Floating-window projective separator (FLOWPS): A data trimming tool for support vector machines (SVM) to improve robustness of the classifier
Tkachev V., Sorokin M. I., Mescheryakov A., Simonov A., Garazha A., Buzdin A. A., Muchnik I., Borisov N. M.
Frontiers in genetics
Vol.10, IssueJAN, Num.717
Опубликовано: 2019
Тип ресурса: Статья
DOI:10.3389/fgene.2018.00717
Аннотация:
Here, we propose a heuristic technique of data trimming for SVM termed FLOating Window Projective Separator (FloWPS), tailored for personalized predictions based on molecular data. This procedure can operate with high throughput genetic datasets like gene expression or mutation profiles. Its application prevents SVM from extrapolation by excluding non-informative features. FloWPS requires training on the data for the individuals with known clinical outcomes to create a clinically relevant classifier. The genetic profiles linked with the outcomes are broken as usual into the training and validation datasets. The unique property of FloWPS is that irrelevant features in validation dataset that don’t have significant number of neighboring hits in the training dataset are removed from further analyses. Next, similarly to the k nearest neighbors (kNN) method, for each point of a validation dataset, FloWPS takes into account only the proximal points of the training dataset. Thus, for every po
Ключевые слова:
Bioinformatics; Gene expression; Machine learning; Oncology; Personalized medicine; Support vector machines
adult; article; bioinformatics; cancer chemotherapy; cancer patient; clinical outcome; female; gene expression; genetic profile; human; k nearest neighbor; major clinical study; male; mutation; oncology; outcome assessment; personalized medicine; prediction; support vector machine; validation process
Язык текста: Английский
ISSN: 1664-8021
Tkachev V.
Sorokin M. I. Maksim Igorevich 1989-
Mescheryakov A.
Simonov A.
Garazha A.
Buzdin A. A. Anton Aleksandrovich 1977-
Muchnik I.
Borisov N. M. Nikolay Mikhaylovich 1973-
Ткачев В.
Сорокин М. И. Максим Игоревич 1989-
Месчеряков А.
Симонов А.
Гаража А.
Буздин А. А. Антон Александрович 1977-
Мучник И.
Борисов Н. М. Николай Михайлович 1973-
Floating-window projective separator (FLOWPS): A data trimming tool for support vector machines (SVM) to improve robustness of the classifier
Текст визуальный непосредственный
Frontiers in genetics
Vol.10, IssueJAN Num.717
2019
Статья
Bioinformatics Gene expression Machine learning Oncology Personalized medicine Support vector machines
adult article bioinformatics cancer chemotherapy cancer patient clinical outcome female gene expression genetic profile human k nearest neighbor major clinical study male mutation oncology outcome assessment personalized medicine prediction support vector machine validation process
Here, we propose a heuristic technique of data trimming for SVM termed FLOating Window Projective Separator (FloWPS), tailored for personalized predictions based on molecular data. This procedure can operate with high throughput genetic datasets like gene expression or mutation profiles. Its application prevents SVM from extrapolation by excluding non-informative features. FloWPS requires training on the data for the individuals with known clinical outcomes to create a clinically relevant classifier. The genetic profiles linked with the outcomes are broken as usual into the training and validation datasets. The unique property of FloWPS is that irrelevant features in validation dataset that don’t have significant number of neighboring hits in the training dataset are removed from further analyses. Next, similarly to the k nearest neighbors (kNN) method, for each point of a validation dataset, FloWPS takes into account only the proximal points of the training dataset. Thus, for every po