Protein secondary structure prediction using neural networks and support vector machines
- Authors: Tsilo, Lipontseng Cecilia
- Date: 2009
- Subjects: Neural networks (Computer science) , Support vector machines , Proteins -- Structure -- Mathematical models
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:5569 , http://hdl.handle.net/10962/d1002809 , Neural networks (Computer science) , Support vector machines , Proteins -- Structure -- Mathematical models
- Description: Predicting the secondary structure of proteins is important in biochemistry because the 3D structure can be determined from the local folds that are found in secondary structures. Moreover, knowing the tertiary structure of proteins can assist in determining their functions. The objective of this thesis is to compare the performance of Neural Networks (NN) and Support Vector Machines (SVM) in predicting the secondary structure of 62 globular proteins from their primary sequence. For each NN and SVM, we created six binary classifiers to distinguish between the classes’ helices (H) strand (E), and coil (C). For NN we use Resilient Backpropagation training with and without early stopping. We use NN with either no hidden layer or with one hidden layer with 1,2,...,40 hidden neurons. For SVM we use a Gaussian kernel with parameter fixed at = 0.1 and varying cost parameters C in the range [0.1,5]. 10- fold cross-validation is used to obtain overall estimates for the probability of making a correct prediction. Our experiments indicate for NN and SVM that the different binary classifiers have varying accuracies: from 69% correct predictions for coils vs. non-coil up to 80% correct predictions for stand vs. non-strand. It is further demonstrated that NN with no hidden layer or not more than 2 hidden neurons in the hidden layer are sufficient for better predictions. For SVM we show that the estimated accuracies do not depend on the value of the cost parameter. As a major result, we will demonstrate that the accuracy estimates of NN and SVM binary classifiers cannot distinguish. This contradicts a modern belief in bioinformatics that SVM outperforms other predictors.
- Full Text:
- Date Issued: 2009
- Authors: Tsilo, Lipontseng Cecilia
- Date: 2009
- Subjects: Neural networks (Computer science) , Support vector machines , Proteins -- Structure -- Mathematical models
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: vital:5569 , http://hdl.handle.net/10962/d1002809 , Neural networks (Computer science) , Support vector machines , Proteins -- Structure -- Mathematical models
- Description: Predicting the secondary structure of proteins is important in biochemistry because the 3D structure can be determined from the local folds that are found in secondary structures. Moreover, knowing the tertiary structure of proteins can assist in determining their functions. The objective of this thesis is to compare the performance of Neural Networks (NN) and Support Vector Machines (SVM) in predicting the secondary structure of 62 globular proteins from their primary sequence. For each NN and SVM, we created six binary classifiers to distinguish between the classes’ helices (H) strand (E), and coil (C). For NN we use Resilient Backpropagation training with and without early stopping. We use NN with either no hidden layer or with one hidden layer with 1,2,...,40 hidden neurons. For SVM we use a Gaussian kernel with parameter fixed at = 0.1 and varying cost parameters C in the range [0.1,5]. 10- fold cross-validation is used to obtain overall estimates for the probability of making a correct prediction. Our experiments indicate for NN and SVM that the different binary classifiers have varying accuracies: from 69% correct predictions for coils vs. non-coil up to 80% correct predictions for stand vs. non-strand. It is further demonstrated that NN with no hidden layer or not more than 2 hidden neurons in the hidden layer are sufficient for better predictions. For SVM we show that the estimated accuracies do not depend on the value of the cost parameter. As a major result, we will demonstrate that the accuracy estimates of NN and SVM binary classifiers cannot distinguish. This contradicts a modern belief in bioinformatics that SVM outperforms other predictors.
- Full Text:
- Date Issued: 2009
The possibility of psychotherapeutic privilege in South Africa
- Authors: Gewald, Rieka Susan
- Date: 2009
- Subjects: Psychology -- Moral and ethical aspects -- South Africa Psychologists -- Professional ethics -- South Africa Psychotherapists -- Professional ethics -- South Africa Confidential communications -- South Africa Privileges and immunities -- South Africa Evidence (Law) -- South Africa
- Language: English
- Type: Thesis , Masters , LLM
- Identifier: vital:3717 , http://hdl.handle.net/10962/d1008208
- Description: Privilege is an evidential principle which, on the grounds of public policy, excludes evidence relevant and otherwise admissible. This thesis aims to discover whether privilege should be applied to the psychotherapeutic profession in South Africa. At present, the only profession in South Africa afforded privilege is the legal profession. There are two main theoretical justifications for privilege: the utilitarian and the individual/human rights approach. This thesis considers whether the psychotherapeutic profession warrants privilege under either theory, and recommends that the law of privilege integrate both theories rather than adopt one or the other. The impact of the Constitution and the right to privacy receive particular attention. Very little literature or case law on the question of psychotherapeutic privilege was found in South Africa. Consequently, extensive comparative research into the common-law systems of England, Canada and United States of America was done. This research yielded some interesting findings. The first is that case-by-case development of the law of privilege is uncel1ain and fragmented. The next is that psychotherapeutic privilege exists in almost absolute form in the United States of America, but is littered with lacunae causing as much uncertainty as the case-by-case approach to privilege law. The most helpful method of dealing with the problem was found in Canada, where a two-stage approach to protecting personal information, including psychotherapeutic records, has been developed. In light of this research, this thesis reassesses the original viability of psychotherapeutic privilege in South Africa. Privilege, it was found, is not the best solution to protecting psychotherapeutic communications. This thesis recommends legislative adoption of an amended two-stage approach based on the Canadian model for sexual offence trials as the best method of protecting psychotherapeutic communications in both civil and criminal proceedings. The thesis ends by suggesting draft legislative provisions.
- Full Text:
- Date Issued: 2009
- Authors: Gewald, Rieka Susan
- Date: 2009
- Subjects: Psychology -- Moral and ethical aspects -- South Africa Psychologists -- Professional ethics -- South Africa Psychotherapists -- Professional ethics -- South Africa Confidential communications -- South Africa Privileges and immunities -- South Africa Evidence (Law) -- South Africa
- Language: English
- Type: Thesis , Masters , LLM
- Identifier: vital:3717 , http://hdl.handle.net/10962/d1008208
- Description: Privilege is an evidential principle which, on the grounds of public policy, excludes evidence relevant and otherwise admissible. This thesis aims to discover whether privilege should be applied to the psychotherapeutic profession in South Africa. At present, the only profession in South Africa afforded privilege is the legal profession. There are two main theoretical justifications for privilege: the utilitarian and the individual/human rights approach. This thesis considers whether the psychotherapeutic profession warrants privilege under either theory, and recommends that the law of privilege integrate both theories rather than adopt one or the other. The impact of the Constitution and the right to privacy receive particular attention. Very little literature or case law on the question of psychotherapeutic privilege was found in South Africa. Consequently, extensive comparative research into the common-law systems of England, Canada and United States of America was done. This research yielded some interesting findings. The first is that case-by-case development of the law of privilege is uncel1ain and fragmented. The next is that psychotherapeutic privilege exists in almost absolute form in the United States of America, but is littered with lacunae causing as much uncertainty as the case-by-case approach to privilege law. The most helpful method of dealing with the problem was found in Canada, where a two-stage approach to protecting personal information, including psychotherapeutic records, has been developed. In light of this research, this thesis reassesses the original viability of psychotherapeutic privilege in South Africa. Privilege, it was found, is not the best solution to protecting psychotherapeutic communications. This thesis recommends legislative adoption of an amended two-stage approach based on the Canadian model for sexual offence trials as the best method of protecting psychotherapeutic communications in both civil and criminal proceedings. The thesis ends by suggesting draft legislative provisions.
- Full Text:
- Date Issued: 2009
- «
- ‹
- 1
- ›
- »