| Chan, P. (1991). Machine Learning in Molecular Biology Sequence Analysis. (Technical Report CUCS-041-91), New York, NY: Department of Computer Science, Columbia University. |
....sequences in symbolic form. Each strand consists of a sequence of nucleotides, which can be one of four types: adenine, cytosine, guanine and thymine. This technique could offer a way of extracting some of the structure from DNA sequences to offer a higher level view of the patterns of nucleotides [2]. 6 Conclusion Data compression takes advantage of regularities in a symbol sequence to reduce its size. Researchers in machine learning and artificial intelligence are also interested in identifying the structure of sequences. The technique for inferring hierarchical grammars serves both ....
Chan, P.K. "Machine Learning in Molecular Biology Sequence Analysis," CUCS-011-91, Department of Computer Science, Columbia University.
....learning algorithm that is based on computing conditional probabilities as described in (Clark Niblett, 1989) The last two algorithms were reimplemented in C . 4. 2 Learning Tasks Various machine learning techniques have been applied to different molecular biology sequence analysis tasks (Chan, 1991; Craven Shavlik, 1994) For our study, we chose three sequence analysis tasks obtained from the Machine Learning Database Repository at University of California, Irvine (Merz Murphy, 1996) Moreover, we also used an artificial data set that can be generated at random. 4.2.1 Molecular biology ....
Chan, P. (1991). Machine Learning in Molecular Biology Sequence Analysis. (Technical Report CUCS-041-91), New York, NY: Department of Computer Science, Columbia University.
....and translating human expertise. Furthermore, machine learning techniques allow the possibility of discovering patterns and concepts unknown to human experts. It has been reported that in some cases, classification systems generated by learning techniques outperform human designed systems (Chan, 1991; Qian Sejnowski, 1988; Towell et al. 1990; Zhang et al. 1992) The Human Genome Project (DeLisi, 1988) initiated by the National Institutes of Health (NIH) and Department of Energy (DOE) aims to map the entire human genome and will inevitably generate orders of magnitude more sequence data ....
Chan, P. (1991). Machine Learning in Molecular Biology Sequence Analysis. (Technical Report CUCS-041-91), New York, NY: Department of Computer Science, Columbia University.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC