Search

This paper addresses the problem of a finite set of entities which are required to achieve a goal within a predefined deadline. For example, a group of students is supposed to submit a homework by a specified cutoff. Further, we are interested in predicting which entities will achieve the goal within the deadline. The predictive models are built based only on the data from that population. The predictions are computed at various time instants by taking into account updated data about the entities. The first contribution of the paper is a formal description of the problem. The important characteristic of the proposed method for model building is the use of the properties of entities that have already achieved the goal. We call such an approach “Self-Learning”. Since typically only a few entities have achieved the goal at the beginning and their number gradually grows, the problem is inherently imbalanced. To mitigate the curse of imbalance, we improved the Self-Learning method by tackling information loss and by several sampling techniques. The original Self-Learning and the modifications have been evaluated in a case study for predicting submission of the first assessment in distance higher education courses. The results show that the proposed improvements outperform the specified two base-line models and the original Self-Learner, and also that the best results are achieved if domain-driven techniques are utilised to tackle the imbalance problem. We also showed that these improvements are statistically significant using Wilcoxon signed rank test.

Millions of protein sequences are being discovered at an incredible pace, representing an inexhaustible source of biocatalysts. Despite genomic databases growing exponentially, classical biochemical characterization techniques are time-demanding, cost-ineffective and low-throughput. Therefore, computational methods are being developed to explore the unmapped sequence space efficiently. Selection of putative enzymes for biochemical characterization based on rational and robust analysis of all available sequences remains an unsolved problem. To address this challenge, we have developed EnzymeMiner—a web server for automated screening and annotation of diverse family members that enables selection of hits for wet-lab experiments. EnzymeMiner prioritizes sequences that are more likely to preserve the catalytic activity and are heterologously expressible in a soluble form in Escherichia coli. The solubility prediction employs the in-house SoluProt predictor developed using machine learning. EnzymeMiner reduces the time devoted to data gathering, multi-step analysis, sequence prioritization and selection from days to hours. The successful use case for the haloalkane dehalogenase family is described in a comprehensive tutorial available on the EnzymeMiner web page. EnzymeMiner is a universal tool applicable to any enzyme family that provides an interactive and easy-to-use web interface freely available at https://loschmidt.chemi.muni.cz/enzymeminer/.

New, purely vision-based, segmentation technique is formally described.Only a few simple visual cues are used to assess similarity of the rectangles.Its performance better by an order of magnitude when compared with competition.Rectangle clustering is a viable way to perform web page segmentation. This paper presents a novel approach to web page segmentation, which is one of substantial preprocessing steps when mining data from web documents. Most of the current segmentation methods are based on algorithms that work on a tree representation of web pages (DOM tree or a hierarchical rendering model) and produce another tree structure as an output.In contrast, our method uses a rendering engine to get an image of the web page, takes the smallest rendered elements of that image, performs clustering using a custom algorithm and produces a flat set of segments of a given granularity. For the clustering metrics, we use purely visual properties only: the distance of elements and their visual similarity.We experimentally evaluate the properties of our algorithm by processing 2400web pages. On this set of web pages, we prove that our algorithm is almost 90% faster than the reference algorithm. We also show that our algorithm accuracy is between 47% and 133% of the reference algorithm accuracy with indirect correlation of our algorithms accuracy to the depth of inspected page structure. In our experiments, we also demonstrate the advantages of producing a flat segmentation structure instead of an hierarchy.

There is a continuous interest in increasing proteins stability to enhance their usability in numerous biomedical and biotechnological applications. A number of in silico tools for the prediction of the effect of mutations on protein stability have been developed recently. However, only single-point mutations with a small effect on protein stability are typically predicted with the existing tools and have to be followed by laborious protein expression, purification, and characterization. Here, we present FireProt, a web server for the automated design of multiple-point thermostable mutant proteins that combines structural and evolutionary information in its calculation core. FireProt utilizes sixteen tools and three protein engineering strategies for making reliable protein designs. The server is complemented with interactive, easy-to-use interface that allows users to directly analyze and optionally modify designed thermostable mutants. FireProt is freely available at http://loschmidt.chemi.muni.cz/fireprot. Web of Science 45 W1 W399 W393

Increasing students' motivation is an essential task during the educational process. One of the possible ways how to achieve this is to use innovative educational mechanics, such as gamification. Gamification provides an opportunity to extend regular learning management systems and virtual learning environments with game-like elements, such as points, levels, and meaningful narrative. This paper describes the implementation and usage of gamified assignments in Web Development. Firstly, we analyzed gamification possibilities in higher educational institutions. After each assignment, we gathered feedback from students to study their involvement, motivation, and influence of gamification on how the information was perceived. Based on the results, several suggestions for the improvement are discussed, such as adaptive variable difficulty or making the achievements public in order to increase social motivational drive influence.

Motivation G-quadruplexes (G4s) are one of the non-B DNA structures easily observed in vitro and assumed to form in vivo. The latest experiments with G4-specific antibodies and G4-unwinding helicase mutants confirm this conjecture. These four-stranded structures have also been shown to influence a range of molecular processes in cells. As G4s are intensively studied, it is often desirable to screen DNA sequences and pinpoint the precise locations where they might form. Results We describe and have tested a newly developed Bioconductor package for identifying potential quadruplex-forming sequences (PQS). The package is easy-to-use, flexible and customizable. It allows for sequence searches that accommodate possible divergences from the optimal G4 base composition. A novel aspect of our research was the creation and training (parametrization) of an advanced scoring model which resulted in increased precision compared to similar tools. We demonstrate that the algorithm behind the searches has a 96% accuracy on 392 currently known and experimentally observed G4 structures. We also carried out searches against the recent G4-seq data to verify how well we can identify the structures detected by that technology. The correlation with pqsfinder predictions was 0.622, higher than the correlation 0.491 obtained with the second best G4Hunter. Availability and implementation http://bioconductor.org/packages/pqsfinder/ This paper is based on pqsfinder-1.4.1. Supplementary information Supplementary data are available at Bioinformatics online.

This paper focuses on the problem of identifying students, who are at risk of failing their course. The presented method proposes a solution in the absence of data from previous courses, which are usually used for training machine learning models. This situation typically occurs in new courses. We present the concept of a "self-learner" that builds the machine learning models from the data generated during the current course. The approach utilises information about already submitted assessments, which introduces the problem of imbalanced data for training and testing the classification models.\ud \ud There are three main contributions of this paper: (1) the concept of training the models for identifying at-risk students using data from the current course, (2) specifying the problem as a classification task, and (3) tackling the challenge of imbalanced data, which appears both in training and testing data.\ud \ud The results show the comparison with the traditional approach of learning the models from the legacy course data, validating the proposed concept.

An important message taken from human genome sequencing projects is that the human population exhibits approximately 99.9% genetic similarity. Variations in the remaining parts of the genome determine our identity, trace our history and reveal our heritage. The precise delineation of phenotypically causal variants plays a key role in providing accurate personalized diagnosis, prognosis, and treatment of inherited diseases. Several computational methods for achieving such delineation have been reported recently. However, their ability to pinpoint potentially deleterious variants is limited by the fact that their mechanisms of prediction do not account for the existence of different categories of variants. Consequently, their output is biased towards the variant categories that are most strongly represented in the variant databases. Moreover, most such methods provide numeric scores but not binary predictions of the deleteriousness of variants or confidence scores that would be more easily understood by users. We have constructed three datasets covering different types of disease-related variants, which were divided across five categories: (i) regulatory, (ii) splicing, (iii) missense, (iv) synonymous, and (v) nonsense variants. These datasets were used to develop category-optimal decision thresholds and to evaluate six tools for variant prioritization: CADD, DANN, FATHMM, FitCons, FunSeq2 and GWAVA. This evaluation revealed some important advantages of the category-based approach. The results obtained with the five best-performing tools were then combined into a consensus score. Additional comparative analyses showed that in the case of missense variations, protein-based predictors perform better than DNA sequence-based predictors. A user-friendly web interface was developed that provides easy access to the five tools' predictions, and their consensus scores, in a user-understandable format tailored to the specific features of different categories of variations. To enable comprehensive evaluation of variants, the predictions are complemented with annotations from eight databases. The web server is freely available to the community at http://loschmidt.chemi.muni.cz/predictsnp2.

Currently many devices provide information about moving objects and location-based services that accumulate a huge volume of moving object data, including trajectories. This paper deals with two useful analysis tasks — mining moving object patterns and trajectory outlier detection. We also present our experience with the TOP-EYE trajectory outlier detection algorithm, which we applied to two real-world data sets.

The paper deals with indexing of a complex type data stream stored in a database. We present a novel indexing schema and framework referred to as ReTIn (Real-Time Indexing), the objective of which is to allow indexing of complex data arriving as a stream to a database with respect to soft real-time constraints met with some level of confidence for the maximum duration of insert and select operations. The idea of ReTIn is a combination of a sequential access to the most recent data and an index-based access to less recent data stored in the database. The collection of statistics makes balancing of indexed and unindexed parts of the database efficient. We have implemented ReTIn using PostgreSQL DBMS and its GIN index. Experimental results presented in the paper demonstrate some properties and advantages of our approach.

Single nucleotide variants represent a prevalent form of genetic variation. Mutations in the coding regions are frequently associated with the development of various genetic diseases. Computational tools for the prediction of the effects of mutations on protein function are very important for analysis of single nucleotide variants and their prioritization for experimental characterization. Many computational tools are already widely employed for this purpose. Unfortunately, their comparison and further improvement is hindered by large overlaps between the training datasets and benchmark datasets, which lead to biased and overly optimistic reported performances. In this study, we have constructed three independent datasets by removing all duplicities, inconsistencies and mutations previously used in the training of evaluated tools. The benchmark dataset containing over 43,000 mutations was employed for the unbiased evaluation of eight established prediction tools: MAPP, nsSNPAnalyzer, PANTHER, PhD-SNP, PolyPhen-1, PolyPhen-2, SIFT and SNAP. The six best performing tools were combined into a consensus classifier PredictSNP, resulting into significantly improved prediction performance, and at the same time returned results for all mutations, confirming that consensus prediction represents an accurate and robust alternative to the predictions delivered by individual tools. A user-friendly web interface enables easy access to all eight prediction tools, the consensus classifier PredictSNP and annotations from the Protein Mutant Database and the UniProt database. The web server and the datasets are freely available to the academic community at http://loschmidt.chemi.muni.cz/predictsnp.

Visualization of evolving data mining models can allow good insight for a data analyst about these models and their changes in time. This paper presents our approach to visualization of evolving association rule models. This approach is based on graph visualization where nodes of the graph represent itemsets, and edges represent association rules. We show how evolving models, produced by data mining algorithms, are stored in the knowledge base, and then how they can be filtered and visualized. Two ways of graph based visualization of evolving models are shown using force based layout algorithms - local and global layout. Experiments with both are illustrated with emphasis on the latter.

VTApi is an open source application programming interface designed to fulfill the needs of specific distributed computer vision data and metadata management and analytic systems and to unify and accelerate their development. It is oriented towards processing and efficient management of image and video data and related metadata for their retrieval, analysis and mining with the special emphasis on their spatio-temporal nature in real-world conditions. VTApi is a free extensible framework based on progressive and scalable open source software as OpenCV for high- performance computer vision and data mining, PostgreSQL for efficient data management, indexing and retrieval extended by similarity search and integrated with geography/spatio-temporal data manipulation.

Mining sequential patterns is an important problem in the field of data mining and many algorithms and optimization techniques have been published to deal with that problem. The GSP algorithm, which is one of them, can be used for mining sequential patterns with some additional constraints. In this paper, we propose a new algorithm for mining multi-level sequential patterns based on GSP. The idea is that if a more general item appears in a pattern, the pattern has higher or at least the same support as the one containing the corresponding specific item. However, too generalized sequence patterns are not important for user. In our algorithm generalization uses a selective method based on information content of patterns. This allows us to mine more patterns with the same minimal support threshold and to reveal new potentially useful patterns.

International audience; Book Front Matter of LNCS 7054

Modeling techniques play an important role in the development of database applications. Well-known entity-relationship modeling and its extensions have become a widely-accepted approach for relational database conceptual design. An object-oriented approach has brought a new view of conceptual modeling. A class as a fundamental concept of the object-oriented approach encapsulates both data and behavior, whereas traditional relational databases are able to store only data. In the early 1990s, the difference between the relational and object-oriented (OO) technologies, which were, and are still used together to build complex software systems, was labeled the object-relational impedance mismatch (Ambler, 2003). The object-oriented approach and the need of new application areas to store complex data have greatly influenced database technology since that time. Besides appearance of object-oriented database systems, which fully implement objectoriented paradigm in a database environment (Catell et al., 2003), traditional relational database management systems become object-relational (Stonebraker & Brown, 1999). The most recent versions of the SQL standard, SQL: 1999 (Melton & Simon (2001) and SQL: 2003 (Eisenberg et al., 2004), introduced object-relational features to the standard and leading database producers have already released packages which incorporate them.

Data mining technology just recently became actually usable in real-world scenarios. At present, the data mining models generated by commercial data mining and statistical applications are often used as components in other systems in such fields as customer relationship management, risk management or processing scientific data. Therefore, it seems to be natural that most data mining products concentrate on data mining technology rather than on the easy-to-use, scalability, or portability. It is evident that employing common standards greatly simplifies the integration, updating, and maintenance of applications and systems containing components provided by other producers (Grossman, Hornick, & Meyer, 2002). Data mining models generated by data mining algorithms are good examples of such components.

Modeling techniques play an important role in the development of database applications. One of the trends in current database management systems is that they become object-relational (Stonebraker & Brown, 1999). The most recent version of the SQL standard, SQL:1999, includes object-relational features, and a number of leading companies have already released packages that incorporate them.

The paper describes a new method for association rule discovery in relational databases, which contain both quantitative and categorical attributes. Most of the methods developed in the past are based on initial equi-depth discretization of quantitative attributes. These approaches bring the loss of information. Distance-based methods are another kind of methods. They try to respect the semantics of data. The basic idea of the new method is to separate processing of categorical and quantitative attributes. The first step finds frequent itemsets containing only values of categorical attributes and then quantitative attributes are processed one by one. Discretization of values during quantitative attributes processing is distance-based. A new measure called average distance is introduced for these purposes. The paper describes the method and results of several experiments on real world data.