RESUMO
Retention of histidine-containing peptides in immobilized metal-affinity chromatography (IMAC) has been studied using several hundred model peptides. Retention in a Nickel column is primarily driven by the number of histidine residues; however, the amino acid composition of the peptide also plays a significant role. A regression model based on support vector machines was used to learn and subsequently predict the relationship between the amino acid composition and the retention time on a Nickel column. The model was predominantly governed by the count of the histidine residues, and the isoelectric point of the peptide.
Assuntos
Técnicas Genéticas , Genótipo , Polimorfismo de Nucleotídeo Único , Alelos , Interpretação Estatística de Dados , Técnicas Genéticas/instrumentação , Técnicas Genéticas/normas , Técnicas Genéticas/estatística & dados numéricos , Variação Genética , Humanos , Reação em Cadeia da Polimerase , Controle de Qualidade , RNA Mensageiro/genéticaRESUMO
Sensitivity, repeatability, and discernment are three major issues in any classification problem. In this study, an electronic nose with an array of 32 sensors was used to classify a range of odorous substances. The collective time response of the sensor array was first partitioned into four time segments, using four smooth time-windowing functions. The dimension of the data associated with each time segment was then reduced by applying the Karhunen-Loéve (truncated) expansion (KLE). An ensemble of the reduced data patterns was then used to train a neural network (NN) using the Levenberg-Marquardt (LM) learning method. A genetic algorithm (GA)-based evolutionary computation method was used to devise the appropriate NN training parameters, as well as the effective database partitions/features. Finally, it was shown that a GA-supervised NN system (GANN) outperforms the NN-only classifier, for the classes of the odorants investigated in this study (fragrances, hog farm air, and soft beverages).
Assuntos
Algoritmos , Modelos Biológicos , Odorantes/análise , Processamento de Sinais Assistido por Computador , Olfato/genética , Evolução Biológica , Redes Neurais de Computação , Reconhecimento Automatizado de Padrão , Distribuição Aleatória , Reprodutibilidade dos Testes , Sensibilidade e Especificidade , Design de SoftwareRESUMO
Packaging materials have been implicated as a source for off-odors in pharmaceutical products. A new instrumentation method employing an array of conducting polymer gas sensors was used to identify the offending packaging components in the canister of a pharmaceutical inhalant. A case study is described in which tainted inhalers as well as elastomeric components of the canisters were 'sniffed' by the electronic nose. The electronic nose was able to differentiate between tainted and untainted canisters. Signal processing algorithms performed on the raw data from the sensors suggested that specific elastomeric components were responsible for the off-odor. A further experiment suggested that the propellant (Freon) extracted the odor from the elastomeric components as the medication was expelled from the canister. These data indicate that the electronic nose is a potential tool to solve odor problems in which human odor assessment is not feasible due to excess exposure to the medically active ingredient.