scholarly journals Deep learning guided image-based droplet sorting for on-demand selection and analysis of single cells and 3D cell cultures

Lab on a Chip ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 889-900 ◽  
Author(s):  
Vasileios Anagnostidis ◽  
Benjamin Sherlock ◽  
Jeremy Metz ◽  
Philip Mair ◽  
Florian Hollfelder ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Cell Cultures ◽  
Mammalian Cells ◽  
Single Cells ◽  
Bright Field ◽  
On Demand ◽  
3D Cell Cultures ◽  
Droplet Sorting ◽  
Demand Selection

To uncover the heterogeneity of cellular populations and multicellular constructs we show on-demand isolation of single mammalian cells and 3D cell cultures by coupling bright-field microdroplet imaging with real-time classification and sorting using convolutional neural networks.

A Covalently Crosslinked Ink for Multimaterials Drop‐on‐Demand 3D Bioprinting of 3D Cell Cultures

2021 ◽  
pp. 2100125
Author(s):  
Robert H. Utama ◽  
Vincent T. G. Tan ◽  
Kristel C. Tjandra ◽  
Andrew Sexton ◽  
Duyen H. T. Nguyen ◽  
...  
Keyword(s):  
Cell Cultures ◽  
3D Bioprinting ◽  
On Demand ◽  
Drop On Demand ◽  
3D Cell Cultures

scholarly journals Sparsity Increases Uncertainty Estimation in Deep Ensemble

Computers ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 54
Author(s):  
Uyanga Dorjsembe ◽  
Ju Hong Lee ◽  
Bumghi Choi ◽  
Jae Won Song
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Energy Efficient ◽  
Deep Neural Networks ◽  
Black Box ◽  
Uncertainty Estimation ◽  
Point Estimation ◽  
On Demand

Deep neural networks have achieved almost human-level results in various tasks and have become popular in the broad artificial intelligence domains. Uncertainty estimation is an on-demand task caused by the black-box point estimation behavior of deep learning. The deep ensemble provides increased accuracy and estimated uncertainty; however, linearly increasing the size makes the deep ensemble unfeasible for memory-intensive tasks. To address this problem, we used model pruning and quantization with a deep ensemble and analyzed the effect in the context of uncertainty metrics. We empirically showed that the ensemble members’ disagreement increases with pruning, making models sparser by zeroing irrelevant parameters. Increased disagreement im-plies increased uncertainty, which helps in making more robust predictions. Accordingly, an energy-efficient compressed deep ensemble is appropriate for memory-intensive and uncertainty-aware tasks.

scholarly journals INSCT: Integrating millions of single cells using batch-aware triplet neural networks

2020 ◽  
Author(s):  
Lukas M. Simon ◽  
Yin-Ying Wang ◽  
Zhongming Zhao
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Single Cells ◽  
Real Data ◽  
Cell Types ◽  
List Type ◽  
Desktop Computer ◽  
Deep Learning Algorithm ◽  
Computer Environment

AbstractEfficient integration of heterogeneous and increasingly large single cell RNA sequencing (scRNA-seq) data poses a major challenge for analysis and in particular, comprehensive atlasing efforts. Here, we developed a novel deep learning algorithm to overcome batch effects using batch-aware triplet neural networks, called INSCT (“Insight”). Using simulated and real data, we demonstrate that INSCT generates an embedding space which accurately integrates cells across experiments, platforms and species. Our benchmark comparisons with current state-of-the-art scRNA-seq integration methods revealed that INSCT outperforms competing methods in scalability while achieving comparable accuracies. Moreover, using INSCT in semi-supervised mode enables users to classify unlabeled cells by projecting them into a reference collection of annotated cells. To demonstrate scalability, we applied INSCT to integrate more than 2.6 million transcriptomes from four independent studies of mouse brains in less than 1.5 hours using less than 25 gigabytes of memory. This feature empowers researchers to perform atlasing scale data integration in a typical desktop computer environment. INSCT is freely available at https://github.com/lkmklsmn/insct.HighlightsINSCT accurately integrates multiple scRNA-seq datasetsINSCT accurately predicts cell types for an independent scRNA-seq datasetEfficient deep learning framework enables integration of millions of cells on a personal computer

Effects of carbamylcholine on chick embryo aggregate retina cell cultures

1988 ◽  
Vol 46 ◽  
pp. 350-351
Author(s):  
Glenn M. Cohen ◽  
Radharaman Ray
Keyword(s):  
Cell Cultures ◽  
Single Cells ◽  
Retinal Cell ◽  
Cell Aggregates ◽  
High Concentration ◽  
In Ovo ◽  
Sterile Culture ◽  
Retinal Tissue ◽  
Synaptic Junctions ◽  
And Control

Retinal,cell aggregates develop in culture in a pattern similar to the in ovo retina, forming neurites first and then synapses. In the present study, we continuously exposed chick retinal cell aggregates to a high concentration (1 mM) of carbamylcholine (carbachol), an acetylcholine (ACh) analog that resists hydrolysis by acetylcholinesterase (AChE). This situation is similar to organophosphorus anticholinesterase poisoning in which the ACh level is elevated at synaptic junctions due to inhibition of AChE, Our objective was to determine whether continuous carbachol exposure either damaged cholino- ceptive neurites, cell bodies, and synaptic elements of the aggregates or influenced (hastened or retarded) their development.The retinal tissue was isolated aseptically from 11 day embryonic White Leghorn chicks and then enzymatically (trypsin) and mechanically (trituration) dissociated into single cells. After washing the cells by repeated suspension and low (about 200 x G) centrifugation twice, aggregate cell cultures (about l0 cells/culture) were initiated in 1.5 ml medium (BME, GIBCO) in 35 mm sterile culture dishes and maintained as experimental (containing 10-3 M carbachol) and control specimens.

Use of Flexible Materials with a Novel Pressure Driven Equibiaxial Cell Stretching Device for Mechanical Stimulation of Single Mammalian Cells

2003 ◽  
Vol 773 ◽  
Author(s):  
James D. Kubicek ◽  
Stephanie Brelsford ◽  
Philip R. LeDuc
Keyword(s):  
Cell Fate ◽  
Mechanical Stimulation ◽  
Mammalian Cells ◽  
Cellular Response ◽  
Single Cells ◽  
Complex Nature ◽  
Cellular Behavior ◽  
Cell Stretching ◽  
Stimulation Of ◽  
Pressure Driven

AbstractMechanical stimulation of single cells has been shown to affect cellular behavior from the molecular scale to ultimate cell fate including apoptosis and proliferation. In this, the ability to control the spatiotemporal application of force on cells through their extracellular matrix connections is critical to understand the cellular response of mechanotransduction. Here, we develop and utilize a novel pressure-driven equibiaxial cell stretching device (PECS) combined with an elastomeric material to control specifically the mechanical stimulation on single cells. Cells were cultured on silicone membranes coated with molecular matrices and then a uniform pressure was introduced to the opposite surface of the membrane to stretch single cells equibiaxially. This allowed us to apply mechanical deformation to investigate the complex nature of cell shape and structure. These results will enhance our knowledge of cellular and molecular function as well as provide insights into fields including biomechanics, tissue engineering, and drug discovery.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

scholarly journals Deep convolutional neural networks for cardiovascular vulnerable plaque detection

2019 ◽  
Vol 277 ◽  
pp. 02024 ◽  
Author(s):  
Lincan Li ◽  
Tong Jia ◽  
Tianqi Meng ◽  
Yizhe Liu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Vulnerable Plaque ◽  
Recall Rate ◽  
Superior Performance ◽  
Learning Approaches ◽  
Deep Convolutional Neural Networks ◽  
Vulnerable Plaques ◽  
Plaque Detection

In this paper, an accurate two-stage deep learning method is proposed to detect vulnerable plaques in ultrasonic images of cardiovascular. Firstly, a Fully Convonutional Neural Network (FCN) named U-Net is used to segment the original Intravascular Optical Coherence Tomography (IVOCT) cardiovascular images. We experiment on different threshold values to find the best threshold for removing noise and background in the original images. Secondly, a modified Faster RCNN is adopted to do precise detection. The modified Faster R-CNN utilize six-scale anchors (122,162,322,642,1282,2562) instead of the conventional one scale or three scale approaches. First, we present three problems in cardiovascular vulnerable plaque diagnosis, then we demonstrate how our method solve these problems. The proposed method in this paper apply deep convolutional neural networks to the whole diagnostic procedure. Test results show the Recall rate, Precision rate, IoU (Intersection-over-Union) rate and Total score are 0.94, 0.885, 0.913 and 0.913 respectively, higher than the 1st team of CCCV2017 Cardiovascular OCT Vulnerable Plaque Detection Challenge. AP of the designed Faster RCNN is 83.4%, higher than conventional approaches which use one-scale or three-scale anchors. These results demonstrate the superior performance of our proposed method and the power of deep learning approaches in diagnose cardiovascular vulnerable plaques.

Sign in / Sign up

Export Citation Format

Share Document