Functional genomic hypothesis generation and experimentation by a robot scientist

By Ross D. King, Ken E. Whelan, F. Jones, Philip G. K. Reiser, C. Bryant, Stephen H. Muggleton, Douglas B. Kell, S. Oliver. Nature, 2004

723 citations recorded by the source corpus.

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. Here we apply the 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.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/98e65b3454813a7d8bcf20b5b2539ff2c4112bd8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Active Learning Literature Survey (2009, methodology): “However, King et al. (2004) describe an innovative and promising real-world application of the membership query scenario.”
Metabolomics by numbers: acquiring and understanding global metabolite data. (2004, methodology): “an algorithm chooses which experiments to do is known as ‘active learning’ [ 87 ] and is the strategy of choice.”
From Theories to Queries (2011, methodology): “King et al. (2004) use a similar decision-theoretic approach to reduce real labeling costs.”
Automated refinement and inference of analytical models for metabolic networks (2011, background): “The ‘robot scientist’ project [14–17] is developing systems that can (1) assemble the background knowledge into a model in the form of a logical graph, (2) use that knowledge to design the best experiment to identify the location of a genetic perturbation on that graph, (3) perform and analyze…”
Big Data consumer analytics and the transformation of marketing (2016, neutral): “Although most research involves some aspects of both inductive and deductive techniques, deductive techniques have been widely used as a method of scienti ﬁ c inquiry (King et al., 2004; Lawson, 2005).”
Probabilistic machine learning and artificial intelligence (2015, methodology): “Important earlier work includes statistical expert systems 84,85 and the Robot Scientist, which integrates machine learning and scientific discovery in a closed loop with an experimental platform in microbiology to automate the design and execution of new experiments 86 .”
The Coming of Age of Artificial Intelligence in Medicine (2008, background): “Moreover, AI is boosting discovery in genetics and molecular medicine, by providing machine learning algorithms, knowledge representation formalisms, biomedical ontologies, and natural language processing tools [16,17].”
A Survey of Deep Active Learning (2020, background): “oracle (e.g., human annotator) for labeling, so as to reduce the cost of labeling as much as possible while still maintaining performance. AL approaches can be divided into membership query synthesis [8, 82], stream-based selective sampling [29, 85] and pool-based [95] AL from application scenarios ”