘要： The application of Machine Learning to cheminformatics is a large and active field of research, but there exist few papers which discuss whether ensembles of different Machine Learning methods can improve upon the performance of their component methodologies. Here we investigated a variety of methods, including kernel-based, tree, linear, neural networks, and both greedy and linear ensemble methods. These were all tested against a standardised methodology for regression with data relevant to the pharmaceutical development process. This investigation focused on QSPR problems within drug-like chemical space. We aimed to investigate which methods perform best, and how the 'wisdom of crowds' principle can be applied to ensemble predictors. It was found that no single method performs best for all problems, but that a dynamic, well-structured ensemble predictor would perform very well across the board, usually providing an improvement in performance over the best single method. Its use of weighting factors allows the greedy ensemble to acquire a bigger contribution from the better performing models, and this helps the greedy ensemble generally to outperform the simpler linear ensemble. Choice of data preprocessing methodology was found to be crucial to performance of each method too.

关键词： monthly inflows   climate change   predictor selection   statistical downscaling   general circulation models   NCEP   NCAR reanalysis data   multi-model ensemble   bias correction  

摘要： In this study, statistical downscaling of general circulation model (GCM) simulations to monthly inflows of Kemer Dam in Turkey under A1B, A2, and B1 emission scenarios has been performed using machine learning methods, multi-model ensemble and bias correction approaches. Principal component analysis (PCA) has been used to reduce the dimension of potential predictors of National Centers for Environmental Prediction and National Center for Atmospheric Research (NCEP/NCAR) reanalysis data. Then, the reasonable GCMs were selected by investigating the rank correlations between the selected predictors in NCEP/NCAR reanalysis data and those in GCMs for 20C3M scenario between periods 1979 and 1999. Upon the training of feedforward neural network (FFNN), least squares support vector machine (LSSVM) and relevance vector machine (RVM) downscaling models, the general performance of the downscaled predictions using NCEP/NCAR reanalysis data for Kemer watershed showed that the trained RVM model produced adequate results. The effectiveness of RVM model was illustrated by its integration with 20C3M scenario between periods 1979 and 1999 and A1B, A2, and B1 future climate scenarios between periods 2010 and 2039. Afterwards, the flow forecasts were obtained by building a multi-model ensemble through the selected GCMs followed by a bias correction approach. Finally, the significance of the probable changes in trends was identified through statistical tests based on the corrected forecasts. Results showed that decreasing flows trends in winter, spring and fall seasons have been foreseen over the study area for the period between 2010 and 2039.

关键词： Associative classification (AC)   Classification based on Predictive Association rule   gain ratio   dimensionality reduction   T-test   reduct Set  

摘要： Health care data diagnosis is a significant task that needs to be executed precisely, which requires much experience and domain-knowledge. Traditional symptoms-based disease diagnosis may perhaps lead to false presumptions. In recent times, Associative Classification (AC), the combination of association rule mining and classification has received attention in health care applications which desires maximum accuracy. Though several AC techniques exist, they lack in generating quality rules for building efficient associative classifier. This paper aims to enhance the accuracy of the existing CPAR (Classification based on Predictive Association Rule) algorithm by generating quality rules using Gain Ratio. Mostly, health care applications deal with high dimensional datasets. Existence of high dimensions causes unfair estimates in disease diagnosis. Dimensionality reduction is commonly applied as a preprocessing step before classification task to improve classifier accuracy. It eliminates redundant and insignificant dimensions by keeping good ones without information loss. In this work, dimensionality reductions by T-test and reduct sets (or simply reducts) are performed as preprocessing step before CPAR and CPAR using Gain Ratio (CPAR-GR) algorithms. An investigation was also performed to determine the impact of T-test and reducts on CPAR and CPAR-GR. This paper synthesizes the existing work carried out in AC, and also discusses the factors that influence the performance of CPAR and CPAR-GR. Experiments were conducted using six health care datasets from UCI machine learning repository. Based on the experiments, CPAR-GR with T-test yields better classification accuracy than CPAR.

关键词： forensic science   forensic anthropology   palate shape   ancestry estimation   palate depth   3D digitizer   shape-matching   machine learning  

摘要： In the past, assessing ancestry relied on the naked eye and observer experience;however, replicability has become an important aspect of such analysis through the application of metric techniques. This study examines palate shape and assesses ancestry quantitatively using a 3D digitizer and shape-matching and machine learning methods. Palate curves and depths were recorded, processed, and tested for 376 individuals. Palate shape was an accurate indicator of ancestry in 58% of cases. Cluster analysis revealed that the parabolic, hyperbolic, and elliptical shapes are discrete from one another. Preliminary results indicate that palate depth in Hispanic individuals is greatest. Palate shape appears to be a useful indicator of ancestry, particularly when assessed by a computer. However, these data suggest that palate shape is not useful for assessing ancestry in Hispanic individuals. Although ancestry may be determined from palate shape, the use of multiple features is recommended and more reliable.

关键词： COHORT analysis   TUMOR diagnosis   BIOCHEMICAL markers   COMPUTED tomography   WILCOXON signed-rank test   MACHINE learning  

摘要： Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pretreatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 +/- 0.05, AUC = 0.65 +/- 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 +/- 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice.

关键词： 联合模型   机器学习   殃残差   Cox-Snell残差  

摘要： 本文运用机器学习方法对纵向数据与生存数据建模,以机器学习方法代替纵向子模型中的线性随机效应模型;生存子模型仍运用Cox比例危险模型。与传统的建模方法做对比,此建模方法的生存子模型残差图诊断符合理论结果,纵向子模型的残差要比线性混合模型分散。

关键词： 大数据   频谱大数据   机器学习   数据挖掘   无线通信   物联网  

摘要： 随着移动互联网与物联网的迅猛发展,个人无线设备的数量呈现指数级增长,随之产生的海量频谱数据与日俱增,频谱大数据的存在已成事实。同时,频谱赤字也日益严峻。为提高频谱利用率,有效的频谱大数据处理显得十分重要。本文从无线通信的角度,首先给出了频谱大数据的定义并分析了它的基本特征;然后总结了一些对于频谱大数据分析与利用颇具前景的机器学习方法,如分布式和并行式学习、极速学习、核学习、深度学习、强化学习、博弈学习和迁移学习;最后给出了几个开放性话题和研究趋势。