View mhc-nips11-v2 (public)
- Summary
Predicting binding affinity of MHC class I molecules. Subset in Krause, Ong, "Contextual Gaussian Process Bandit Optimization", NIPS 2011
- License
- CC0
- Dependencies
- Tags
- bioinformatics mhc UCB
- Attribute Types
- Download
-
# Instances: 4418 / # Attributes: 47
HDF5 (1.6 MB) XML CSV ARFF LibSVM Matlab OctaveFiles are converted on demand and the process can take up to a minute. Please wait until download begins.
You can edit this item to add more meta information and make use of the site's premium features.
- Original Data Format
- csv
- Name
- mhc-nips11-v2
- Version mldata
- 0
- Comment
CSV
- Names
- label,context,0,1,2,3,4,5,6,7,
- Data (first 10 data points)
label cont... 0 1 2 3 4 5 6 7 ... -1.60... 0.0 0.13... -0.17... -0.19... 0.09... 0.19... 0.12... 0.15... -0.00... ... -1.60... 0.0 0.26... -0.04... -0.01... 0.19... 0.13... 0.05... 0.12... -0.01... ... -1.60... 0.0 0.15... 0.39... -0.01... 0.01... 0.07... 0.14... 0.16... -0.01... ... -1.60... 0.0 0.17... 0.02... 0.08... 0.08... -0.03... 0.13... 0.16... -0.01... ... -1.60... 0.0 0.11... -0.24... 0.07... -0.17... -0.24... -0.09... -0.03... 0.28... ... -1.60... 0.0 -0.19... -0.12... 0.25... 0.05... 0.19... 0.13... 0.15... -0.00... ... -0.74... 0.0 0.12... -0.25... 0.07... -0.18... -0.25... 0.04... 0.10... -0.01... ... -1.60... 0.0 -0.16... 0.08... -0.11... -0.12... -0.18... 0.04... 0.09... -0.00... ... -1.60... 0.0 -0.23... -0.01... 0.05... -0.00... 0.14... -0.16... -0.10... -0.10... ... -1.60... 0.0 0.14... 0.37... -0.01... 0.01... 0.07... -0.15... -0.09... -0.10... ... ... ... ... ... ... ... ... ... ... ... ...
- Description
Data used in experiment in: Andreas Krause, Cheng Soon Ong. Contextual Gaussian Process Bandit Optimization. Advances in Neural Information Processing, 2011.
- URLs
- (No information yet)
- Publications
- Data Source
- B. Peters et. al. A community resource benchmarking predictions of peptide binding to mhc-i molecules. PLoS Computational Biology, 2(6):e65, 2006.
- Measurement Details
Output kernel matrices (task similarity) obtained from
C. Widmer, N. Toussaint, Y. Altun, and G. Raetsch. Inferring latent task structure for multitask learning by multiple kernel learning. BMC Bioinformatics, 11(Suppl 8:S5), 2010.
all_tasks = ['A_2403', 'A_2402', 'A_2301', 'A_0201', 'A_0203', 'A_0202', 'A_6901'] Ky = array([[1., 0.9, 0.85, 0.25, 0., 0.3, 0.], [0.9, 1., 0.9, 0., 0., 0.25, 0.], [0.85, 0.9, 1., 0.25, 0., 0.25, 0.], [0.25, 0., 0.25, 1., 0.85, 0.85, 0.55], [0., 0., 0., 0.85, 1., 0.85, 0.45], [0.3, 0.25, 0.25, 0.85, 0.85, 1., 0.45], [0., 0., 0., 0.55, 0.45, 0.45, 1.]])
- Usage Scenario
Data conversion
- 1st data point from split 0, and all data from split 2,3,4.
- Features are the 45 PCA values of encoded peptides (divided by the vector norm)
- Labels are -log10(ic50s)+log10(500)
- First column contains the label, second column the context, the rest the features
Experimental notes
- A base GP is trained on the first example
- GP UCB run on all the rest
- revision 1
- by cong on 2016-01-07 02:25
No one has posted any comments yet. Perhaps you would like to be the first?
Leave a comment
To post a comment, please sign in.This item was downloaded 10858 times and viewed 18 times.
No Tasks yet on dataset mhc-nips11-v2
Submit a new Task for this Data itemDisclaimer
We are acting in good faith to make datasets submitted for the use of the scientific community available to everybody, but if you are a copyright holder and would like us to remove a dataset please inform us and we will do it as soon as possible.
Acknowledgements
This project is supported by PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning)
http://www.pascal-network.org/.