p53 Mutants

Donated on 2/8/2010

The goal is to model mutant p53 transcriptional activity (active vs inactive) based on data extracted from biophysical simulations.

Dataset Characteristics


Subject Area

Life Science

Associated Tasks


Feature Type


# Instances


# Features


Dataset Information

Additional Information

Biophysical models of mutant p53 proteins yield features which can be used to predict p53 transcriptional activity. All class labels are determined via in vivo assays. K8.data - full dataset, 'K8' The following files are provided in order to reconstruct this historical subsets of this data set: K8.instance.tags - provides the precise p53 mutant tag for each instance in the K8.data, for use with the historical definition files: K1.def - defines instances in the 'K1' set. K2.def - defines instances in the 'K2' set. K3.def - defines instances in the 'K3' set. K4.def - defines instances in the 'K4' set. K5.def - defines instances in the 'K5' set. K6.def - defines instances in the 'K6' set. K7.def - defines instances in the 'K7' set. K8.def - defines instances in the 'K8' (full) set.

Has Missing Values?


Introductory Paper

Predicting Positive p53 Cancer Rescue Regions Using Most Informative Positive (MIP) Active Learning

By Samuel A. Danziger, Roberta Baronio, L. Ho, Linda Hall, K. Salmon, G. W. Hatfield, P. Kaiser, R. Lathrop. 2009

Published in PLoS Comput. Biol.

Variable Information

There are a total of 5409 attributes per instance. Attributes 1-4826 represent 2D electrostatic and surface based features. Attributes 4827-5408 represent 3D distance based features. Attribute 5409 is the class attribute, which is either active or inactive. The class labels are to be interpreted as follows: 'active' represents transcriptonally competent, active p53 whereas the 'inactive' label represents cancerous, inactive p53. Class labels are determined experimentally. More information is provided in the relevant papers cited.

1 citations


Richard Lathrop


By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy