Optimization of supervised self-organizing maps with genetic algorithms for classification electrophoretic profiles

Abstract

Standard electrophoresis methods were used to classify analyzed proteins in cerebrospinal fluid from patients with multiple sclerosis. Disc electrophoresis was carried out on polyacrylamide gels for the detection of oligoclonal IgG bands in cerebrospinal fluid, mainly from patients with multiple sclerosis and other central nervous system dysfunctions. ImageMaster 1D Elite and Gel-Pro specialized software packages were used for fast accurate image and gel analysis. The classification model was based on supervised self-organizing maps. In order to perform modeling in an automated manner, genetic algorithms were used. Using this approach and a data set composed of 69 samples, we developed models based on supervised self-organizing maps which were able to correctly classify 83% of the samples in the data set used for external validation.Keywords: disc electrophoresis; cerebrospinal fluid; protein analysis; supervised self-organizing maps ОПТИМИЗАЦИЈА НА САМООРГАНИЗИРАНИ МАПИ ТРЕНИРАНИ СО НАДГЛЕДУВАНО УЧЕЊЕ СО ГЕНЕТСКИ АЛГОРИТМИ ЗА КЛАСИФИКАЦИЈА НА ЕЛЕКТРОФОРЕТСКИ ПРОФИЛИСтандардна електрофоретска метода беше користена за анализа на протеините во церебро-спиналниот ликвор кај пациенти претежно со мултипла склероза, но и со други заболувања на централниот нервен систем, со намера да се изврши класификација на експерименталните резул-тати. За оваа намена беше користена диск-електрофорезата за детекција на олигоклонални IgG ленти во електрофореграмите добиени со гел-електрофореза. Анализата на електрофореграмите беше направена со специјализираниот софтвер ImageMaster 1D Elite и софтверскиот пакет GelPro. За класификација на добиените експериментални резултати беа користени самоорганизирани мапи тренирани со надгледувано учење. За да се автоматизира моделирањето, беше користен генет-скиот алгоритам. Користејќи го овој пристап и податоците од 69 примероци за анализа, добивме модели базирани на самоорганизирани мапи, со кои може коректно да се класифицираат 83 % од податоците користени за екстерна валидација.Клучни зборови: диск-електрофореза; церебрален флуид; анализа на протеини; самоорганизирани мапи тренирани со надгледувано учење

Classification of urban soils for forensic purposes using supervised self‐organizing maps

“…GAs have been proven as an effective optimization tool 46–48 allowing relatively fast convergence without need of running every permutation of variables. In chemistry literature, the theory and use of GAs as a variable selection tool has been reported several times, 49–55 but also it has been used for automated optimization of different parameters of the models 39–45 . Here, only a brief summary of the main ideas of the GA algorithm as well as the procedure used in this work is explained.…”

“…In chemistry literature, the theory and use of GAs as a variable selection tool has been reported several times, [49][50][51][52][53][54][55] but also it has been used for automated optimization of different parameters of the models. [39][40][41][42][43][44][45] Here, only a brief summary of the main ideas of the GA algorithm as well as the procedure used in this work is explained.…”

“…This artificial neural network algorithm has previously been used for the analysis of IR spectra 37,38 . This algorithm together with some of its variants has been previously used in our laboratory 39–45 . To the best of our knowledge, SOMs have not been used previously for forensic purposes.…”

“…37,38 This algorithm together with some of its variants has been previously used in our laboratory. [39][40][41][42][43][44][45] To the best of our knowledge, SOMs have not been used previously for forensic purposes. The optimization of the parameters of the SOM as well as for the selection of the parts of the IR spectra that are most suitable for classification purposes, in this study, were performed in automated manner using genetic algorithm (GA).…”