Deep Learning-Based Strategy For Macromolecules Classification with Imbalanced Data from Cellular Electron Cryotomography

Abstract

Deep learning model trained by imbalanced data may not work satisfactorily since it could be determined by major classes and thus may ignore the classes with small amount of data. In this paper, we apply deep learning based imbalanced data classification for the first time to cellular macromolecular complexes captured by Cryo-electron tomography (Cryo-ET). We adopt a range of strategies to cope with imbalanced data, including data sampling, bagging, boosting, Genetic Programming based method and. Particularly, inspired from Inception 3D network, we propose a multi-path CNN model combining focal loss and mixup on the Cryo-ET dataset to expand the dataset, where each path had its best performance corresponding to each type of data and let the network learn the combinations of the paths to improve the classification performance. In addition, extensive experiments have been conducted to show our proposed method is flexible enough to cope with different number of classes by adjusting the number of paths in our multi-path model. To our knowledge, this work is the first application of deep learning methods of dealing with imbalanced data to the internal tissue classification of cell macromolecular complexes, which opened up a new path for cell classification in the field of computational biology.

Energy management of distribution network with inverter‐based renewable virtual power plant considering voltage security index

“…This study uses GAMS software to code and simulate the presented scheme [132], in which the IPOPT solver [132] has been utilized to find a solution to the problem. This problem is a mathematical model, including objective function and constraints [133][134][135][136][137][138][139][140][141][142].…”

Survey on Highly Imbalanced Multi-class Data

“…Over-fitting, outlier influence, revision on iteration ending point, and lack of transparency owing to complexity are some of the flaws of this technique, which optimize the cost function. [96], [118]- [120], [121].…”

Using firefly algorithm to optimally size a hybrid renewable energy system constrained by battery degradation and considering uncertainties of power sources and loads

“…Now, if the RESs were able to supply the load and also their output generation is greater than the demand, the excess power is stored in the storage device [ [49] , [50] , [51] , [52] , [53] ] (battery). Conversely, if RESs are not able to sufficiently meet the load, and in other words, their generation is smaller than the demand, the surplus power consumption is met by the storage device [ [54] , [55] , [56] , [57] , [58] , [59] , [60] , [61] , [62] , [63] ]. Finally, the step-by-step process of this strategy is described as follows [ 64 ]: Step 1 .…”