RESUMO

This study addresses the environmental problem of PET plastic through in silico bioprospecting for the identification and experimental validation of novel PET degrading eukaryotes through the in silico bioprospectingI of PETases, employing a methodology that combines Hidden Markov Models (HMMs), clustering techniques, molecular docking, and dynamic simulations. A total of 424 putative PETase sequences were identified from 219 eukaryotic organisms, highlighting six sequences with low affinity energies. The Aspergillus luchuensis sequence showed the lowest Gibbs free energy and exhibited stability at different temperatures in molecular dynamics assays. Experimental validation, through a plate clearance assay and HPLC, confirmed PETase activity in three wild-type fungal strains, with A. luchuensis showing the highest efficiency. The results obtained demonstrate the effectiveness of combining computational and experimental approaches as proof of concept to discover and validate eukaryotes with PET-degrading capabilities opening new perspectives for the sustainable management of this type of waste and contributing to its environmental mitigation.

Assuntos

RESUMO

As a neurodevelopmental pathology, Attention Deficit Hyperactivity Disorder (ADHD) mainly arises during childhood. Persistent patterns of generalized inattention, impulsivity, or hyperactivity characterize ADHD that may persist into adulthood. The conventional diagnosis relies on clinical observational processes yielding high rates of overdiagnosis due to varying interpretations among specialists or missing information. Although several studies have designed objective behavioral features to overcome such an issue, they lack significance. Despite electroencephalography (EEG) analyses extracting alternative biomarkers using signal processing techniques, the nonlinearity and nonstationarity of EEG signals restrain performance and generalization of hand-crafted features. This work proposes a methodology to support ADHD diagnosis by characterizing EEG signals from hidden Markov models (HMM), classifying subjects based on similarity measures for probability functions, and spatially interpreting the results using graphic embeddings of stochastic dynamic models. The methodology learns a single HMM for EEG signal from each patient, so favoring the inter-subject variability. Then, the Probability Product Kernel, specifically developed for assessing the similarity between HMMs, fed a support vector machine that classifies subjects according to their stochastic dynamics. Lastly, the kernel variant of Principal Component Analysis provided a means to visualize the EEG transitions in a two-dimensional space, evidencing dynamic differences between ADHD and Healthy Control children. From the electrophysiological perspective, we recorded EEG under the Stop Signal Task modified with reward levels, which considers cognitive features of interest as insufficient motivational circuits recruitment. The methodology compares the supported diagnosis in two EEG channel setups (whole channel set and channels of interest in frontocentral area) and four frequency bands (Theta, Alpha, Beta rhythms, and a wideband). Results evidence an accuracy rate of 97.0% in the Beta band and in the channels where previous works found error-related negativity events. Such accuracy rate strongly supports the dual pathway hypothesis and motivational deficit concerning the pathophysiology of ADHD. It also demonstrates the utility of joining inhibitory and motivational paradigms with dynamic EEG analysis into a noninvasive and affordable diagnostic tool for ADHD patients.

Assuntos

RESUMO

Many human activities are tactile. Recognizing how a person touches an object or a surface surrounding them is an active area of research and it has generated keen interest within the interactive surface community. In this paper, we compare two machine learning techniques, namely Artificial Neural Network (ANN) and Hidden Markov Models (HMM), as they are some of the most common techniques with low computational cost used to classify an acoustic-based input. We employ a small and low-cost hardware design composed of a microphone, a stethoscope, a conditioning circuit, and a microcontroller. Together with an appropriate surface, we integrated these components into a passive gesture recognition input system for experimental evaluation. To perform the evaluation, we acquire the signals using a small microphone and send it through the microcontroller to MATLAB's toolboxes to implement and evaluate the ANN and HMM models. We also present the hardware and software implementation and discuss the advantages and limitations of these techniques in gesture recognition while using a simple alphabet of three geometrical figures: circle, square, and triangle. The results validate the robustness of the HMM technique that achieved a success rate of 90%, with a shorter training time than the ANN.

Assuntos

RESUMO

In plant-pathogen interactions, plant immunity through pathogen-associated molecular pattern receptors (PAMPs) and R proteins, also called pattern recognition receptors (PRRs), occurs in different ways depending on both plant and pathogen species. The use and search for a structural pattern based on the presence and absence of characteristic domains, regardless of their disposition within a sequence, could be efficient in identifying PRRs proteins. Here, we develop a method mainly based on text mining and set theory to identify PRR and R genes that classify them into 13 categories based on the presence and absence of the main domains. Analyzing 24 plant and algae genomes, we showed that the RRGPredictor was more efficient, specific and sensitive than other tools already available, and identified PRR proteins with variations in size and in domain distribution throughout the sequence. Besides an easy identification of new plant PRRs proteins, RRGPredictor provided a low computational cost.

Assuntos

RESUMO

BACKGROUND Ubiquitin (Ub) and Ub-like proteins (Ub-L) are critical regulators of complex cellular processes such as the cell cycle, DNA repair, transcription, chromatin remodeling, signal translation, and protein degradation. Giardia intestinalis possesses an experimentally proven Ub-conjugation system; however, a limited number of enzymes involved in this process were identified using basic local alignment search tool (BLAST). This is due to the limitations of BLAST's ability to identify homologous functional regions when similarity between the sequences dips to < 30%. In addition Ub-Ls and their conjugating enzymes have not been fully elucidated in Giardia. OBJETIVE To identify the enzymes involved in the Ub and Ub-Ls conjugation processes using intelligent systems based on the hidden Markov models (HMMs). METHODS We performed an HMM search of functional Pfam domains found in the key enzymes of these pathways in Giardia's proteome. Each open reading frame identified was analysed by sequence homology, domain architecture, and transcription levels. FINDINGS We identified 118 genes, 106 of which corresponded to the ubiquitination process (Ub, E1, E2, E3, and DUB enzymes). The E3 ligase group was the largest group with 82 members; 71 of which harbored a characteristic RING domain. Four Ub-Ls were identified and the conjugation enzymes for NEDD8 and URM1 were described for first time. The 3D model for Ub-Ls displayed the β-grasp fold typical. Furthermore, our sequence analysis for the corresponding activating enzymes detected the essential motifs required for conjugation. MAIN CONCLUSIONS Our findings highlight the complexity of Giardia's Ub-conjugation system, which is drastically different from that previously reported, and provides evidence for the presence of NEDDylation and URMylation enzymes in the genome and transcriptome of G. intestinalis.

Assuntos

RESUMO

Resumen: La auscultación de señales basada en un estetoscopio estándar y/o electrónico no solo incluye sonidos internos del cuerpo, también incluye frecuentemente ruido externo de interferencia con componentes en el mismo rango. Esta forma de examinar es incluso afectada por los umbrales auditivos variantes de los profesionales de la salud y el grado de experiencia en reconocimiento de indicadores peculiares. Además, los resultados son a menudo caracterizados en términos cualitativos descriptivos sujetos a interpretaciones individuales. Para direccionar esta preocupación, los estudios presentados en este artículo contienen un procesamiento concurrente de las componentes dominantes de sonidos del corazón (HS) y del pulmón (HS), y una etapa de acondicionamiento que incluye la reducción de HS presente en señales LS. Específicamente, la transformada de Hilbert fue una técnica de caracterización para HS. En el caso de señales enfocadas a LS, las técnicas de detección de actividad de voz y el cálculo de umbrales de algunos componentes de los vectores acústicos de Coeficientes Cepstrales en Frecuencia Mel (MFCC), fueron útiles en la caracterización de eventos acústicos asociados. Las fases de inspiración y expiración fueron diferenciadas por medio de la sexta componente de MFCC. Con el fin de evaluar la eficiencia de esta aproximación, proponemos los Modelos Ocultos de Markov con Modelos Mesclados Gaussianos (HMM-GMM). Los resultados utilizando esta forma de detección son superiores cuando se desarrolla la clasificación con modelos HMM-GMM, la cual refleja las ventajas de la forma de detección cuantificable y clasificación sobre la aproximación clínica tradicional.

Abstract: A standard and/or electronic stethoscope based auscultatory signals include not only the internal sounds of the body but also interfering external noise often with similar frequency components. This form of examination is also affected by varying thresholds of clinical practitioner's hearing and degree of experience in recognition of peculiar auscultatory indicators. Further, the results are often characterized in qualitative descriptive terms subject to individual's interpretation. To address these concerns, presented studies include concurrent processing of dominant heart (HS) and lung (LS) sounds components and a conditioning stage involving HS presence reduction within LS focused signals. Specifically as determined, the Hilbert transform was a technique of choice in HS characterization. In the case of LS focused signals, the speech activity detection techniques (VAD) and the thresholds calculation of some components of acoustic vectors of Cepstral Coefficients in Mel Frequency (MFCC), were useful in characterization of associated acoustic events. The phases of inspiration and expiration were differentiated by means of the sixth component of MFCC. In order to evaluate the efficiency of this approach, we propose Hidden Markov Models with Mixed Gaussian Models (HMM-GMM). The results utilizing this form of detection are superior when performing classification with HMM-GMM models, which reflect the advantages of presented form of quantifiable detection and classification over traditional clinical approach.

RESUMO

Profile hidden Markov models (pHMMs) have been used to search for transposable elements (TEs) in genomes. For the learning of pHMMs aimed to search for TEs of the retrotransposon class, the conventional protocol is to use the whole internal nucleotide portions of these elements as representative sequences. To further explore the potential of pHMMs in such a search, we propose five alternative ways to obtain the sets of representative sequences of TEs other than the conventional protocol. In this study, we are interested in Bel-PAO, Copia, Gypsy, and DIRS superfamilies from the retrotransposon class. We compared the pHMMs of all six protocols. The test results show that, for each TE superfamily, the pHMMs of at least two of the proposed protocols performed better than the conventional one and that the number of correct predictions provided by the latter can be improved by considering together the results of one or more of the alternative protocols.

Assuntos

RESUMO

Our daily interaction with the world is plagued of situations in which we develop expertise through self-motivated repetition of the same task. In many of these interactions, and especially when dealing with computer and machine interfaces, we must deal with sequences of decisions and actions. For instance, when drawing cash from an ATM machine, choices are presented in a step-by-step fashion and a specific sequence of choices must be performed in order to produce the expected outcome. But, as we become experts in the use of such interfaces, is it possible to identify specific search and learning strategies? And if so, can we use this information to predict future actions? In addition to better understanding the cognitive processes underlying sequential decision making, this could allow building adaptive interfaces that can facilitate interaction at different moments of the learning curve. Here we tackle the question of modeling sequential decision-making behavior in a simple human-computer interface that instantiates a 4-level binary decision tree (BDT) task. We record behavioral data from voluntary participants while they attempt to solve the task. Using a Hidden Markov Model-based approach that capitalizes on the hierarchical structure of behavior, we then model their performance during the interaction. Our results show that partitioning the problem space into a small set of hierarchically related stereotyped strategies can potentially capture a host of individual decision making policies. This allows us to follow how participants learn and develop expertise in the use of the interface. Moreover, using a Mixture of Experts based on these stereotyped strategies, the model is able to predict the behavior of participants that master the task.

RESUMO

Resumen Este artículo está relacionado con el análisis y la propuesta de una arquitectura HMM-GMM para clasificación de señales HS y LS, haciendo un énfasis en el tamaño del modelo. Actualmente, las enfermedades respiratorias y cardiovasculares son un problema a nivel mundial y con una alta mortandad, esto podría ser disminuido mediante un diagnóstico temprano y objetivo; las herramientas digitales y el empleo de reconocimiento de patrones ampliarían las perspectivas de aplicación. Particularmente, aquí se demuestra que los modelos HMM-GMM son eficientes para consultorios de atención primaria, así mismo los extractores de características tales como MFCC y Cuantiles mejoran la tarea de clasificación. Si bien la visualización con siluetas, dendrogramas y algoritmos tales como BIC no son concluyentes cuando se aplican GMM's, no obstante sí fue el punto de partida para dimensionar el tamaño del modelo, disminuyendo la cantidad de experimentos con distintos tamaños del mismo. Adicionalmente, se constata que la estructura de señales normales HS y LS cambian cuando hay patologías y permite la clasificación aplicando MFCC o Cuantiles. Además, se observa que con una gran cantidad de datos se podrían obtener modelos más robustos y adaptados, pero esto no es una limitante para el cálculo de los modelos.

Abstract This paper demonstrates the analysis and proposed HMM-GMM models architecture to classify heart and lung sounds (HS and LS) signals emphasizing the model size optimization. Respiratory and cardiovascular diseases continue to represent one of the major worldwide healthcare problems associated with a liigli mortality rate, wliicli can be reduced by an early and effective diagnosis; in this context, the use of digital tools utilizing signal pattern recognition allows efficient screening for abnormalities and their quantitative assessment. In particular, the HMM-GMM models demonstrated their efficiency in normal and traditionally noisy environments in light of very low intensities of these auscultation signals used as diagnostic indicators. Furthermore, applied MFCC and Quantiles feature extractors improve overall classification. While characterization with silhouettes, dendrograms and algorithms such as BIC was inconclusive when GMM was applied, however they were useful as a starting point in the determination of a size of the model as it allowed a reduction in the number of iterations considering different model size. In addition one can note that application of MFCC or Quantiles allowed differentiating the characteristics of normal HS and LS from those associated with pathological conditions. Furthermore, it was observed that a large amount of data leads to more robust and adapted models, but does not limit the calculation demand. Overall, this approach may enhance efficiency and precision of the diagnostic screening for abnormal auscultation indicators.

RESUMO

Se realiza un estudio del desempeño de los modelos ocultos de Márkov (HMM) en la clasificación morfológica supervisada de eritrocitos en muestras de sangre periférica de pacientes con anemia drepanocítica. Los contornos se representan de forma novedosa considerando las diferencias angulares en la curvatura de los puntos del mismo. El entrenamiento de cada modelo se realiza tanto con la descripción normal de los contornos como con la representación de la rotación de los mismos, para garantizar una mayor estabilidad en los parámetros estimados. Se desarrolla un proceso de validación cruzada de 5x1 para estimación del error. Se obtienen las medidas de sensibilidad, precisión y especificidad de la clasificación. Los mejores resultados en cuanto a sensibilidad se obtienen al clasificar eritrocitos pertenecientes a dos clases: normales (96 por ciento) y elongados (99 por ciento). Al considerar además una clase de eritrocitos con otras deformaciones los mejores resultados se obtienen realizando el entrenamiento de los modelos con la rotación de todos los contornos, que alcanzó sensibilidades de normales (94 por ciento), elongados (82 por ciento) y con otras deformaciones (76 por ciento)(AU)

A study of the performance of Hidden Markov Models (HMM) in morphologic supervised classification of erythrocytes in peripheral blood smears of patients with sickle cell disease is realized. Contours are represented in original way considering the angular differences in the curvature of the points of the same. The training of every model comes true with the normal description of the contours and with the representation of the rotation of the same, in order to guarantee a bigger stability in the esteemed parameters. A process of validation crossed of 5x1 for estimate of the error is developed. The measures of sensibility, precision and specificity of classification are obtained. The best results obtain when classifying erythrocytes in two classes, with sensibility values in normal of 96 percent and elongated 99 percent. In the classification of erythrocytes considering the class of other deformations better results obtain accomplishing the training of the models with the rotation of all the contours, that it attained sensibilities of normal (94 percent), elongated (82 percent) and with other deformations (76 percent)(AU)

Assuntos

RESUMO

We describe an automatic segmentation method for polyproteins of the viruses belonging to the Potyviridae family. It uses machine learning techniques in order to predict the cleavage site which define the segments in which said polyproteins are cut in their process of functional maturation. The segmentation application is publicly available for use on a website and it can be accessed through the web service interface too. The prediction models have an average sensitivity of 0.79 and a Matthews correlation coefficient average of 0.23. This method is capable of predicting correctly (coinciding with previously published segmentation) the segmentation of sequences which come from Potyvirus and Rymovirus, genera. However accurate prediction capabilities are affected when faced with either atypical sequences or viruses belonging to less common genera in the Potyviridae family. Future work will focus on establishing greater flexibility in this sense.