Increasing phenotypic annotation improves the diagnostic rate of exome sequencing in a rare neuromuscular disorder

Phenotype‐based filtering and prioritization contribute to the interpretation of genetic variants detected in exome sequencing. However, it is currently unclear how extensive this phenotypic annotation should be. In this study, we compare methods for incorporating phenotype into the interpretation process and assess the extent to which phenotypic annotation aids prioritization of the correct variant. Using a cohort of 29 patients with congenital myasthenic syndromes with causative variants in known or newly discovered disease genes, exome data and the Human Phenotype Ontology (HPO)‐coded phenotypic profiles, we show that gene‐list filters created from phenotypic annotations perform similarly to curated disease‐gene virtual panels. We use Exomiser, a prioritization tool incorporating phenotypic comparisons, to rank candidate variants while varying phenotypic annotation. Analyzing 3,712 combinations, we show that increasing phenotypic annotation improved prioritization of the causative variant, from 62% ranked first on variant alone to 90% with seven HPO annotations. We conclude that any HPO‐based phenotypic annotation aids variant discovery and that annotation with over five terms is recommended in our context. Although focused on a constrained cohort, this provides real‐world validation of the utility of phenotypic annotation for variant prioritization. Further research is needed to extend this concept to other diseases and more diverse cohorts.     

ECGene: A Literature‐Based Knowledgebase of Endometrial Cancer Genes

Endometrial cancer (EC) ranks as the sixth common cancer for women worldwide. To better distinguish cancer subtypes and identify effective early diagnostic biomarkers, we need improved understanding of the biological mechanisms associated with EC dysregulated genes. Although there is a wealth of clinical and molecular information relevant to EC in the literature, there has been no systematic summary of EC‐implicated genes. In this study, we developed a literature‐based database ECGene (Endometrial Cancer Gene database) with comprehensive annotations. ECGene features manual curation of 414 genes from thousands of publications, results from eight EC gene expression datasets, precomputation of coexpressed long noncoding RNAs, and an EC‐implicated gene interactome. In the current release, we generated and comprehensively annotated a list of 458 EC‐implicated genes. We found the top‐ranked EC‐implicated genes are frequently mutated in The Cancer Genome Atlas (TCGA) tumor samples. Furthermore, systematic analysis of coexpressed lncRNAs provided insight into the important roles of lncRNA in EC development. ECGene has a user‐friendly Web interface and is freely available at http://ecgene.bioinfo‐minzhao.org/ . As the first literature‐based online resource for EC, ECGene serves as a useful gateway for researchers to explore EC genetics.     

Systematic learning of gene functional classes from DNA array expression data by using multilayer perceptrons

Recent advances in microarray technology have opened new ways for functional annotation of previously uncharacterised genes on a genomic scale. This has been demonstrated by unsupervised clustering of co-expressed genes and, more importantly, by supervised learning algorithms. Using prior knowledge, these algorithms can assign functional annotations based on more complex expression signatures found in existing functional classes. Previously, support vector machines (SVMs) and other machine-learning methods have been applied to a limited number of functional classes for this purpose. Here we present, for the first time, the comprehensive application of supervised neural networks (SNNs) for functional annotation. Our study is novel in that we report systematic results for ~100 classes in the Munich Information Center for Protein Sequences (MIPS) functional catalog. We found that only ~10% of these are learnable (based on the rate of false negatives). A closer analysis reveals that false positives (and negatives) in a machine-learning context are not necessarily "false" in a biological sense. We show that the high degree of interconnections among functional classes confounds the signatures that ought to be learned for a unique class. We term this the "Borges effect" and introduce two new numerical indices for its quantification. Our analysis indicates that classification systems with a lower Borges effect are better suitable for machine learning. Furthermore, we introduce a learning procedure for combining false positives with the original class. We show that in a few iterations this process converges to a gene set that is learnable with considerably low rates of false positives and negatives and contains genes that are biologically related to the original class, allowing for a coarse reconstruction of the interactions between associated biological pathways. We exemplify this methodology using the well-studied tricarboxylic acid cycle.     

UniProt genomic mapping for deciphering functional effects of missense variants

Understanding the association of genetic variation with its functional consequences in proteins is essential for the interpretation of genomic data and identifying causal variants in diseases. Integration of protein function knowledge with genome annotation can assist in rapidly comprehending genetic variation within complex biological processes. Here, we describe mapping UniProtKB human sequences and positional annotations, such as active sites, binding sites, and variants to the human genome (GRCh38) and the release of a public genome track hub for genome browsers. To demonstrate the power of combining protein annotations with genome annotations for functional interpretation of variants, we present specific biological examples in disease‐related genes and proteins. Computational comparisons of UniProtKB annotations and protein variants with ClinVar clinically annotated single nucleotide polymorphism (SNP) data show that 32% of UniProtKB variants colocate with 8% of ClinVar SNPs. The majority of colocated UniProtKB disease‐associated variants (86%) map to 'pathogenic' ClinVar SNPs. UniProt and ClinVar are collaborating to provide a unified clinical variant annotation for genomic, protein, and clinical researchers. The genome track hubs, and related UniProtKB files, are downloadable from the UniProt FTP site and discoverable as public track hubs at the UCSC and Ensembl genome browsers.     

一种基于Gene Ontology注释信息的基因选择算法

基因选择算法是辅助生物学分析最重要的方法之一,但这类统计学算法受样本量相对基因数目过少的困扰.提出一种结合Gene Ontology(GO)注释信息的基因选择算法,用GO注释接近基因的方差的加权平均进行修正,增强小样本量下对总体的估计,进而寻找差异表达基因.将该算法与其他5种常见算法对比,以选择出的基因为特征构建分类器,以分类器的可靠性作为衡量算法的标准.3组芯片实验的结果表明,该算法在小样本情况下具有一定优势.亦有Pubmed文献证明,该算法可以鉴别出其他算法未曾发现的致病基因.该方法所建立起来的框架,是把生物学注释信息引入算法改进的一种有效尝试.     

Assessing the Pathogenicity of Insertion and Deletion Variants with the Variant Effect Scoring Tool (VEST‐Indel)

Insertion/deletion variants (indels) alter protein sequence and length, yet are highly prevalent in healthy populations, presenting a challenge to bioinformatics classifiers. Commonly used features—DNA and protein sequence conservation, indel length, and occurrence in repeat regions—are useful for inference of protein damage. However, these features can cause false positives when predicting the impact of indels on disease. Existing methods for indel classification suffer from low specificities, severely limiting clinical utility. Here, we further develop our variant effect scoring tool (VEST) to include the classification of in‐frame and frameshift indels (VEST‐indel) as pathogenic or benign. We apply 24 features, including a new “PubMed” feature, to estimate a gene's importance in human disease. When compared with four existing indel classifiers, our method achieves a drastically reduced false‐positive rate, improving specificity by as much as 90%. This approach of estimating gene importance might be generally applicable to missense and other bioinformatics pathogenicity predictors, which often fail to achieve high specificity. Finally, we tested all possible meta‐predictors that can be obtained from combining the four different indel classifiers using Boolean conjunctions and disjunctions, and derived a meta‐predictor with improved performance over any individual method.     

Classification of a large microarray data set: algorithm comparison and analysis of drug signatures

A large gene expression database has been produced that characterizes the gene expression and physiological effects of hundreds of approved and withdrawn drugs, toxicants, and biochemical standards in various organs of live rats. In order to derive useful biological knowledge from this large database, a variety of supervised classification algorithms were compared using a 597-microarray subset of the data. Our studies show that several types of linear classifiers based on Support Vector Machines (SVMs) and Logistic Regression can be used to derive readily interpretable drug signatures with high classification performance. Both methods can be tuned to produce classifiers of drug treatments in the form of short, weighted gene lists which upon analysis reveal that some of the signature genes have a positive contribution (act as "rewards" for the class-of-interest) while others have a negative contribution (act as "penalties") to the classification decision. The combination of reward and penalty genes enhances performance by keeping the number of false positive treatments low. The results of these algorithms are combined with feature selection techniques that further reduce the length of the drug signatures, an important step towards the development of useful diagnostic biomarkers and low-cost assays. Multiple signatures with no genes in common can be generated for the same classification end-point. Comparison of these gene lists identifies biological processes characteristic of a given class.     

Development and Evaluation of an Automated Annotation Pipeline and cDNA Annotation System

Manual curation has long been held to be the “gold standard” for functional annotation of DNA sequence. Our experience with the annotation of more than 20,000 full-length cDNA sequences revealed problems with this approach, including inaccurate and inconsistent assignment of gene names, as well as many good assignments that were difficult to reproduce using only computational methods. For the FANTOM2 annotation of more than 60,000 cDNA clones, we developed a number of methods and tools to circumvent some of these problems, including an automated annotation pipeline that provides high-quality preliminary annotation for each sequence by introducing an “uninformative filter” that eliminates uninformative annotations, controlled vocabularies to accurately reflect both the functional assignments and the evidence supporting them, and a highly refined, Web-based manual annotation tool that allows users to view a wide array of sequence analyses and to assign gene names and putative functions using a consistent nomenclature. The ultimate utility of our approach is reflected in the low rate of reassignment of automated assignments by manual curation. Based on these results, we propose a new standard for large-scale annotation, in which the initial automated annotations are manually investigated and then computational methods are iteratively modified and improved based on the results of manual curation.     

Matching whole genomes to rare genetic disorders: Identification of potential causative variants using phenotype‐weighted knowledge in the CAGI SickKids5 clinical genomes challenge

Precise identification of causative variants from whole‐genome sequencing data, including both coding and noncoding variants, is challenging. The Critical Assessment of Genome Interpretation 5 SickKids clinical genome challenge provided an opportunity to assess our ability to extract such information. Participants in the challenge were required to match each of the 24 whole‐genome sequences to the correct phenotypic profile and to identify the disease class of each genome. These are all rare disease cases that have resisted genetic diagnosis in a state‐of‐the‐art pipeline. The patients have a range of eye, neurological, and connective‐tissue disorders. We used a gene‐centric approach to address this problem, assigning each gene a multiphenotype‐matching score. Mutations in the top‐scoring genes for each phenotype profile were ranked on a 6‐point scale of pathogenicity probability, resulting in an approximately equal number of top‐ranked coding and noncoding candidate variants overall. We were able to assign the correct disease class for 12 cases and the correct genome to a clinical profile for five cases. The challenge assessor found genes in three of these five cases as likely appropriate. In the postsubmission phase, after careful screening of the genes in the correct genome, we identified additional potential diagnostic variants, a high proportion of which are noncoding.     

Automatic classification of radiological reports for clinical care

Radiological reporting generates a large amount of free-text clinical narratives, a potentially valuable source of information for improving clinical care and supporting research. The use of automatic techniques to analyze such reports is necessary to make their content effectively available to radiologists in an aggregated form. In this paper we focus on the classification of chest computed tomography reports according to a classification schema proposed for this task by radiologists of the Italian hospital ASST Spedali Civili di Brescia. The proposed system is built exploiting a training data set containing reports annotated by radiologists. Each report is classified according to the schema developed by radiologists and textual evidences are marked in the report. The annotations are then used to train different machine learning based classifiers. We present in this paper a method based on a cascade of classifiers which make use of a set of syntactic and semantic features. The resulting system is a novel hierarchical classification system for the given task, that we have experimentally evaluated.     

A new classification model with simple decision rule for discovering optimal feature gene pairs

Classifiers have been widely used to select an optimal subset of feature genes from microarray data for accurate classification of cancer samples and cancer-related studies. However, the classification rules derived from most classifiers are complex and difficult to understand in biological significance. How to solve this problem is a new challenge. In this paper, a new classification model based on gene pair is proposed to address the problem. The experimental results on several microarray data demonstrate that the proposed classification model performs well in finding a large number of excellent feature gene pairs. A 100% LOOCV classification accuracy can be achieved using a single classification model based on optimal feature gene pair or combining multiple top-ranked classification models. Using the proposed method, we successfully identified important cancer-related genes that had been validated in previous biological studies while they were not discovered by the other methods.     

CARSVM: a class association rule-based classification framework and its application to gene expression data

OBJECTIVE: In this study, we aim at building a classification framework, namely the CARSVM model, which integrates association rule mining and support vector machine (SVM). The goal is to benefit from advantages of both, the discriminative knowledge represented by class association rules and the classification power of the SVM algorithm, to construct an efficient and accurate classifier model that improves the interpretability problem of SVM as a traditional machine learning technique and overcomes the efficiency issues of associative classification algorithms. METHOD: In our proposed framework: instead of using the original training set, a set of rule-based feature vectors, which are generated based on the discriminative ability of class association rules over the training samples, are presented to the learning component of the SVM algorithm. We show that rule-based feature vectors present a high-qualified source of discrimination knowledge that can impact substantially the prediction power of SVM and associative classification techniques. They provide users with more conveniences in terms of understandability and interpretability as well. RESULTS: We have used four datasets from UCI ML repository to evaluate the performance of the developed system in comparison with five well-known existing classification methods. Because of the importance and popularity of gene expression analysis as real world application of the classification model, we present an extension of CARSVM combined with feature selection to be applied to gene expression data. Then, we describe how this combination will provide biologists with an efficient and understandable classifier model. The reported test results and their biological interpretation demonstrate the applicability, efficiency and effectiveness of the proposed model. CONCLUSION: From the results, it can be concluded that a considerable increase in classification accuracy can be obtained when the rule-based feature vectors are integrated in the learning process of the SVM algorithm. In the context of applicability, according to the results obtained from gene expression analysis, we can conclude that the CARSVM system can be utilized in a variety of real world applications with some adjustments.     

TEAM: a tool for the integration of expression, and linkage and association maps

The identification of genes primarily responsible for complex genetic disorders is a daunting task. Despite the assignment of many susceptibility loci, there has only been limited success in identifying disease genes based solely on positional information from genome-wide screens. The incorporation of several complementary strategies in a single integrated approach should facilitate and further enhance the efficacy of this search for genes. To permit the integration of linkage, association and expression data, together with functional annotations, we have developed a Java-based software tool: TEAM (tool for the integration of expression, and linkage and association maps). TEAM includes a genome viewer, capable of overlaying karyobands, genes, markers, linkage graphs, association data, gene expression levels and functional annotations in one composite view. Data management, analysis and filtering functionality was implemented and extended with links to the Ensembl, Unigene and Gene Ontology databases to facilitate gene annotation. Filtering functionality can help prevent the exclusion of poorly annotated, but differentially expressed, genes that reside in candidate regions that show linkage or association. Here we demonstrate the program's functionality in our study on coeliac disease (OMIM 212750), a multifactorial gluten-sensitive enteropathy. We performed a combined data analysis of a genome-wide linkage screen in 82 Dutch families with affected siblings and the microarray expression profiles of 18,110 cDNAs in 22 intestinal biopsies.     

Induction of comprehensible models for gene expression datasets by subgroup discovery methodology

Finding disease markers (classifiers) from gene expression data by machine learning algorithms is characterized by a high risk of overfitting the data due the abundance of attributes (simultaneously measured gene expression values) and shortage of available examples (observations). To avoid this pitfall and achieve predictor robustness, state-of-the-art approaches construct complex classifiers that combine relatively weak contributions of up to thousands of genes (attributes) to classify a disease. The complexity of such classifiers limits their transparency and consequently the biological insights they can provide. The goal of this study is to apply to this domain the methodology of constructing simple yet robust logic-based classifiers amenable to direct expert interpretation. On two well-known, publicly available gene expression classification problems, the paper shows the feasibility of this approach, employing a recently developed subgroup discovery methodology. Some of the discovered classifiers allow for novel biological interpretations.     

Computational selection of distinct class- and subclass-specific gene expression signatures

In this investigation we used statistical methods to select genes with expression profiles that partition classes and subclasses of biological samples. Gene expression data corresponding to liver samples from rats treated for 24 h with an enzyme inducer (phenobarbital) or a peroxisome proliferator (clofibrate, gemfibrozil or Wyeth 14,643) were subjected to a modified Z-score test to identify gene outliers and a binomial distribution to reduce the probability of detecting genes as differentially expressed by chance. Hierarchical clustering of 238 statistically valid differentially expressed genes partitioned class-specific gene expression signatures into groups that clustered samples exposed to the enzyme inducer or to peroxisome proliferators. Using analysis of variance (ANOVA) and linear discriminant analysis methods we identified single genes as well as coupled gene expression profiles that separated the phenobarbital from the peroxisome proliferator treated samples and discerned the fibrate (gemfibrozil and clofibrate) subclass of peroxisome proliferators. A comparison of genes ranked by ANOVA with genes assessed as significant by mixedlinear models analysis [J. Comput. Biol. 8 (2001) 625] or ranked by information gain revealed good congruence with the top 10 genes from each statistical method in the contrast between phenobarbital and peroxisome proliferators expression profiles. We propose building upon a classification regimen comprised of analysis of replicate data, outlier diagnostics and gene selection procedures to utilize cDNA microarray data to categorize subclasses of samples exposed to pharmacologic agents.     

Associating genes with gene ontology codes using a maximum entropy analysis of biomedical literature.

Functional characterizations of thousands of gene products from many species are described in the published literature. These discussions are extremely valuable for characterizing the functions not only of these gene products, but also of their homologs in other organisms. The Gene Ontology (GO) is an effort to create a controlled terminology for labeling gene functions in a more precise, reliable, computer-readable manner. Currently, the best annotations of gene function with the GO are performed by highly trained biologists who read the literature and select appropriate codes. In this study, we explored the possibility that statistical natural language processing techniques can be used to assign GO codes. We compared three document classification methods (maximum entropy modeling, na?ve Bayes classification, and nearest-neighbor classification) to the problem of associating a set of GO codes (for biological process) to literature abstracts and thus to the genes associated with the abstracts. We showed that maximum entropy modeling outperforms the other methods and achieves an accuracy of 72% when ascertaining the function discussed within an abstract. The maximum entropy method provides confidence measures that correlate well with performance. We conclude that statistical methods may be used to assign GO codes and may be useful for the difficult task of reassignment as terminology standards evolve over time.     

Gene expression profile class prediction using linear Bayesian classifiers

Due to recent advances in DNA microarray technology, using gene expression profiles, diagnostic category of tissue samples can be predicted with high accuracy. In this study, we discuss shortcomings of some existing gene expression profile classification methods and propose a new approach based on linear Bayesian classifiers. In our approach, we first construct gene-level linear classifiers to identify genes that provide high class-prediction accuracies, i.e., low error rates. After this screening phase, starting with the gene that offers the lowest error rate, we construct a multi-dimensional linear classifier by incorporating next best-performing genes, until the prediction error becomes minimum or 0, if possible. When we compared classification performance of our approach against prediction analysis of microarrays (PAM) and support vector machines (SVM) based approaches, we found that our method outperforms PAM and produces comparable results with SVM. In addition, we observed that the gene selection scheme of PAM could be misleading. Albeit SVM achieves relatively higher prediction performance, it has two major disadvantages: Complexity and lack of insight about important genes. Our intuitive approach offers competing performance and also an efficient means for finding important genes.     

Evaluation of training with an annotation schema for manual annotation of clinical conditions from emergency department reports

OBJECTIVE: Determine whether agreement among annotators improves after being trained to use an annotation schema that specifies: what types of clinical conditions to annotate, the linguistic form of the annotations, and which modifiers to include. METHODS: Three physicians and 3 lay people individually annotated all clinical conditions in 23 emergency department reports. For annotations made using a Baseline Schema and annotations made after training on a detailed annotation schema, we compared: (1) variability of annotation length and number and (2) annotator agreement, using the F-measure. RESULTS: Physicians showed higher agreement and lower variability after training on the detailed annotation schema than when applying the Baseline Schema. Lay people agreed with physicians almost as well as other physicians did but showed a slower learning curve. CONCLUSION: Training annotators on the annotation schema we developed increased agreement among annotators and should be useful in generating reference standard sets for natural language processing studies. The methodology we used to evaluate the schema could be applied to other types of annotation or classification tasks in biomedical informatics.     

Modern classification of breast cancer: should we stick with morphology or convert to molecular profile characteristics

Breast cancer represents a heterogeneous group of tumors with varied morphologic and biological features, behavior, and response to therapy. The present routine clinical management of breast cancer relies on the availability of robust prognostic and predictive factors to support decision making. Breast cancer patients are stratified into risk groups based on a combination of classical time-dependent prognostic variables (staging) and biological prognostic and predictive variables. Staging variables include tumor size, lymph node stage, and extent of tumor spread. Classical biological variables include morphologic variables such as tumor grade and molecular markers such as hormone receptor and human epidermal growth factor receptor 2 status. Although individual molecular markers were introduced in the field of breast cancer management many years ago, the concept of molecular classification was raised after the introduction of global gene expression profiling and the identification of multigene classifiers. Although there is no doubt that gene expression profiling technology has revolutionized the field of breast cancer research and have been widely expected to improve breast cancer prognostication, the unprecedented speed of progress and publicity associated with the introduction of these commercially-based multigene classifiers should not lead us to expect this technology to replace the classical classification systems. These multigene classifiers have the potential to complement traditional methods through provision of additional biological prognostic and predictive information in presently indeterminate risk groups. Here we present updated information on the present clinical value of classical clinicopathologic factors, molecular taxonomy, and multigene classifiers in routine patients management and provide some critical views and practical expectations.     

Assessing the Drosophila melanogaster and Anopheles gambiae genome annotations using genome-wide sequence comparisons

We performed genome-wide sequence comparisons at the protein coding level between the genome sequences of Drosophila melanogaster and Anopheles gambiae. Such comparisons detect evolutionarily conserved regions (ecores) that can be used for a qualitative and quantitative evaluation of the available annotations of both genomes. They also provide novel candidate features for annotation. The percentage of ecores mapping outside annotations in the A. gambiae genome is about fourfold higher than in D. melanogaster. The A. gambiae genome assembly also contains a high proportion of duplicated ecores, possibly resulting from artefactual sequence duplications in the genome assembly. The occurrence of 4063 ecores in the D. melanogaster genome outside annotations suggests that some genes are not yet or only partially annotated. The present work illustrates the power of comparative genomics approaches towards an exhaustive and accurate establishment of gene models and gene catalogues in insect genomes.