Towards a semi-automatic functional annotation tool based on decision tree techniques

coauthor: Jean-François Gibrat, INRA - Paris

You might be experiencing some problems with Your Video player.

*Slides*
0:00	- Towards a semi-automatic functional annotation tool based on decision tree techniques - Announcement
0:05	Towards a semi-automatic functional annotation tool based on decision tree techniques
0:26	Context
0:31	Annotation : from raw data to knowledge
1:59	Annotation platform AGMIAL
3:05	Atlas view of the lactobacillus sakei genom
3:36	Pareo
3:54	Annotation platform AGMIAL
3:58	In summary - 1
4:12	In summary - 2
4:29	In summary - 3
4:33	In summary - 4
4:39	In summary - 5
5:18	Project motivation
5:22	Goal - 1
5:28	Goal - 2
5:32	Goal - 3
6:01	Goal - 4
6:14	Goal - 5
6:23	Goal - 6
6:33	Data
6:36	Genomes - 1
6:51	Genomes - 2
7:49	Subtilist functional hierarchy - 1
8:32	Subtilist functional hierarchy - 2
8:39	Subtilist functional hierarchy - 3
8:55	Genomes - 2
9:06	Genomes - 3
9:44	Annotation in a nutshell
10:43	Annotation rules
12:29	Machine learning techniques
12:33	Problem to be solved
12:40	Inductive logic programming framework Tilde
14:03	Relational data } attribute-value data
15:14	Multilabel probabilistic decision-tree
15:49	Evaluation measures
15:53	Hierarchical evaluation measures
16:48	Hierarchical evaluation measures - Example
17:46	Hierarchical evaluation measures
18:13	Results
18:16	Prediction parameters
19:07	Influence of threshold on hierarchical precision
19:20	Influence of threshold on hierarchical recall
19:30	Influence of threshold on hierarchical F score
19:47	Prediction parameters
19:49	Results for a 75% threshold
20:55	Multilabel probabilistic decision tree
21:06	TILDE decision trees
21:08	Example of rule : protein 1739 of L sakei - 1
22:39	Example of rule : protein 1739 of L sakei - 2
22:52	Example of rule : protein 1739 of L sakei - 3
23:00	Example of rule : protein 1739 of L sakei - 4
23:06	Perspectives
23:10	Conclusions – perspectives
25:15	- Questions
25:43	- Questions
26:01	- Questions
27:04	- Questions

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.