China 
Africa 
Explore chapters and articles related to this topic
Applications of AI in Medical Science and Drug Development
Published in Mark Chang, Artificial Intelligence for Drug Development, Precision Medicine, and Healthcare, 2020
SVMs as a special case of kernel methods have been used in protein remote homology detection, protein structural classification, and DNA-binding protein prediction. SVM-based protein-fold recognition methods (Shamim et al., 2007, 2013; Damoulas and Girolami, 2008; Dong et al., 2009; Yang and Chen, 2011). The main difference among these SVM-based methods is their feature representation algorithms. Wei and Zou (2016) provided a review of the recent progress in machine learning-based methods for protein-fold recognition prior to 2011. Poorinmohammad et al. (2014) combined the SVM approach with pseudo amino acid composition descriptors to classify anti-HIV peptides, with a prediction accuracy of 96.76%.
EightyDVec: a method for protein sequence similarity analysis using physicochemical properties of amino acids
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2022
Ranjeet Kumar Rout, Saiyed Umer, Sabha Sheikh, Sanchit Sindhwani, Smitarani Pati
Fuzzy integral methods (Wei et al. 2014) for similarity comparison earmark similarity scores within close intervals (0, Altschul et al. 1990) for two selected sequences. Protein sequences can be delineated by employing transition probability matrix, fuzzy measures and fuzzy integrals. Distance matrix can be derived by identified fuzzy integral similarities and a phylogenetic tree can be constructed with the data. The Chou’s pseudo amino acid composition (He et al. 2010) can also be utilised for alignment free similarity comparison. Based on the acquired proportion of amino acids, the distance between the foremost and every other amino acid, and the organisation of the amino acids, a 60-dimensional feature vector is derived. The phylogenetic tree is contrived out of this matrix. This proved to be economic in terms of space and time complexity as compared to other alignment free methods.
A Novel Approach of Ensemble Methods Using the Stacked Generalization for High-dimensional Datasets
Published in IETE Journal of Research, 2022
Suvita Rani Sharma, Birmohan Singh, Manpreet Kaur
In 2006, Wang et al. proposed a stacking method to predict the types of protein-membrane based on pseudo-amino acid composition. They used support vector machine and instance base learner at the first level and used decision tree C45 at the second level of the stacking method [23].