Computational Prediction of Transposon Insertion Sites
| dc.contributor.author | Ayat, Maryam | |
| dc.contributor.examiningcommittee | Bunt, Andrea (Computer Science) Whyard, Steven (Biological Science) | en_US |
| dc.contributor.supervisor | Domaratzki, Michael (Computer Science) | en_US |
| dc.date.accessioned | 2013-04-04T15:09:22Z | |
| dc.date.available | 2013-04-04T15:09:22Z | |
| dc.date.issued | 2013-04-04 | |
| dc.degree.discipline | Computer Science | en_US |
| dc.degree.level | Master of Science (M.Sc.) | en_US |
| dc.description.abstract | Transposons are DNA segments that can move or transpose themselves to new positions within the genome of an organism. Biologists need to predict preferred insertion sites of transposons to devise strategies in functional genomics and gene therapy studies. It has been found that the deformability property of the local DNA structure of the integration sites, called Vstep, is of significant importance in the target-site selection process. We considered the Vstep profiles of insertion sites and developed predictors based on Artificial Neural Networks (ANN) and Support Vector Machines (SVM). We trained our ANN and SVM predictors with the Sleeping Beauty transposonal data, and used them for identifying preferred individual insertion sites (each 12bp in length) and regions (each 100bp in length). Running a five-fold cross-validation showed that (1) Both ANN and SVM predictors are more successful in recognizing preferred regions than preferred individual sites; (2) Both ANN and SVM predictors have excellent performance in finding the most preferred regions (more than 90% sensitivity and specificity); and (3) The SVM predictor outperforms the ANN predictor in recognizing preferred individual sites and regions. The SVM has 83% sensitivity and 72% specificity in identifying preferred individual insertion sites, and 85% sensitivity and 90% specificity in recognizing preferred insertion regions. | en_US |
| dc.description.note | May 2013 | en_US |
| dc.identifier.uri | http://hdl.handle.net/1993/18340 | |
| dc.language.iso | eng | en_US |
| dc.rights | open access | en_US |
| dc.subject | Artificial Neural Networks | en_US |
| dc.subject | Support Vector Machines | en_US |
| dc.subject | Transposons | en_US |
| dc.subject | Insertion Site Prediction | en_US |
| dc.title | Computational Prediction of Transposon Insertion Sites | en_US |
| dc.type | master thesis | en_US |