Imbalanced classification for protein subcellular localisation with multilabel oversampling-Reference-Cited by-同舟云学术

Imbalanced classification for protein subcellular localisation with multilabel oversampling

Published:2022-09-15 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

Rana Priyanka^ORCID,Sowmya Arcot,Meijering Erik,Song Yang

Abstract

AbstractMotivationSubcellular localisation of human proteins is essential to comprehend their functions and roles in physiological processes, which in turn helps in diagnostic and prognostic studies of pathological conditions and impacts clinical decision making. Since proteins reside at multiple locations at the same time and few subcellular locations host far more proteins than other locations, the computational task for their subcellular localisation is to train a multilabel classifier while handling data imbalance. In imbalanced data, minority classes are underrepresented, thus leading to a heavy bias towards the majority classes and the degradation of predictive capability for the minority classes. Furthermore, data imbalance in multilabel settings is an even more complex problem due to the coexistence of majority and minority classes.ResultsOur studies reveal that based on the extent of concurrence of majority and minority classes, oversampling of minority samples through appropriate data augmentation techniques holds promising scope for boosting the classification performance for the minority classes. We measured the magnitude of data imbalance per class and the concurrence of majority and minority classes in the dataset. Based on the obtained values, we identified minority and medium classes, and a new oversampling method is proposed that includes nonlinear mixup, geometric and colour transformations for data augmentation and a sampling approach to prepare minibatches. Performance evaluation on the Human Protein Atlas Kaggle challenge dataset shows that the proposed method is capable of achieving better predictions for minority classes than existing methods.AvailabilityData used in this study is available at https://www.kaggle.com/competitions/human-protein-atlas-image-classification/data.Contactyang.song1@unsw.edu.auSupplementary informationSupplementary data are available at Bioinformatics online.

Publisher

Cold Spring Harbor Laboratory

Reference37 articles.

1. Aggarwal, S. et al. (2022). A convolutional neural network-based framework for classification of protein localization using confocal microscopy images. IEEE Access.

2. Arcamone, F. et al. (2021). Prediction of protein subcellular localization from microscopic images via few-shot learning. In International Symposium on Bioinformatics Research and Applications, pages 241–253. Springer.

3. Berman, M. et al. (2018). The Lovász-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 4413–4421.

4. Charte, F. et al. (2013). A first approach to deal with imbalance in multi-label datasets. In International Conference on Hybrid Artificial Intelligence Systems, pages 150–160. Springer.

5. Charte, F. et al. (2014). Concurrence among imbalanced labels and its influence on multilabel resampling algorithms. In International Conference on Hybrid Artificial Intelligence Systems, pages 110–121. Springer.