|
|
Prediction of the Effect of Amino Acid Substitutions on the Secondary Structure of Proteins
Kadlec, Miroslav ; Vogel, Ivan (referee) ; Bendl, Jaroslav (advisor)
This thesis is focused on amino acid substitutions and their impact on protein secondary structure. The main aim is to prove, that although the protein sequence is frequently mutated during the evolution, protein secondary structure is more robust against changes. In this case, the elements of protein secondary structure stay almost unchanged although a significant number of substitutions is observed. The proof of this hypothesis was obtained by developed simulator of evolution which employs two well-estabilished predicting tools: PSIPRED for prediction of protein secondary structure and PhD-SNP for prediction of the effect of amino acid substitution on protein function. The results of the experiments are provided as graphs and their meainings is discussed.
|
|
|
Prediction of Protein Stability upon Amino Acid Mutations Using Evolution Strategy
Kadlec, Miroslav ; Burgetová, Ivana (referee) ; Bendl, Jaroslav (advisor)
This thesis is focused on predicting the impact of amino acid substitution on protein stability. The main goal is to create a consensual predictor that uses the outputs of chosen existing tools in order to improve accuracy of prediction. The optimal consensus of theese tools was designed using evolution strategies in three variants: 1/5 success rule, self-adaptation variant and the CMA-ES method. Then, the quality of calculated weight vectors was tested on the independent dataset. Although the highest prediction performance was attained by self-adaptation method, the differences between all three variants were not significant. Compared to the individual tools, the predictions provided by consensual methods were generally more accurate - the self-adaptation variant imporved the Pearson's corelation coeficient of the predictions by 0,057 on the training dataset. On the testing dataset, the improvement of designed method was smaller (0,040). Relatively low improvement of prediction performance (both on the training and the testing dataset) were caused by the fact, that for some records of testing dataset, some individual tools vere not able to provide their results. When omitting these records, consensual method improved the Pearson's corelations coeficient by 0,118.
|
|
|
Machine Learning as a Tool for the Prediction of the Effect of Mutations on Protein Stability
Dúbrava, Juraj Ondrej ; Martínek, Tomáš (referee) ; Musil, Miloš (advisor)
The main focus of this thesis is the prediction of the effect of amino acid substitutions on protein stability. My goal was to develop a predictive tool for the classification of the effect of mutations by combining several machine learning techniques. The implemented predictor, which utilizes SVM and Random forest methods, has achieved higher accuracy than any of the integrated methods. The novel predictive tool was compared with the existing ones using independent testing dataset. The predictor has yield 67 % accuracy and MCC 0,3.
|
|
|
Machine Learning as a Tool for the Prediction of the Effect of Mutations on Protein Stability
Dúbrava, Juraj Ondrej ; Martínek, Tomáš (referee) ; Musil, Miloš (advisor)
The main focus of this thesis is the prediction of the effect of amino acid substitutions on protein stability. My goal was to develop a predictive tool for the classification of the effect of mutations by combining several machine learning techniques. The implemented predictor, which utilizes SVM and Random forest methods, has achieved higher accuracy than any of the integrated methods. The novel predictive tool was compared with the existing ones using independent testing dataset. The predictor has yield 67 % accuracy and MCC 0,3.
|
|
|
Prediction of the Effect of Amino Acid Substitutions on the Secondary Structure of Proteins
Kadlec, Miroslav ; Vogel, Ivan (referee) ; Bendl, Jaroslav (advisor)
This thesis is focused on amino acid substitutions and their impact on protein secondary structure. The main aim is to prove, that although the protein sequence is frequently mutated during the evolution, protein secondary structure is more robust against changes. In this case, the elements of protein secondary structure stay almost unchanged although a significant number of substitutions is observed. The proof of this hypothesis was obtained by developed simulator of evolution which employs two well-estabilished predicting tools: PSIPRED for prediction of protein secondary structure and PhD-SNP for prediction of the effect of amino acid substitution on protein function. The results of the experiments are provided as graphs and their meainings is discussed.
|
|
|
Prediction of Protein Stability upon Amino Acid Mutations Using Evolution Strategy
Kadlec, Miroslav ; Burgetová, Ivana (referee) ; Bendl, Jaroslav (advisor)
This thesis is focused on predicting the impact of amino acid substitution on protein stability. The main goal is to create a consensual predictor that uses the outputs of chosen existing tools in order to improve accuracy of prediction. The optimal consensus of theese tools was designed using evolution strategies in three variants: 1/5 success rule, self-adaptation variant and the CMA-ES method. Then, the quality of calculated weight vectors was tested on the independent dataset. Although the highest prediction performance was attained by self-adaptation method, the differences between all three variants were not significant. Compared to the individual tools, the predictions provided by consensual methods were generally more accurate - the self-adaptation variant imporved the Pearson's corelation coeficient of the predictions by 0,057 on the training dataset. On the testing dataset, the improvement of designed method was smaller (0,040). Relatively low improvement of prediction performance (both on the training and the testing dataset) were caused by the fact, that for some records of testing dataset, some individual tools vere not able to provide their results. When omitting these records, consensual method improved the Pearson's corelations coeficient by 0,118.
|
guest ::
