Well-annotated Datasets Research Articles

Robust 3-D Human Detection in Complex Environments With a Depth Camera

Human detection has received great attention during the past few decades, which is yet still a challenging problem. In this paper, we focus on the problem of 3-D human detection, i.e., finding the human bodies and determining their 3-D coordinates in complex 3-D space using depth data only. Since the traditional sliding-window-based approaches for target localization are time-consuming and the recent deep-learning-based object detectors generate too many region proposals, we propose to utilize the candidate head-top locating stage to efficiently and quickly find the plausible head-top locations. In the second stage, we propose a Depth map, Multiorder depth template, and Height difference map representation encoding three channels of information for each candidate region to utilize the neural network pretrained on large-scale well-annotated datasets to classify the candidate regions. We evaluate our method on four publicly available challenging datasets. Extensive experimental results demonstrate that the proposed method is superior to the state-of-the-art methods while achieving real-time performance.

Supervised Segmentation of Un-Annotated Retinal Fundus Images by Synthesis.

We focus on the practical challenge of segmenting new retinal fundus images that are dissimilar to existing well-annotated data sets. It is addressed in this paper by a supervised learning pipeline, with its core being the construction of a synthetic fundus image data set using the proposed R-sGAN technique. The resulting synthetic images are realistic-looking in terms of the query images while maintaining the annotated vessel structures from the existing data set. This helps to bridge the mismatch between the query images and the existing well-annotated data set. As a consequence, any known supervised fundus segmentation technique can be directly utilized on the query images, after training on this synthetic data set. Extensive experiments on different fundus image data sets demonstrate the competitiveness of the proposed approach in dealing with a diverse range of mismatch settings.

Comprehensive review and empirical analysis of hallmarks of DNA-, RNA- and protein-binding residues in protein chains.

Proteins interact with a variety of molecules including proteins and nucleic acids. We review a comprehensive collection of over 50 studies that analyze and/or predict these interactions. While majority of these studies address either solely protein-DNA or protein-RNA binding, only a few have a wider scope that covers both protein-protein and protein-nucleic acid binding. Our analysis reveals that binding residues are typically characterized with three hallmarks: relative solvent accessibility (RSA), evolutionary conservation and propensity of amino acids (AAs) for binding. Motivated by drawbacks of the prior studies, we perform a large-scale analysis to quantify and contrast the three hallmarks for residues that bind DNA-, RNA-, protein- and (for the first time) multi-ligand-binding residues that interact with DNA and proteins, and with RNA and proteins. Results generated on a well-annotated data set of over 23000 proteins show that conservation of binding residues is higher for nucleic acid- than protein-binding residues. Multi-ligand-binding residues are more conserved and have higher RSA than single-ligand-binding residues. We empirically show that each hallmark discriminates between binding and nonbinding residues, even predicted RSA, and that combining them improves discriminatory power for each of the five types of interactions. Linear scoring functions that combine these hallmarks offer good predictive performance of residue-level propensity for binding and provide intuitive interpretation of predictions. Better understanding of these residue-level interactions will facilitate development of methods that accurately predict binding in the exponentially growing databases of protein sequences.

A semantic relatedness-based solution for reducing missing problem in TBIR

In text-based image retrieval, matching is a technique that retrieves for a concept query Q, images annotated with Q. The result performance is very influenced by the annotation quality. Since it is difficult to have a well-annotated data set, the retrieval neglects many relevant images simply because they are not annotated with the query concept (i.e. missing problem). In this paper, we propose a solution that considerably minimises such a problem, by integrating the semantic relatedness between concepts into the retrieval. We compute the semantic relatedness between pairs of concepts from Wikipedia articles. We use term frequency - inverse collection term frequency weighting scheme and the cosine similarity. After evaluating the obtained values, using the human judgement benchmark WordSimilarity-353, we incorporated them into image retrieval task. The experimental results on Corel 5K data set clearly show the ability of the proposed method in detecting missing images, compared with matching and some literature works.

Feature-based classification of human transcription factors into hypothetical sub-classes related to regulatory function.

BackgroundTranscription factors are key proteins in the regulation of gene transcription. An important step in this process is the opening of chromatin in order to make genomic regions available for transcription. Data on DNase I hypersensitivity has previously been used to label a subset of transcription factors as Pioneers, Settlers and Migrants to describe their potential role in this process. These labels represent an interesting hypothesis on gene regulation and possibly a useful approach for data analysis, and therefore we wanted to expand the set of labeled transcription factors to include as many known factors as possible. We have used a well-annotated dataset of 1175 transcription factors as input to supervised machine learning methods, using the subset with previously assigned labels as training set. We then used the final classifier to label the additional transcription factors according to their potential role as Pioneers, Settlers and Migrants. The full set of labeled transcription factors was used to investigate associated properties and functions of each class, including an analysis of interaction data for transcription factors based on DNA co-binding and protein-protein interactions. We also used the assigned labels to analyze a previously published set of gene lists associated with a time course experiment on cell differentiation.ResultsThe analysis showed that the classification of transcription factors with respect to their potential role in chromatin opening largely was determined by how they bind to DNA. Each subclass of transcription factors was enriched for properties that seemed to characterize the subclass relative to its role in gene regulation, with very general functions for Pioneers, whereas Migrants to a larger extent were associated with specific processes. Further analysis showed that the expanded classification is a useful resource for analyzing other datasets on transcription factors with respect to their potential role in gene regulation. The analysis of transcription factor interaction data showed complementary differences between the subclasses, where transcription factors labeled as Pioneers often interact with other transcription factors through DNA co-binding, whereas Migrants to a larger extent use protein-protein interactions. The analysis of time course data on cell differentiation indicated a shift in the regulatory program associated with Pioneer-like transcription factors during differentiation.ConclusionsThe expanded classification is an interesting resource for analyzing data on gene regulation, as illustrated here on transcription factor interaction data and data from a time course experiment. The potential regulatory function of transcription factors seems largely to be determined by how they bind DNA, but is also influenced by how they interact with each other through cooperativity and protein-protein interactions.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1349-2) contains supplementary material, which is available to authorized users.

A comparative study for multiple visual concepts detection in images and videos

Automatic indexing of images and videos is a highly relevant and important research area in multimedia information retrieval. The difficulty of this task is no longer something to prove. Most efforts of the research community have been focusing, in the past, on the detection of single concepts in images/videos, which is already a hard task. With the evolution of information retrieval systems, users' needs become more abstract, and lead to a larger number of words composing the queries. It is important to think about indexing multimedia documents with more than just individual concepts, to help retrieval systems to answer such complex queries. Few studies addressed specifically the problem of detecting multiple concepts (multi-concept) in images and videos. Most of them concern the detection of concept pairs. These studies showed that such challenge is even greater than the one of single concept detection. In this work, we address the problem of multi-concept detection in images/videos by making a comparative and detailed study. Three types of approaches are considered: 1) building detectors for multi-concept, 2) fusing single concepts detectors and 3) exploiting detectors of a set of single concepts in a stacking scheme. We conducted our evaluations on PASCAL VOC'12 collection regarding the detection of pairs and triplets of concepts. We extended the evaluation process on TRECVid 2013 dataset for infrequent concept pairs' detection. Our results show that the three types of approaches give globally comparable results for images, but they differ for specific kinds of pairs/triplets. In the case of videos, late fusion of detectors seems to be more effective and efficient when single concept detectors have good performances. Otherwise, directly building bi-concept detectors remains the best alternative, especially if a well-annotated dataset is available. The third approach did not bring additional gain or efficiency.

A property-based analysis of human transcription factors.

BackgroundTranscription factors are essential proteins for regulating gene expression. This regulation depends upon specific features of the transcription factors, including how they interact with DNA, how they interact with each other, and how they are post-translationally modified. Reliable information about key properties associated with transcription factors will therefore be useful for data analysis, in particular of data from high-throughput experiments.ResultsWe have used an existing list of 1978 human proteins described as transcription factors to make a well-annotated data set, which includes information on Pfam domains, DNA-binding domains, post-translational modifications and protein–protein interactions. We have then used this data set for enrichment analysis. We have investigated correlations within this set of features, and between the features and more general protein properties. We have also used the data set to analyze previously published gene lists associated with cell differentiation, cancer, and tissue distribution.ConclusionsThe study shows that well-annotated feature list for transcription factors is a useful resource for extensive data analysis; both of transcription factor properties in general and of properties associated with specific processes. However, the study also shows that such analyses are easily biased by incomplete coverage in experimental data, and by how gene sets are defined.Electronic supplementary materialThe online version of this article (doi:10.1186/s13104-015-1039-6) contains supplementary material, which is available to authorized users.

Arpeggio: harmonic compression of ChIP-seq data reveals protein-chromatin interaction signatures

Researchers generating new genome-wide data in an exploratory sequencing study can gain biological insights by comparing their data with well-annotated data sets possessing similar genomic patterns. Data compression techniques are needed for efficient comparisons of a new genomic experiment with large repositories of publicly available profiles. Furthermore, data representations that allow comparisons of genomic signals from different platforms and across species enhance our ability to leverage these large repositories. Here, we present a signal processing approach that characterizes protein–chromatin interaction patterns at length scales of several kilobases. This allows us to efficiently compare numerous chromatin-immunoprecipitation sequencing (ChIP-seq) data sets consisting of many types of DNA-binding proteins collected from a variety of cells, conditions and organisms. Importantly, these interaction patterns broadly reflect the biological properties of the binding events. To generate these profiles, termed Arpeggio profiles, we applied harmonic deconvolution techniques to the autocorrelation profiles of the ChIP-seq signals. We used 806 publicly available ChIP-seq experiments and showed that Arpeggio profiles with similar spectral densities shared biological properties. Arpeggio profiles of ChIP-seq data sets revealed characteristics that are not easily detected by standard peak finders. They also allowed us to relate sequencing data sets from different genomes, experimental platforms and protocols. Arpeggio is freely available at http://sourceforge.net/p/arpeggio/wiki/Home/.

Validation of Genetic Sequence Variants as Prognostic Factors in Early-Stage Head and Neck Squamous Cell Cancer Survival

From the published literature, we identified 23 germ line sequence variants in 17 genes from hypothesis-generating studies that were associated with prognosis of head and neck cancer, including sequence variants of DNA repair (ERCC1, ERCC4, ERCC5, MSH2, XPA, ERCC2, XRCC1, XRCC3), DNA methylation (DNMT3B), cell cycle and proliferation (CCND1, TP53), xenobiotic metabolism (GSTM1, GSTT1, CYP2D6), metastatic -potential (MMP3), immunologic (CTLA4), and growth factor pathways (FGFR4). The purpose of this study was to validate the role of these 23 sequence variants for overall (OS) and disease-free survival (DFS) in a large, comprehensive, well-annotated data set of patients with head and neck cancer. We genotyped these sequence variants in 531 patients with stage I and II radiation-treated head and neck cancer (originally recruited for an alpha-tocopherol/beta-carotene placebo-controlled secondary prevention study), and analyzed using Cox proportional hazards models, stratified by treatment arm, adjusting for clinical prognostic factors. Two OS associations were statistically significant for each variant allele when compared with the wild-type: CTLA4: A49G [rs231775; adjusted HR (aHR), 1.32 (1.1-1.6); P = 0.01] and XRCC1: Arg339Gln [rs25487; aHR, 1.28 (1.05-1.57); P = 0.02]. Both of these sequence variants had significant results in the opposite direction as prior published literature. Two DFS associations were of borderline significance in the same direction as prior literature: ERCC2: Lys751Gln [rs13181; aHR, 0.80 (0.6-1.0); P = 0.05] and TP53: Arg72Pro [rs1042522; aHR, 1.28 (1.0-1.6); P = 0.03], comparing number of variant alleles with reference of zero variants. None of the prognostic sequence variants previously published was validated for OS in our patients with early-stage radiation-treated head and neck cancer, though rs1381and rs1042522 had borderline significant association with DFS.

Predicting B cell epitope residues with network topology based amino acid indices.

We evaluate the performance of six amino acid indices in B cell epitope residue prediction using the classical sliding window method on five data sets. Four of the indices: i.e. relative connectivity, clustering coefficient, closeness and betweenness are newly derived from the topological parameters of residue networks. The other two are Parker's hydrophilicity and Levitt's index, known as the best indices so far for B cell epitope prediction. On four of the data sets, the performance of all the indices was comparable and poor in general. When applied to one well-annotated data set, the performances improved and the 4 network based indices showed better performance than that of Parker's hydrophilicity and Levitt's index. When using the relative connectivity index on this data set, the prediction accuracy, sensitivity and specificity reached 73.6%, 73.0% and 75.0% respectively, with an area under the curve about 0.796. Thus, we suggested that this index is a good choice for B cell epitope prediction. It also indicates that the low performance of B cell epitope prediction is not only due to the methods and amino acid indices used, but also the data set as well. Interestingly, on the well-annotated data set, the performance of B cell epitope residue prediction is very similar to that of protein surface residue prediction, especially at the 10 and 20 A2 cutoffs. It is suggested that the performance in surface residue prediction might form a theoretical upper limit for the performance of B cell epitope residue prediction methods.

ProFITS of maize: a database of protein families involved in the transduction of signalling in the maize genome

BackgroundMaize (Zea mays ssp. mays L.) is an important model for plant basic and applied research. In 2009, the B73 maize genome sequencing made a great step forward, using clone by clone strategy; however, functional annotation and gene classification of the maize genome are still limited. Thus, a well-annotated datasets and informative database will be important for further research discoveries. Signal transduction is a fundamental biological process in living cells, and many protein families participate in this process in sensing, amplifying and responding to various extracellular or internal stimuli. Therefore, it is a good starting point to integrate information on the maize functional genes involved in signal transduction.ResultsHere we introduce a comprehensive database 'ProFITS' (Protein Families Involved in the Transduction of Signalling), which endeavours to identify and classify protein kinases/phosphatases, transcription factors and ubiquitin-proteasome-system related genes in the B73 maize genome. Users can explore gene models, corresponding transcripts and FLcDNAs using the three abovementioned protein hierarchical categories, and visualize them using an AJAX-based genome browser (JBrowse) or Generic Genome Browser (GBrowse). Functional annotations such as GO annotation, protein signatures, protein best-hits in the Arabidopsis and rice genome are provided. In addition, pre-calculated transcription factor binding sites of each gene are generated and mutant information is incorporated into ProFITS. In short, ProFITS provides a user-friendly web interface for studies in signal transduction process in maize.ConclusionProFITS, which utilizes both the B73 maize genome and full length cDNA (FLcDNA) datasets, provides users a comprehensive platform of maize annotation with specific focus on the categorization of families involved in the signal transduction process. ProFITS is designed as a user-friendly web interface and it is valuable for experimental researchers. It is freely available now to all users at http://bioinfo.cau.edu.cn/ProFITS.

Linking publication, gene and protein data

The computational reconstruction of biological systems, 'systems biology', is necessarily dependent on the existence of well-annotated data sets defining and describing the components of these systems, especially genes and the proteins they encode. Information about these components can be accessed either through structured bioinformatics databases, which store basic chemical and functional information abstracted from (or supplementing) the scientific literature, or through the literature itself, which is richer in content but essentially unstructured.

Full-genome RNAi profiling of early embryogenesis in Caenorhabditis elegans

A key challenge of functional genomics today is to generate well-annotated data sets that can be interpreted across different platforms and technologies. Large-scale functional genomics data often fail to connect to standard experimental approaches of gene characterization in individual laboratories. Furthermore, a lack of universal annotation standards for phenotypic data sets makes it difficult to compare different screening approaches. Here we address this problem in a screen designed to identify all genes required for the first two rounds of cell division in the Caenorhabditis elegans embryo. We used RNA-mediated interference to target 98% of all genes predicted in the C. elegans genome in combination with differential interference contrast time-lapse microscopy. Through systematic annotation of the resulting movies, we developed a phenotypic profiling system, which shows high correlation with cellular processes and biochemical pathways, thus enabling us to predict new functions for previously uncharacterized genes.