Bayesian Optimization-Based Diagnosis of Covid-19 Chest X-Rays -Ai Perspective

Coronavirus is the deadliest disease globally, and no efficient treatment has been established. The prognosis of illnesses caused by virus outbreaks is a severe medical process that demands a large amount of accurate data comprised of many factors to produce an appropriate analysis. We have researched and analyzed the factors that might affect humans and increase the chances of infection with Covid-19. One of them is the breathing symptoms directly affecting the lungs and chest. To analyze the factors, we have used traditional machine learning and deep learning models to classify and predict the chances of a human getting infected with different SARs variants. So, we used a Cyclic Generative Adversarial Networks (CGANs) model, Convolutional Neural Networks (CNNs), to generate, predict and classify the Covid-19 occurrence through chest x-rays and other attributes like Diabetes and Hypertension. These models are deployed to the cloud with appropriate hypermeter tuning to use the result in real time. This paper proposed CGANs and CNNs, which automatically use ADAM, RMSprop and Bayesian optimizers to identify chest X-ray COVID-19 pneumonia images. Then, using extracted features has increased the performance of the proposed technique. The experiments suggest that the presented ADAM method fits RMSprop and Bayesian optimization achieves better accuracy. Within proposed algorithms, Bayesian optimization effectively predicts the diagnosis of covid-19 patients.Copyright All © 2023 are reserved by International Journal of Pharmaceutical Sciences and Research.

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandwidth ( ∼ 100 Kbps to a few Mbps), improved video compression can have a substantial impact on network performance for live and pre-recorded content, providing broader access to multimedia content worldwide. We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam videos ('talking-head videos') to a text transcript. The text is transmitted and decoded into a realistic reconstruction of the original video using recent advances in deep learning based voice cloning and lip syncing models. Our generative pipeline achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders), while maintaining equivalent Quality-of-Experience based on a subjective evaluation by users ( n=242 ) in an online study. The Txt2Vid framework opens up the potential for creating novel applications such as enabling audio-video communication during poor internet connectivity, or in remote terrains with limited bandwidth. The code for this work is available at https://github.com/tpulkit/txt2vid.git. © 1983-2012 IEEE.

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandwidth (~100 Kbps to a few Mbps), improved video compression can have a substantial impact on network performance for live and pre-recorded content, providing broader access to multimedia content worldwide. We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam videos (“talking-head videos”) to a text transcript. The text is transmitted and decoded into a realistic reconstruction of the original video using recent advances in deep learning based voice cloning and lip syncing models. Our generative pipeline achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders), while maintaining equivalent Quality-of-Experience based on a subjective evaluation by users (n = 242) in an online study. The Txt2Vid framework opens up the potential for creating novel applications such as enabling audio-video communication during poor internet connectivity, or in remote terrains with limited bandwidth. The code for this work is available at https://github.com/tpulkit/txt2vid.git. IEEE

Towards Deep Interpretable Features

The problem of interpretability for binary image classification is considered through the lens of kernel two-sample tests and generative modelling. A feature extraction framework coined Deep Interpretable Features is developed, which is used in combination with IntroVAE, a generative model capable of high-resolution image synthesis. Experimental results on a variety of datasets, including COVID-19 chest x-rays demonstrate the benefits of combining deep generative models with the ideas from kernel-based hypothesis testing in moving towards more robust interpretable deep generative models.

Data Analysis and Synthesis of COVID-19 Patients using Deep Generative Models: A Case Study of Jakarta, Indonesia

Two years have passed since COVID-19 broke out in Indonesia. In Indonesia, the central and regional governments have used vast amounts of data on COVID-19 patients for policymaking. However, it is clear that privacy problems can arise when people use their data. Thus, it is crucial to keep COVID-19 data private, using synthetic data publishing (SDP). One of the well-known SDP methods is by using deep generative models. This study explores the usage of deep generative models to synthesise COVID-19 individual data. The deep generative models used in this paper are Generative Adversarial Networks (GAN), Adversarial Autoencoders (AAE), and Adversarial Variational Bayes (AVB). This study found that AAE and AVB outperform GAN in loss, distribution, and privacy preservation, mainly when using the Wasserstein approach. Furthermore, the synthetic data produced predictions in the real dataset with sensitivity and an F1 score of more than 0.8. Unfortunately, the synthetic data produced still has drawbacks and biases, especially in conducting statistical models. Therefore, it is essential to improve the deep generative models, especially in maintaining the statistical guarantee of the dataset. © 2022 IEEE.

VAEResTL: A Novel Generative Model for Designing Complementarity Determining Region of Antibody for SARS-CoV-2

The global impact of the COVID-19 pandemic underlines the importance of developing a competent machine learning (ML) approach that can rapidly design therapeutics and prophylactics such as antibodies/nanobodies against novel viral infections despite data shortage problems and sequence complexity. Here, we propose a novel end-to-end deep generative model based on convolutional Variational Autoencoder (VAE), Residual Neural Network (Resnet), and Transfer Learning (TL), named VAEResTL that can competently generate CDR-H3 sequences for a novel target lacking sufficient training data. We further demonstrate that our proposed method generates the third complementarity-determining region (CDR) of the heavy chain (CDR-H3) sequences for designing and developing therapeutic antibodies/nanobodies that can bind to different variants of SARS-CoV-2 despite the shortage of SARS-CoV-2 training data. The predicted CDR-H3 sequences are then screened and filtered for their developability parameters namely viscosity, clearance, solubility, stability, and immunogenicity through several in-silico steps resulting in a list of highly optimized lead candidates.

EXAM SUBJECTS GENERATION FOR A COMPILER DESIGN DISCIPLINE DURING PANDEMICS

Education during pandemics was disrupted by the social distancing restrictions that were imposed by authorities. In this context, education was moved online together with all the knowledge assessment mechanisms like online examination. Oral online exams are good methods to examine students but it requires a lot of resources like time and tutors which usually universities cannot afford to allocate. Usually, exam results must be provided in a few days from the exam date and session periods are short. Written online examinations are prone to cheating due to the availability of multiple communication channels between students or students or third parties. Several cases were reported by tutors and they had to be discussed in the faculty’s management board. Expelling students from universities for cheating reasons may result in serious financial shortages. The only feasible way is to keep away students from cheating in online exams. One potential solution in this sense is to generate unique sets of subjects for each student and to allocate a limited amount of time for solving each subject. Thus, the solution of one student will not be reusable by others. On the other hand, the time limit will restrict the capacity of communication between students when supervised by video cameras. The video cameras must be at least two: one for identifying the student's face and the other focused on the written paper. To generate unique exam subjects, we propose an ion process to infer a template and a synthesis process where the template is instantiated with data computed from random numbers. The approach was tested on a group of 29 students and no cheating incidents were reported. © 2021, National Defence University - Carol I Printing House. All rights reserved.

Deep Generative Learning-Based 1-SVM Detectors for Unsupervised COVID-19 Infection Detection Using Blood Tests.

A sample blood test has recently become an important tool to help identify false-positive/false-negative real-time reverse transcription polymerase chain reaction (rRT-PCR) tests. Importantly, this is mainly because it is an inexpensive and handy option to detect the potential COVID-19 patients. However, this test should be conducted by certified laboratories, expensive equipment, and trained personnel, and 3-4 h are needed to deliver results. Furthermore, it has relatively large false-negative rates around 15%-20%. Consequently, an alternative and more accessible solution, quicker and less costly, is needed. This article introduces flexible and unsupervised data-driven approaches to detect the COVID-19 infection based on blood test samples. In other words, we address the problem of COVID-19 infection detection using a blood test as an anomaly detection problem through an unsupervised deep hybrid model. Essentially, we amalgamate the features extraction capability of the variational autoencoder (VAE) and the detection sensitivity of the one-class support vector machine (1SVM) algorithm. Two sets of routine blood tests samples from the Albert Einstein Hospital, S ao Paulo, Brazil, and the San Raffaele Hospital, Milan, Italy, are used to assess the performance of the investigated deep learning models. Here, missing values have been imputed based on a random forest regressor. Compared to generative adversarial networks (GANs), deep belief network (DBN), and restricted Boltzmann machine (RBM)-based 1SVM, the traditional VAE, GAN, DBN, and RBM with softmax layer as discriminator layer, and the standalone 1SVM, the proposed VAE-based 1SVM detector offers superior discrimination performance of potential COVID-19 infections. Results also revealed that the deep learning-driven 1SVM detection approaches provide promising detection performance compared to the conventional deep learning models.

Predicting novel drug candidates against Covid-19 using generative deep neural networks.

The novel Coronavirus outbreak has created a massive economic crisis, and many succumb to death, disturbing the lives of mankind all over the world. Currently, there are no viable treatment for this condition, drug development approaches are being pursued with vigor. The major treatment options are to repurpose existing drugs or to find new ones. Traditional methods for drug discovery take a longer time, so there is an urgent need to develop some alternative techniques that reduces search space for drug candidates. Towards this endeavor, we propose a novel drug discovery method that leverages on long short term memory (LSTM) model to generate novel molecules that are adept at binding with novel Coronavirus protease. Our study demonstrates that the proposed method is able to recreate novel molecules that correlate very much with the properties of trained molecules. Further, we fine-tune the model to generate novel drug-like molecules that are active towards a specific target. We consider 3CLPro, the main protease of novel Coronavirus, as a therapeutic target and demonstrated in silico screening to assess target structural binding affinities with docking simulations. We observed that 80% of generated molecules show docking free energy of less than -5.8 kcal/mol. The top generated drug candidate has the highest binding affinity with a docking score of -8.5 kcal/mol, which is very much lower when compared to approved existing commercial drugs including, Remdesivir. The low binding energy indicates that the generated molecules could be explored as potential drug candidates for Covid-19.

Generating hard-to-obtain information from easy-to-obtain information: Applications in drug discovery and clinical inference.

Often when biological entities are measured in multiple ways, there are distinct categories of information: some information is easy-to-obtain information (EI) and can be gathered on virtually every subject of interest, while other information is hard-to-obtain information (HI) and can only be gathered on some. We propose building a model to make probabilistic predictions of HI using EI. Our feature mapping GAN (FMGAN), based on the conditional GAN framework, uses an embedding network to process conditions as part of the conditional GAN training to create manifold structure when it is not readily present in the conditions. We experiment on generating RNA sequencing of cell lines perturbed with a drug conditioned on the drug's chemical structure and generating FACS data from clinical monitoring variables on a cohort of COVID-19 patients, effectively describing their immune response in great detail.