Protein Subcellular Localization Prediction by Concatenation of Convolutional Blocks for Deep Features Extraction From Microscopic Images

Understanding where proteins are located within the cells is essential for proteomics research. Knowledge of protein subcellular location aids in early disease detection and drug targeting treatments. Incorrect localization can interfere with functioning leads to illnesses like cancer. Technological advances have enabled computational methods detect protein’s living organisms. The advent high-quality microscopy has led development image-based prediction algorithms localization. Confocal microscopy, which used by Human Protein Atlas (HPA), a great tool locating proteins. HPA database comprises millions images been procured using confocal annotated single as well multi-labels. However, multi-instance nature classification task low quality make an extremely difficult problem. There probably just few automatically predicting localization, most them limited single-label classification. Therefore, it important develop satisfactory automatic multi-label recognition system. aim this research design model based on deep learning system classifying HPA. Specifically, novel Convolutional Neural Network distribution across 28 compartments presented paper. Extensive experiments done proposed achieve best results multilabel With CNN framework F1-score 0.77 was achieved outperformed latest approaches.