Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography

Gao, Shan; Ren, Han; Zeng, Xiangrui; Li, Yong; Xu, Min; Zhang, Fa

doi:10.1109/tcbb.2021.3065986

Cited by 6 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, many times, the test fails to detect the disease in case of a newly evolved coronavirus strain before extracting the new virus's DNA sequence, potentially delaying testing [9]. Today, deep learning (DL) has been used widely to develop solutions for aiding the visually impaired [10], solving a 50-year-old grand protein folding challenge in biology [11], analyzing macromolecules from Cellular Electron Cryo-Tomography (CECT) [12], [13], developing complex intrusion-based detection systems [14]- [18], enabling IoT based systems [19], [20], etc. DL-based computer-aided diagnosis (CAD) has drawn immense attention in recent years for its capability to enhance diagnosis performance and elucidate complex clinical tasks.…”

Section: A Backgroundmentioning

confidence: 99%

Deep-Precognitive Diagnosis: Preventing Future Pandemics by Novel Disease Detection With Biologically-Inspired Conv-Fuzzy Network

et al. 2022

Self Cite

View full text Add to dashboard Cite

Deep learning-based Computer-Aided Diagnosis has gained immense attention in recent years due to its capability to enhance diagnostic performance and elucidate complex clinical tasks. However, conventional supervised deep learning models are incapable of recognizing novel diseases that do not exist in the training dataset. Automated early-stage detection of novel infectious diseases can be vital in controlling its rapid spread. Moreover, development of a conventional CAD model is only possible after disease outbreak and datasets become available for training (viz. COVID-19 outbreak). Since novel diseases are unknown and cannot be included in training data, recognizing them is a challenge in existing supervised deep learning models. Even after data becomes available, recognizing new classes with conventional models requires a complete extensive re-training. The present study is the first to report this problem and propose a novel solution to it. In this study, we propose a new class of CAD models i.e., Deep-Precognitive Diagnosis, wherein artificial agents are enabled to identify unknown diseases that have potential to cause pandemic in future. A de novo biologically-inspired Conv-Fuzzy network is developed. Experimental results show that the model trained to classify chest X-ray scans into normal and bacterial pneumonia detected a novel disease during testing, unseen by it in the training sample and confirmed to be COVID-19 later. The model is also tested on SARS-CoV-1 and MERS-CoV samples as unseen diseases and achieved state-of-the-art accuracy. The proposed model eliminates the need for model re-training by creating a new class in real-time for the detected novel disease thus classifying it on all subsequent occurrences. Second, the model addresses the challenge of limited labeled data availability, which renders most supervised learning techniques ineffective and establishes that modified fuzzy classifiers can achieve high accuracy on image classification tasks.

show abstract

Section: A Backgroundmentioning

confidence: 99%

Deep-Precognitive Diagnosis: Preventing Future Pandemics by Novel Disease Detection With Biologically-Inspired Conv-Fuzzy Network

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In principle, the cellular tomograms imaged by cryo-ET can capture millions of macromolecules with diverse structures. To recover structures of macromolecules, diverse macromolecules in tomograms should be detected ( Melia and Bharat, 2018 ), classified ( Gao et al, 2021 ), aligned and averaged ( Zeng et al, 2021 ), and called subtomogram averaging (STA) ( Bharat and Scheres, 2016 ). Macromolecule classification aims to classify diverse macromolecules into structurally homogeneous subsets accurately.…”

Section: Introductionmentioning

confidence: 99%

FSCC: Few-Shot Learning for Macromolecule Classification Based on Contrastive Learning and Distribution Calibration in Cryo-Electron Tomography

Gao

Zeng

et al. 2022

Front. Mol. Biosci.

View full text Add to dashboard Cite

Cryo-electron tomography (Cryo-ET) is an emerging technology for three-dimensional (3D) visualization of macromolecular structures in the near-native state. To recover structures of macromolecules, millions of diverse macromolecules captured in tomograms should be accurately classified into structurally homogeneous subsets. Although existing supervised deep learning–based methods have improved classification accuracy, such trained models have limited ability to classify novel macromolecules that are unseen in the training stage. To adapt the trained model to the macromolecule classification of a novel class, massive labeled macromolecules of the novel class are needed. However, data labeling is very time-consuming and labor-intensive. In this work, we propose a novel few-shot learning method for the classification of novel macromolecules (named FSCC). A two-stage training strategy is designed in FSCC to enhance the generalization ability of the model to novel macromolecules. First, FSCC uses contrastive learning to pre-train the model on a sufficient number of labeled macromolecules. Second, FSCC uses distribution calibration to re-train the classifier, enabling the model to classify macromolecules of novel classes (unseen class in the pre-training). Distribution calibration transfers learned knowledge in the pre-training stage to novel macromolecules with limited labeled macromolecules of novel class. Experiments were performed on both synthetic and real datasets. On the synthetic datasets, compared with the state-of-the-art (SOTA) method based on supervised deep learning, FSCC achieves competitive performance. To achieve such performance, FSCC only needs five labeled macromolecules per novel class. However, the SOTA method needs 1100 ∼ 1500 labeled macromolecules per novel class. On the real datasets, FSCC improves the accuracy by 5% ∼ 16% when compared to the baseline model. These demonstrate good generalization ability of contrastive learning and calibration distribution to classify novel macromolecules with very few labeled macromolecules.

show abstract

PickerOptimizer: A Deep Learning-Based Particle Optimizer for Cryo-Electron Microscopy Particle-Picking Algorithms

Chen

Gao

et al. 2021

Bioinformatics Research and Applications

View full text Add to dashboard Cite

Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography

Cited by 6 publications

References 28 publications

Deep-Precognitive Diagnosis: Preventing Future Pandemics by Novel Disease Detection With Biologically-Inspired Conv-Fuzzy Network

Deep-Precognitive Diagnosis: Preventing Future Pandemics by Novel Disease Detection With Biologically-Inspired Conv-Fuzzy Network

FSCC: Few-Shot Learning for Macromolecule Classification Based on Contrastive Learning and Distribution Calibration in Cryo-Electron Tomography

PickerOptimizer: A Deep Learning-Based Particle Optimizer for Cryo-Electron Microscopy Particle-Picking Algorithms

Contact Info

Product

Resources

About