Subspace learning using structure learning and non-convex regularization: Hybrid technique with mushroom reproduction optimization in gene selection

• Published in: Computers in biology and medicine Vol. 164; p. 107309
• Main Authors: Moslemi, Amir, Bidar, Mahdi, Ahmadian, Arash
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.09.2023; Elsevier Limited
• Subjects: Accuracy; Breast; Chromosomes; Chronic obstructive pulmonary disease; Colon; Computer applications; Datasets; Decision analysis; Decision trees; Effectiveness; Feature selection; Gene selection; Genetic algorithms; Internal Medicine; Leukemia; Machine learning; Medical imaging; Mushrooms; Nonconvex; Nonnegative matrix factorization; Optimization; Optimization techniques; Other; Prostate; Regularization; Structure learning and mushroom reproduction; Feature selection; Gene selection; Nonnegative matrix factorization; optimization; Nonconvex; Structure learning and mushroom reproduction
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107309

Gene selection as a problem with high dimensions has drawn considerable attention in machine learning and computational biology over the past decade. In the field of gene selection in cancer datasets, different types of feature selection techniques in terms of strategy (filter, wrapper and embedded) and label information (supervised, unsupervised, and semi-supervised) have been developed. However, using hybrid feature selection can still improve the performance. In this paper, we propose a hybrid feature selection based on filter and wrapper strategies. In the filter-phase, we develop an unsupervised features selection based on non-convex regularized non-negative matrix factorization and structure learning, which we deem NCNMFSL. In the wrapper-phase, for the first time, mushroom reproduction optimization (MRO) is leveraged to obtain the most informative features subset. In this hybrid feature selection method, irrelevant features are filtered-out through NCNMFSL, and most discriminative features are selected by MRO. To show the effectiveness and proficiency of the proposed method, numerical experiments are conducted on Breast, Heart, Colon, Leukemia, Prostate, Tox-171 and GLI-85 benchmark datasets. SVM and decision tree classifiers are leveraged to analyze proposed technique and top accuracy are 0.97, 0.84, 0.98, 0.95, 0.98, 0.87 and 0.85 for Breast, Heart, Colon, Leukemia, Prostate, Tox-171 and GLI-85, respectively. The computational results show the effectiveness of the proposed method in comparison with state-of-art feature selection techniques. •Proposing hybrid feature selection based NMF and MRO.•Graph regularized NMF feature selection with non-convex constraint and MRO algorithm.•Proposing MRO for feature selection.