Deep learning methods for scientific and industrial research

Deep learning (DL) is a very powerful computational tool for various applications in scientific and industrial research which can be real-time implemented for societal benefits. Several factors impact the development of optimized DL models for better prediction including the amount of quality sample data, domain-specific knowledge, and the architecture of the model for extraction of the useful features/patterns from the data. The present chapter demonstrates the state-of-the-art DL methodologies used by the researchers from different laboratories under the Council of Scientific and Industrial Research (CSIR), India to solve important research activities across several sectors like Medical, Healthcare, Agriculture, Energy, etc. The Convolutional Neural Network (CNN) techniques are utilized for Tumor diagnosis, classifying molecular subtypes of glioma tissues, and predicting driver gene mutations in glioma. Similarly, the Long short-term memory (LSTM) model is applied for the assessment of crop production, and transfer learning is used for the classification of tea leaves. Further, the ensemble LSTM methodology is implemented for short-term prediction of wind speed to enhance the renewable energy sectors. Finally, the multivariate LSTM models were developed by integrating the weather parameters for the prediction of covid-19 spread over different states in India which is an input for policy planning and supply chain management during the pandemic time. All the use cases are being validated and the results are quite satisfying and provide confidence for the real-time application of DL for scientific and industrial research and societal benefit to the common people. © 2023 Elsevier B.V.

Repurposing of Drugs and HTS to Combat SARS-CoV-2 Main Protease Utilizing Structure-Based Molecular Docking

Background: COVID-19, first reported in China, from the new strain of severe acute respiratory syndrome coronaviruses (SARS-CoV-2), poses a great threat to the world by claiming uncountable lives. SARS-CoV-2 is a highly infectious virus that has been spreading rapidly throughout the world. In the absence of any specific medicine to cure COVID-19, there is an urgent need to develop novel thera-peutics, including drug repositioning along with diagnostics and vaccines to combat the COVID-19. Many antivirals, antimalarials, antiparasitic, antibacterials, immunosuppressive anti-inflammatory, and immunoregulatory agents are being clinically investigated for the treatment of COVID-19. Objectives: The earlier developed one parameter regression model correlating the dock scores with in vitro anti-SARS-CoV-2 main protease activity well predicted the six drugs viz remdesivir, chloroquine, favipiravir, ribavirin, penciclovir, and nitazoxanide as potential anti-COVID agents. To further validate our earlier model, the biological activity of nine more recently published SARS-CoV-2 main protease inhibitors has been predicted using our previously reported model. Methods: In the present study, this regression model has been used to screen the existing antiviral, an-tiparasitic, antitubercular, and anti pneumonia chemotherapeutics utilizing dock score analyses to explore the potential including mechanism of action of these compounds in combating SARS-CoV-2 main prote-ase. Results: The high correlation (R=0.91) explaining 82.3% variance between the experimental versus predicted activities for the nine compounds is observed. It proves the robustness of our developed model. Therefore, this robust model has been further improved, taking a total number of 15 compounds to formu-late another model with an R-value of 0.887 and the explained variance of 78.6%. These models have been used for high throughput screening (HTS) of the 21 diverse compounds belonging to antiviral, an-tiparasitic, antitubercular, and anti pneumonia chemotherapeutics as potential repurpose agents to combat SARS-CoV-2 main protease. The models screened that the drugs bedaquiline and lefamulin have higher binding affinities (dock scores of-8.989 and-9.153 Kcal/mol respectively) than the reference compound {N}-[2-(5-fluoranyl-1~{H}-indol-3-yl)ethyl]ethanamide (dock score of-7.998 Kcal/Mol), as well as higher predicted activities with pEC50 of 0.783 and 0.937 µM and the 0.611 and 0.724 µM respectively. The clinically used repurposed drugs dexamethasone and cefixime have been predicted with pEC50 val-ues of-0.463 and-0.622 µM and-0.311 and-0.428 µM respectively for optimal inhibition. The drugs such as doxycycline, cefpodoxime, ciprofloxacin, sparfloxacin, moxifloxacin, and TBAJ-876 showed moderate binding affinity corresponding to the moderate predicted activity (-1.540 to-1.109 µM). Conclusion: In the present study, validation of our previously developed dock score-based one parametric regression model has been carried out by predicting 9 more SARS-CoV-2 main protease inhibitors. Another model has been formulated to explore the model's robustness. These models have been taken as a barometer for the screening of more potent compounds. The HTS revealed that the drugs such as bedaqui-line and lefamulin are highly predicted active compounds, whereas dexamethasone and cefixime have optimal inhibition towards SARS-CoV-2 main protease. The drugs such as doxycycline, cefpodoxime, ciprofloxacin, sparfloxacin, moxifloxacin, and TBAJ-876 have moderately active compounds towards the target inhibition.

Comprehensive Telerobotic Ultrasound System for Abdominal Imaging: Development and in-vivo Feasibility Study

During the COVID-19 pandemic, the lives of healthcare professionals are at significant threat because of the enormous workload and cross-infection risk. Ultrasound (US) imaging plays a vital role in the diagnosis and follow-up of COVID-19 patients;however, it requires a close-physical contact by the sonographer. In this context, this paper presents a Telerobotic Ultrasound (TR-US) system for complete remote control of the US probe, thereby preventing direct physical contact between patients and sonographers. The system consists of a 6-DOF robot arm at the remote site and a haptic device at the doctor's site. The control architecture precisely transmits the intended position and orientation of the US probe to the remote location for transversal and sagittal plane scanning. This architecture, when integrated with an admittance controller-based force modulation and feedback transmission, enables the radiologists to obtain high-quality images for diagnosis. The advantages and effectiveness of the system are demonstrated by conducting in-vivo feasibility study at AIIMS, Delhi, for imaging abdomen organs (liver, spleen, kidneys, bladders). The system provides image quality equivalent to a manually-guided probe, can identify various pathology and reports high acceptability among volunteers and doctors from a questionnaire survey.

“Face mask use and disposal practices during COVID-19 Lockdown in India: Online survey report”

Use of protective face mask is recommended to prevent/reduce COVID19 (SARS- CoV-2) human to human transmission. However, situation analysis of rational of use in view of different guidelines and its implementation at ground level, availability of mask, use, public perception, and disposal methods is required. Hence this online survey from literate population of 1019 adults across India from high and upper middle group (mean age 26.4 years) was conducted during lockdown April- May2020. High awareness (99.7%) and use (99.6%) of mask is reported, however mask disposal knowledge was found to be low as only 44.4% were doing waste segregation while using non-biodegradable mask. As such bio-waste may become potential reservoir for secondary transmissions, hence require attention and public education. If measures are not undertaken, 11.7 lakh Kg of non-biodegradable waste and through this 7.8 X 1016 virus copy anticipated to spread in environment per day. Despite limitation of design, language and representation of all this study provides matching assumptions on biomedical waste burden.

Interaction Design for the Next Billion Users

As the first pandemic wave of Covid-19 hit India and the Indian Government announced a nationwide lockdown in March 2020, [1] it left millions of interstate migrant workers/daily-wage earners without a source of livelihood. Many of them had to return to their hometowns, often hundreds of kilometers away, with many walking a major part or the entirety of the distance [2]. This situation called for a design that could empower migrant workers to thrive in the new normal. An app was designed to enable migrant workers to search for jobs, learn about micro-entrepreneurship, get mental health assistance and develop skills. In terms of usage and interaction, this app proposes several unique features - a result of researching about and understanding our target demographic. At the core of the interaction is a chatbot. It asks questions to the user through text and audio, but the user replies through clickable buttons only. This makes it easy, even for those who may not be literate. The keyboard has been removed from this app. Another unique feature is the usage of interactive videos to explain various things, such as micro-entrepreneurship, skill training, etc. These videos make use of buttons for the users to make choices. In this paper, we discuss these two new interactions that will introduce a visual input method and an interactive video interface which will be inclusive of those less-privileged in terms of literacy in our ever-expanding tech world. The contents of the paper are targeted toward helping the next billion users. However, some of the things proposed may go on to improve interactions for all. © 2021, Springer Nature Switzerland AG.

Demographic and digestive laboratory characteristics predict mortality among hospitalized COVID-19 patients

Introduction: Digestive laboratory abnormalities related to COVID-19 have been previously described, but most reports came from single centers and findings have been conflicting. We conducted a multi-center study using data from three large urban VA centers (New York Harbor VA, New Orleans VA and Detroit VA) to examine the association between demographics and digestive laboratory values with mortality on index hospitalization among individuals diagnosed with COVID-19. Methods: We manually extracted data on individuals hospitalized for COVID-19 between December 2019 and June 2020 at the three facilities. For this analysis, data on demographics and seven digestive laboratory values (highest AST, ALT, alkaline phosphatase, total bilirubin, and INR during admission, as well as lowest hemoglobin and platelets) were analyzed in relation to index hospitalization mortality. We performed descriptive statistics and conducted a multivariable logistic regression model. Results: Out of a total of 390 individuals who were hospitalized with COVID-19, 168 (43%) died and 222 survived. The median age of patients who died was higher than those who survived (75 vs. 69 years). The vast majority (94%) of patients were male. Black patients accounted for a higher proportion of those who died than those who survived (61% vs. 55%), whereas the opposite was true for Whites (26% vs. 31%) and Hispanics (9% vs. 12%). In the multivariable model (Table), mortality was associated with older age (OR 1.07, 95% CI 1.03-1.10), higher BMI (OR 1.05, 95% CI 1.01-1.10), higher AST (OR 1.01, 95% CI 1.004-1.02), lower ALT (OR 0.99, 95% CI 0.98-0.996), higher alkaline phosphatase (OR 1.02, 95% CI 1.01-1.02), and lower hemoglobin (OR 0.83, 95% CI 0.72-0.97). Conclusion: In this multicenter VA study of patients hospitalized with COVID-19 during the first half of 2020, overall mortality was 43%. For mortality during index hospitalization, we observed a positive association with age, BMI, AST, and alkaline phosphatase, and an inverse association with ALT and hemoglobin. Every 1 unit increase in hemoglobin was associated with 17% decreased odds of death. These findings suggest that commonly used digestive laboratory tests have prognostic significance for COVID-related survival.

Conceptualising Circular economy performance with non-traditional valuation methods: Lessons for a post-Pandemic recovery

The circular economy (CE) has gained importance in the post-COVID-19 pandemic recovery. Businesses, while realising the CE benefits, have challenges in justifying and evaluating the CE benefits using available performance measurement tools, specifically when considering sustainability and other non-traditional benefits. Given the rising institutional pressures for environmental and social sustainability, we argue that organisations can evaluate their CE implementation performance using non-market-based environmental goods valuation methods. Further, the effectiveness of the CE performance measurement model can be enhanced to support supply chain sustainability and resilience through an ecosystem of multi-stakeholder digital technologies that include a range of emerging technologies such as blockchain technology, the internet-of-things (IoT), artificial intelligence, remote sensing, and tracking technologies. Accordingly, a CE performance measurement model (CEPMM) is conceptualised and exemplified using seven COVID-19 disruption scenarios to provide insights that can be addressed through CE practices. Analyses and implications are presented along with areas for future research. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

Exploring the SARS-Cov-2 Main Protease (Mpro) and RdRp Targets by Updating Current Structure-based Drug Design Utilizing Co-crystals to Combat COVID-19.

The unprecedented pandemic of COVID-19 caused by the novel strain of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) engulfs millions of death worldwide. It has directly hit the socio-economic status of the affected countries. There are more than 219 countries badly affected by the COVID-19. There are no particular small molecule inhibitors to combat the dreadful virus. Many antivirals, antimalarials, antiparasitic, antibacterials, immunosuppressive antiinflammatory, and immune stimulatory agents have been repurposed for the treatment of COVID-19. But the exact mechanism of action of these drugs towards COVID-19 targets has not been experimented with yet. Under the effect of chemotherapeutics, the virus may change its genetic material and produces various strains, which are the main reasons behind the dreadful attack of COVID-19. The nuclear genetic components are composed of main protease and RNA-dependent RNA polymerase (RdRp) which are responsible for producing nascent virion and viral replication in the host cells. To explore the biochemical mechanisms of various small molecule inhibitors, structure-based drug design can be attempted utilizing NMR crystallography. The process identifies and validates the target protein involved in the disease pathogenesis by the binding of a chemical ligand at a well-defined pocket on the protein surface. In this way, the mode of binding of the ligands inside the target cavity can be predicted for the design of potent SARS-CoV-2 inhibitors.

3D printing in managing supply disruptions related to COVID-19 pandemic: Food and Drug Administration's current thinking on regulation

Recent developments and collaborations of pharmaceutical manufacturers, hospitals, and government funded research bodies using 3D printing technology have been highlighted for the management of the healthcare crisis. 3D printing is a process of converting virtual 3D models developed by computer aided design into physical forms upon addition of material layer-by-layer (also known as additive manufacturing). This 3D printing is supposed to revolutionize significantly the healthcare system in the coming years. This process involves a tailored deposition of biomaterials layer by layer such as polylactic acid (PLA), polyvinyl alcohol (PVA), or other suitable pharma-grade polymers, copolymers, and their combinations to formulate three-dimensional custom designs with controlled architecture and composition. Food and Drug Administration (FDA) is currently thinking on regulation to ease the import restrictions for products intended for the detection and diagnosis of COVID-19 to ensure the timely availability of test kits.

Natural infection of Delta mutant of SARS-CoV-2 in Asiatic lions of India.

The current pandemic caused by a novel coronavirus (SARS-CoV-2) has underlined the importance of emerging diseases of zoonotic importance. Along with human beings, several species of wild and pet animals have been demonstrated to be infected by SARS-CoV-2, both naturally and experimentally. In addition, with constant emergence of new variants, the species susceptibility might further change which warrants intensified screening efforts. India is a vast and second most populated country, with a habitat of a very diverse range of animal species. In this study we place on record of SARS-CoV-2 infections in three captive Asiatic lions. Detailed genomic characterization revealed involvement of Delta mutant (Pango lineage B.1.617.2) of SARS-CoV-2 at two different locations. Interestingly, no other feline species enclosed in the zoo/park were found infected. The epidemiological and molecular analysis will contribute to the understanding of the emerging mutants of SARS-CoV-2 in wild and domestic animals.

Preventing COVID-19 Spread Using Information and Communication Technology

Without an effective vaccine, treatment, or therapy, the Coronavirus Disease 2019 (COVID-19) is spreading like fire and claiming lives. Countries began to adopt various strategies such as lockdown, mass testing, tracing, quarantine, sanitization, isolation, and treatment to contain COVID-19. However, it was soon realized that we need to take the help of powerful technologies to combat the spread of deadly COVID-19 until a vaccine or a drug is discovered. In this article, we discuss how the use of cutting edge technologies such as the Internet of Things (IoT), Big data, artificial intelligence (AI), unmanned aerial vehicles (UAVs)/drones, blockchain, robotics, autonomous ground vehicles, communication technologies in screening, testing, contact tracing, spread analysis, sanitization, and protocol enforcements can help prevent the COVID-19 spread.

Deep Greedy Network: A Tool for Medical Diagnosis on Exiguous Dataset of COVID-19

The extensive outbreak of COVID-19 has created a worldwide health crisis. Transmission of this disease occurs among people through droplets which causes severe respiratory distress and in turn can also lead to fatal death. At the pinnacle of this pandemic, scientists endeavor to discover the medication for the COVID-19 victims. Artificial Intelligence algorithms, especially, deep learning, on the other hand, is used for the diagnosis of the COVID-19 patients but this requires an enormous radiographic data set to effectively provide an optimized outcome for a particular scenario. This work presents a new technique called 'Deep Greedy Network' which will work efficiently with a finite number of datasets. In spite of peculiarity caused due to limited dataset, the anomaly of overfitting and underfitting could be effectively overcome using the proposed algorithm. This, in turn, is simultaneously going to be both cost-effective and efficient. The proposed architecture ensures the efficacious result after the proper judgement of the trained model on the given X-ray datasets of COVID-19 cases. © 2020 IEEE.

Do blockchain and circular economy practices improve post COVID-19 supply chains? A resource-based and resource dependence perspective

Purpose: Using the resource-based and the resource dependence theoretical approaches of the firm, the paper explores firm responses to supply chain disruptions during COVID-19. The paper explores how firms develop localization, agility and digitization (L-A-D) capabilities by applying (or not applying) their critical circular economy (CE) and blockchain technology (BCT)-related resources and capabilities that they either already possess or acquire from external agents. Design/methodology/approach: An abductive approach, applying exploratory qualitative research was conducted over a sample of 24 firms. The sample represented different industries to study their critical BCT and CE resources and capabilities and the L-A-D capabilities. Firm resources and capabilities were classified using the technology, organization and environment (TOE) framework. Findings: Findings show significant patterns on adoption levels of the blockchain-enabled circular economy system (BCES) and L-A-D capability development. The greater the BCES adoption capabilities, the greater the L-A-D capabilities. Organizational size and industry both influence the relationship between BCES and L-A-D. Accordingly, research propositions and a research framework are proposed. Research limitations/implications: Given the limited sample size, the generalizability of the findings is limited. Our findings extend supply chain resiliency research. A series of propositions provide opportunities for future research. The resource-based view and resource-dependency theories are useful frameworks to better understanding the relationship between firm resources and supply chain resilience. Practical implications: The results and discussion of this study serve as useful guidance for practitioners to create CE and BCT resources and capabilities for improving supply chain resiliency. Social implications: The study shows the socio-economic and socio-environmental importance of BCES in the COVID-19 or similar crises. Originality/value: The study is one of the initial attempts that highlights the possibilities of BCES across multiple industries and their value during pandemics and disruptions. © 2020, Emerald Publishing Limited.

The prevalence, preventive measures and economic impact of pandemic COVID-19 in India: The initial phase

The novel coronavirus (SARS-CoV-2) is posing a serious threat to the mankind with its massive infection rate and potentially fatality. A total of 212 countries have been infected within the 112 days of first report causing 2 314 621 confirmed cases and 157 847 deaths worldwide. India, the country which is already battling with poverty, malnutrition and high population density is also at the second stage of coronavirus transmission. The situation is worsening and the attention has focused on the prevalence and preventive measures to be taken to protect 1.35 billion people of the largest democratic country of the world. In this review, a study has been designed to evaluate the prevalence, transmission, clinical symptoms, and preventive measures to control the community transmission of this fatal disease. The initial impact of coronavirus disease (COVID-19) outbreak on Indian economy has also been dealt with. This study reviews and summarizes the main points of the epidemic in India until the end of April 2020.