Machine Learning Summer School 2007 - Tuebingen

Lost in Translation -- Solving biological problems with machine learning

author: Oliver Kohlbacher, Universität Tübingen

Description

We demonstrate the application of machine learning methods to problems from biology, chemistry, and pharmacy, nameley the prediction of protein subcellular localization, prediction of chromatiographic separation of oligo nucleotides, and the prediction of percutaneous drug absorption. For these examples, we show how translating the primary data into problem-specific features is essential for solving classification and regression problems.

Categories

Top: Computer Science: Bioinformatics

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Lost in Translation
1:22	Computer Science and Biology
3:28	Machine Learning in Bioinformatics
4:45	Machine Learning
8:39	Clash of Cultures - part 1
10:49	Clash of Cultures - part 2
11:49	Outline
12:29	Case Study I
14:05	Experiment: Confocal Microscopy
15:20	Motivation
16:30	Protein Targeting
17:14	Address Tags
18:34	Protein sorting pathways
19:16	Biological knowledge
19:55	Challenges
21:03	Encoding the data
21:55	Data sets
22:35	MultiLoc architecture
24:11	SVMTarget
25:01	Results
25:38	Pushing it further
26:25	Text Source – PubMed via SwissProt
27:01	Text PreProcessing
27:57	Distinguishing Terms
29:31	SherLoc: System Architecture
30:03	Results
31:10	Summary
32:04	Case Study II
33:26	HPLC Basics - part 1
34:07	HPLC Basics - part 2
34:10	HPLC Basics - part 3
34:13	HPLC Basics - part 4
34:28	HPLC Basics - part 5
34:34	HPLC Basics - part 6
34:40	HPLC Basics - part 7
34:42	How does HPLC work?
34:44	How does HPLC work?
34:59	HPLC Analysis of DNA Oligos
35:41	Previous Model (Gilar et al.)
36:50	Performance of the Gilar model
37:23	Problems
38:48	Retention Mechanism
39:40	Melting of DNA
40:27	Support Vector Regression Model
40:58	Regression Model
41:18	Comparison with Gilar Model
41:45	Case Study 3
42:27	Structure of Human Skin
43:17	The brick-and-mortar model
43:53	Trans- & paracellular pathways
44:14	The Franz Diffusion Cell
46:22	Computational Models
46:49	QSAR/QSPR
47:16	Decriptors
47:59	Initial Descriptors
48:52	Feature Selection
49:41	Problem-Relevant Descriptors
50:03	Drug Absorption Model
50:35	kNN Model
51:12	Conclusion
52:34	Things to Keep in Mind
53:44	Acknowledgements

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.