Supervised reconstruction of biological networks

author:Jean-Philippe Vert, MINES ParisTech
published: Nov. 20, 2007, recorded: September 2007, views: 311

You might be experiencing some problems with Your Video player.

Slides

Slides
0:00	- Supervised inference of biological networks - Announcement
0:44	Supervised inference of biological networks
2:22	Outline - 1
2:27	Outline - 2
2:49	Outline - 3
3:16	Outline - 4
3:22	Outline - 5
3:23	- Motivation
3:25	Biological networks
4:49	Example: metabolic network
6:34	What are the challenges? - 1
7:46	What are the challenges? - 2
8:15	How can bioinformatics help?
9:47	Our goal: Summary
9:59	- Unsupervised inference
10:28	Unsupervised inference - 1
11:23	Unsupervised inference - 2
11:38	Model-based approaches - 1
11:45	Model-based approaches - 2
12:35	Model-based approaches - 3
14:50	Similarity-based approaches - 1
15:38	Similarity-based approaches - 2
16:05	Similarity-based approaches - 3
16:18	Integrations of genomic data
17:26	Evaluation on metabolic network reconstruction
19:48	What went wrong?
21:37	- Supervised inference
21:51	Setting
23:25	- Supervised inference - Metric learning
23:52	Metric learning - 1
25:13	Metric learning - 2
25:51	Metric learning - 3
26:07	Metric learning - 4
27:09	Metric learning by kernel CCA - 1
27:58	Metric learning by kernel CCA - 2
27:59	Metric learning by kernel CCA - 3
29:03	Metric learning by kernel CCA - 4
29:44	Metric learning by kernel CCA - 5
29:46	Kernel metric learning
31:13	Metric learning: Summary - 1
31:41	Metric learning: Summary - 2
32:14	- Supervised inference - Matrix completion
32:32	Matrix completion
33:47	Matrix completion by em algorithm
35:43	Matrix completion by kernel matrix regression
36:04	Matrix completion : Summary
36:26	- Supervised inference - Global pattern recognition
36:59	Pattern recognition - 1
37:37	Pattern recognition - 2
38:21	Pattern recognition for supervised graph inference - 1
39:31	Pattern recognition for supervised graph inference - 2
40:17	Pattern recognition for supervised graph inference - 3
40:42	Tensor product SVM - 1
42:05	Tensor product SVM - 2
42:23	Tensor product SVM - 3
43:23	Metric learning pairwise SVM - 1
43:59	Metric learning pairwise SVM - 2
44:00	Metric learning pairwise SVM - 3
44:41	Remarks about pattern recognition for pairs - 1
45:07	Remarks about pattern recognition for pairs - 2
46:11	- Supervised inference - Local pattern recognition
46:22	Local pattern recognition - 1
46:27	Local pattern recognition - 2
48:02	The LOCAL model
48:04	The LOCAL model: training edges
48:15	The LOCAL model: testing edges
48:16	The LOCAL model: learning - 1
48:19	The LOCAL model: learning - 2
48:21	The LOCAL model: learning - 3
48:26	The LOCAL model: learning - 4
48:27	The LOCAL model: learning - 5
48:29	The LOCAL model: decision boundary
48:34	The LOCAL model: testing - 1
48:45	The LOCAL model: testing - 2
48:47	The LOCAL model: predictions
48:50	The LOCAL model: target graph
48:52	The LOCAL model: two correct edges, one error
48:53	The LOCAL model: do same for each learning node - 1
48:54	The LOCAL model: do same for each learning node - 2
48:55	The LOCAL model: do same for each learning node - 3
48:56	The LOCAL model: do same for each learning node - 4
48:57	The LOCAL model: do same for each learning node - 5
48:58	The LOCAL model: do same for each learning node - 6
48:59	Local predictions: pros and cons - 1
49:05	Local predictions: pros and cons - 2
49:48	- Experiments
49:50	Experiments
50:15	Results: protein-protein interaction
52:07	Results: metabolic gene network
53:10	Results: effect of data integration - 1
53:12	Results: effect of data integration - 2
53:13	Experiments: summary
53:43	Applications: missing enzyme prediction - 1
54:26	Applications: missing enzyme prediction - 2
54:29	Applications: missing enzyme prediction - 3
54:39	Applications: function annotation
55:16	- Conclusion
55:17	Take-home messages
55:56	People I need to thank
56:24	- Questions

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.

Lecture popularity: You need to login to cast your vote.

Description

The inference or reconstruction of various biological networks, including regulatory, signalling or metabolic pathways, from large-scale heterogeneous data is currently an active research subject with several important applications in systems biology. While several approaches proposed so far cast this problem as inferring a graph de novo from genomic data, I will argue in this talk that the network of interest is often partially known and that the reconstruction process should use this partial knowledge to guide the inference of the missing edges. I will then review how this paradigm leads naturally to various supervised machine learning algorithms for graph inference, and illustrate the relevance of the approach through several examples of successful prediction of missing enzymes in metabolic networks.