Show simple item record

dc.contributor.authorNeezi, Nazia Afrin
dc.contributor.authorShadab, Shadman
dc.contributor.authorKhan, Md. Tawab Alam
dc.date.accessioned2019-04-03T08:22:39Z
dc.date.available2019-04-03T08:22:39Z
dc.date.issued2019-03
dc.identifier.urihttp://dspace.uiu.ac.bd/handle/52243/962
dc.description.abstractDNA-Binding proteins are associated with many cellular level functions which includes but not limited to body’s defense mechanism and oxygen transportation. They bind DNAs and interact with them. In the past DBPs were identified using experimental lab based methods. But nowadays researchers use supervised learning to identify DBPs solely from protein sequences. At the time of writing this paper, to our knowledge, no approach has been taken to apply deep learning in order to identify DBP. So we decided to try out to different approach using deep learning to identify DNA-Binding proteins; DeepDBP(ANN) and DeepDBP(CNN). Both of our methods were able to produce state-of-the-art results.DeepDBP(ANN) had a train accuracy of 99.02% and test accuracy of 82.80%.And DeepDBP(CNN) though had train accuracy of 94.32%, it excelled at identifying test instances with 84.31% accuracy. All the source codes and other resources including the datasets of DeepDBPcan be found at https://github.com/antorkhan/deepdbpen_US
dc.language.isoen_USen_US
dc.subjectMachine Learningen_US
dc.subjectDeep Learningen_US
dc.titleDeepDBP:A Novel Prediction Method for Identification of DNA-binding Protein Using Deep Neural Networksen_US
dc.typeThesisen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record