Biomedical subjects

Matthew Landry

Publications and source records attributed to Matthew Landry.

3 recordsLinked to original sources

PubMed2006

DNA molecule classification using feature primitives.

BACKGROUND: We present a novel strategy for classification of DNA molecules using measurements from an alpha-Hemolysin channel detector. The proposed approach provides excellent classification performance for five different DNA hairpins that differ in only one base-pair. For multi-class DNA classification problems, practitioners usually adopt approaches that use decision trees consisting of binary classifiers. Finding the best tree topology requires exploring all possible tree topologies and is computationally prohibitive. We propose a computational framework based on feature primitives that eliminates the need of a decision tree of binary classifiers. In the first phase, we generate a pool of weak features from nanopore blockade current measurements by using HMM analysis, principal component analysis and various wavelet filters. In the next phase, feature selection is performed using AdaBoost. AdaBoost provides an ensemble of weak learners of various types learned from feature primitives. RESULTS AND CONCLUSION: We show that our technique, despite its inherent simplicity, provides a performance comparable to recent multi-class DNA molecule classification results. Unlike the approach presented by Winters-Hilt et al., where weaker data is dropped to obtain better classification, the proposed approach provides comparable classification accuracy without any need for rejection of weak data. A weakness of this approach, on the other hand, is the very "hands-on" tuning and feature selection that is required to obtain good generalization. Simply put, this method obtains a more informed set of features and provides better results for that reason. The strength of this approach appears to be in its ability to identify strong features, an area where further results are actively being sought.

Computational Biology↗

PubMed2006

Cheminformatics methods for novel nanopore analysis of HIV DNA termini.

BACKGROUND: Channel current feature extraction methods, using Hidden Markov Models (HMMs) have been designed for tracking individual-molecule conformational changes. This information is derived from observation of changes in ionic channel current blockade "signal" upon that molecule's interaction with (and occlusion of) a single nanometer-scale channel in a "nanopore detector". In effect, a nanopore detector transduces single molecule events into channel current blockades. HMM analysis tools described are used to help systematically explore DNA dinucleotide flexibility, with particular focus on HIV's highly conserved (and highly flexible/reactive) viral DNA termini. One of the most critical stages in HIV's attack is the binding between viral DNA and the retroviral integrase, which is influenced by the dynamic-coupling induced high flexibility of a CA/TG dinucleotide positioned precisely two base-pairs from the blunt terminus of the duplex viral DNA. This suggests the study of a family of such CA/TG dinucleotide molecules via nanopore measurement and cheminformatics analysis. RESULTS: HMMs are used for level identification on the current blockades, HMM/EM with boosted variance emissions are used for level projection pre-processing, and time-domain FSAs are used to parse the level-projected waveform for kinetic information. The observed state kinetics of the DNA hairpins containing the CA/TG dinucleotide provides clear evidence for HIV's selection of a peculiarly flexible/interactive DNA terminus.

Base Sequence↗

PubMed2006

Support vector machine implementations for classification & clustering.

BACKGROUND: We describe Support Vector Machine (SVM) applications to classification and clustering of channel current data. SVMs are variational-calculus based methods that are constrained to have structural risk minimization (SRM), i.e., they provide noise tolerant solutions for pattern recognition. The SVM approach encapsulates a significant amount of model-fitting information in the choice of its kernel. In work thus far, novel, information-theoretic, kernels have been successfully employed for notably better performance over standard kernels. Currently there are two approaches for implementing multiclass SVMs. One is called external multi-class that arranges several binary classifiers as a decision tree such that they perform a single-class decision making function, with each leaf corresponding to a unique class. The second approach, namely internal-multiclass, involves solving a single optimization problem corresponding to the entire data set (with multiple hyperplanes). RESULTS: Each SVM approach encapsulates a significant amount of model-fitting information in its choice of kernel. In work thus far, novel, information-theoretic, kernels were successfully employed for notably better performance over standard kernels. Two SVM approaches to multiclass discrimination are described: (1) internal multiclass (with a single optimization), and (2) external multiclass (using an optimized decision tree). We describe benefits of the internal-SVM approach, along with further refinements to the internal-multiclass SVM algorithms that offer significant improvement in training time without sacrificing accuracy. In situations where the data isn't clearly separable, making for poor discrimination, signal clustering is used to provide robust and useful information--to this end, novel, SVM-based clustering methods are also described. As with the classification, there are Internal and External SVM Clustering algorithms, both of which are briefly described.

Algorithms↗