Classification of Human Protein in Multiple Cells Microscopy Images Using燙NN
Source abstract
Abstract
The subcellular localization of human proteins is vital for understanding the structure of human cells. Proteins play a significant role within human cells, as many different groups of proteins are located in a specific location to perform a particular function. Understanding these functions will help in discovering many diseases and developing their treatments. The importance of imaging analysis techniques, specifically in proteomics research, is becoming more prevalent. Despite recent advances in deep learning techniques for analyzing microscopy images, classification models have faced critical challenges in achieving high performance. Most protein subcellular images have a significant class imbalance. We use oversampling and under sampling techniques in this research to overcome this issue. We have used a Convolutional Neural Network (CNN) model called GapNet-PL for the multi-label classification task on the Human Protein Atlas Classification (HPA) Dataset. Authors have found that the Parametric Rectified Linear Unit (PreLU) activation function is better than the Scaled Exponential Linear Unit (SeLU) activation function in the GapNet-PL model in most classification metrics. The results showed that the GapNet-PL model with the PReLU activation function achieved an area under the ROC curve (AUC) equal to 0.896, an F1 score of 0.541, and a recall of 0.473.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Cell Image Analysis Techniques · Digital Imaging for Blood Diseases · Machine Learning in Bioinformatics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (38)
Show source-provided references
1. Transcription factors and 3D genome conformation in cell-fate decisions
2. Human protein classification in microscope images using deep learning and Focal-Lovász loss
3. Critical evaluation of web-based prediction tools for human protein subcellular localization
4. An efficient method to identify essential proteins for different species by integrating protein subcellular localization information
5. Hybrid Xception model for human protein atlas image classification
6. A review on protein subcellular localization prediction using microscopic images
7. Deep learning in microscopy image analysis: A survey10.1109/TNNLS.2017.2766168 ↗
8. The Human Protein Atlas. Introduction of the human protein atlas, 2003. Available: https://www.proteinatlas.org/about#the_human_protein_atlas
9. Human-level protein localization with convolutional neural networks
10. HPA Team Kaggle. “Human protein atlas image classification,” 2018. Available: https://www.kaggle.com/c/human-protein-atlas-image-classification/data
11. The imaging tsunami: Computational opportunities and challenges10.1016/j.coisb.2017.07.011 ↗
12. Dermatologist-level classification of skin cancer with deep neural networks
13. Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists
14. Cervical cancer diagnosis using intelligent living behavior of artificial jellyfish optimized with artificial neural network10.1109/ACCESS.2022.3221451 ↗
15. Image analysis and machine learning for detecting malaria
16. Single-cell phenotype classification using deep convolutional neural networks10.1177/1087057116631284 ↗
17. A multi-scale convolutional neural network for phenotyping high-content cellular images
18. Prediction of human protein subcellular localization using deep learning10.1016/j.jpdc.2017.08.009 ↗
19. Deep learning-based classification of protein subcellular localization from immunohistochemistry images
20. Automated analysis of high-content microscopy data with deep learning10.15252/msb.20177551 ↗
21. Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks10.1186/s12859-021-04196-3 ↗
22. A. Mitra, “Multi-label classification of human protein subcellular locations from microscopy images using convolutional neural networks,” Masters Thesis, Bangladesh University of Engineering and Technology, Bangladesh, 2021.
23. Deep learning is combined with massive-scale citizen science to improve large-scale image classification
24. Convolutional neural network-based artificial intelligence for classification of protein localization patterns10.3390/biom11020264 ↗
25. Deep learning method to classification human protein Atlas
26. SIFLoc: A self-supervised pre-training method for enhancing the recognition of protein subcellular localization in immunofluorescence microscopic images10.1093/bib/bbab605 ↗
27. Imbalanced classification for protein subcellular localization with multilabel oversampling10.1093/bioinformatics/btac841 ↗
28. Target recognition based on CNN with LeakyReLU and PReLU activation functions
29. Cervical cancer diagnosis using very deep networks over different activation functions10.1109/ACCESS.2021.3067195 ↗
30. Probact: A probabilistic activation function for deep neural networks10.48550/arXiv.1905.10761 ↗
31. Learning from class-imbalanced data: Review of methods and applications10.1016/j.eswa.2016.12.035 ↗
32. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
33. A multiple expert approach to the class imbalance problem using inverse random under sampling
34. Oversampling based on data augmentation in convolutional neural network for silicon wafer defect classification
35. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification
36. S. Narkhede. “Understanding AUC-ROC curve,” 2018. Available: https://towardsdatascience.com/understanding-auc-roc-curve-68b2303cc9c5
37. TensorFlow: A system for large-scale machine learning
38. MLCM: Multi-label confusion matrix10.1109/ACCESS.2022.3151048 ↗