Active learning for sampling in time-series experiments with application to gene expression analysis

ABSTRACT

Many time-series experiments seek to estimate some signal as a continuous function of time. In this paper, we address the sampling problem for such experiments: determining which time-points ought to be sampled in order to minimize the cost of data collection. We restrict our attention to a growing class of experiments which measure multiple signals at each time-point and where raw materials/observations are archived initially, and selectively analyzed later, this analysis being the more expensive step. We present an active learning algorithm for iteratively choosing time-points to sample, using the uncertainty in the quality of the currently estimated time-dependent curve as the objective function. Using simulated data as well as gene expression data, we show that our algorithm performs well, and can significantly reduce experimental cost without loss of information.

REFERENCES

• 1: Baldi, P. & Hatfield, G. (2002). DNA Microarrays and Gene Expression. Cambridge University Press.
• 2: Bar-Joseph, Z. et al.(2003). Continuous representations of time series gene expression data J of Comp Bio, 3--4, 341--356.
• 3: Bay, S. D. et al. (2003). Temporal aggregation bias and inference of causal regulatory networks Proc. of the IJCAI Workshop on Learning Graphical Models for Comp. Genomics.
• 4: Darya Chudova , Scott Gaffney , Eric Mjolsness , Padhraic Smyth, Translation-invariant mixture models for curve clustering, Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, August 24-27, 2003, Washington, D.C. [doi>10.1145/956750.956763]
• 5: Cummins, D., Filloon, T. & Nychka, D. (2001). Confidence intervals for nonparametric curve estimates. J Am Stat Assoc, 96:453, 233--246.
• 6: DeBoor C. et al. (2001) A Practical Guide to Splines.
• 7: Deshpande, A. et al. (2004). Model Driven Data Acquisition in Sensor Networks. Proceedings of VLDB 2004.
• 8: James, G., & Hastie, T. (2001). Functional linear discriminant analysis for irregularly sampled curves. Journal of the Royal Statistical Society, to appear.
• 9: Lizotte, D., Madani, O., & Greiner, R. (2003). Budgeted Learning of Naive-Bayes Classifiers. Proc. of UAI 2003.
• 10: Sophocles J. Orfanidis, Introduction to signal processing, Prentice-Hall, Inc., Upper Saddle River, NJ, 1995
• 11: Qian, J. et al. (2001). Beyond synexpression relationships: local clustering of time-shifted and inverted gene expression profiles identifies new, biologically relevant interactions. J Mol Biol, 314(5), 1053--66.
• 12: Spellman, P. T. et al. (1998). Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization. Mol. Biol. of the Cell, 9, 3273--3297.
• 13: Simon Tong , Daphne Koller, Active learning: theory and applications, 2001
• 14: Wahba, G. (1983). Bayesian confidence intervals for the cross-validated smoothing spline. J Royal Stat Soc, Ser B, 45, 133--150.
• 15: Sofia Wichert , Konstantinos Fokianos , Korbinian Strimmer, Identifying periodically expressed transcripts in microarray time series data, Bioinformatics, v.20 n.1, p.5-20, January 2004 [doi>10.1093/bioinformatics/btg364]
• 16: Zhu, X., Lafferty, J., & Ghahramani, Z. (2003). Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions. ICML 2003 Workshop on the Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining.