Artificial neural network classification of Drosophila courtship song mutants

Courtship songs produced by Drosophila males — wild-type, plus the cacophony and dissonance behavioral mutants — were examined with the aid of newly developed strategies for adaptive acoustic analysis and classification. This system used several techniques involving artificial neural networks (a.k.a. parallel distributed processing), including learned vector quantization of signals and non-linear adaption (back-propagation) of data analysis. “Pulse” song from several individual wild-type and mutant males were first vector-quantized according to their frequency spectra. The accumulated quantized data of this kind, for a given song, were then used to “teach” or adapt a multiple-layered feedforward artificial neural network, which classified that song according to its original genotype. Results are presented on the performance of the final adapted system when faced with novel test data and on acoustic features the system decides upon for predicting the song-mutant genotype in question. The potential applications and extensions of this new system are discussed, including how it could be used to screen for courtship mutants, search novel behavior patterns or cause-and-effect relationships associated with reproduction, compress these kinds of data for digital storage, and analyze Drosophila behavior beyond the case of courtship song.

[1]  PAUL J. WERBOS,et al.  Generalization of backpropagation with application to a recurrent gas market model , 1988, Neural Networks.

[2]  J. Makhoul,et al.  Vector quantization in speech coding , 1985, Proceedings of the IEEE.

[3]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[4]  R. W. Siegel,et al.  Genetic elements of courtship inDrosophila: Mosaics and learning mutants , 1984, Behavior genetics.

[5]  Teuvo Kohonen,et al.  Statistical pattern recognition with neural networks , 1988, Neural Networks.

[6]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[7]  T. Markow,et al.  Behavioral and sensory basis of courtship success in Drosophila melanogaster. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[8]  H. Bennet-Clark,et al.  THE COURTSHIP SONGS OF DROSOPHILA , 1968 .

[9]  A. W. Smith,et al.  Encoding sequential structure: experience with the real-time recurrent learning algorithm , 1989, International 1989 Joint Conference on Neural Networks.

[10]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[11]  H. T. Spieth Courtship behavior in Drosophila. , 1974, Annual review of entomology.

[12]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[13]  I. Jolliffe Principal Component Analysis , 2002 .

[14]  J. C. Hall,et al.  Spectral analysis of courtship songs in behavioral mutants ofDrosophila melanogaster , 1989, Behavior genetics.

[15]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[16]  Terrence J. Sejnowski,et al.  Parallel Networks that Learn to Pronounce English Text , 1987, Complex Syst..

[17]  Jeffrey C. Hall,et al.  Drosophila courtship song cycles in normal andperiod mutant males revisited , 1990, Behavior genetics.

[18]  R. Cook The extent of visual control in the courtship tracking of D. melanogaster , 1980, Biological Cybernetics.

[19]  Abhijit S. Pandya,et al.  Dynamic pattern recognition of coordinated biological motion , 1990, Neural Networks.

[20]  J. C. Hall,et al.  Chemosensory elements of courtship in normal and mutant, olfaction-deficientDrosophila melanogaster , 1986, Behavior genetics.

[21]  W. Krzanowski Between-Groups Comparison of Principal Components , 1979 .

[22]  F. Schilcher A mutation which changes courtship song inDrosophila melanogaster , 1977 .

[23]  David G. Bounds,et al.  A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders , 1990, Neural Networks.

[24]  B. Burnet,et al.  Courtship songs and genetic control of their acoustic characteristics in sibling species of the Drosophila melanogaster subgroup , 1981, Animal Behaviour.

[25]  J. C. Hall,et al.  Behavioral and cytogenetic analysis of the cacophony courtship song mutant and interacting genetic variants in Drosophila melanogaster. , 1987, Genetics.

[26]  J. C. Hall Control of male reproductive behavior by the central nervous system of Drosophila: dissection of a courtship pathway by genetic mosaics. , 1979, Genetics.

[27]  Spectral analysis ofDrosophila courtship songs:D. melanogaster, D. simulans, and their interspecific hybrid , 1988, Behavior genetics.

[28]  S. Knudsen,et al.  Cleaning up gene databases , 1990, Nature.

[29]  G. Rubin,et al.  Molecular analysis of no-on-transient A, a gene required for normal vision in drosophila , 1990, Neuron.

[30]  Murali M. Menon,et al.  Classification of patterns using a self-organizing neural network , 1988, Neural Networks.

[31]  Terrence J. Sejnowski,et al.  Analysis of hidden units in a layered network trained to classify sonar targets , 1988, Neural Networks.

[32]  Jeffrey C. Hall,et al.  The function of courtship song rhythms in Drosophila , 1982, Animal Behaviour.

[33]  B. Skinner The Measurement of “Spontaneous Activity” , 1933 .

[34]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[35]  Jeffrey C. Hall,et al.  Neural topography of courtship song in sex mosaics ofDrosophila melanogaster , 1979, Journal of comparative physiology.

[36]  B. Logan Information in the zero crossings of bandpass signals , 1977, The Bell System Technical Journal.

[37]  R. Cook The courtship tracking of Drosophila melanogaster , 1979, Biological Cybernetics.

[38]  Jainendra K. Navlakha,et al.  On Hopfield neural networks , 1988, Neural Networks.

[39]  J. C. Hall,et al.  Germ-line transformation involving DNA from the period locus in Drosophila melanogaster: overlapping genomic fragments that restore circadian and ultradian rhythmicity to per0 and per- mutants. , 1986, Journal of neurogenetics.

[40]  F. Schilcher The function of pulse song and sine song in the courtship of Drosophila melanogaster , 1976, Animal Behaviour.

[41]  Wojtek J. Krzanowski,et al.  Between-group comparison of principal components — some sampling results , 1982 .

[42]  Jeffrey C. Hall,et al.  Learning and memory mutations impair acoustic priming of mating behaviour in Drosophila , 1984, Nature.

[43]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[44]  R. Greenspan,et al.  Acetylcholinesterase mutants in drosophila and their effects on the structure and function of the cental nervous system , 1980, The Journal of comparative neurology.

[45]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[46]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[47]  Mitsuo Kawato,et al.  Feedback-error-learning neural network for trajectory control of a robotic manipulator , 1988, Neural Networks.

[48]  C. Chatfield,et al.  Analysing sequences of behavioural events. , 1970, Journal of theoretical biology.

[49]  F. Schilcher,et al.  The role of auditory stimuli in the courtship of Drosophila melanogaster , 1976, Animal Behaviour.

[50]  Harold B. Dowse,et al.  The search for hidden periodicities in biological time series revisited , 1989 .

[51]  S. Knudsen,et al.  Neural network detects errors in the assignment of mRNA splice sites. , 1990, Nucleic acids research.

[52]  S. Hanson,et al.  Multivariate analysis of Drosophila courtship. , 1981, Proceedings of the National Academy of Sciences of the United States of America.

[53]  F. von Schilcher A mutation which changes courtship song in Drosophila melanogaster. , 1977, Behavior genetics.

[54]  Jeffrey C. Hall Learning and rhythms in courting, mutant Drosophila , 1986, Trends in Neurosciences.

[55]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[56]  R. Hoy,et al.  Hawaiian courtship songs: evolutionary innovation in communication signals of Drosophila. , 1988, Science.

[57]  David Lowe,et al.  The optimised internal representation of multilayer classifier networks performs nonlinear discriminant analysis , 1990, Neural Networks.

[58]  A. Ewing FUNCTIONAL ASPECTS OF DROSOPHILA COURTSHIP , 1983 .

[59]  J. C. Hall,et al.  Behavior and cytogenetics of fruitless in Drosophila melanogaster: different courtship defects caused by separate, closely linked lesions. , 1989, Genetics.

[60]  J. C. Hall,et al.  The dissonance mutant of courtship song in Drosophila melanogaster: isolation, behavior and cytogenetics. , 1988, Genetics.

[61]  Jeffrey C. Hall,et al.  Temporal analysis of tone pulses within the courtship songs of two siblingDrosophila species, their interspecific hybrid, and behavioral mutants ofD. melanogaster (Diptera: Drosophilidae) , 2005, Journal of Insect Behavior.

[62]  C P Kyriacou,et al.  Circadian rhythm mutations in Drosophila melanogaster affect short-term fluctuations in the male's courtship song. , 1980, Proceedings of the National Academy of Sciences of the United States of America.

[63]  John A. Stankovic,et al.  Distributed Processing , 1978, Computer.

[64]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[65]  L. Tompkins Genetic analysis of sex appeal inDrosophila , 1984, Behavior genetics.

[66]  David Rogers Weather prediction using a genetic memory , 1990 .

[67]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[68]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[69]  M A Geyer,et al.  Application of entropy measures derived from the ergodic theory of dynamical systems to rat locomotor behavior. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[70]  Takayuki Ito,et al.  Neocognitron: A neural network model for a mechanism of visual pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[71]  Bishnu S. Atal,et al.  Predictive Coding of Speech at Low Bit Rates , 1982, IEEE Trans. Commun..