scholarly journals Convolutional Neural Network Can Recognize Drug Resistance of Single Cancer Cells

2020 ◽  
Vol 21 (9) ◽  
pp. 3166
Author(s):  
Kiminori Yanagisawa ◽  
Masayasu Toratani ◽  
Ayumu Asai ◽  
Masamitsu Konno ◽  
Hirohiko Niioka ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Single Cell ◽  
Tumor Cells ◽  
Antitumor Drugs ◽  
Single Cell Level ◽  
Cell Level ◽  
Single Cancer ◽  
Deep Learning Model

It is known that single or isolated tumor cells enter cancer patients’ circulatory systems. These circulating tumor cells (CTCs) are thought to be an effective tool for diagnosing cancer malignancy. However, handling CTC samples and evaluating CTC sequence analysis results are challenging. Recently, the convolutional neural network (CNN) model, a type of deep learning model, has been increasingly adopted for medical image analyses. However, it is controversial whether cell characteristics can be identified at the single-cell level by using machine learning methods. This study intends to verify whether an AI system could classify the sensitivity of anticancer drugs, based on cell morphology during culture. We constructed a CNN based on the VGG16 model that could predict the efficiency of antitumor drugs at the single-cell level. The machine learning revealed that our model could identify the effects of antitumor drugs with ~0.80 accuracies. Our results show that, in the future, realizing precision medicine to identify effective antitumor drugs for individual patients may be possible by extracting CTCs from blood and performing classification by using an AI system.

scholarly journals PIKE-R2P: Protein–protein interaction network-based knowledge embedding with graph neural network for single-cell RNA to protein prediction

2021 ◽  
Vol 22 (S6) ◽  
Author(s):  
Xinnan Dai ◽  
Fan Xu ◽  
Shike Wang ◽  
Piyushkumar A. Mundra ◽  
Jie Zheng
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Single Cell ◽  
Prior Knowledge ◽  
Protein Interactions ◽  
Interaction Network ◽  
Superior Performance ◽  
Single Cell Level ◽  
Cell Level ◽  
Protein Prediction

Abstract Background Recent advances in simultaneous measurement of RNA and protein abundances at single-cell level provide a unique opportunity to predict protein abundance from scRNA-seq data using machine learning models. However, existing machine learning methods have not considered relationship among the proteins sufficiently. Results We formulate this task in a multi-label prediction framework where multiple proteins are linked to each other at the single-cell level. Then, we propose a novel method for single-cell RNA to protein prediction named PIKE-R2P, which incorporates protein–protein interactions (PPI) and prior knowledge embedding into a graph neural network. Compared with existing methods, PIKE-R2P could significantly improve prediction performance in terms of smaller errors and higher correlations with the gold standard measurements. Conclusion The superior performance of PIKE-R2P indicates that adding the prior knowledge of PPI to graph neural networks can be a powerful strategy for cross-modality prediction of protein abundances at the single-cell level.

scholarly journals Heterogeneity of PIK3CA mutational status at the single cell level in circulating tumor cells from metastatic breast cancer patients

2014 ◽  
Vol 9 (4) ◽  
pp. 749-757 ◽  
Author(s):  
Marta Pestrin ◽  
Francesca Salvianti ◽  
Francesca Galardi ◽  
Francesca De Luca ◽  
Natalie Turner ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Metastatic Breast Cancer ◽  
Single Cell ◽  
Cancer Patients ◽  
Tumor Cells ◽  
Metastatic Breast ◽  
Single Cell Level ◽  
Breast Cancer Patients ◽  
Cell Level ◽  
Mutational Status

scholarly journals Combined Molecular Genetic and Cytogenetic Analysis from Single Cells after Isothermal Whole-Genome Amplification

2011 ◽  
Vol 57 (7) ◽  
pp. 1032-1041 ◽  
Author(s):  
Thomas Kroneis ◽  
Jochen B Geigl ◽  
Amin El-Heliebi ◽  
Martina Auer ◽  
Peter Ulz ◽  
...  
Keyword(s):  
Single Cell ◽  
Tumor Cells ◽  
Whole Genome Amplification ◽  
Single Cells ◽  
Molecular Genetic ◽  
Target Cells ◽  
Whole Genome ◽  
Single Cell Level ◽  
Cell Level ◽  
Genome Amplification

BACKGROUND Analysis of chromosomal aberrations or single-gene disorders from rare fetal cells circulating in the blood of pregnant women requires verification of the cells' genomic identity. We have developed a method enabling multiple analyses at the single-cell level that combines verification of the genomic identity of microchimeric cells with molecular genetic and cytogenetic diagnosis. METHODS We used a model system of peripheral blood mononuclear cells spiked with a colon adenocarcinoma cell line and immunofluorescence staining for cytokeratin in combination with DNA staining with the nuclear dye TO-PRO-3 in a preliminary study to define candidate microchimeric (tumor) cells in Cytospin preparations. After laser microdissection, we performed low-volume on-chip isothermal whole-genome amplification (iWGA) of single and pooled cells. RESULTS DNA fingerprint analysis of iWGA aliquots permitted successful identification of all analyzed candidate microchimeric cell preparations (6 samples of pooled cells, 7 samples of single cells). Sequencing of 3 single-nucleotide polymorphisms was successful at the single-cell level for 20 of 32 allelic loci. Metaphase comparative genomic hybridization (mCGH) with iWGA products of single cells showed the gains and losses known to be present in the genomic DNA of the target cells. CONCLUSIONS This method may be instrumental in cell-based noninvasive prenatal diagnosis. Furthermore, the possibility to perform mCGH with amplified DNA from single cells offers a perspective for the analysis of nonmicrochimeric rare cells exhibiting genomic alterations, such as circulating tumor cells.

Co-detection of ALDH1A1, ABCG2, ALCAM and CD133 in three A549 subpopulations at the single cell level by one-step digital RT-PCR

2018 ◽  
Vol 10 (6) ◽  
pp. 364-369 ◽  
Author(s):  
Yanan Xu ◽  
Jiumei Hu ◽  
Qiangyuan Zhu ◽  
Qi Song ◽  
Ying Mu
Keyword(s):  
Stem Cell ◽  
Cancer Stem Cell ◽  
Single Cell ◽  
Single Cell Level ◽  
Cell Analysis ◽  
Rt Pcr ◽  
Cell Level ◽  
One Step ◽  
Single Cancer ◽  
Co Detection

Single cancer stem cell analysis of four biomarker genes by microfluidic one-step digital RT-PCR.

scholarly journals Development of an optimal protocol for molecular profiling of tumor cells in pleural effusions at single‐cell level

2021 ◽  
Author(s):  
Ikuko Takeda Nakamura ◽  
Masachika Ikegami ◽  
Nobuhiko Hasegawa ◽  
Takuo Hayashi ◽  
Toshihide Ueno ◽  
...  
Keyword(s):  
Single Cell ◽  
Tumor Cells ◽  
Molecular Profiling ◽  
Single Cell Level ◽  
Pleural Effusions ◽  
Cell Level ◽  
Optimal Protocol

scholarly journals Identification Method of Wheat Cultivars by Using a Convolutional Neural Network Combined with Images of Multiple Growth Periods of Wheat

Symmetry ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 2012
Author(s):  
Jiameng Gao ◽  
Chengzhong Liu ◽  
Junying Han ◽  
Qinglin Lu ◽  
Hengxing Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Wheat Variety ◽  
Learning Model ◽  
Wheat Cultivars ◽  
Learning Methods ◽  
Wheat Varieties ◽  
Deep Learning Model

Wheat is a very important food crop for mankind. Many new varieties are bred every year. The accurate judgment of wheat varieties can promote the development of the wheat industry and the protection of breeding property rights. Although gene analysis technology can be used to accurately determine wheat varieties, it is costly, time-consuming, and inconvenient. Traditional machine learning methods can significantly reduce the cost and time of wheat cultivars identification, but the accuracy is not high. In recent years, the relatively popular deep learning methods have further improved the accuracy on the basis of traditional machine learning, whereas it is quite difficult to continue to improve the identification accuracy after the convergence of the deep learning model. Based on the ResNet and SENet models, this paper draws on the idea of the bagging-based ensemble estimator algorithm, and proposes a deep learning model for wheat classification, CMPNet, which is coupled with the tillering period, flowering period, and seed image. This convolutional neural network (CNN) model has a symmetrical structure along the direction of the tensor flow. The model uses collected images of different types of wheat in multiple growth periods. First, it uses the transfer learning method of the ResNet-50, SE-ResNet, and SE-ResNeXt models, and then trains the collected images of 30 kinds of wheat in different growth periods. It then uses the concat layer to connect the output layers of the three models, and finally obtains the wheat classification results through the softmax function. The accuracy of wheat variety identification increased from 92.07% at the seed stage, 95.16% at the tillering stage, and 97.38% at the flowering stage to 99.51%. The model’s single inference time was only 0.0212 s. The model not only significantly improves the classification accuracy of wheat varieties, but also achieves low cost and high efficiency, which makes it a novel and important technology reference for wheat producers, managers, and law enforcement supervisors in the practice of wheat production.

Sign in / Sign up

Export Citation Format

Share Document