A Bootstrap-Based Covariate Selection Method for Modeling the Risk of Lightning-Induced Fires at a Local Scale: A Case Study in Northwest Spain

In lightning-induced fire risk prediction models, the number of potential predictors is usually high, with some redundancy among them. It is therefore important to select the best subset of predictors that obtain models with the greatest discrimination capacity. With this aim in mind, the logistic generalized linear model was used to estimate lightning-induced fire occurrence using a case study of the province of León (northwest Spain). A bootstrap-based test was used to obtain the optimal number of predictors and to model this optimal number of predictors displaying the largest area under the receiver operating characteristics curve. The results show that of the 16 variables initially considered, only three were necessary to obtain the model with the best discriminatory capacity for estimating lightning-induced fire occurrence. Moreover, this model can be considered equivalent to another nine alternative models with three covariates. Both the optimal and the equivalent models are useful in the spatially explicit assessment of fire risk, the planning and coordination of regional efforts to identify areas at greatest risk, and the design of long-term wildfire management strategies. The methodology used for this case study can be applied to other wildfire risk assessment situations where multiple and interconnected covariates are available.     

Combining diagnostic test results to increase accuracy

When multiple diagnostic tests are performed on an individual or multiple disease markers are available it may be possible to combine the information to diagnose disease. We consider how to choose linear combinations of markers in order to optimize diagnostic accuracy. The accuracy index to be maximized is the area or partial area under the receiver operating characteristic (ROC) curve. We propose a distribution-free rank-based approach for optimizing the area under the ROC curve and compare it with logistic regression and with classic linear discriminant analysis (LDA). It has been shown that the latter method optimizes the area under the ROC curve when test results have a multivariate normal distribution for diseased and non-diseased populations. Simulation studies suggest that the proposed non-parametric method is efficient when data are multivariate normal.The distribution-free method is generalized to a smooth distribution-free approach to: (i) accommodate some reasonable smoothness assumptions; (ii) incorporate covariate effects; and (iii) yield optimized partial areas under the ROC curve. This latter feature is particularly important since it allows one to focus on a region of the ROC curve which is of most relevance to clinical practice. Neither logistic regression nor LDA necessarily maximize partial areas. The approaches are illustrated on two cancer datasets, one involving serum antigen markers for pancreatic cancer and the other involving longitudinal prostate specific antigen data.     

Prediction of thermophilic proteins using feature selection technique

The thermostability of proteins is particularly relevant for enzyme engineering. Developing a computational method to identify mesophilic proteins would be helpful for protein engineering and design. In this work, we developed support vector machine based method to predict thermophilic proteins using the information of amino acid distribution and selected amino acid pairs. A reliable benchmark dataset including 915 thermophilic proteins and 793 non-thermophilic proteins was constructed for training and testing the proposed models. Results showed that 93.8% thermophilic proteins and 92.7% non-thermophilic proteins could be correctly predicted by using jackknife cross-validation. High predictive successful rate exhibits that this model can be applied for designing stable proteins.     

Computational prediction of nucleosome positioning by calculating the relative fragment frequency index of nucleosomal sequences

We developed an accurate method to predict nucleosome positioning from genome sequences by refining the previously developed method of Peckham et al. (2007) [19]. Here, we used the relative fragment frequency index we developed and a support vector machine to screen for nucleosomal and linker DNA sequences. Our twofold cross-validation revealed that the accuracy of our method based on the area under the receiver operating characteristic curve was 81%, whereas that of Peckham’s method was 75% when both of two nucleosomal sequence data obtained from independent experiments were used for validation. We suggest that our method is more effective in predicting nucleosome positioning.     

Discovery of novel mGluR1 antagonists: a multistep virtual screening approach based on an SVM model and a pharmacophore hypothesis significantly increases the hit rate and enrichment factor

Development of glutamate non-competitive antagonists of mGluR1 (Metabotropic glutamate receptor subtype 1) has increasingly attracted much attention in recent years due to their potential therapeutic application for various nervous disorders. Since there is no crystal structure reported for mGluR1, ligand-based virtual screening (VS) methods, typically pharmacophore-based VS (PB-VS), are often used for the discovery of mGluR1 antagonists. Nevertheless, PB-VS usually suffers a lower hit rate and enrichment factor. In this investigation, we established a multistep ligand-based VS approach that is based on a support vector machine (SVM) classification model and a pharmacophore model. Performance evaluation of these methods in virtual screening against a large independent test set, M-MDDR, show that the multistep VS approach significantly increases the hit rate and enrichment factor compared with the individual SB-VS and PB-VS methods. The multistep VS approach was then used to screen several large chemical libraries including PubChem, Specs, and Enamine. Finally a total of 20 compounds were selected from the top ranking compounds, and shifted to the subsequent in vitro and in vivo studies, which results will be reported in the near future.     

hCKSAAP_UbSite: Improved prediction of human ubiquitination sites by exploiting amino acid pattern and properties

As one of the most common post-translational modifications, ubiquitination regulates the quantity and function of a variety of proteins. Experimental and clinical investigations have also suggested the crucial roles of ubiquitination in several human diseases. The complicated sequence context of human ubiquitination sites revealed by proteomic studies highlights the need of developing effective computational strategies to predict human ubiquitination sites. Here we report the establishment of a novel human-specific ubiquitination site predictor through the integration of multiple complementary classifiers. Firstly, a Support Vector Machine (SVM) classier was constructed based on the composition of k-spaced amino acid pairs (CKSAAP) encoding, which has been utilized in our previous yeast ubiquitination site predictor. To further exploit the pattern and properties of the ubiquitination sites and their flanking residues, three additional SVM classifiers were constructed using the binary amino acid encoding, the AAindex physicochemical property encoding and the protein aggregation propensity encoding, respectively. Through an integration that relied on logistic regression, the resulting predictor termed hCKSAAP_UbSite achieved an area under ROC curve (AUC) of 0.770 in 5-fold cross-validation test on a class-balanced training dataset. When tested on a class-balanced independent testing dataset that contains 3419 ubiquitination sites, hCKSAAP_UbSite has also achieved a robust performance with an AUC of 0.757. Specifically, it has consistently performed better than the predictor using the CKSAAP encoding alone and two other publicly available predictors which are not human-specific. Given its promising performance in our large-scale datasets, hCKSAAP_UbSite has been made publicly available at our server (http://protein.cau.edu.cn/cksaap_ubsite/).     

基于遗传算法特征选择的HBV再激活分类预测模型

探讨原发性肝癌患者精确放疗后乙型肝炎病毒(hepatitis b virus,HBV)再激活的危险特征和分类预测模型。提出基于遗传算法的特征选择方法,从原发性肝癌数据的初始特征集中选择HBV再激活的最优特征子集。建立贝叶斯和支持向量机的HBV再激活分类预测模型,并预测最优特征子集和初始特征集的分类性能。实验结果表明,基于遗传算法的特征选择提高了HBV再激活分类性能,最优特征子集的分类性能明显优于初始特征子集的分类性能。影响HBV再激活的最优特征子集包括:HBV DNA水平,肿瘤分期TNM,Child-Pugh,外放边界和全肝最大剂量。贝叶斯的分类准确性最高可达82.89%,支持向量机的分类准确性最高可达83.34%。     

Remote protein homology detection using recurrence quantification analysis and amino acid physicochemical properties

Remote homology detection refers to the detection of structure homology in evolutionarily related proteins with low sequence similarity. Supervised learning algorithms such as support vector machine (SVM) are currently the most accurate methods. In most of these SVM-based methods, efforts have been dedicated to developing new kernels to better use the pairwise alignment scores or sequence profiles. Moreover, amino acids’ physicochemical properties are not generally used in the feature representation of protein sequences. In this article, we present a remote homology detection method that incorporates two novel features: (1) a protein's primary sequence is represented using amino acid's physicochemical properties and (2) the similarity between two proteins is measured using recurrence quantification analysis (RQA). An optimization scheme was developed to select different amino acid indices (up to 10 for a protein family) that are best to characterize the given protein family. The selected amino acid indices may enable us to draw better biological explanation of the protein family classification problem than using other alignment-based methods. An SVM-based classifier will then work on the space described by the RQA metrics. The classification scheme is named as SVM-RQA. Experiments at the superfamily level of the SCOP1.53 dataset show that, without using alignment or sequence profile information, the features generated from amino acid indices are able to produce results that are comparable to those obtained by the published state-of-the-art SVM kernels. In the future, better prediction accuracies can be expected by combining the alignment-based features with our amino acids property-based features. Supplementary information including the raw dataset, the best-performing amino acid indices for each protein family and the computed RQA metrics for all protein sequences can be downloaded from http://ym151113.ym.edu.tw/svm-rqa.     

Identification of the functional alteration signatures across different cancer types with support vector machine and feature analysis

Cancers are regarded as malignant proliferations of tumor cells present in many tissues and organs, which can severely curtail the quality of human life. The potential of using plasma DNA for cancer detection has been widely recognized, leading to the need of mapping the tissue-of-origin through the identification of somatic mutations. With cutting-edge technologies, such as next-generation sequencing, numerous somatic mutations have been identified, and the mutation signatures have been uncovered across different cancer types. However, somatic mutations are not independent events in carcinogenesis but exert functional effects. In this study, we applied a pan-cancer analysis to five types of cancers: (I) breast cancer (BRCA), (II) colorectal adenocarcinoma (COADREAD), (III) head and neck squamous cell carcinoma (HNSC), (IV) kidney renal clear cell carcinoma (KIRC), and (V) ovarian cancer (OV). Based on the mutated genes of patients suffering from one of the aforementioned cancer types, patients they were encoded into a large number of numerical values based upon the enrichment theory of gene ontology (GO) terms and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. We analyzed these features with the Monte-Carlo Feature Selection (MCFS) method, followed by the incremental feature selection (IFS) method to identify functional alteration features that could be used to build the support vector machine (SVM)-based classifier for distinguishing the five types of cancers. Our results showed that the optimal classifier with the selected 344 features had the highest Matthews correlation coefficient value of 0.523. Sixteen decision rules produced by the MCFS method can yield an overall accuracy of 0.498 for the classification of the five cancer types. Further analysis indicated that some of these features and rules were supported by previous experiments. This study not only presents a new approach to mapping the tissue-of-origin for cancer detection but also unveils the specific functional alterations of each cancer type, providing insight into cancer-specific functional aberrations as potential therapeutic targets. This article is part of a Special Issue entitled: Accelerating Precision Medicine through Genetic and Genomic Big Data Analysis edited by Yudong Cai & Tao Huang.