We have developed a new approach for locating transmembrane domains in protein sequences based on hydrophobicity analysis and backpropagation neural network or k-nearest-neighbor as classifiers. Our system was able to locate over 98% of the transmembrane domains and the total accuracy including overpredictions was above 95%.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:bth-2752 |
| Date | January 2003 |
| Creators | Hagelbäck, Johan, Svensson, Kenny |
| Publisher | Blekinge Tekniska Högskola, Institutionen för programvaruteknik och datavetenskap, Blekinge Tekniska Högskola, Institutionen för programvaruteknik och datavetenskap |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.1893 seconds