Machine Learning Methods to Analyze Arabidopsis Thaliana Plant Root Growth
This work addresses a time-consuming and costly phenotypic analysis problem for biologists studying plant genetics, but it is incremental as it builds on existing SVM and ensemble methods.
The paper tackled the problem of classifying Arabidopsis Thaliana plants as mutated or wild types by analyzing root growth, using modified feature extraction based on velocity and acceleration and employing SVM kernels and hybrid neural network ensembles; the results showed that some SVM kernels outperformed neural network methods in classification rate and time efficiency.
One of the challenging problems in biology is to classify plants based on their reaction on genetic mutation. Arabidopsis Thaliana is a plant that is so interesting, because its genetic structure has some similarities with that of human beings. Biologists classify the type of this plant to mutated and not mutated (wild) types. Phenotypic analysis of these types is a time-consuming and costly effort by individuals. In this paper, we propose a modified feature extraction step by using velocity and acceleration of root growth. In the second step, for plant classification, we employed different Support Vector Machine (SVM) kernels and two hybrid systems of neural networks. Gated Negative Correlation Learning (GNCL) and Mixture of Negatively Correlated Experts (MNCE) are two ensemble methods based on complementary feature of classical classifiers; Mixture of Expert (ME) and Negative Correlation Learning (NCL). The hybrid systems conserve of advantages and decrease the effects of disadvantages of NCL and ME. Our Experimental shows that MNCE and GNCL improve the efficiency of classical classifiers, however, some SVM kernels function has better performance than classifiers based on neural network ensemble method. Moreover, kernels consume less time to obtain a classification rate.