Choosing where to look next in a mutation sequence space: Active Learning of informative p53 cancer rescue mutants

MOTIVATION Many biomedical projects would benefit from reducing the time and expense of in vitro experimentation by using computer models for in silico predictions. These models may help determine which expensive biological data are most useful to acquire next. Active Learning techniques for choosing the most informative data enable biologists and computer scientists to optimize experimental data choices for rapid discovery of biological function. To explore design choices that affect this desirable behavior, five novel and five existing Active Learning techniques, together with three control methods, were tested on 57 previously unknown p53 cancer rescue mutants for their ability to build classifiers that predict protein function. The best of these techniques, Maximum Curiosity, improved the baseline accuracy of 56-77%. This article shows that Active Learning is a useful tool for biomedical research, and provides a case study of interest to others facing similar discovery challenges.

• Publication year

  2007

• Venue

  ISMB/ECCB

• Publication date

  2007-07-01

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1093/bioinformatics/btm166PMID 17646286PMCID PMC2811495
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• The UMD TP53 database and website: update and revisions

  2006cited by this paper
• A global map of p53 transcription-factor binding sites in the human genome.

  2006cited by this paper
• Mutations in the p 53 Tumor Suppressor Gene : Clues to Cancer Etiology and Molecular

  2006cited by this paper
• Functional census of mutation sequence spaces: the example of p53 cancer rescue mutants

  2006influential reference
• Data mining - practical machine learning tools and techniques, Second Edition

  2005cited by this paper
• Bayesian Surprise Attracts Human Attention

  2005influential reference
• A unified framework for image retrieval using keyword and visual features

  2005cited by this paper
• Binding of Rad51 and Other Peptide Sequences to a Promiscuous, Highly Electrostatic Binding Site in p53*

  2005cited by this paper
• Global Cancer Statistics, 2002

  2005cited by this paper
• Stress-induced p53 runs a transcription-independent death program.

  2005cited by this paper
• Fast Binary Feature Selection with Conditional Mutual Information

  2004cited by this paper
• p53 Mutants: the Achilles’ Heel of Human Cancers?

  2004cited by this paper
• Convergence and application of online active sampling using orthogonal pillar vectors

  2004cited by this paper
• Active Learning with Support Vector Machine Applied to Gene Expression Data for Cancer Classification

  2004cited by this paper
• Cancer genes and the pathways they control

  2004cited by this paper
• Active Sampling for Class Probability Estimation and Ranking

  2004cited by this paper
• Crystal structures of histone Sin mutant nucleosomes reveal altered protein–DNA interactions

  2004cited by this paper
• A global suppressor motif for p53 cancer mutants.

  2004cited by this paper
• The Tumor Suppressor Gene TP53: Implications for Cancer Management and Therapy

  2004cited by this paper
• Transcriptional repression mediated by the p53 tumour suppressor

  2003cited by this paper
• Small molecules that reactivate mutant p53.

  2003cited by this paper
• Genetic strategies in Saccharomyces cerevisiae to study human tumor suppressor genes.

  2003cited by this paper
• Restoring p53-Dependent Tumor Suppression

  2003cited by this paper
• Groups of p53 target genes involved in specific p53 downstream effects cluster into different classes of DNA binding sites

  2002cited by this paper
• The IARC TP53 database: New online mutation analysis and recommendations to users

  2002cited by this paper
• Data Mining: Practical Machine Learning Tools and Techniques - Book Review

  2002cited by this paper
• Assessing TP53 status in human tumours to evaluate clinical outcome

  2001cited by this paper
• Toward Optimal Active Learning through Sampling Estimation of Error Reduction

  2001cited by this paper
• Active Learning for Class Probability Estimation and Ranking

  2001cited by this paper
• Rescuing the function of mutant p53

  2001cited by this paper
• Surfing the p53 network

  2000cited by this paper
• Oncogenic mutations of the p53 tumor suppressor: the demons of the guardian of the genome.

  2000cited by this paper
• p53 from complexity to simplicity: mutant p53 stabilization, gain‐of‐function, and dominant‐negative effect

  2000cited by this paper
• The p53 pathway

  1999cited by this paper
• Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines

  1998cited by this paper
• Genetic selection of intragenic suppressor mutations that reverse the effect of common p53 cancer mutations

  1998cited by this paper
• Active Learning with Statistical Models

  1996cited by this paper
• p53: puzzle and paradigm.

  1996cited by this paper
• Dominant-negative p53 mutations selected in yeast hit cancer hot spots.

  1996cited by this paper
• Crystal structure of a p53 tumor suppressor-DNA complex: understanding tumorigenic mutations.

  1994cited by this paper
• Mutations in the p53 tumor suppressor gene: clues to cancer etiology and molecular pathogenesis.

  1994cited by this paper
• p53 mutations in human cancers.

  1991cited by this paper
• Human tumor suppressor genes.

  1990cited by this paper

• Model-free feature screening for massive high-dimensional imbalanced classification data via a fused inverse probability weighted absolute filter

  2025cites this paper
• Intelligence on the Graph: Graph Neural Networks for Mechanistic Drug Target Discovery

  2025cites this paper
• Alleviating the Cold-Start Problem in Recommender Systems Using Error-Based Learning

  2024cites this paper
• Integrating optimized item selection with active learning for continuous exploration in recommender systems

  2024cites this paper
• NMR Hydrogen Exchange and Relaxation Reveal Positions Stabilized by p53 Rescue Mutants N239Y and N235K

  2021cites this paper
• A Parallel Multilevel Feature Selection algorithm for improved cancer classification

  2020cites this paper
• Fused variable screening for massive imbalanced data

  2020cites this paper
• Performance evaluation and analysis of distributed multi-agent optimization algorithms with sparsified directed communication

  2020cites this paper
• Approximate Cross-Validation with Low-Rank Data in High Dimensions

  2020cites this paper
• Categorical Matrix Completion With Active Learning for High-Throughput Screening

  2020cites this paper
• Roles of computational modelling in understanding p53 structure, biology, and its therapeutic targeting

  2019cites this paper
• Big data scalability based on Spark Machine Learning Libraries

  2019cites this paper
• A comparative analysis to predict p53 activity using classification models

  2019influential citation
• Big data execution time based on Spark Machine Learning Libraries

  2019cites this paper
• Unsupervised dimensionality reduction versus supervised regularization for classification from sparse data

  2019cites this paper
• Addressing the Item Cold-Start Problem by Attribute-Driven Active Learning

  2018cites this paper
• Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection

  2018cites this paper
• Isolation‐based anomaly detection using nearest‐neighbor ensembles

  2018cites this paper
• Active learning framework of informative p53 cancer rescue mutants

  2017cites this paper
• An indicator cell assay for blood-based diagnostics

  2017cites this paper
• Combining Multiple Feature Selection Methods and Deep Learning for High-dimensional Data

  2016cites this paper
• Which to View: Personalized Prioritization for Broadcast Emails

  2016cites this paper
• The Molecular Basis for Restoring Function to Oncogenic p53 Mutants

  2016cites this paper
• Prediction of Rescue Mutants to Restore Functional Activity of Tumor Protein TP53 through Data Mining Techniques

  2015cites this paper
• Deciding when to stop: efficient experimentation to learn to predict drug-target interactions

  2015cites this paper
• Deciding when to stop: Efficient stopping of active learning guided drug-target prediction

  2015cites this paper
• Efficient Anomaly Detection by Isolation Using Nearest Neighbour Ensemble

  2014cites this paper
• Explanation and prediction of nsSNP-induced pathology using association mining, transduction, and active learning

  2013cites this paper
• Structures of oncogenic, suppressor and rescued p53 core-domain variants: mechanisms of mutant p53 rescue.

  2013cites this paper
• Computational identification of a transiently open L1/S3 pocket for reactivation of mutant p53

  2013cites this paper
• Prediction of P53 Mutants (Multiple Sites) Transcriptional Activity Based on Structural (2D&3D) Properties

  2013cites this paper
• Machine Learning Methods for Property Prediction in Chemoinformatics: Quo Vadis?

  2012cites this paper
• Restoring coverage to the Bayesian false discovery rate control procedure

  2012cites this paper
• The Johnson-Lindenstrauss Transform: An Empirical Study

  2011cites this paper
• An artificial experimenter for automated response characterisation

  2011cites this paper
• Diversified ensemble classifiers for highly imbalanced data learning and its application in bioinformatics

  2011cites this paper
• Experiencias de desarrollo en tareas de procesamiento y gestión de datos en bioinformática

  2011cites this paper
• Function prediction for in silico protein mutagenesis using transduction and active learning

  2011cites this paper
• Fast locality-sensitive hashing

  2011influential citation
• Compensated pathogenic deviations

  2011cites this paper
• Predicting Transcriptional Activity of Multiple Site p53 Mutants Based on Hybrid Properties

  2011cites this paper
• Active Learning in Recommender Systems

  2011influential citation
• An active role for machine learning in drug development.

  2011cites this paper
• Learning Active Fusion of Multiple Experts' Decisions: An Attention-Based Approach

  2011cites this paper
• Incremental nonparametric discriminant analysis based active learning and its applications

  2010cites this paper
• Resource-aware annotation through active learning

  2010cites this paper
• An Economic Framework to Prioritize Confirmatory Tests after a High-Throughput Screen

  2010cites this paper
• Guest editorial: Thematic issue on ‘Adaptive Soft Computing Techniques and Applications’

  2009cites this paper
• Predicting Positive p53 Cancer Rescue Regions Using Most Informative Positive (MIP) Active Learning

  2009cites this paper
• Dynamic analysis of synchronous machine using neural network based characterization clustering and pattern recognition

  2009influential citation
• Curiosity driven incremental LDA agent active learning

  2009cites this paper
• Active Mode Incremental Nonparametric Discriminant Analysis Learning

  2009cites this paper
• Convex Optimization for Active Learning with Large Margins

  2009cites this paper