A Comparative Analysis of Predictive Learning Algorithms on High-Dimensional Microarray Cancer Data

This research evaluates pattern recognition techniques on a subclass of big data where the dimensionality of the input space (p) is much larger than the number of observations (n). Specifically, we evaluate massive gene expression microarray cancer data where the ratio κ is less than one. We explore the statistical and computational challenges inherent in these high dimensional low sample size (HDLSS) problems and present statistical machine learning methods used to tackle and circumvent these difficulties. Regularization and kernel algorithms were explored in this research using seven datasets where κ < 1. These techniques require special attention to tuning necessitating several extensions of cross-validation to be investigated to support better predictive performance. While no single algorithm was universally the best predictor, the regularization technique produced lower test errors in five of the seven datasets studied.

On Provable Algorithms for Determination of Continuous Protein Interdomain Motions from Residual Dipolar Couplings

Dynamics of biomolecules over various spatial and time scales are essential for biological functions such as molecular recognition, catalysis and signaling. However, reconstruction of biomolecular dynamics from experimental observables requires the determination of a conformational probability distribution. Unfortunately, these distributions cannot be fully constrained by the limited information from experiments, making the problem an ill-posed one in the terminology of Hadamard. The ill-posed nature of the problem comes from the fact that it has no unique solution. Multiple or even an infinite number of solutions may exist. To avoid the ill-posed nature, the problem needs to be regularized by making assumptions, which inevitably introduce biases into the result.

Here, I present two continuous probability density function approaches to solve an important inverse problem called the RDC trigonometric moment problem. By focusing on interdomain orientations we reduced the problem to determination of a distribution on the 3D rotational space from residual dipolar couplings (RDCs). We derived an analytical equation that relates alignment tensors of adjacent domains, which serves as the foundation of the two methods. In the first approach, the ill-posed nature of the problem was avoided by introducing a continuous distribution model, which enjoys a smoothness assumption. To find the optimal solution for the distribution, we also designed an efficient branch-and-bound algorithm that exploits the mathematical structure of the analytical solutions. The algorithm is guaranteed to find the distribution that best satisfies the analytical relationship. We observed good performance of the method when tested under various levels of experimental noise and when applied to two protein systems. The second approach avoids the use of any model by employing maximum entropy principles. This 'model-free' approach delivers the least biased result which presents our state of knowledge. In this approach, the solution is an exponential function of Lagrange multipliers. To determine the multipliers, a convex objective function is constructed. Consequently, the maximum entropy solution can be found easily by gradient descent methods. Both algorithms can be applied to biomolecular RDC data in general, including data from RNA and DNA molecules.

Object detection and recognition in complex scenes

Dissertação de Mestrado, Engenharia Informática, Faculdade de Ciências e Tecnologia, Universidade do Algarve, 2014

Improving Bangla ocr output through correction algorithms

Bangla OCR (Optical Character Recognition) is a long deserving software for Bengali community all over the world. Numerous e efforts suggest that due to the inherent complex nature of Bangla alphabet and its word formation process development of high fidelity OCR producing a reasonably acceptable output still remains a challenge. One possible way of improvement is by using post processing of OCR’s output; algorithms such as Edit Distance and the use of n-grams statistical information have been used to rectify misspelled words in language processing. This work presents the first known approach to use these algorithms to replace misrecognized words produced by Bangla OCR. The assessment is made on a set of fifty documents written in Bangla script and uses a dictionary of 541,167 words. The proposed correction model can correct several words lowering the recognition error rate by 2.87% and 3.18% for the character based n- gram and edit distance algorithms respectively. The developed system suggests a list of 5 (five) alternatives for a misspelled word. It is found that in 33.82% cases, the correct word is the topmost suggestion of 5 words list for n-gram algorithm while using Edit distance algorithm the first word in the suggestion properly matches 36.31% of the cases. This work will ignite rooms of thoughts for possible improvements in character recognition endeavour.

Antibody Recognition Of Plasmodium Falciparum Infected Red Blood Cells By Symptomatic And Asymptomatic Individuals In The Brazilian Amazon.

In the Amazon Region, there is a virtual absence of severe malaria and few fatal cases of naturally occurring Plasmodium falciparum infections; this presents an intriguing and underexplored area of research. In addition to the rapid access of infected persons to effective treatment, one cause of this phenomenon might be the recognition of cytoadherent variant proteins on the infected red blood cell (IRBC) surface, including the var gene encoded P. falciparum erythrocyte membrane protein 1. In order to establish a link between cytoadherence, IRBC surface antibody recognition and the presence or absence of malaria symptoms, we phenotype-selected four Amazonian P. falciparum isolates and the laboratory strain 3D7 for their cytoadherence to CD36 and ICAM1 expressed on CHO cells. We then mapped the dominantly expressed var transcripts and tested whether antibodies from symptomatic or asymptomatic infections showed a differential recognition of the IRBC surface. As controls, the 3D7 lineages expressing severe disease-associated phenotypes were used. We showed that there was no profound difference between the frequency and intensity of antibody recognition of the IRBC-exposed P. falciparum proteins in symptomatic vs. asymptomatic infections. The 3D7 lineages, which expressed severe malaria-associated phenotypes, were strongly recognised by most, but not all plasmas, meaning that the recognition of these phenotypes is frequent in asymptomatic carriers, but is not necessarily a prerequisite to staying free of symptoms.

Biased Random-key Genetic Algorithms For The Winner Determination Problem In Combinatorial Auctions.

Abstract In this paper, we address the problem of picking a subset of bids in a general combinatorial auction so as to maximize the overall profit using the first-price model. This winner determination problem assumes that a single bidding round is held to determine both the winners and prices to be paid. We introduce six variants of biased random-key genetic algorithms for this problem. Three of them use a novel initialization technique that makes use of solutions of intermediate linear programming relaxations of an exact mixed integer-linear programming model as initial chromosomes of the population. An experimental evaluation compares the effectiveness of the proposed algorithms with the standard mixed linear integer programming formulation, a specialized exact algorithm, and the best-performing heuristics proposed for this problem. The proposed algorithms are competitive and offer strong results, mainly for large-scale auctions.

Concepção e implementação de um sistema para analise cinematica de movimentos humanos

Universidade Estadual de Campinas. Faculdade de Educação Física

Long-term social recognition memory in adult male rats: factor analysis of the social and non-social behaviors

A modified version of the intruder-resident paradigm was used to investigate if social recognition memory lasts at least 24 h. One hundred and forty-six adult male Wistar rats were used. Independent groups of rats were exposed to an intruder for 0.083, 0.5, 2, 24, or 168 h and tested 24 h after the first encounter with the familiar or a different conspecific. Factor analysis was employed to identify associations between behaviors and treatments. Resident rats exhibited a 24-h social recognition memory, as indicated by a 3- to 5-fold decrease in social behaviors in the second encounter with the same conspecific compared to those observed for a different conspecific, when the duration of the first encounter was 2 h or longer. It was possible to distinguish between two different categories of social behaviors and their expression depended on the duration of the first encounter. Sniffing the anogenital area (49.9% of the social behaviors), sniffing the body (17.9%), sniffing the head (3%), and following the conspecific (3.1%), exhibited mostly by resident rats, characterized social investigation and revealed long-term social recognition memory. However, dominance (23.8%) and mild aggression (2.3%), exhibited by both resident and intruders, characterized social agonistic behaviors and were not affected by memory. Differently, sniffing the environment (76.8% of the non-social behaviors) and rearing (14.3%), both exhibited mostly by adult intruder rats, characterized non-social behaviors. Together, these results show that social recognition memory in rats may last at least 24 h after a 2-h or longer exposure to the conspecific.

A novel polar-based human face recognition computational model

Motivated by a recently proposed biologically inspired face recognition approach, we investigated the relation between human behavior and a computational model based on Fourier-Bessel (FB) spatial patterns. We measured human recognition performance of FB filtered face images using an 8-alternative forced-choice method. Test stimuli were generated by converting the images from the spatial to the FB domain, filtering the resulting coefficients with a band-pass filter, and finally taking the inverse FB transformation of the filtered coefficients. The performance of the computational models was tested using a simulation of the psychophysical experiment. In the FB model, face images were first filtered by simulated V1- type neurons and later analyzed globally for their content of FB components. In general, there was a higher human contrast sensitivity to radially than to angularly filtered images, but both functions peaked at the 11.3-16 frequency interval. The FB-based model presented similar behavior with regard to peak position and relative sensitivity, but had a wider frequency band width and a narrower response range. The response pattern of two alternative models, based on local FB analysis and on raw luminance, strongly diverged from the human behavior patterns. These results suggest that human performance can be constrained by the type of information conveyed by polar patterns, and consequently that humans might use FB-like spatial patterns in face processing.

The Anopheles albitarsis complex with the recognition of Anopheles oryzalimnetes Wilkerson and Motoki, n. sp. and Anopheles janconnae Wilkerson and Sallum, n. sp. (Diptera: Culicidae)

The Anopheles (Nyssorhynchus) albitarsis complex includes six species: An. albitarsis, Anopheles oryzalymnetes Wilkerson and Motoki, n. sp., Anopheles marajoara, Anopheles dencorum, Anopheles janconnae Wilkerson and Sallum, n. sp., and An. albitarsis F. Except for An. deancorum, species of the complex are indistinguishable when only using morphology. The problematic distinction among species of the complex has made study of malaria transmission and ecology of An. albitarsis s.l. difficult. Consequently, involvement of species of the An. albitarsis complex in human Plasmodium transmission is not clear throughout its distribution range. With the aim of clarifying the taxonomy of the above species, with the exception of An. albitarsis F, we present comparative morphological and morphometric analyses, morphological redescriptions of three species and descriptions of two new species using individuals from populations in Brazil, Paraguay, Argentina and Venezuela. The study included characters from adult females, males, fourth-instar larvae, pupae and male genitalia of An. albitarsis, An. deaneorum and An. oryzalimnetes n. sp. For An. janconnae n. sp. only characters of the female, male and male genitalia were analysed. Fourth-instar larvae and pupae and male genitalia characteristics of all five species are illustrated. Bionomics and distribution data are given based on published literature records

Leishmania-Specific Surface Antigens Show Sub-Genus Sequence Variation and Immune Recognition

Background: A family of hydrophilic acylated surface (HASP) proteins, containing extensive and variant amino acid repeats, is expressed at the plasma membrane in infective extracellular (metacyclic) and intracellular (amastigote) stages of Old World Leishmania species. While HASPs are antigenic in the host and can induce protective immune responses, the biological functions of these Leishmania-specific proteins remain unresolved. Previous genome analysis has suggested that parasites of the sub-genus Leishmania (Viannia) have lost HASP genes from their genomes. Methods/Principal Findings: We have used molecular and cellular methods to analyse HASP expression in New World Leishmania mexicana complex species and show that, unlike in L. major, these proteins are expressed predominantly following differentiation into amastigotes within macrophages. Further genome analysis has revealed that the L. (Viannia) species, L. (V.) braziliensis, does express HASP-like proteins of low amino acid similarity but with similar biochemical characteristics, from genes present on a region of chromosome 23 that is syntenic with the HASP/SHERP locus in Old World Leishmania species and the L. (L.) mexicana complex. A related gene is also present in Leptomonas seymouri and this may represent the ancestral copy of these Leishmania-genus specific sequences. The L. braziliensis HASP-like proteins (named the orthologous (o) HASPs) are predominantly expressed on the plasma membrane in amastigotes and are recognised by immune sera taken from 4 out of 6 leishmaniasis patients tested in an endemic region of Brazil. Analysis of the repetitive domains of the oHASPs has shown considerable genetic variation in parasite isolates taken from the same patients, suggesting that antigenic change may play a role in immune recognition of this protein family. Conclusions/Significance: These findings confirm that antigenic hydrophilic acylated proteins are expressed from genes in the same chromosomal region in species across the genus Leishmania. These proteins are surface-exposed on amastigotes (although L. (L.) major parasites also express HASPB on the metacyclic plasma membrane). The central repetitive domains of the HASPs are highly variant in their amino acid sequences, both within and between species, consistent with a role in immune recognition in the host.

Bayesian online algorithms for learning in discrete Hidden Markov Models

We propose and analyze two different Bayesian online algorithms for learning in discrete Hidden Markov Models and compare their performance with the already known Baldi-Chauvin Algorithm. Using the Kullback-Leibler divergence as a measure of generalization we draw learning curves in simplified situations for these algorithms and compare their performances.

Adenosine binding to low-molecular-weight purine nucleoside phosphorylase: the structural basis for recognition based on its complex with the enzyme from Schistosoma mansoni

Schistosomes are unable to synthesize purines de novo and depend exclusively on the salvage pathway for their purine requirements. It has been suggested that blockage of this pathway could lead to parasite death. The enzyme purine nucleoside phosphorylase (PNP) is one of its key components and molecules designed to inhibit the low-molecular-weight (LMW) PNPs, which include both the human and schistosome enzymes, are typically analogues of the natural substrates inosine and guanosine. Here, it is shown that adenosine both binds to Schistosoma mansoni PNP and behaves as a weak micromolar inhibitor of inosine phosphorolysis. Furthermore, the first crystal structures of complexes of an LMW PNP with adenosine and adenine are reported, together with those with inosine and hypoxanthine. These are used to propose a structural explanation for the selective binding of adenosine to some LMW PNPs but not to others. The results indicate that transition-state analogues based on adenosine or other 6-amino nucleosides should not be discounted as potential starting points for alternative inhibitors.

Feature selection environment for genomic applications

Background: Feature selection is a pattern recognition approach to choose important variables according to some criteria in order to distinguish or explain certain phenomena (i.e., for dimensionality reduction). There are many genomic and proteomic applications that rely on feature selection to answer questions such as selecting signature genes which are informative about some biological state, e. g., normal tissues and several types of cancer; or inferring a prediction network among elements such as genes, proteins and external stimuli. In these applications, a recurrent problem is the lack of samples to perform an adequate estimate of the joint probabilities between element states. A myriad of feature selection algorithms and criterion functions have been proposed, although it is difficult to point the best solution for each application. Results: The intent of this work is to provide an open-source multiplataform graphical environment for bioinformatics problems, which supports many feature selection algorithms, criterion functions and graphic visualization tools such as scatterplots, parallel coordinates and graphs. A feature selection approach for growing genetic networks from seed genes ( targets or predictors) is also implemented in the system. Conclusion: The proposed feature selection environment allows data analysis using several algorithms, criterion functions and graphic visualization tools. Our experiments have shown the software effectiveness in two distinct types of biological problems. Besides, the environment can be used in different pattern recognition applications, although the main concern regards bioinformatics tasks.

Improvements on ICA mixture models for image pre-processing and segmentation

Today several different unsupervised classification algorithms are commonly used to cluster similar patterns in a data set based only on its statistical properties. Specially in image data applications, self-organizing methods for unsupervised classification have been successfully applied for clustering pixels or group of pixels in order to perform segmentation tasks. The first important contribution of this paper refers to the development of a self-organizing method for data classification, named Enhanced Independent Component Analysis Mixture Model (EICAMM), which was built by proposing some modifications in the Independent Component Analysis Mixture Model (ICAMM). Such improvements were proposed by considering some of the model limitations as well as by analyzing how it should be improved in order to become more efficient. Moreover, a pre-processing methodology was also proposed, which is based on combining the Sparse Code Shrinkage (SCS) for image denoising and the Sobel edge detector. In the experiments of this work, the EICAMM and other self-organizing models were applied for segmenting images in their original and pre-processed versions. A comparative analysis showed satisfactory and competitive image segmentation results obtained by the proposals presented herein. (C) 2008 Published by Elsevier B.V.