Academic Journal
Multiple Kernel Learning for Drug Discovery
| العنوان: | Multiple Kernel Learning for Drug Discovery |
|---|---|
| المؤلفون: | Pilkington, Nicholas C. V., Trotter, Matthew W. B., Holden, Sean B. |
| المصدر: | Molecular Informatics ; volume 31, issue 3-4, page 313-322 ; ISSN 1868-1743 1868-1751 |
| بيانات النشر: | Wiley |
| سنة النشر: | 2012 |
| المجموعة: | Wiley Online Library (Open Access Articles via Crossref) |
| الوصف: | The support vector machine (SVM) methodology has become a popular and well‐used component of present chemometric analysis. We assess a relatively recent development of the algorithm, multiple kernel learning (MKL), on published structure‐property relationship (SPR) data. The MKL algorithm learns a weighting across multiple kernel‐based representations of the data during supervised classifier creation and, thereby, may be used to describe the influence of distinct groups of structural descriptors upon a single structure–property classifier without explicitly omitting any of them. We observe a statistically significant performance improvement over a conventional, single kernel SVM on all three SPR data sets analysed. Furthermore, MKL output is observed to provide useful information regarding the relative influence of five distinct descriptor subsets present in each data set. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| DOI: | 10.1002/minf.201100146 |
| الاتاحة: | http://dx.doi.org/10.1002/minf.201100146 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fminf.201100146 https://onlinelibrary.wiley.com/doi/pdf/10.1002/minf.201100146 |
| Rights: | http://onlinelibrary.wiley.com/termsAndConditions#vor |
| رقم الانضمام: | edsbas.E5FC3DE5 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1002/minf.201100146 |
|---|