Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

TW-SIR: time-window based SIR for COVID-19 forecasts.

In Scientific reports ; h5-index 158.0

Since the outbreak of COVID-19, many COVID-19 research studies have proposed different models for predicting the trend of COVID-19. Among them, the prediction model based on mathematical epidemiology (SIR) is the most widely used, but most of these models are adapted in special situations based on various assumptions. In this study, a general adapted time-window based SIR prediction model is proposed, which is characterized by introducing a time window mechanism for dynamic data analysis and using machine learning method predicts the basic reproduction number and the exponential growth rate of the epidemic. We analyzed COVID-19 data from February to July 2020 in seven countries---China, South Korea, Italy, Spain, Brazil, Germany and France, and the numerical results showed that the framework can effectively measure the real-time changes of the parameters during the epidemic, and error rate of predicting the number of COVID-19 infections in a single day is within 5%.

Liao Zhifang, Lan Peng, Liao Zhining, Zhang Yan, Liu Shengzong

2020-12-31

Public Health Public Health

Modeling dengue vector population with earth observation data and a generalized linear model.

In Acta tropica ; h5-index 41.0

Mosquitoes propagate many human diseases, some widespread and with no vaccines. The Ae. aegypti mosquito vector transmits Zika, Chikungunya, and Dengue viruses. Effective public health interventions to control the spread of these diseases and protect the population require models that explain the core environmental drivers of the vector population. Field campaigns are expensive, and data from meteorological sites that feed models with the required environmental data often lack detail. As a consequence, we explore temporal modeling of the population of Ae. aegypti mosquito vector species and environmental conditions- temperature, moisture, precipitation, and vegetation- have been shown to have significant effects. We use earth observation (EO) data as our source for estimating these biotic and abiotic environmental variables based on proxy features, namely: Normalized difference vegetation index, Normalized difference water index, Precipitation, and Land surface temperature. We obtained our response variable from field-collected mosquito population measured weekly using 791 mosquito traps in Vila Velha city, Brazil, for 36 weeks in 2017, and 40 weeks in 2018. Recent similar studies have used machine learning (ML) techniques for this task. However, these techniques are neither intuitive nor explainable from an operational point of view. As a result, we use a Generalized Linear Model (GLM) to model this relationship due to its fitness for count response variable modeling, its interpretability, and the ability to visualize the confidence intervals for all inferences. Also, to improve our model, we use the Akaike Information Criterion to select the most informative environmental features. Finally, we show how to improve the quality of the model by weighting our GLM. Our resulting weighted GLM compares well in quality with ML techniques: Random Forest and Support Vector Machines. These results provide an advancement with regards to qualitative and explainable epidemiological risk modeling in urban environments.

Mudele Oladimeji, Frery Alejandro C, Zanandrez Lucas F R, Eiras Alvaro E, Gamba Paolo

2020-Dec-29

Aedes aegypti, Dengue risks, Machine learning, Regression analysis, Remote sensing

General General

Quantitative analysis of blood cells from microscopic images using convolutional neural network.

In Medical & biological engineering & computing ; h5-index 32.0

Blood cell count provides relevant clinical information about different kinds of disorders. Any deviation in the number of blood cells implies the presence of infection, inflammation, edema, bleeding, and other blood-related issues. Current microscopic methods used for blood cell counting are very tedious and are highly prone to different sources of errors. Besides, these techniques do not provide full information related to blood cells like shape and size, which play important roles in the clinical investigation of serious blood-related diseases. In this paper, deep learning-based automatic classification and quantitative analysis of blood cells are proposed using the YOLOv2 model. The model was trained on 1560 images and 2703-labeled blood cells with different hyper-parameters. It was tested on 26 images containing 1454 red blood cells, 159 platelets, 3 basophils, 12 eosinophils, 24 lymphocytes, 13 monocytes, and 28 neutrophils. The network achieved detection and segmentation of blood cells with an average accuracy of 80.6% and a precision of 88.4%. Quantitative analysis of cells was done following classification, and mean accuracy of 92.96%, 91.96%, 88.736%, and 92.7% has been achieved in the measurement of area, aspect ratio, diameter, and counting of cells respectively.Graphical abstract Graphical abstract where the first picture shows the input image of blood cells seen under a compound light microscope. The second image shows the tools used like OpenCV to pre-process the image. The third image shows the convolutional neural network used to train and perform object detection. The 4th image shows the output of the network in the detection of blood cells. The last images indicate post-processing applied on the output image such as counting of each blood cells using the class label of each detection and quantification of morphological parameters like area, aspect ratio, and diameter of blood cells so that the final result provides the number of each blood cell types (seven) and morphological information providing valuable clinical information.

Tessema Abel Worku, Mohammed Mohammed Aliy, Simegn Gizeaddis Lamesgin, Kwa Timothy Chung

2021-Jan

Blood cells, Detection, Morphological parameters, YOLOv2

General General

sgRNACNN: identifying sgRNA on-target activity in four crops using ensembles of convolutional neural networks.

In Plant molecular biology

We proposed an ensemble convolutional neural network model to identify sgRNA high on-target activity in four crops and we used one-hot encoding and k-mers for sequence encoding. As an important component of the CRISPR/Cas9 system, single-guide RNA (sgRNA) plays an important role in gene redirection and editing. sgRNA has played an important role in the improvement of agronomic species, but there is a lack of effective bioinformatics tools to identify the activity of sgRNA in agronomic species. Therefore, it is necessary to develop a method based on machine learning to identify sgRNA high on-target activity. In this work, we proposed a simple convolutional neural network method to identify sgRNA high on-target activity. Our study used one-hot encoding and k-mers for sequence data conversion and a voting algorithm for constructing the convolutional neural network ensemble model sgRNACNN for the prediction of sgRNA activity. The ensemble model sgRNACNN was used for predictions in four crops: Glycine max, Zea mays, Sorghum bicolor and Triticum aestivum. The accuracy rates of the four crops in the sgRNACNN model were 82.43%, 80.33%, 78.25% and 87.49%, respectively. The experimental results showed that sgRNACNN realizes the identification of high on-target activity sgRNA of agronomic data and can meet the demands of sgRNA activity prediction in agronomy to a certain extent. These results have certain significance for guiding crop gene editing and academic research. The source code and relevant dataset can be found in the following link: https://github.com/nmt315320/sgRNACNN.git .

Niu Mengting, Lin Yuan, Zou Quan

2021-Jan-01

Convolutional neural networks, One-hot encoding, k-mer, sgRNA high on-target activity

General General

Patient Specific Classification of Dental Root Canal and Crown Shape.

In Shape in Medical Imaging : International Workshop, ShapeMI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Proceedings

This paper proposes machine learning approaches to support dentistry researchers in the context of integrating imaging modalities to analyze the morphology of tooth crowns and roots. One of the challenges to jointly analyze crowns and roots with precision is that two different image modalities are needed. Precision in dentistry is mainly driven by dental crown surfaces characteristics, but information on tooth root shape and position is of great value for successful root canal preparation, pulp regeneration, planning of orthodontic movement, restorative and implant dentistry. An innovative approach is to use image processing and machine learning to combine crown surfaces, obtained by intraoral scanners, with three dimensional volumetric images of the jaws and teeth root canals, obtained by cone beam computed tomography. In this paper, we propose a patient specific classification of dental root canal and crown shape analysis workflow that is widely applicable.

Dumont Maxime, Prieto Juan Carlos, Brosset Serge, Cevidanes Lucia, Bianchi Jonas, Ruellas Antonio, Gurgel Marcela, Massaro Camila, Castillo Aron Aliaga Del, Ioshida Marcos, Yatabe Marilia, Benavides Erika, Rios Hector, Soki Fabiana, Neiva Gisele, Aristizabal Juan Fernando, Rey Diego, Alvarez Maria Antonia, Najarian Kayvan, Gryak Jonathan, Styner Martin, Fillion-Robin Jean-Christophe, Paniagua Beatriz, Soroushmehr Reza

2020-Oct

Deep learning, Dentistry, Shape analysis

Dermatology Dermatology

SkinBug: an artificial intelligence approach to predict human skin microbiome-mediated metabolism of biotics and xenobiotics.

In iScience

In addition to being pivotal for the host health, the skin microbiome possesses a large reservoir of metabolic enzymes, which can metabolize molecules (cosmetics, medicines, pollutants, etc.) that form a major part of the skin exposome. Therefore, to predict the complete metabolism of any molecule by skin microbiome, a curated database of metabolic enzymes (1,094,153), reactions, and substrates from ∼900 bacterial species from 19 different skin sites were used to develop "SkinBug." It integrates machine learning, neural networks, and chemoinformatics methods, and displays a multiclass multilabel accuracy of up to 82.4% and binary accuracy of up to 90.0%. SkinBug predicts all possible metabolic reactions and associated enzymes, reaction centers, skin microbiome species harboring the enzyme, and the respective skin sites. Thus, SkinBug will be an indispensable tool to predict xenobiotic/biotic metabolism by skin microbiome and will find applications in exposome and microbiome studies, dermatology, and skin cancer research.

Jaiswal Shubham K, Agarwal Shitij Manojkumar, Thodum Parikshit, Sharma Vineet K

2021-Jan-22

In Silico Biology, Metabolomics, Systems Biology