Susan M. Bridges

Mining fuzzy association rules and fuzzy frequency episodes for intrusion detection

Lee, Stolfo, and Mok 1 previously reported the use of association rules and frequency episodes for mining audit data to gain knowledge for intrusion detection. The integration of association rules and frequency episodes with fuzzy logic can produce more abstract and flexible patterns for intrusion detection, since many quantitative features are involved in intrusion detection and security itself is fuzzy. We present a modification of a previously reported algorithm for mining fuzzy association rules, define the concept of fuzzy frequency episodes, and present an original algorithm for mining fuzzy frequency episodes. We add a normalization step to the procedure for mining fuzzy association rules in order to prevent one data instance from contributing more than others. We also modify the procedure for mining frequency episodes to learn fuzzy frequency episodes. Experimental results show the utility of fuzzy association rules and fuzzy frequency episodes for intrusion detection. © 2000 John Wiley & Sons, Inc.

Empirical comparison of ab initio repeat finding programs

Identification of dispersed repetitive elements can be difficult, especially when elements share little or no homology with previously described repeats. Consequently, a growing number of computational tools have been designed to identify repetitive elements in an ab initio manner, i.e. without using prior sequence data. Here we present the results of side-by-side evaluations of six of the most widely used ab initio repeat finding programs. Using sequence from rice chromosome 12, tools were compared with regard to time requirements, ability to find known repeats, utility in identifying potential novel repeats, number and types of repeat elements recognized and compactness of family descriptions. The study reveals profound differences in the utility of the tools with some identifying virtually their entire substrate as repetitive, others making reasonable estimates of repetition, and some missing almost all repeats. Of note, even when tools recognized similar numbers of repeats they often showed marked differences in the nature and number of repeat families identified. Within the context of this comparative study, ReAS and RepeatScout showed the most promise in analysis of sequence reads and assembled genomic regions, respectively. Our results should help biologists identify the program(s), if any, that is best suited for their needs.

Fuzzy cognitive maps for decision support in an intelligent intrusion detection system

The health of a computer network needs to be assessed and protected in much the same manner as the health of a person. The task of an intrusion detection system is to protect a computer system by detecting and diagnosing attempted breaches of the integrity of the system. A robust intrusion detection system for a computer network will necessarily use multiple sensors, each providing different types of information about some aspect of the monitored system. In addition, the sensor data will often be analyzed in several different ways. We describe a decision engine for an intelligent intrusion detection system that fuses information from different intrusion detection modules using a causal knowledge based inference technique. Fuzzy cognitive maps (FCMs) and fuzzy rule-bases are used for the causal knowledge acquisition and to support the causal knowledge reasoning process.

AgBase: a unified resource for functional analysis in agriculture

Analysis of functional genomics (transcriptomics and proteomics) datasets is hindered in agricultural species because agricultural genome sequences have relatively poor structural and functional annotation. To facilitate systems biology in these species we have established the curated, web-accessible, public resource ‘AgBase’ (). We have improved the structural annotation of agriculturally important genomes by experimentally confirming the in vivo expression of electronically predicted proteins and by proteogenomic mapping. Proteogenomic data are available from the AgBase proteogenomics link. We contribute Gene Ontology (GO) annotations and we provide a two tier system of GO annotations for users. The ‘GO Consortium’ gene association file contains the most rigorous GO annotations based solely on experimental data. The ‘Community’ gene association file contains GO annotations based on expert community knowledge (annotations based directly from author statements and submitted annotations from the community) and annotations for predicted proteins. We have developed two tools for proteomics analysis and these are freely available on request. A suite of tools for analyzing functional genomics datasets using the GO is available online at the AgBase site. We encourage and publicly acknowledge GO annotations from researchers and provide an online mechanism for agricultural researchers to submit requests for GO annotations.

Isolation and characterization of an iron-containing superoxide dismutase from a eucaryote, Brassica campestris

Abstract A cyanide-insensitive superoxide dismutase was purified from mustard leaves, Brassica campestris . The protein had a molecular weight of 41,000 and was composed of two equally sized subunits. Metal analysis revealed that the enzyme contained 1.6 g atoms of iron per dimer. The isolation of an iron-containing superoxide dismutase from mustard leaves represents the first report of this enzyme in a multicellular eucaryotic organism.

Prediction of peptides observable by mass spectrometry applied at the experimental set level

BackgroundWhen proteins are subjected to proteolytic digestion and analyzed by mass spectrometry using a method such as 2D LC MS/MS, only a portion of the proteotypic peptides associated with each protein will be observed. The ability to predict which peptides can and cannot potentially be observed for a particular experimental dataset has several important applications in proteomics research including calculation of peptide coverage in terms of potentially detectable peptides, systems biology analysis of data sets, and protein quantification.ResultsWe have developed a methodology for constructing artificial neural networks that can be used to predict which peptides are potentially observable for a given set of experimental, instrumental, and analytical conditions for 2D LC MS/MS (a.k.a Multidimensional Protein Identification Technology [MudPIT]) datasets. Neural network classifiers constructed using this procedure for two MudPIT datasets exhibit 10-fold cross validation accuracy of about 80%. We show that a classifier constructed for one dataset has poor predictive performance with the other dataset, thus demonstrating the need for dataset specific classifiers. Classification results with each dataset are used to compute informative percent amino acid coverage statistics for each protein in terms of the predicted detectable peptides in addition to the percent coverage of the complete sequence. We also demonstrate the utility of predicted peptide observability for systems analysis to help determine if proteins that were expected but not observed generate sufficient peptides for detection.ConclusionClassifiers that accurately predict the likelihood of detecting proteotypic peptides by mass spectrometry provide proteomics researchers with powerful new approaches for data analysis. We demonstrate that the procedure we have developed for building a classifier based on an individual experimental data set results in classifiers with accuracy comparable to those reported in the literature based on large training sets collected from multiple experiments. Our approach allows the researcher to construct a classifier that is specific for the experimental, instrument, and analytical conditions of a single experiment and amenable to local, condition-specific, implementation. The resulting classifiers have application in a number of areas such as determination of peptide coverage for protein identification, pathway analysis, and protein quantification.

Prediction of Cell Penetrating Peptides by Support Vector Machines

Cell penetrating peptides (CPPs) are those peptides that can transverse cell membranes to enter cells. Once inside the cell, different CPPs can localize to different cellular components and perform different roles. Some generate pore-forming complexes resulting in the destruction of cells while others localize to various organelles. Use of machine learning methods to predict potential new CPPs will enable more rapid screening for applications such as drug delivery. We have investigated the influence of the composition of training datasets on the ability to classify peptides as cell penetrating using support vector machines (SVMs). We identified 111 known CPPs and 34 known non-penetrating peptides from the literature and commercial vendors and used several approaches to build training data sets for the classifiers. Features were calculated from the datasets using a set of basic biochemical properties combined with features from the literature determined to be relevant in the prediction of CPPs. Our results using different training datasets confirm the importance of a balanced training set with approximately equal number of positive and negative examples. The SVM based classifiers have greater classification accuracy than previously reported methods for the prediction of CPPs, and because they use primary biochemical properties of the peptides as features, these classifiers provide insight into the properties needed for cell-penetration. To confirm our SVM classifications, a subset of peptides classified as either penetrating or non-penetrating was selected for synthesis and experimental validation. Of the synthesized peptides predicted to be CPPs, 100% of these peptides were shown to be penetrating.

Intrusion sensor data fusion in an intelligent intrusion detection system architecture

Most modern intrusion detection systems employ multiple intrusion sensors to maximize their trustworthiness. The overall security view of the multi-sensor intrusion detection system can serve as an aid to appraise the trustworthiness in the system. This paper presents our research effort in that direction by describing a decision engine for an intelligent intrusion detection system (IIDS) that fuses information from different intrusion detection sensors using an artificial intelligence technique. The decision engine uses fuzzy cognitive maps (FCMs) and fuzzy rule-bases for causal knowledge acquisition and to support the causal knowledge reasoning process. In this paper, we report on the workings of the decision engine that has been successfully embedded into the IIDS architecture being built at the Center for Computer Security Research (CCSR), Mississippi State University.

AgBase: supporting functional modeling in agricultural organisms

AgBase (http://www.agbase.msstate.edu/) provides resources to facilitate modeling of functional genomics data and structural and functional annotation of agriculturally important animal, plant, microbe and parasite genomes. The website is redesigned to improve accessibility and ease of use, including improved search capabilities. Expanded capabilities include new dedicated pages for horse, cat, dog, cotton, rice and soybean. We currently provide 590 240 Gene Ontology (GO) annotations to 105 454 gene products in 64 different species, including GO annotations linked to transcripts represented on agricultural microarrays. For many of these arrays, this provides the only functional annotation available. GO annotations are available for download and we provide comprehensive, species-specific GO annotation files for 18 different organisms. The tools available at AgBase have been expanded and several existing tools improved based upon user feedback. One of seven new tools available at AgBase, GOModeler, supports hypothesis testing from functional genomics data. We host several associated databases and provide genome browsers for three agricultural pathogens. Moreover, we provide comprehensive training resources (including worked examples and tutorials) via links to Educational Resources at the AgBase website.

Polycomb Group Gene OsFIE2 Regulates Rice (Oryza sativa) Seed Development and Grain Filling via a Mechanism Distinct from Arabidopsis

Cereal endosperm represents 60% of the calories consumed by human beings worldwide. In addition, cereals also serve as the primary feedstock for livestock. However, the regulatory mechanism of cereal endosperm and seed development is largely unknown. Polycomb complex has been shown to play a key role in the regulation of endosperm development in Arabidopsis, but its role in cereal endosperm development remains obscure. Additionally, the enzyme activities of the polycomb complexes have not been demonstrated in plants. Here we purified the rice OsFIE2-polycomb complex using tandem affinity purification and demonstrated its specific H3 methyltransferase activity. We found that the OsFIE2 gene product was responsible for H3K27me3 production specifically in vivo. Genetic studies showed that a reduction of OsFIE2 expression led to smaller seeds, partially filled seeds, and partial loss of seed dormancy. Gene expression and proteomics analyses found that the starch synthesis rate limiting step enzyme and multiple storage proteins are down-regulated in OsFIE2 reduction lines. Genome wide ChIP–Seq data analysis shows that H3K27me3 is associated with many genes in the young seeds. The H3K27me3 modification and gene expression in a key helix-loop-helix transcription factor is shown to be regulated by OsFIE2. Our results suggest that OsFIE2-polycomb complex positively regulates rice endosperm development and grain filling via a mechanism highly different from that in Arabidopsis.