• Publications
  • Influence
Knowledge Discovery in Multi-label Phenotype Data
We present work using KDD to analyse data from mutant phenotype growth experiments with the yeast S. cerevisiae to predict novel gene functions. Expand
  • 630
  • 40
  • PDF
Theories for Mutagenicity: A Study in First-Order and Feature-Based Induction
Inductive logic programming is used to test a conjecture that in domains for which data are most naturally represented by graphs, theories constructed with inductive logic programming (ILP) will significantly outperform those using simpler feature-based methods. Expand
  • 374
  • 31
Functional genomic hypothesis generation and experimentation by a robot scientist
The question of whether it is possible to automate the scientific process is of both great theoretical interest and increasing practical importance because, in many scientific areas, data are beingExpand
  • 517
  • 22
  • PDF
Statistical Evaluation of the Predictive Toxicology Challenge 2000-2001
We developed a statistical method to test if a model performs significantly better than random in ROC space, if the missing fragment is relevant for a toxic mechanism. Expand
  • 115
  • 19
  • PDF
The Predictive Toxicology Challenge 2000-2001
We initiated the Predictive Toxicology Challenge (PTC) to stimulate the development of advanced SAR techniques for predictive toxicology models based on the experimental results of the NTP. Expand
  • 169
  • 16
  • PDF
Hierarchical metabolomics demonstrates substantial compositional similarity between genetically modified and conventional potato crops.
There is current debate whether genetically modified (GM) plants might contain unexpected, potentially undesirable changes in overall metabolite composition. However, appropriate analyticalExpand
  • 348
  • 14
  • PDF
The Automation of Science
The basis of science is the hypothetico-deductive method and the recording of experiments in sufficient detail to enable reproducibility. We report the development of Robot Scientist “Adam,” whichExpand
  • 415
  • 12
  • PDF
STALOG: Comparison of classification algorithms on large real-world problems
Comparative Testing of Statistical and Logical Learning Algorithms on Large-Scale Applications to Classiication, Prediction and Control. Expand
  • 194
  • 12
Predicting gene function in Saccharomyces cerevisiae
MOTIVATION S.cerevisiae is one of the most important model organisms, and has has been the focus of over a century of study. Expand
  • 141
  • 11
  • PDF
An ontology of scientific experiments
  • L. Soldatova, R. King
  • Computer Science, Medicine
  • Journal of The Royal Society Interface
  • 22 December 2006
The formal description of experiments for efficient analysis, annotation and sharing of results is a fundamental part of the practice of science. Expand
  • 193
  • 11