Wojciech Stach

Improved sequence-based prediction of disordered regions with multilayer fusion of multiple information sources

Motivation: Intrinsically disordered proteins play a crucial role in numerous regulatory processes. Their abundance and ubiquity combined with a relatively low quantity of their annotations motivate research toward the development of computational models that predict disordered regions from protein sequences. Although the prediction quality of these methods continues to rise, novel and improved predictors are urgently needed. Results: We propose a novel method, named MFDp (Multilayered Fusion-based Disorder predictor), that aims to improve over the current disorder predictors. MFDp is as an ensemble of 3 Support Vector Machines specialized for the prediction of short, long and generic disordered regions. It combines three complementary disorder predictors, sequence, sequence profiles, predicted secondary structure, solvent accessibility, backbone dihedral torsion angles, residue flexibility and B-factors. Our method utilizes a custom-designed set of features that are based on raw predictions and aggregated raw values and recognizes various types of disorder. The MFDp is compared at the residue level on two datasets against eight recent disorder predictors and top-performing methods from the most recent CASP8 experiment. In spite of using training chains with ≤25% similarity to the test sequences, our method consistently and significantly outperforms the other methods based on the MCC index. The MFDp outperforms modern disorder predictors for the binary disorder assignment and provides competitive real-valued predictions. The MFDps outputs are also shown to outperform the other methods in the identification of proteins with long disordered regions. Availability: http://biomine.ece.ualberta.ca/MFDp.html Supplementary information: Supplementary data are available at Bioinformatics online. Contact: lkurgan@ece.ualberta.ca

Numerical and Linguistic Prediction of Time Series With the Use of Fuzzy Cognitive Maps

In this paper, we introduce a novel approach to time-series prediction realized both at the linguistic and numerical level. It exploits fuzzy cognitive maps (FCMs) along with a recently proposed learning method that takes advantage of real-coded genetic algorithms. FCMs are used for modeling and qualitative analysis of dynamic systems. Within the framework of FCMs, the systems are described by means of concepts and their mutual relationships. The proposed prediction method combines FCMs with granular, fuzzy-set-based model of inputs. One of their main advantages is an ability to carry out modeling and prediction at both numerical and linguistic levels. A comprehensive set of experiments has been carried out with two major goals in mind. One is to assess quality of the proposed architecture, the other to examine the influence of its parameters of the prediction technique on the quality of prediction. The obtained results, which are compared with other prediction techniques using fuzzy sets, demonstrate that the proposed architecture offers substantial accuracy expressed at both linguistic and numerical levels.

A divide and conquer method for learning large Fuzzy Cognitive Maps

Fuzzy Cognitive Maps (FCMs) are a convenient tool for modeling and simulating dynamic systems. FCMs were applied in a large number of diverse areas and have already gained momentum due to their simplicity and easiness of use. However, these models are usually generated manually, and thus they cannot be applied when dealing with large number of variables. In such cases, their development could be significantly affected by the limited knowledge and skills of the designer. In the past few years we have witnessed the development of several methods that support experts in establishing the FCMs or even replace humans by automating the construction of the maps from data. One of the problems of the existing automated methods is their limited scalability, which results in inability to handle large number of variables. The proposed method applies a divide and conquer strategy to speed up a recently proposed genetic optimization of FCMs. We empirically contrast several different designs, including parallelized genetic algorithms, FCM-specific designs based on sampling of the input data, and existing Hebbian-based methods. The proposed method, which utilizes genetic algorithm to learn and merge multiple FCM models that are computed from subsets of the original data, is shown to be faster than other genetic algorithm-based designs while resulting in the FCMs of comparable quality. We also show that the proposed method generates FCMs of higher quality than those obtained with the use of Hebbian-based methods.

Data-driven Nonlinear Hebbian Learning method for Fuzzy Cognitive Maps

Fuzzy cognitive maps (FCMs) are a convenient tool for modeling of dynamic systems by means of concepts connected by cause-effect relationships. The FCM models can be developed either manually (by the experts) or using an automated learning method (from data). Some of the methods from the latter group, including recently proposed Nonlinear Hebbian Learning (NHL) algorithm, use Hebbian law and a set of conditions imposed on output concepts. In this paper, we propose a novel approach named data-driven NHL (DD-NHL) that extends NHL method by using historical data of the input concepts to provide improved quality of the learned FCMs. DD-NHL is tested on both synthetic and real-life data, and the experiments show that if historical data are available, then the proposed method produces better FCM models when compared with those formed by the generic NHL method.

Parallel Learning of Large Fuzzy Cognitive Maps

Fuzzy cognitive maps (FCMs) are a class of discrete-time artificial neural networks that are used to model dynamic systems. A recently introduced supervised learning method, which is based on real-coded genetic algorithm (RCGA), allows learning high-quality FCMs from historical data. The current bottleneck of this learning method is its scalability, which originates from large continuous search space (of quadratic size with respect to the size of the FCM) and computational complexity of genetic optimization. To this end, the goal of this paper is to explore parallel nature of genetic algorithms to alleviate the scalability problem. We use the global single-population master-slave parallelization method to speed up the FCMs learning method. We investigate the influence of different hardware architectures on the computational time of the learning method by executing a wide range of synthetic and real-life benchmarking tests. We analyze the quality of the proposed parallel learning method in application to both dense and sparse large FCMs, i.e. maps that consist of several dozens of concepts. The parallelization is shown to provide substantial speed-ups, allowing doubling the size of the FCM that can be learned by parallelization with 8 processors.

Critical assessment of high-throughput standalone methods for secondary structure prediction

Sequence-based prediction of protein secondary structure (SS) enjoys wide-spread and increasing use for the analysis and prediction of numerous structural and functional characteristics of proteins. The lack of a recent comprehensive and large-scale comparison of the numerous prediction methods results in an often arbitrary selection of a SS predictor. To address this void, we compare and analyze 12 popular, standalone and high-throughput predictors on a large set of 1975 proteins to provide in-depth, novel and practical insights. We show that there is no universally best predictor and thus detailed comparative studies are needed to support informed selection of SS predictors for a given application. Our study shows that the three-state accuracy (Q3) and segment overlap (SOV3) of the SS prediction currently reach 82% and 81%, respectively. We demonstrate that carefully designed consensus-based predictors improve the Q3 by additional 2% and that homology modeling-based methods are significantly better by 1.5% Q3 than ab initio approaches. Our empirical analysis reveals that solvent exposed and flexible coils are predicted with a higher quality than the buried and rigid coils, while inverse is true for the strands and helices. We also show that longer helices are easier to predict, which is in contrast to longer strands that are harder to find. The current methods confuse 1-6% of strand residues with helical residues and vice versa and they perform poorly for residues in the β- bridge and 3(10)-helix conformations. Finally, we compare predictions of the standalone implementations of four well-performing methods with their corresponding web servers.

Parallel fuzzy cognitive maps as a tool for modeling software development projects

Fuzzy cognitive maps (FCM) are useful tool for simulating and analyzing dynamic systems. The FCMs have a very simple structure, and thus are very easy to comprehend and use. Despite of the simplicity, they have been successfully adopted in many different areas, such as electrical engineering, medicine political science, international relations, military science, history: supervisory systems, etc. Software development is a complex process, and there are many factors that influence its progress. To effectively handle larger development processes, they are usually divided into subtasks, which are assigned to different teams of workers, and often are performed in parallel. However, some constraints that impose particular sequence of realization of these subtasks, i.e. some tasks cannot be started before completing others, usually exist. Proper division of a project into subtasks and establishing relations between them are essential to correctly manage software projects. Neglecting these constraints often leads to problems that, in consequence, cause misestimating the overall time and budget. This paper introduces a new architecture of FCM, which combines a number of simple FCM models that work simultaneously into a novel parallel FCMs model. It uses a special purpose coordinator module to synchronize simulation of each FCM model. This approach extends application of FCMs to complex systems, which contain multiple subtasks that run in parallel, and thus must be simulated with multiple FCM models. In addition, application of parallel FCMs to analyze and design software development processes is presented. FCM models are focused on simulating and analyzing factors, such as progress and communication, and their relationships, which are based on theoretical research studies and practical implementations. The parallel FCM model is used to simulate complex projects where multiple tasks exist. The paper is based on our previous work where FCM models, which describe relationships between the above factors for individual development tasks, were developed. The newly proposed architecture allows for efficient analysis of dependences between tasks performed in parallel.

Expert-Based and Computational Methods for Developing Fuzzy Cognitive Maps

Development of Fuzzy Cognitive Maps (FCMs) that accurately describe a given dynamic system is a challenging task which in many cases cannot be fully completed based solely on human expertise. Some of the reasons behind this limitation include potential bias of the human experts and excessive size of the problem itself. However, due to the lack of automated or semi-automated methods that would replace or support designers, most of existing FCMs were developed using expert-based approaches. Interestingly, in the recent years we have witnessed the development of algorithms that support learning of FCMs from data. The learning corresponds to the construction of connection matrices based on historical data presented in the form of multivariate time series. Since the FCM may include feedback loops and they incorporate nontrivial transformation functions, forming these models from data is a complex task that requires searching through a large solution space. The existing automated learning methods are based either on the Hebbian learning or they apply evolutionary algorithms. This chapter formulates the task of learning FCMs and describes the corresponding design challenges. We present a comprehensive survey of the current expert-based and semi-automated/automated methods for learning FCMs. The leading learning methods are described and analyzed both analytically and experimentally with the help of a case study. We also contrast computational approaches versus expert-based methods and outline future research directions.

Evolutionary Development of Fuzzy Cognitive Maps

Fuzzy cognitive maps (FCMs) form a convenient, simple, and powerful tool for simulation and analysis of dynamic systems. The popularity of FCMs stems from their simplicity and transparency. While being successful in a variety of application domains, FCMs are hindered by necessity of involving domain experts to develop the model. Since human experts are subjective and can handle only relatively simple networks (maps), there is an urgent need to develop methods for automated generation of FCM models. This study proposes a novel evolutionary learning that is able to generate FCM models from input historical data, and without any human intervention. The proposed method is based on genetic algorithms, and is carried out through supervised learning. The paper tests the method through a series of carefully selected experimental studies

Learning of Fuzzy Cognitive Maps Using Density Estimate

Fuzzy cognitive maps (FCMs) are convenient and widely used architectures for modeling dynamic systems, which are characterized by a great deal of flexibility and adaptability. Several recent works in this area concern strategies for the development of FCMs. Although a few fully automated algorithms to learn these models from data have been introduced, the resulting FCMs are structurally considerably different than those developed by human experts. In particular, maps that were learned from data are much denser (with the density over 90% versus about 40% density of maps developed by humans). The sparseness of the maps is associated with their interpretability: the smaller the number of connections is, the higher is the transparency of the map. To this end, a novel learning approach, sparse real-coded genetic algorithms (SRCGAs), to learn FCMs is proposed. The method utilizes a density parameter to guide the learning toward a formation of maps of a certain predefined density. Comparative tests carried out for both synthetic and real-world data demonstrate that, given a suitable density estimate, the SRCGA method significantly outperforms other state-of-the-art learning methods. When the density estimate is unknown, the new method can be used in an automated fashion using a default value, and it is still able to produce models whose performance exceeds or is equal to the performance of the models generated by other methods.