東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Computational prediction of protein-...

University of Massachusetts Lowell.

FindBook

Google Book

Amazon

博客來

Computational prediction of protein-protein interactions in novel organisms with application to chloroviruses.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Computational prediction of protein-protein interactions in novel organisms with application to chloroviruses./
作者:	Shaughnessy, Patrick.
面頁冊數:	121 p.
附註:	Adviser: Gary Livingston.
Contained By:	Dissertation Abstracts International69-11B.
標題:	Biology, Bioinformatics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3335715
ISBN:	9780549891949

Computational prediction of protein-protein interactions in novel organisms with application to chloroviruses.
Shaughnessy, Patrick.

Computational prediction of protein-protein interactions in novel organisms with application to chloroviruses. - 121 p.

Adviser: Gary Livingston.

Thesis (Sc.D.)--University of Massachusetts Lowell, 2008.

Machine learning methods are often used to predict the existence and nature of protein-protein interactions (PPI). It is common practice to train and evaluate these methods using known PPI data from well-characterized reference organisms, drawing from the same organisms the data used for inferring a predictive model and the data used for evaluating the model. However, when predicting PPI in an organism for which such reference data is not available, same-organism evaluation is not a good indicator of performance. This dissertation presents evaluation experiments towards finding a general predictive model for protein-protein interaction that can be applied to proteomically novel organisms. It is shown that training random forest models on PPI data from the plant Arabidopsis thaliana using a variety of representational features gives significant predictive performance on other proteomes, namely the yeast Saccharomyces cerevisiae and human herpesvirus 8. Predictions from such A. thaliana-trained models were made for the large and genetically unusual viruses known as Chloroviruses, and are presented here. While physical experiments on the predicted interacting proteins will not occur until 2009, the predictions appear to be highly consistent with existing Chlorovirus knowledge and consistent from one Chlorovirus to another.

ISBN: 9780549891949Subjects--Topical Terms:

1018415
Biology, Bioinformatics.

Computational prediction of protein-protein interactions in novel organisms with application to chloroviruses.
LDR:02268nmm 2200277 a 45 001 891446
005 20101111
008 101111s2008 ||||||||||||||||| ||eng d
020 $a 9780549891949
035 $a (UMI)AAI3335715
035 $a AAI3335715
040 $a UMI $c UMI
100 1 $a Shaughnessy, Patrick. $3 1065443
245 1 0 $a Computational prediction of protein-protein interactions in novel organisms with application to chloroviruses.
300 $a 121 p.
500 $a Adviser: Gary Livingston.
500 $a Source: Dissertation Abstracts International, Volume: 69-11, Section: B, page: 6934.
502 $a Thesis (Sc.D.)--University of Massachusetts Lowell, 2008.
520 $a Machine learning methods are often used to predict the existence and nature of protein-protein interactions (PPI). It is common practice to train and evaluate these methods using known PPI data from well-characterized reference organisms, drawing from the same organisms the data used for inferring a predictive model and the data used for evaluating the model. However, when predicting PPI in an organism for which such reference data is not available, same-organism evaluation is not a good indicator of performance. This dissertation presents evaluation experiments towards finding a general predictive model for protein-protein interaction that can be applied to proteomically novel organisms. It is shown that training random forest models on PPI data from the plant Arabidopsis thaliana using a variety of representational features gives significant predictive performance on other proteomes, namely the yeast Saccharomyces cerevisiae and human herpesvirus 8. Predictions from such A. thaliana-trained models were made for the large and genetically unusual viruses known as Chloroviruses, and are presented here. While physical experiments on the predicted interacting proteins will not occur until 2009, the predictions appear to be highly consistent with existing Chlorovirus knowledge and consistent from one Chlorovirus to another.
590 $a School code: 0111.
650 4 $a Biology, Bioinformatics. $3 1018415
650 4 $a Computer Science. $3 626642
690 $a 0715
690 $a 0984
710 2 $a University of Massachusetts Lowell. $3 1017839
773 0 $t Dissertation Abstracts International $g 69-11B.
790 $a 0111
790 1 0 $a Livingston, Gary, $e advisor
791 $a Sc.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3335715