Binary Classification of COVID-19 CT Images Using CNN

COVID-19 pandemic has hit the world with such a force that the world's leading economies are finding it challenging to come out of it. Countries with the best medical facilities are even cannot handle the increasing number of cases and fatalities. This disease causes significant damage to the lungs and respiratory system of humans, leading to their death. Computed tomography (CT) images of the respiratory system are analyzed in the proposed work to classify the infected people with non-infected people. Deep learning binary classification algorithms have been applied, which have shown an accuracy of 86.9% on 746 CT images of chest having COVID-19 related symptoms.

The immune synapses reveal aberrant functions of CD8 T cells during chronic HIV infection

It is well-established that chronic HIV infection causes persistent low-grade inflammation that induces premature aging of the immune system in HIV patient including senescence of memory and effector CD8 T cells. To uncover the reasons of gradually diminished potency of CD8 T cells from chronically HIV infected people, we have analyzed cellular morphology and dynamics of the synaptic interface followed exposure of peripheral polyclonal CD8 T cells at various differentiation stages to planar lipid bilayers. The above parameters were linked to pattern of degranulation that determines efficiency of CD8 T cells cytolytic response. We found a large fraction of naive T cells from HIV infected people developing mature synapses and demonstrating focused degranulation, a signature of a differentiated T cells. Further differentiation of aberrant naive T cells leads to development of anomalous effector T cells undermining their capacity to control HIV and other viruses that could be contained otherwise.

Deep Ensemble Learning-Based Models for Diagnosis of COVID-19 from Chest CT Images

Novel coronavirus (COVID-19) has been endangering human health and life since 2019. The timely quarantine, diagnosis, and treatment of infected people are the most necessary and important work. The most widely used method of detecting COVID-19 is real-time polymerase chain reaction (RT-PCR). Along with RT-PCR, computed tomography (CT) has become a vital technique in diagnosing and managing COVID-19 patients. COVID-19 reveals a number of radiological signatures that can be easily recognized through chest CT. These signatures must be analyzed by radiologists. It is, however, an error-prone and time-consuming process. Deep Learning-based methods can be used to perform automatic chest CT analysis, which may shorten the analysis time. The aim of this study is to design a robust and rapid medical recognition system to identify positive cases in chest CT images using three Ensemble Learning-based models. There are several techniques in Deep Learning for developing a detection system. In this paper, we employed Transfer Learning. With this technique, we can apply the knowledge obtained from a pre-trained Convolutional Neural Network (CNN) to a different but related task. In order to ensure the robustness of the proposed system for identifying positive cases in chest CT images, we used two Ensemble Learning methods namely Stacking and Weighted Average Ensemble (WAE) to combine the performances of three fine-tuned Base-Learners (VGG19, ResNet50, and DenseNet201). For Stacking, we explored 2-Levels and 3-Levels Stacking. The three generated Ensemble Learning-based models were trained on two chest CT datasets. A variety of common evaluation measures (accuracy, recall, precision, and F1-score) are used to perform a comparative analysis of each method. The experimental results show that the WAE method provides the most reliable performance, achieving a high recall value which is a desirable outcome in medical applications as it poses a greater risk if a true infected patient is not identified.

Serious role of non-quarantined COVID-19 patients for random walk simulations

The infectious disease (COVID-19) causes serious damages and outbreaks. A large number of infected people have been reported in the world. However, such a number only represents those who have been tested; e.g. PCR test. We focus on the infected individuals who are not checked by inspections. The susceptible-infected-recovered (SIR) model is modified: infected people are divided into quarantined (Q) and non-quarantined (N) agents. Since N-agents behave like uninfected people, they can move around in a stochastic simulation. Both theory of well-mixed population and simulation of random-walk reveal that the total population size of Q-agents decrease in spite of increasing the number of tests. Such a paradox appears, when the ratio of Q exceeds a critical value. Random-walk simulations indicate that the infection hardly spreads, if the movement of all people is prohibited ("lockdown"). In this case the infected people are clustered and locally distributed within narrow spots. The similar result can be obtained, even when only non-infected people move around. However, when both N-agents and uninfected people move around, the infection spreads everywhere. Hence, it may be important to promote the inspections even for asymptomatic people, because most of N-agents are mild or asymptomatic.

SIMLR: Machine Learning inside the SIR Model for COVID-19 Forecasting

Accurate forecasts of the number of newly infected people during an epidemic are critical for making effective timely decisions. This paper addresses this challenge using the SIMLR model, which incorporates machine learning (ML) into the epidemiological SIR model. For each region, SIMLR tracks the changes in the policies implemented at the government level, which it uses to estimate the time-varying parameters of an SIR model for forecasting the number of new infections one to four weeks in advance. It also forecasts the probability of changes in those government policies at each of these future times, which is essential for the longer-range forecasts. We applied SIMLR to data from in Canada and the United States, and show that its mean average percentage error is as good as state-of-the-art forecasting models, with the added advantage of being an interpretable model. We expect that this approach will be useful not only for forecasting COVID-19 infections, but also in predicting the evolution of other infectious diseases.

Comprehensive Flow Cytometry Profiling of the Immune System in COVID-19 Convalescent Individuals

SARS-CoV-2 has infected more than 200 million people worldwide, with more than 4 million associated deaths. Although more than 80% of infected people develop asymptomatic or mild COVID-19, SARS-CoV-2 can induce a profound dysregulation of the immune system. Therefore, it is important to investigate whether clinically recovered individuals present immune sequelae. The potential presence of a long-term dysregulation of the immune system could constitute a risk factor for re-infection and the development of other pathologies. Here, we performed a deep analysis of the immune system in 35 COVID-19 recovered individuals previously infected with SARS-CoV-2 compared to 16 healthy donors, by flow cytometry. Samples from COVID-19 individuals were analysed from 12 days to 305 days post-infection. We observed that, 10 months post-infection, recovered COVID-19 patients presented alterations in the values of some T-cell, B-cell, and innate cell subsets compared to healthy controls. Moreover, we found in recovered COVID-19 individuals increased levels of circulating follicular helper type 1 (cTfh1), plasmablast/plasma cells, and follicular dendritic cells (foDC), which could indicate that the Tfh-B-foDC axis might be functional to produce specific immunoglobulins 10 months post-infection. The presence of this axis and the immune system alterations could constitute prognosis markers and could play an important role in potential re-infection or the presence of long-term symptoms in some individuals.

Implications of the Immune Polymorphisms of the Host and the Genetic Variability of SARS-CoV-2 in the Development of COVID-19

The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is responsible for the current pandemic affecting almost all countries in the world. SARS-CoV-2 is the agent responsible for coronavirus disease 19 (COVID-19), which has claimed millions of lives around the world. In most patients, SARS-CoV-2 infection does not cause clinical signs. However, some infected people develop symptoms, which include loss of smell or taste, fever, dry cough, headache, severe pneumonia, as well as coagulation disorders. The aim of this work is to report genetic factors of SARS-CoV-2 and host-associated to severe COVID-19, placing special emphasis on the viral entry and molecules of the immune system involved with viral infection. Besides this, we analyze SARS-CoV-2 variants and their structural characteristics related to the binding to polymorphic angiotensin-converting enzyme type 2 (ACE2). Additionally, we also review other polymorphisms as well as some epigenetic factors involved in the immunopathogenesis of COVID-19. These factors and viral variability could explain the increment of infection rate and/or in the development of severe COVID-19.

B cell overexpression of FCRL5 and PD-1 is associated with low antibody titers in HCV infection

Antibodies targeting the hepatitis C virus (HCV) envelope glycoprotein E2 are associated with delayed disease progression, and these antibodies can also facilitate spontaneous clearance of infection in some individuals. However, many infected people demonstrate low titer and delayed anti-E2 antibody responses. Since a goal of HCV vaccine development is induction of high titers of anti-E2 antibodies, it is important to define the mechanisms underlying these suboptimal antibody responses. By staining lymphocytes with a cocktail of soluble E2 (sE2) glycoproteins, we detected HCV E2-specific (sE2+) B cells directly ex vivo at multiple acute infection timepoints in 29 HCV-infected subjects with a wide range of anti-E2 IgG titers, including 17 persistently infected subjects and 12 subjects with spontaneous clearance of infection. We performed multi-dimensional flow cytometric analysis of sE2+ and E2-nonspecific (sE2-) class-switched B cells (csBC). In sE2+ csBC from both persistence and clearance subjects, frequencies of resting memory B cells (rMBC) were reduced, frequencies of activated MBC (actMBC) and tissue-like MBC (tlMBC) were increased, and expression of FCRL5, an IgG receptor, was significantly upregulated. Across all subjects, plasma anti-E2 IgG levels were positively correlated with frequencies of sE2+ rMBC and sE2+ actMBC, while anti-E2 IgG levels were negatively correlated with levels of FCRL5 expression on sE2+ rMBC and PD-1 expression on sE2+ actMBC. Upregulation of FCRL5 on sE2+ rMBC and upregulation of PD-1 on sE2+ actMBC may limit anti-E2 antibody production in vivo. Strategies that limit upregulation of these molecules could potentially generate higher titers of protective antibodies against HCV or other pathogens.

Elucidating the 3D Structure of a Surface Membrane Antigen from Trypanosoma cruzi as a Serodiagnostic Biomarker of Chagas Disease

Chagas disease (CD) is a vector-borne parasitosis, caused by the protozoan parasite Trypanosoma cruzi, that affects millions of people worldwide. Although endemic in South America, CD is emerging throughout the world due to climate change and increased immigratory flux of infected people to non-endemic regions. Containing of the diffusion of CD is challenged by the asymptomatic nature of the disease in early infection stages and by the lack of a rapid and effective diagnostic test. With the aim of designing new serodiagnostic molecules to be implemented in a microarray-based diagnostic set-up for early screening of CD, herein, we report the recombinant production of the extracellular domain of a surface membrane antigen from T. cruzi (TcSMP) and confirm its ability to detect plasma antibodies from infected patients. Moreover, we describe its high-resolution (1.62 Å) crystal structure, to which in silico epitope predictions were applied in order to locate the most immunoreactive regions of TcSMP in order to guide the design of epitopes that may be used as an alternative to the full-length antigen for CD diagnosis. Two putative, linear epitopes, belonging to the same immunogenic region, were synthesized as free peptides, and their immunological properties were tested in vitro. Although both peptides were shown to adopt a structural conformation that allowed their recognition by polyclonal antibodies raised against the recombinant protein, they were not serodiagnostic for T. cruzi infections. Nevertheless, they represent good starting points for further iterative structure-based (re)design cycles.