|
|
Prediction of the Effect of Nucleotide Substitution Using Machine Learning
Šalanda, Ondřej ; Martínek, Tomáš (referee) ; Bendl, Jaroslav (advisor)
This thesis brings a new approach to the prediction of the effect of nucleotide polymorphism on human genome. The main goal is to create a new meta-classifier, which combines predictions of several already implemented software classifiers. The novelty of developed tool lies in using machine learning methods to find consensus over those tools, that would enhance accuracy and versatility of prediction. Final experiments show, that compared to the best integrated tool, the meta-classifier increases the area under ROC curve by 3,4 in average and normalized accuracy is improved by up to 7\,\%. The new classifying service is available at http://ll06.sci.muni.cz:6232/snpeffect/.
|
|
|
Travelling Salesman Problem
Kolář, Adam ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
The aim of this bachelor's thesis is to design a testing environment for the traveling salesman problem and compare the effectiveness of different approaches to the solution. The first part discussed the possibility of genetic algorithms, depending on the setting of a crossover, mutations and population size. In the second part, there is the same problem using two types of neural networks. The representative of the self-learning net was chosen Kohonen neural network. Hopfield neural network represents a method of minimizing the energy function with fixed coefficients. At both neural networks, there were described possible advantages and disadvantages. In the end, all the findings were interpreted in a global context.
|
|
|
Genetic programming - Java implementation
Tomaštík, Marek ; Kuba,, Martin (referee) ; Matoušek, Radomil (advisor)
This Master´s thesis implements computer program in Java, useful for automatic model generating, specially in symbolic regression problem. Thesis includes short description of genetic programming (GP) and own implementation with advanced GP operands (non-destructive operations, elitism, exptression reduction). Mathematical model is generating by symbolic regression, exacly for choosen data set. For functioning check are used test tasks. Optimal settings is found for choosen GP parameters.
|
|
|
Cardiac IKs channel: rate-dependence of the current magnitude
Kachan, Ksenia ; Čmiel, Vratislav (referee) ; Bébarová,, Markéta (advisor)
This diploma thesis deals with study of the rate-dependence of the magnitude of a current through the heart channel that conducts slowly activating component of delayed rectifier outward current (IKs). This property is very important for the IKs channel function. When other repolarizing currents are insufficient, but also when the heart rate accelerates, especially during elevated sympathetic tone, IKs provides so-called repolarization reserve, which prevents excessive lengthening of cardiac action potential repolarization. The IKs channel structure is encoded by the KCNQ1 (pore-forming -subunit) and KCNE1 (modulatory -subunit) genes. Mutations in these genes disrupt the physiological function of the IKs channel and cause inherited arrhythmogenic syndromes, especially long QT syndrome (LQTS). Such mutations include the c.926C>T (p.T309I) mutation in the KCNQ1 gene, which results in LQTS type 1 in heterozygous carriers. The theoretical part of the thesis provides basic information about the IKs channel and the patch clamp technique, this knowledge is necessary for the practical part. The experimental part is focused on cultivation of the CHO cell line and its transient transfection for subsequent electrophysiological measurements by whole-cell patch clamp technique to study the dependence of the IKs magnitude on stimulation frequency, both in the wild type channels (i.e. without mutation) and in those with cotransfected wild type and T309I subunits.
|
|
|
The global optimalization methods
Dudová, Aneta ; Kozumplík, Jiří (referee) ; Mézl, Martin (advisor)
This bachelor work is dedicated to advanced methods of global optimization, and especially problem traveling salesman. It focuses on the description of the problem and its various options, including graph theory, heuristic algorithms, evolutionary algorithms, in which mainly genetic algorithms and optimization by ant colonies. In conclusion, the implementation of these methods and performed testing on different data sets of algorithms that approximately solve the traveling salesman problem.
|
|
|
Prediction of the Effect of Mutation on Protein Solubility
Velecký, Jan ; Martínek, Tomáš (referee) ; Hon, Jiří (advisor)
The goal of the thesis is to create a predictor of the effect of a mutation on protein solubility given its initial 3D structure. Protein solubility prediction is a bioinformatics problem which is still considered unsolved. Especially a prediction using a 3D structure has not gained much attention yet. A relevant knowledge about proteins, protein solubility and existing predictors is included in the text. The principle of the designed predictor is inspired by the Surface Patches article and therefore it also aims to validate the results achieved by its authors. The designed tool uses changes of positive regions of the electric potential above the protein's surface to make a prediction. The tool has been successfully implemented and series of computationally expensive experiments have been performed. It was shown that the electric potential, hence the predictor itself too, can be successfully used just for a limited set of proteins. On top of that, the method used in the article correlates with a much simpler variable - the protein's net charge.
|
|
|
Comparison of genomes by synteny block analysis
Pavel, Tomáš ; Škutková, Helena (referee) ; Maděránková, Denisa (advisor)
The theoretical part of this bachelor thesis is aimed at basics of genetics. Term of gene and mutation are introduced in this section. There are gene and chromosome mutations mentioned and described. Following section is devoted to comparative genomics and especially to synteny. There is described what the synteny actually is and how the synteny arises. The end of the theoretical part of this thesis is about the evolution and there are described ways of sorting permutation vectors. The practical part of this bachelor thesis includes description of developed software. Output of this software is a dot-plot which shows detected synteny blocks. Indexes of these blocks are listed in GUI. The second important output is number of permutation steps. This number determines evolutionary distance between two analysed DNA sequences. The very last section is aimed at analyse of synthetic and real DNA sequences.
|
|
|
Multi-Agent System for the Prediction of the Effect of Mutations on Protein Stability
Doseděl, Ondřej ; Martínek, Tomáš (referee) ; Musil, Miloš (advisor)
Proteiny jsou základním stavebním blokem všech žijících organismů, kde jsou zodpovědné za mnoho důležitých procesů. Jsou složeny z řetězců aminokyselin. Tyto řetězce mohou být jakkoliv změněné. Tomuto procesu se říká mutace a může být samovolná nebo indukovaná v laboratoři. Cílem této práce bylo vytvoření nových modelů pro určení stability proteinů. Skládá se ze dvou modelů. První model je multi-agentní systém pro klasifikaci stability proteinů. Nejlepší multi-agentní systém získal přesnost 0.7 a 0.41 MCC. Druhá část se~zabývala predikcí konkrétních hodnot G, kde byl vytvořený Extreme Gradient Boosting model, který získal 1.67 RMSE a 0.53 PCC. Součástí této práce byly představené 2 datasety, které jsou na sobě plně nezávislé, použitelné pro trénování a validaci modelů.
|
|
|
Evolutionary models for evaluation of organisms relationship
Gregorová, Kateřina ; Maděránková, Denisa (referee) ; Škutková, Helena (advisor)
The work is focused on the study and description of evolutionary models for the evaluation of the evolutionary distances of DNA sequences and protein sequences in the amino acids and the codon representation. In the framework of this work was created a program that evaluates the genetic distance between DNA sequences and protein sequences for the use of some evolutionary models. The program calculates the genetic distance of the compared sequences and on the basis thereof renders the phylogenetic tree. This can be relatively easily and quickly evaluate the affinity of the organisms. For easy operation is part of the evaluation program also graphical user interface (GUI).
|
|
|
Genetic Algorithms - Multi-core CPU Implementation
Studnička, Vladimír ; Kuba, Martin (referee) ; Matoušek, Radomil (advisor)
his diploma thesis deals with creating the most universal library of genetic algorithms in C++, as much as possible, implemented with the certain number of universal operators, and then with testing created library on some examples. Library must support multi-core processors, implementation will be done over OpenMP. The library will be tested on three examples in all. The first two examples are mathematical functions, that are used just for genetic algorithms testing. Last problem for test is N-Queens problem. Finally we will use genetic algorithms to try find solution for Eternity II puzzle, there is declared a 2 million bounty for full solution.
|
guest ::
