DeepEMhancer: a deep learning solution for cryo-EM volume post-processing

AbstractCryo-EM maps are valuable sources of information for protein structure modeling. However, due to the loss of contrast at high frequencies, they generally need to be post-processed to improve their interpretability. Most popular approaches, based on global B-factor correction, suffer from limitations. For instance, they ignore the heterogeneity in the map local quality that reconstructions tend to exhibit. Aiming to overcome these problems, we present DeepEMhancer, a deep learning approach designed to perform automatic post-processing of cryo-EM maps. Trained on a dataset of pairs of experimental maps and maps sharpened using their respective atomic models, DeepEMhancer has learned how to post-process experimental maps performing masking-like and sharpening-like operations in a single step. DeepEMhancer was evaluated on a testing set of 20 different experimental maps, showing its ability to reduce noise levels and obtain more detailed versions of the experimental maps. Additionally, we illustrated the benefits of DeepEMhancer on the structure of the SARS-CoV-2 RNA polymerase.

Download Full-text

DeepEMhancer: a deep learning solution for cryo-EM volume post-processing

10.1101/2020.06.12.148296 ◽

2020 ◽

Cited By ~ 5

Author(s):

R Sanchez-Garcia ◽

J Gomez-Blanco ◽

A Cuervo ◽

JM Carazo ◽

COS Sorzano ◽

...

Keyword(s):

Deep Learning ◽

Single Step ◽

Learning Approach ◽

Structure Modeling ◽

Sources Of Information ◽

Post Processing ◽

High Frequencies ◽

Post Process ◽

Protein Structure Modeling ◽

Local Quality

AbstractCryo-EM maps are valuable sources of information for protein structure modeling. However, due to the loss of contrast at high frequencies, they generally need to be post-processed to improve their interpretability. Most popular approaches, based on B-factor correction, suffer from limitations. For instance, they ignore the heterogeneity in the map local quality that reconstructions tend to exhibit. Aiming to overcome these problems, we present DeepEMhancer, a deep learning approach designed to perform automatic post-processing of cryo-EM maps. Trained on a dataset of pairs of experimental maps and maps sharpened using their respective atomic models, DeepEMhancer has learned how to post-process experimental maps performing masking-like and sharpening-like operations in a single step. DeepEMhancer was evaluated on a testing set of 20 different experimental maps, showing its ability to obtain much cleaner and more detailed versions of the experimental maps. Additionally, we illustrated the benefits of DeepEMhancer on the structure of the SARS-CoV-2 RNA polymerase.

Download Full-text

In situ analysis and visualization to enable better workflows with CREATE-AV™ Helios

10.21079/11681/40846 ◽

2021 ◽

Author(s):

Andrew Bauer ◽

James Forsythe ◽

Jayanarayanan Sitaraman ◽

Andrew Wissink ◽

Buvana Jayaraman ◽

...

Keyword(s):

Cfd Simulation ◽

Internal Surface ◽

In Situ Analysis ◽

Sources Of Information ◽

Post Processing ◽

Full Data ◽

Simulation Code ◽

In Situ Data ◽

Post Process

The CREATE-AV™ Helios CFD simulation code has been used to accurately predict rotorcraft performance under a variety of flight conditions. The Helios package contains a suite of tools that contain almost the entire set of functionality needed for a variety of workflows. These workflows include tools customized to properly specify many in situ analysis and visualization capabilities appropriate for rotorcraft analysis. In situ is the process of computing analysis and visualization information during a simulation run before data is saved to disk. In situ has been referred to with a variety of terms including co-processing, covisualization, coviz, etc. In this paper we describe the customization of the pre-processing GUI and corresponding development of the Helios solver code-base to effectively implement in situ analysis and visualization to reduce file IO and speed up workflows for CFD analysts. We showcase how the workflow enables the wide variety of Helios users to effectively work in post-processing tools they are already familiar with as opposed to forcing them to learn new tools in order post-process in situ data extracts being produced by Helios. These data extracts include various sources of information customized to Helios, such as knowledge about the near- and off-body grids, internal surface extracts with patch information, and volumetric extracts meant for fast post-processing of data. Additionally, we demonstrate how in situ can be used by workflow automation tools to help convey information to the user that would be much more difficult when using full data dumps.

Download Full-text

Arabic named entity recognition using deep learning approach

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v9i3.pp2025-2032 ◽

2019 ◽

Vol 9 (3) ◽

pp. 2025 ◽

Cited By ~ 3

Author(s):

Ismail El Bazi ◽

Nabil Laachfoubi

Keyword(s):

Deep Learning ◽

Network Architecture ◽

Short Term Memory ◽

State Of The Art ◽

Named Entity Recognition ◽

Entity Recognition ◽

Feature Engineering ◽

Learning Approach ◽

Sources Of Information ◽

Named Entity

Most of the Arabic Named Entity Recognition (NER) systems depend massively on external resources and handmade feature engineering to achieve state-of-the-art results. To overcome such limitations, we proposed, in this paper, to use deep learning approach to tackle the Arabic NER task. We introduced a neural network architecture based on bidirectional Long Short-Term Memory (LSTM) and Conditional Random Fields (CRF) and experimented with various commonly used hyperparameters to assess their effect on the overall performance of our system. Our model gets two sources of information about words as input: pre-trained word embeddings and character-based representations and eliminated the need for any task-specific knowledge or feature engineering. We obtained state-of-the-art result on the standard ANERcorp corpus with an F1 score of 90.6%.

Download Full-text

Comparison of various Activation Functions A Deep Learning Approach

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6i3.122126 ◽

2018 ◽

Vol 6 (3) ◽

pp. 122-126

Author(s):

Mohammed Ibrahim Khan ◽

◽

Akansha Singh ◽

Anand Handa ◽

◽

...

Keyword(s):

Deep Learning ◽

Learning Approach ◽

Activation Functions

Download Full-text

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

The International Arab Journal of Information Technology ◽

10.34028/iajit/17/3/3 ◽

2020 ◽

Vol 17 (3) ◽

pp. 299-305 ◽

Cited By ~ 1

Author(s):

Riaz Ahmad ◽

Saeeda Naz ◽

Muhammad Afzal ◽

Sheikh Rashid ◽

Marcus Liwicki ◽

...

Keyword(s):

Deep Learning ◽

Character Recognition ◽

Data Augmentation ◽

Short Term Memory ◽

Recognition System ◽

Learning Approach ◽

Arabic Text ◽

Data Set ◽

Processing Step ◽

Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Download Full-text