Vaidyanathan K. Jayaraman

CAMP: a useful resource for research on antimicrobial peptides

Antimicrobial peptides (AMPs) are gaining popularity as better substitute to antibiotics. These peptides are shown to be active against several bacteria, fungi, viruses, protozoa and cancerous cells. Understanding the role of primary structure of AMPs in their specificity and activity is essential for their rational design as drugs. Collection of Anti-Microbial Peptides (CAMP) is a free online database that has been developed for advancement of the present understanding on antimicrobial peptides. It is manually curated and currently holds 3782 antimicrobial sequences. These sequences are divided into experimentally validated (patents and non-patents: 2766) and predicted (1016) datasets based on their reference literature. Information like source organism, activity (MIC values), reference literature, target and non-target organisms of AMPs are captured in the database. The experimentally validated dataset has been further used to develop prediction tools for AMPs based on the machine learning algorithms like Random Forests (RF), Support Vector Machines (SVM) and Discriminant Analysis (DA). The prediction models gave accuracies of 93.2% (RF), 91.5% (SVM) and 87.5% (DA) on the test datasets. The prediction and sequence analysis tools, including BLAST, are integrated in the database. CAMP will be a useful database for study of sequence-activity and -specificity relationships in AMPs. CAMP is freely available at http://www.bicnirrh.res.in/antimicrobial.

Knowledge incorporated support vector machines to detect faults in Tennessee Eastman Process

A support vector machine with knowledge incorporation is applied to detect the faults in Tennessee Eastman Process, a benchmark problem in chemical engineering. The knowledge incorporated algorithm takes advantage of the information on horizontal translation invariance in tangent direction of the instances in dataset. This essentially changes the representation of the input data while training the algorithm. These local translations do not alter the class membership of the instances in the dataset. The results on binary as well as multiple fault detection justify the use of knowledge incorporation.

Dynamic optimization of chemical processes using ant colony framework

Ant colony framework is illustrated by considering dynamic optimization of six important bench marking examples. This new computational tool is simple to implement and can tackle problems with state as well as terminal constraints in a straightforward fashion. It requires fewer grid points to reach the global optimum at relatively very low computational effort. The examples with varying degree of complexities, analyzed here, illustrate its potential for solving a large class of process optimization problems in chemical engineering.

Support vector classification with parameter tuning assisted by agent-based technique

This paper describes a robust support vector machines (SVMs) classification methodology, which can offer superior classification performance for important process engineering problems. The method incorporates efficient tuning procedures based on minimization of radius/margin and span bound for leave-one-out errors. An agent-based asynchronous teams (A-teams) software framework, which combines Genetic-Quasi-Newton algorithms for the optimization is highly successful in obtaining the optimal SVM hyper-parameters. The algorithm has been applied for classification of binary as well as multi-class real world problems.

An ant colony classifier system: application to some process engineering problems

Recently developed ant colony optimization metaheuristic procedure has been recast as a rule based machine learning method, called as ant colony classifier system, and applied to three process engineering examples. The learning algorithm addresses the problem of knowledge acquisition in terms of rules from example cases by developing and maintaining the knowledge base through the use of simple mechanism, pheromone trail information matrix and use of available heuristic information. The performance of an ant colony classifier is compared with the well-known decision tree based C4.5 algorithm in terms of the predictive accuracy on test cases and the simplicity of rules discovered. The results indicate that the ant classifier is able to discover rules in the data sets with better predictive accuracy than the C4.5 algorithm.

A Tabu Search Based Approach for Solving a Class of Bilevel Programming Problems in Chemical Engineering

In this paper an approach based on the tabu search paradigm to tackle the bilevel programming problems is presented. The algorithm has been tested for a number of benchmark problems and the results obtained show superiority of the approach over the conventional methods in solving such problems.

An SVM classifier incorporating simultaneous noise reduction and feature selection: illustrative case examples

A hybrid technique involving symbolization of data to remove noise and use of conditional entropy minima to extract relevant and non-redundant features is proposed in conjunction with support vector machines to obtain more robust classification algorithm. The technique tested on three data sets shows improvements in classification efficiencies.

ClassAMP: A Prediction Tool for Classification of Antimicrobial Peptides

Antimicrobial peptides (AMPs) are gaining popularity as anti-infective agents. Information on sequence features that contribute to target specificity of AMPs will aid in accelerating drug discovery programs involving them. In this study, an algorithm called ClassAMP using Random Forests (RFs) and Support Vector Machines (SVMs) has been developed to predict the propensity of a protein sequence to have antibacterial, antifungal, or antiviral activity. ClassAMP is available at http://www.bicnirrh.res.in/classamp/.

Symbolization assisted SVM classifier for noisy data

The paper reports on the robust pattern classification of experimental data using a combined approach of symbolization followed by support vector machine (SVM) classification. Symbolization of data removes unwanted features such as noise whereas SVM provides the classification. The SVM parameters are tuned on-line using a genetic-quasi-Newton algorithm. Benchmark examples illustrate the proposed approach.

Arrhythmia classification using local hölder exponents and support vector machine

We propose a novel hybrid Holder-SVM detection algorithm for arrhythmia classification. The Holder exponents are computed efficiently using the wavelet transform modulus maxima (WTMM) method. The hybrid system performance is evaluated using the benchmark MIT-BIH arrhythmia database. The implemented model classifies 160 of Normal sinus rhythm, 25 of Ventricular bigeminy, 155 of Atrial fibrillation and 146 of Nodal (A-V junctional) rhythm with 96.94% accuracy. The distinct scaling properties of different types of heart rhythms may be of clinical importance.