scholarly journals A deep learning framework for quantitative analysis of actin microridges

2021 ◽  
Author(s):  
Rajasekaran Bhavna ◽  
Mahendra Sonawane
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Persistence Length ◽  
Spatiotemporal Analysis ◽  
Apical Surface ◽  
Learning Framework ◽  
Segmentation Strategy ◽  
Epithelial Development ◽  
Segmented Images ◽  
Genetic Perturbations

Microridges are evolutionarily conserved actin-rich protrusions present on the apical surface of the squamous epithelial cells. In zebrafish epidermal cells, microridges form self-evolving patterns due to the underlying actomyosin network dynamics. However, their morphological and dynamic characteristics have remained poorly understood owing to lack of automated segmentation methods. We achieved ~97% pixel-level accuracy with the deep learning microridge segmentation strategy enabling quantitative insights into their bio-physical-mechanical characteristics. From the segmented images, we estimated an effective microridge persistence length as ~0.61μm. We discovered the presence of mechanical fluctuations and found relatively greater stresses stored within patterns of yolk than flank, indicating distinct regulation of their actomyosin networks. Furthermore, spontaneous formations and positional fluctuations of actin clusters within microridge influenced pattern rearrangements over short length/time-scales. Our framework allows large-scale spatiotemporal analysis of microridges during epithelial development and probing of their responses to chemical and genetic perturbations to unravel the underlying patterning mechanisms.

scholarly journals Mol-BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Juncai Li ◽  
Xiaofei Jiang
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Large Scale ◽  
Molecular Data ◽  
Molecular Property ◽  
Property Prediction ◽  
Learning Framework ◽  
Learning Techniques ◽  
Potential Benefits ◽  
Current Sequence

Molecular property prediction is an essential task in drug discovery. Most computational approaches with deep learning techniques either focus on designing novel molecular representation or combining with some advanced models together. However, researchers pay fewer attention to the potential benefits in massive unlabeled molecular data (e.g., ZINC). This task becomes increasingly challenging owing to the limitation of the scale of labeled data. Motivated by the recent advancements of pretrained models in natural language processing, the drug molecule can be naturally viewed as language to some extent. In this paper, we investigate how to develop the pretrained model BERT to extract useful molecular substructure information for molecular property prediction. We present a novel end-to-end deep learning framework, named Mol-BERT, that combines an effective molecular representation with pretrained BERT model tailored for molecular property prediction. Specifically, a large-scale prediction BERT model is pretrained to generate the embedding of molecular substructures, by using four million unlabeled drug SMILES (i.e., ZINC 15 and ChEMBL 27). Then, the pretrained BERT model can be fine-tuned on various molecular property prediction tasks. To examine the performance of our proposed Mol-BERT, we conduct several experiments on 4 widely used molecular datasets. In comparison to the traditional and state-of-the-art baselines, the results illustrate that our proposed Mol-BERT can outperform the current sequence-based methods and achieve at least 2% improvement on ROC-AUC score on Tox21, SIDER, and ClinTox dataset.

scholarly journals Progressive System: A Deep-Learning Framework for Real-Time Data in Industrial Production

Processes ◽  
2020 ◽  
Vol 8 (6) ◽  
pp. 649
Author(s):  
Yifeng Liu ◽  
Wei Zhang ◽  
Wenhao Du
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Large Scale ◽  
Quality Data ◽  
Time Data ◽  
High Quality ◽  
Real Time System ◽  
High Quality Data ◽  
Learning Framework ◽  
Data Accumulation

Deep learning based on a large number of high-quality data plays an important role in many industries. However, deep learning is hard to directly embed in the real-time system, because the data accumulation of the system depends on real-time acquisitions. However, the analysis tasks of such systems need to be carried out in real time, which makes it impossible to complete the analysis tasks by accumulating data for a long time. In order to solve the problems of high-quality data accumulation, high timeliness of the data analysis, and difficulty in embedding deep-learning algorithms directly in real-time systems, this paper proposes a new progressive deep-learning framework and conducts experiments on image recognition. The experimental results show that the proposed framework is effective and performs well and can reach a conclusion similar to the deep-learning framework based on large-scale data.

scholarly journals DeepT3 2.0: improving type III secreted effector predictions by an integrative deep learning framework

2021 ◽  
Vol 3 (4) ◽  
Author(s):  
Runyu Jing ◽  
Tingke Wen ◽  
Chengxiang Liao ◽  
Li Xue ◽  
Fengjuan Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Amino Acid Sequences ◽  
Secretion Systems ◽  
Gram Negative ◽  
Type Iii ◽  
Learning Framework ◽  
Genome Wide ◽  
Type Iii Secretion Systems ◽  
Animal Pathogens

Abstract Type III secretion systems (T3SSs) are bacterial membrane-embedded nanomachines that allow a number of humans, plant and animal pathogens to inject virulence factors directly into the cytoplasm of eukaryotic cells. Export of effectors through T3SSs is critical for motility and virulence of most Gram-negative pathogens. Current computational methods can predict type III secreted effectors (T3SEs) from amino acid sequences, but due to algorithmic constraints, reliable and large-scale prediction of T3SEs in Gram-negative bacteria remains a challenge. Here, we present DeepT3 2.0 (http://advintbioinforlab.com/deept3/), a novel web server that integrates different deep learning models for genome-wide predicting T3SEs from a bacterium of interest. DeepT3 2.0 combines various deep learning architectures including convolutional, recurrent, convolutional-recurrent and multilayer neural networks to learn N-terminal representations of proteins specifically for T3SE prediction. Outcomes from the different models are processed and integrated for discriminating T3SEs and non-T3SEs. Because it leverages diverse models and an integrative deep learning framework, DeepT3 2.0 outperforms existing methods in validation datasets. In addition, the features learned from networks are analyzed and visualized to explain how models make their predictions. We propose DeepT3 2.0 as an integrated and accurate tool for the discovery of T3SEs.

ORCA-SLANG: An Automatic Multi-Stage Semi-Supervised Deep Learning Framework for Large-Scale Killer Whale Call Type Identification

2021 ◽  
Author(s):  
Christian Bergler ◽  
Manuel Schmitt ◽  
Andreas Maier ◽  
Helena Symonds ◽  
Paul Spong ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Killer Whale ◽  
Call Type ◽  
Learning Framework ◽  
Multi Stage

scholarly journals Large-Scale Detection and Categorization of Oil Spills from SAR Images with Deep Learning

2020 ◽  
Vol 12 (14) ◽  
pp. 2260 ◽  
Author(s):  
Filippo Maria Bianchi ◽  
Martine M. Espeseth ◽  
Njål Borch
Keyword(s):  
Deep Learning ◽  
Oil Spill ◽  
Large Scale ◽  
Oil Spills ◽  
Sar Images ◽  
Oil Spill Detection ◽  
Learning Framework ◽  
Large Scale Data ◽  
Human Operators ◽  
Scale Detection

We propose a deep-learning framework to detect and categorize oil spills in synthetic aperture radar (SAR) images at a large scale. Through a carefully designed neural network model for image segmentation trained on an extensive dataset, we obtain state-of-the-art performance in oil spill detection, achieving results that are comparable to results produced by human operators. We also introduce a classification task, which is novel in the context of oil spill detection in SAR. Specifically, after being detected, each oil spill is also classified according to different categories of its shape and texture characteristics. The classification results provide valuable insights for improving the design of services for oil spill monitoring by world-leading providers. Finally, we present our operational pipeline and a visualization tool for large-scale data, which allows detection and analysis of the historical occurrence of oil spills worldwide.

scholarly journals Learning to Design From Humans: Imitating Human Designers Through Deep Learning

2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Ayush Raina ◽  
Christopher McComb ◽  
Jonathan Cagan
Keyword(s):  
Deep Learning ◽  
Problem Solving ◽  
Large Scale ◽  
Performance Metrics ◽  
Design Strategies ◽  
Learning Framework ◽  
Human Data ◽  
Design Generation ◽  
And Performance ◽  
Computational Resources

Abstract Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large-scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem-solving team can be created. This paper presents an approach to extract human design strategies and implicit rules, purely from historical human data, and use that for design generation. A two-step framework that learns to imitate human design strategies from observation is proposed and implemented. This framework makes use of deep learning constructs to learn to generate designs without any explicit information about objective and performance metrics. The framework is designed to interact with the problem through a visual interface as humans did when solving the problem. It is trained to imitate a set of human designers by observing their design state sequences without inducing problem-specific modeling bias or extra information about the problem. Furthermore, an end-to-end agent is developed that uses this deep learning framework as its core in conjunction with image processing to map pixel-to-design moves as a mechanism to generate designs. Finally, the designs generated by a computational team of these agents are then compared with actual human data for teams solving a truss design problem. Results demonstrate that these agents are able to create feasible and efficient truss designs without guidance, showing that this methodology allows agents to learn effective design strategies.

scholarly journals Embedding Convolution Neural Network-Based Defect Finder for Deployed Vision Inspector in Manufacturing Company Frontec

2020 ◽  
Vol 34 (08) ◽  
pp. 13164-13171
Author(s):  
Kyoung Jun Lee ◽  
Jun Woo Kwon ◽  
Soohong Min ◽  
Jungho Yoon
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Response Time ◽  
Automobile Industry ◽  
Large Scale ◽  
Group Model ◽  
Quality Inspection ◽  
Circular Hough Transform ◽  
Learning Framework ◽  
Visual Geometry

In collaboration with Frontec, which produces parts such as bolts and nuts for the automobile industry, Kyung Hee University and Benple Inc. develop and deploy AI system for automatic quality inspection of weld nuts. Various constraints to consider exist in adopting AI for the factory, such as response time and limited computing resources available. Our convolutional neural network (CNN) system using large-scale images must classify weld nuts within 0.2 seconds with accuracy over 95%. We designed Circular Hough Transform based preprocessing and an adjusted VGG (Visual Geometry Group) model. The system showed accuracy over 99% and response time of about 0.14 sec. We use TCP / IP protocol to communicate the embedded classification system with an existing vision inspector using LabVIEW. We suggest ways to develop and embed a deep learning framework in an existing manufacturing environment without a hardware change.

scholarly journals AWGAN: A Powerful Batch Correction Model for scRNA-seq Data

2021 ◽  
Author(s):  
Tianyu Liu ◽  
Yuge Wang ◽  
Hong-yu Zhao
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Batch Effects ◽  
Generative Adversarial Network ◽  
Correction Model ◽  
Batch Correction ◽  
Learning Framework ◽  
Adversarial Network ◽  
Genomics Research ◽  
Downstream Analysis

With the advancement of technology, we can generate and access large-scale, high dimensional and diverse genomics data, especially through single-cell RNA sequencing (scRNA-seq). However, integrative downstream analysis from multiple scRNA-seq datasets remains challenging due to batch effects. In this paper, we focus on scRNA-seq data integration and propose a new deep learning framework based on Wasserstein Generative Adversarial Network (WGAN) combined with an attention mechanism to reduce the differences among batches. We also discuss the limitations of the existing methods and demonstrate the advantages of our new model from both theoretical and practical aspects, advocating the use of deep learning in genomics research.

Sign in / Sign up

Export Citation Format

Share Document