The Robot Scientist Project
(invited lecture for DS 2005)

Author: Ross D. King

Affiliation: Department of Computer Science, The University of Wales, Aberystwyth, Penglais, Aberystwyth, Ceredigion, Wales, U.K.

Source: Discovery Science, 8th International Conference, DS 2005, Singapore, October 2005, Proceedings, (Achim Hoffmann, Hiroshi Motada, Tobias Scheffer, Eds.), Lecture Notes in Artificial Intelligence 3735, pp. 16 - 25, Springer 2005.

Abstract. 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 being generated much faster than they can be effectively analysed. We describe a physically implemented robotic system that applies techniques from artificial intelligence to carry out cycles of scientific experimentation. The system automatically originates hypotheses to explain observations, devises experiments to test these hypotheses, physically runs the experiments using a laboratory robot, interprets the results to falsify hypotheses inconsistent with the data, and then repeats the cycle. We applied this system to the determination of gene function using deletion mutants of yeast (Saccharomyces cerevisiae) and auxotrophic growth experiments. We built and tested a detailed logical model (involving genes, proteins and metabolites) of the aromatic amino acid synthesis pathway. In biological experiments that automatically reconstruct parts of this model, we show that an intelligent experiment selection strategy is competitive with human performance and significantly outperforms, with a cost decrease of 3-fold and 100-fold (respectively), both cheapest and random-experiment selection. We have now scaled up this approach to discover novel biology. To achieve this we combined our logical reasoning approach with bioinformatics. We have built a logical model of all known S. cerevisiae metabolism. In this model there are still reactions where the gene encoding the enzyme is unknown.

We demonstrate that we can automatically hypothesize these genes, and generate "wet" biological evidence that either confirms or contradicts this hypothesis. This approach can also be used to automatically test biological genome annotations.

©Copyright 2005 Springer