@inproceedings{conf/fuzzIEEE/Pal07, title = {A Fuzzy Rule Based approach to Identify Biomarkers for Diagnostic Classification of Cancers.}, author = {Nikhil R. Pal}, booktitle = {FUZZ-IEEE}, crossref = {conf/fuzzIEEE/2007}, pages = {1-6}, publisher = {IEEE}, url = {http://dblp.uni-trier.de/db/conf/fuzzIEEE/fuzzIEEE2007.html#Pal07}, year = {2007}, biburl = {http://www.bibsonomy.org/bibtex/2930031848ee7920c073e219518877c15/dblp}, description = {dblp}, ee = {http://dx.doi.org/10.1109/FUZZY.2007.4295533}, date = {2008-07-04}, keywords = {dblp } } @article{wei89, title = {Untitled}, annote = {self trapped states en el gap}, author = {X. Wei and C. Chen and Z. V. Vardeny and C. Taliani and R. Zamboni and A. J. Pal and G. Ruani}, journal = {Phys. C}, pages = {1109}, volume = {162-164}, year = {1989}, biburl = {http://www.bibsonomy.org/bibtex/2f9a3c59b54072636000462be0b64dfe4/jgl}, posted-at = {2008-04-22 13:44:44}, priority = {2}, citeulike-article-id = {2701871}, comment = {self trapped states en el gap}, keywords = {experiment, high-tc, htsce } } @incollection{tal90, title = {Untitled}, address = {Berlin}, annote = {Low Energy Optical Excitations in the High Tc Superconducting systems from photomodulation spectroscopy estados en el gap, relajacion de la red}, author = {C. Taliani and A. J. Pal and G. Ruani and R. Zamboni and X. Wei and Z. V. Vardeny}, booktitle = {Electronic properties of High Tc Superconductors and Related Compounds, {bf Vol. 99 of } Springer Series of Solid State Sciences}, editor = {H. Kuzmany and M. Mehring and J. Fink}, publisher = {Springer-Verlag}, year = {1990}, biburl = {http://www.bibsonomy.org/bibtex/2daf93c71602233032b1c669863b7d35f/jgl}, posted-at = {2008-04-22 13:44:44}, citeulike-article-id = {2701872}, priority = {2}, comment = {Low Energy Optical Excitations in the High Tc Superconducting systems from photomodulation spectroscopy estados en el gap, relajacion de la red}, keywords = {experiment, high-tc, htsce } } @incollection{Saetrom:2006:GPTP, title = {Boosting improves stability and accuracy of genetic programming in biological classification}, address = {Ann Arbor}, author = {Pal Saetrom and Olaf Rene Birkeland and Ola {Snove Jr.}}, booktitle = {Genetic Programming Theory and Practice {IV}}, chapter = {18}, editor = {Rick L. Riolo and Terence Soule and Bill Worzel}, month = {11-13 May}, pages = {-}, publisher = {Springer}, series = {Genetic and Evolutionary Computation}, volume = {5}, year = {2006}, biburl = {http://www.bibsonomy.org/bibtex/2491a43838cb4a9eee10fc5a5d9a02b39/brazovayeye}, abstract = {Biological sequence analysis presents interesting challenges for machine learning. Using one of the most important current problems -- the recognition of functional target sites for microRNA molecules -- as an example, we show how joining multiple genetic programming classifiers improves accuracy and stability tremendously. When moving from single classifiers to bagging and boosting with cross validation and parameter optimisation, you require more computing power. We use a special-purpose search processor for fitness evaluation, which renders boosted genetic programming practical for our purposes.}, size = {16 pages}, isbn = {0-387-33375-4}, notes = {part of \cite{Riolo:2006:GPTP} Published Jan 2007 after the workshop}, keywords = {Bioinformatics, RNAi algorithms, gene genetic microRNA, prediction, programming, } } @article{oai:pubmedcentral.gov:1143698, title = {Predicting non-coding {RNA} genes in Escherichia coli with boosted genetic programming}, author = {Pal Saetrom and Ragnhild Sneve and Knut I. Kristiansen and Ola Snove and Thomas Grunfeld and Torbjorn Rognes and Erling Seeberg}, journal = {Nucleic Acids Research}, month = {June~08}, number = {10}, pages = {3263--3270}, url = {http://www.pubmedcentral.gov/picrender.fcgi?artid=1143698&blobtype=pdf}, volume = {33}, year = {2005}, biburl = {http://www.bibsonomy.org/bibtex/281efdcdc6c153fbcbaee01be899cd288/brazovayeye}, abstract = {Several methods exist for predicting non-coding RNA (ncRNA) genes in Escherichia coli (E.coli). In addition to about sixty known ncRNA genes excluding tRNAs and rRNAs, various methods have predicted more than thousand ncRNA genes, but only 95 of these candidates were confirmed by more than one study. Here, we introduce a new method that uses automatic discovery of sequence patterns to predict ncRNA genes. The method predicts 135 novel candidates. In addition, the method predicts 152 genes that overlap with predictions in the literature. We test sixteen predictions experimentally, and show that twelve of these are actual ncRNA transcripts. Six of the twelve verified candidates were novel predictions. The relatively high confirmation rate indicates that many of the untested novel predictions are also ncRNAs, and we therefore speculate that E.coli contains more ncRNA genes than previously estimated.}, bibsource = {OAI-PMH server at www.pubmedcentral.gov}, rights = {{\copyright} The Author 2005. Published by Oxford University Press. All rights reserved}, size = {8 pages}, oai = {oai:pubmedcentral.gov:1143698}, language = {en}, notes = {Included in \cite{drphil-satrom-05} Interagon AS, Medisinsk teknisk senter, NO-7489 Trondheim, Norway and 1Centre for Molecular Biology and Neuroscience, Institute of Medical Microbiology, Rikshospitalet University Hospital, NO-0027 Oslo, Norway}, doi = {doi:10.1093/nar/gki644}, keywords = {algorithms, genetic programming } } @phdthesis{drphil-satrom-05, title = {Hardware accelerated genetic programming for pattern mining in strings}, address = {Norway}, author = {Pal Saetrom}, school = {Faculty of Information Technology, Mathematics and Electrical Engineering Department of Computer and Information Science, Norwegian University of Science and Technology, NTNU}, type = {Dr.philos thesis}, url = {http://www.idi.ntnu.no/grupper/su/publ/phd/drphil-satrom-05.pdf}, year = {2005?}, biburl = {http://www.bibsonomy.org/bibtex/219f5a5febd5ed6fdc9a00d3e0be14e9e/brazovayeye}, abstract = {This thesis considers the problem of mining patterns in strings. Informally, this is the problem of extracting information (patterns) that characterises parts of, or even the complete, string. The thesis describes a high performance hardware for string searching, which together with genetic programming, forms the basis for the thesis' pattern mining algorithms. This work considers two different pattern mining problems and develops several different algorithms to solve different variants of these problems. Common to all algorithms is that they use genetic programming to evolve patterns that can be evaluated by the special purpose search hardware. The first pattern mining problem considered is unsupervised mining of prediction rules in discretised time series. Such prediction rules describe relations between consecutive patterns in the discretized time series; that is, the prediction rules state that if the first pattern occurs, the second pattern will, with high probability, follow within a fixed number of symbols. The goal is to automatically extract prediction rules that are accurate, comprehensible, and interesting. The second pattern mining problem considered is supervised learning of classifiers that predict whether or not a given string belongs to a specific class of strings. This binary classification problem is very general, but this thesis focuses on two recent problems from molecular biology: i) predicting the efficacy of short interfering RNAs and antisense oligonucleotides; and ii) predicting whether or not a given DNA sequence is a non-coding RNA gene. The thesis describes a genetic programming-based mining algorithm that produce state-of-the-art classifiers on both problems.}, notes = {cf http://www.diva-portal.org/ntnu/theses/abstract.xsql?dbid=713}, size = {162 pages}, keywords = {algorithms, genetic programming } } @article{Saetrom:2004:BI, title = {Predicting the efficacy of short oligonucleotides in antisense and {RNA}i experiments with boosted genetic programming}, author = {Pal Saetrom}, journal = {Bioinformatics}, month = {November 22}, number = {17}, pages = {3055--3063}, volume = {20}, year = {2004}, biburl = {http://www.bibsonomy.org/bibtex/2f59bbffa7a2e089e946604f6d98d46e6/brazovayeye}, abstract = {Motivation: Both small interfering RNAs (siRNAs) and antisense oligonucleotides can selectively block gene expression. Although the two methods rely on different cellular mechanisms, these methods share the common property that not all oligonucleotides (oligos) are equally effective. That is, if mRNA target sites are picked at random, many of the antisense or siRNA oligos will not be effective. Algorithms that can reliably predict the efficacy of candidate oligos can greatly reduce the cost of knockdown experiments, but previous attempts to predict the efficacy of antisense oligos have had limited success. Machine learning has not previously been used to predict siRNA efficacy. Results: We develop a genetic programming based prediction system that shows promising results on both antisense and siRNA efficacy prediction. We train and evaluate our system on a previously published database of antisense efficacies and our own database of siRNA efficacies collected from the literature. The best models gave an overall correlation between predicted and observed efficacy of 0.46 on both antisense and siRNA data. As a comparison, the best correlations of support vector machine classifiers trained on the same data were 0.40 and 0.30, respectively. Availability: The prediction system uses proprietary hardware and is available for both commercial and strategic academic collaborations. The siRNA database is available upon request.}, doi = {doi:doi:10.1093/bioinformatics/bth364}, keywords = {algorithms, genetic programming } } @article{Saetrom:2004:BBRC, title = {A comparison of si{RNA} efficacy predictors}, author = {Pal Saetrom and Ola {Snove, Jr.}}, journal = {Biochemical and Biophysical Research Communications}, month = {13 August}, number = {1}, pages = {247--253}, url = {http://www.sciencedirect.com/science/article/B6WBK-4CW546Y-S/2/1c4d9091ea50571084790a39c8ff0b81}, volume = {321}, year = {2004}, biburl = {http://www.bibsonomy.org/bibtex/2a96e519ae8458c8d37b95800816f005c/brazovayeye}, abstract = {Short interfering RNA (siRNA) efficacy prediction algorithms aim to increase the probability of selecting target sites that are applicable for gene silencing by RNA interference. Many algorithms have been published recently, and they base their predictions on such different features as duplex stability, sequence characteristics, mRNA secondary structure, and target site uniqueness. We compare the performance of the algorithms on a collection of publicly available siRNAs. First, we show that our regularised genetic programming algorithm GPboost appears to have a higher and more stable performance than other algorithms on the collected datasets. Second, several algorithms gave close to random classification on unseen data, and only GPboost and three other algorithms have a reasonably high and stable performance on all parts of the dataset. Third, the results indicate that the siRNAs' sequence is sufficient input to siRNA efficacy algorithms, and that other features that have been suggested to be important may be indirectly captured by the sequence.}, owner = {wlangdon}, notes = {PMID: 15358242}, doi = {doi:10.1016/j.bbrc.2004.06.116}, keywords = {algorithms, genetic programming } } @inproceedings{Muni:2006:ICARCV, title = {Texture Generation for Fashion Design Using Genetic Programming}, address = {Singapore}, author = {D. P. Muni and N. R. Pal and J. Das}, booktitle = {9th International Conference on Control, Automation, Robotics and Vision, ICARCV '06}, month = {5-8 December}, pages = {1--5}, publisher = {IEEE}, year = {2006}, biburl = {http://www.bibsonomy.org/bibtex/21817aa4448782bc5ec4a6c43c1827bae/brazovayeye}, abstract = {We present a methodology to generate textures for fashion design using genetic programming (GP). The proposed GP based scheme evolves tree representation of procedures to generate textures. We use Contrast of the generated textures/images to filter out poor textures. After filtering, the fitness value of a new texture is set as the fitness value of a cluster of (already generated) textures which is more similar to this new texture. For this, we execute a clustering step during the evolution. Statistical features are used to find the similarity between textures. Since the quality of a texture is best assessed by a human being, if the generated texture is quite dissimilar to the existing textures then user's discretion is sought to assign a fitness value to it by visual inspection of the texture}, isbn_broken = {1-4214-042-1}, doi_broken = {doi:10.1109/ICARCV.2006.345073}, keywords = {algorithms, genetic programming } } @article{MPD06, title = {Genetic programming for simultaneous feature selection and classifier design}, author = {Durga Prasad Muni and Nikhil R. Pal and Jyotirmoy Das}, journal = {IEEE Transactions on Systems, Man and Cybernetics, Part B}, month = {February}, number = {1}, pages = {106--117}, volume = {36}, year = {2006}, biburl = {http://www.bibsonomy.org/bibtex/2a30ea546032308429d3ff3ef5a848e44/brazovayeye}, abstract = {This paper presents an online feature selection algorithm using genetic programming (GP). The proposed GP methodology simultaneously selects a good subset of features and constructs a classifier using the selected features. For a c-class problem, it provides a classifier having c trees. In this context, we introduce two new crossover operations to suit the feature selection process. As a byproduct, our algorithm produces a feature ranking scheme. We tested our method on several data sets having dimensions varying from 4 to 7129. We compared the performance of our method with results available in the literature and found that the proposed method produces consistently good results. To demonstrate the robustness of the scheme, we studied its effectiveness on data sets with known (synthetically added) redundant/bad features.}, issn = {1083-4419}, size = {12 pages}, notes = {INSPEC Accession Number:8736962 PMID: 16468570 Electron. & Commun. Sci. Unit, Indian Stat. Inst., Calcutta, India also known as \cite{bb38981}}, doi = {doi:10.1109/TSMCB.2005.854499}, keywords = {(artificial Classification, algorithm, algorithms, c-class classification, classifier classifier, design evolutionary extraction, feature genetic intelligence), learning online pattern problem, programming, ranking scheme, selection } }