Drug Design and Disease Diagnosis: The Potential of Deep Learning Models in Biology

Early prediction and detection enable reduced transmission of human diseases and provide healthcare professionals ample time to make subsequent diagnoses and treatment strategies. This, in turn, aids in saving more lives and results in lower medical costs. Designing small chemical molecules to treat fatal disorders is also urgently needed to address the high death rate of these diseases worldwide. A recent analysis of published literature suggested that deep learning (DL) based models apply more potential algorithms to hybrid databases of chemical data. Considering the above, we first discussed the concept of DL architectures and their applications in drug development and diagnostics in this review. Although DL-based approaches have applications in several fields, in the following sections of the arti-cle, we focus on recent developments of DL-based techniques in biology, notably in structure predic-tion, cancer drug development, COVID infection diagnostics, and drug repurposing strategies. Each review section summarizes several cutting-edge, recently developed DL-based techniques. Additionally, we introduced the approaches presented in our group, whose prediction accuracy is relatively compara-ble with current computational models. We concluded the review by discussing the benefits and draw-backs of DL techniques and outlining the future paths for data collecting and developing efficient computational models.Copyright © 2023 Bentham Science Publishers.

Sensitivity of RT-PCR tests for SARS-CoV-2 through time.

Reverse transcriptase polymerase chain reaction (RT-PCR) tests are the gold standard for detecting recent infection with SARS-CoV-2. RT-PCR sensitivity varies over the course of an individual's infection, related to changes in viral load. Differences in testing methods, and individual-level variables such as age, may also affect sensitivity. Using data from New Zealand, we estimate the time-varying sensitivity of SARS-CoV-2 RT-PCR under varying temporal, biological and demographic factors. Sensitivity peaks 4-5 days post-infection at 92.7% [91.4%, 94.0%] and remains over 88% between 5 and 14 days post-infection. After the peak, sensitivity declined more rapidly in vaccinated cases compared to unvaccinated, females compared to males, those aged under 40 compared to over 40 s, and Pacific peoples compared to other ethnicities. RT-PCR remains a sensitive technique and has been an effective tool in New Zealand's border and post-border measures to control COVID-19. Our results inform model parameters and decisions concerning routine testing frequency.

Comparison of Real-time RT-PCR cycle threshold (Ct) values with clinical features and severity of COVID-19 disease among hospitalized patients in the first and second waves of COVID-19 pandemic in Chennai, India

Introduction Real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) of nasopharyngeal/ oropharyngeal swab has been the gold standard test for detection of SARS-CoV-2 infection The relationship between cycle threshold (Ct) values of rRT-PCR and severity of disease remain disputable and not clearly defined in COVID-19. Methodology This is a single-centred retrospective observational study conducted at Government Corona Hospital (GCH), Guindy, Chennai. In the present study, we compared the Ct value of rRT-PCR from nasopharyngeal swab specimens with a diverse range of symptoms and disease severity among 240 individuals who were hospitalized with COVID-19, viz., mild cases (MC;n=160), moderately severe cases (MSC;n=46) and severe cases (SC;n=34) in the first and second waves of COVID-19 pandemic. Results The study included 240 hospitalized COVID-19 patients with a median age of 52 years (range 21 to 90 years). MC, MSC, and SC all had median Ct values of 25.0 (interquartile range – IQR 20.0 to 30.5), 29.5 (IQR 23.0 to 34.0), and 29.0 (IQR 24 to 37.5) for the ORF1ab gene. The Ct value differed significantly between mild vs moderate, and mild vs severe cases. The Ct value of SC group with co-morbidity of type 2 diabetes have a significant difference compared to non-diabetes group (p value <0.05). There was a significant difference in the median Ct value of ORF1ab gene among the MSC group and MC but not in the SC group in the first and second waves of the pandemic (p<0.05). Conclusion We conclude that SARS-CoV-2 Ct values of rRT-PCR alone does not have a role in aiding severity stratification among patients with COVID-19 since the viral dynamics and Ct value may vary due to the emerging variants that occur in different waves of the pandemic.

An Early Detection Of NIPAH Infectious Disease Based On Integrated Medical Features For Human Using Ensemble RBM Techniques

Background: The importance of early diagnosis of a hazardous illness cannot be overstated. The transmission rate is extremely high, especially in the current pandemic condition. The ability to predict epidemics will aid public health in reducing mortality and morbidity. Machine Learning (ML) approaches are used in the construction of an effective disease prognosis model. Furthermore, only if the model learns good associated features from the data is it possible to generate a speedy outcome. As a result, selecting features is also necessary before beginning the forecasting process. Objective(s): However, because of the virus's dynamic structure, it's difficult to predict Nipah disease and/or zoonotic infection. Furthermore, there is no clinical treatment for Nipah. The major goal of this research is to develop a prognostic model for early diagnosis of Nipah disease using a combination of several clinical factors such as symptoms, disease incubation information, and routine blood test results confirmed by a lab technician.Proposed System: The healthcare application and data are more complex to handle than other ML applications since various clinical features are assessed throughout disease manifestation. As a result, selecting the most relevant variables is critical when designing a prognosis model for any viral disease. To deal with clinical features from a vast number of features, we proposed a Restricted Boltzmann Machine (RBM) method in this research. Additionally, we employed a hybrid ensemble learning method to predict if the patient was infected with NiV after choosing features using the RBM. Data Collection: The proposed system is being implemented using the NiV infection dataset that erupted in Kozhikode, Kerala in 2018 and 2019. Result(s): The developed stacking-based ensemble Meta classifier was successfully implemented using the python programming language, and its performance was evaluated using a variety of metrics includingaccuracy, precision, recall, f1-score, log loss, AUROC and MCC. Our proposed Stacking Ensemble Meta Classifier (SEMC) model achieved an accuracy rate of 88.3% with a log loss of 0.36. Model precision, recall, f1-score, AUROC, and MCC value were 92.5%, 89.2%, 90.9%, 92.1%, and 0.74 respectively. In addition, we calculated the gravitational pull of each feature using the SHAP approach and discovered that altered sensorium, fever, headache, and cough were the most critical clinical indicators that distinguished NiVD infection from our dataset. Therefore, this classification may assist the pathologist in diagnosing NiVD with symptoms before performing the RT-PCR medical test. Conclusion(s): Using our proposed SEMC technique, we developed a prognostic model for the diagnosis of Nipah in humans. The proposed technique's discriminatory efficiency exhibited good NiVD diagnosis efficacy. We anticipate that this model will aid medics in determining a prognosis more quickly during future epidemics. However, to achieve maximum accuracy, the model requires more unique samples.Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.

Comparison of Real-time RT-PCR cycle threshold (Ct) values with clinical features and severity of COVID-19 disease among hospitalized patients in the first and second waves of COVID-19 pandemic in Chennai, India.

Introduction: Real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) of nasopharyngeal/ oropharyngeal swab has been the gold standard test for detection of SARS-CoV-2 infection The relationship between cycle threshold (Ct) values of rRT-PCR and severity of disease remain disputable and not clearly defined in COVID-19. Methodology: This is a single-centered retrospective observational study conducted at Government Corona Hospital (GCH), Guindy, Chennai. In the present study, we compared the Ct value of rRT-PCR from nasopharyngeal swab specimens with a diverse range of symptoms and disease severity among 240 individuals who were hospitalized with COVID-19, viz., mild cases (MC; n = 160), moderately severe cases (MSC; n = 46) and severe cases (SC; n = 34) in the first and second waves of COVID-19 pandemic. Results: The study included 240 hospitalized COVID-19 patients with a median age of 52 years (range 21 to 90 years). MC, MSC, and SC all had median Ct values of 25.0 (interquartile range - IQR 20.0 to 30.5), 29.5 (IQR 23.0 to 34.0), and 29.0 (IQR 24 to 37.5) for the ORF1ab gene. The Ct value differed significantly between mild vs moderate, and mild vs severe cases. The Ct value of SC group with co-morbidity of type 2 diabetes have a significant difference compared to non-diabetes group (p value <0.05). There was a significant difference in the median Ct value of ORF1ab gene among the MSC group and MC but not in the SC group in the first and second waves of the pandemic (p<0.05). Conclusion: We conclude that SARS-CoV-2 Ct values of rRT-PCR alone does not have a role in aiding severity stratification among patients with COVID-19 since the viral dynamics and Ct value may vary due to the emerging variants that occur in different waves of the pandemic.

Real-time estimation of the effective reproduction number of SARS-CoV-2 in Aotearoa New Zealand.

During an epidemic, real-time estimation of the effective reproduction number supports decision makers to introduce timely and effective public health measures. We estimate the time-varying effective reproduction number, Rt , during Aotearoa New Zealand's August 2021 outbreak of the Delta variant of SARS-CoV-2, by fitting the publicly available EpiNow2 model to New Zealand case data. While we do not explicitly model non-pharmaceutical interventions or vaccination coverage, these two factors were the leading drivers of variation in transmission in this period and we describe how changes in these factors coincided with changes in Rt . Alert Level 4, New Zealand's most stringent restriction setting which includes stay-at-home measures, was initially effective at reducing the median Rt to 0.6 (90% CrI 0.4, 0.8) on 29 August 2021. As New Zealand eased certain restrictions and switched from an elimination strategy to a suppression strategy, Rt subsequently increased to a median 1.3 (1.2, 1.4). Increasing vaccination coverage along with regional restrictions were eventually sufficient to reduce Rt below 1. The outbreak peaked at an estimated 198 (172, 229) new infected cases on 10 November, after which cases declined until January 2022. We continue to update Rt estimates in real time as new case data become available to inform New Zealand's ongoing pandemic response.

Safety and efficacy of a Siddha Medicine fixed regimen for the treatment of asymptomatic and mild COVID-19 patients.

Background: The Coronavirus disease 2019 (COVID-19) pandemic caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a massive threat to public health worldwide. Siddha system of medicine is one of the traditional medicines of South India. The recommended formulations in Siddha Sasthric Medicines- Fixed Regimen (SSM-FiRe) are Amukkura tablets, Kaba Sura Kudineer (KSK) for asymptomatic COVID-19 positive (RT-PCR) patients, and Athimathuram tablets, Adathodai Manappagu syrup, Thippili Rasayanam, Brahmananda Bairavam tablet, and Notchi Kudineer for mild symptomatic patients. The core objective of the trial was to document the efficacy of SSM-FiRe in the prevention of asymptomatic and mild COVID-19 disease progression to the next level of severity, reduce the severity of symptoms and revert to RT-PCR Negative. Methods: An exploratory, prospective, open-labeled, single-arm, non-randomized trial was designed as per GCP guidelines to assess the efficacy of SSM-FiRe. Sixty RT-PCR positive participants who were asymptomatic or with mild COVID-19 symptoms were recruited for the study at the Siddha COVID Care Centre, Vyasarpadi, Chennai from June to August 2020. Nasal and oropharyngeal swab tests were performed on the 0, 7th, and 14th days. All participants were treated with SSM - FiRe regimen. All the participants were also assessed based on Siddha Yakkkaiyin Ilakkanam, which included Clinical symptoms and vitals. Laboratory investigations such as Haemogram, Liver Function Test, Renal Function Test, HbA1C, Electrolytes, Inflammatory markers, Cardiac profile, Immunoglobulins, and anti-SARS-CoV-2 antibody tests were performed. Results: 83% of COVID-19 patients turned RT-PCR negative on the 7th day and in most of the cases, symptoms were reduced within the first 5 days of admission. The RT-PCR cycle threshold (ct) value increased significantly (<0.001) after treatment and all the participants were RT-PCR negative, except one, who was positive even after 14 days. Anti-SARS-CoV-2 antibodies developed significantly (p-value - 0.006). LFT, RFT, CBC, Total proteins, and electrolytes continued to be in the normal range after treatment, indicating the safety of the intervention. Conclusion: Asymptomatic and mild COVID-19 disease can be well managed by SSM - FiRe treatment, Further studies could be taken up to strengthen the findings.

Early intervention is the key to success in COVID-19 control.

New Zealand responded to the COVID-19 pandemic with a combination of border restrictions and an Alert Level (AL) system that included strict stay-at-home orders. These interventions were successful in containing an outbreak and ultimately eliminating community transmission of COVID-19 in June 2020. The timing of interventions is crucial to their success. Delaying interventions may reduce their effectiveness and mean that they need to be maintained for a longer period. We use a stochastic branching process model of COVID-19 transmission and control to simulate the epidemic trajectory in New Zealand's March-April 2020 outbreak and the effect of its interventions. We calculate key measures, including the number of reported cases and deaths, and the probability of elimination within a specified time frame. By comparing these measures under alternative timings of interventions, we show that changing the timing of AL4 (the strictest level of restrictions) has a far greater impact than the timing of border measures. Delaying AL4 restrictions results in considerably worse outcomes. Implementing border measures alone, without AL4 restrictions, is insufficient to control the outbreak. We conclude that the early introduction of stay-at-home orders was crucial in reducing the number of cases and deaths, enabling elimination.

Mml classification techniques for the pathogen based on pnuemonia-ncovid-19 and the detection of closely related lung diseases using efficacious learning algorithms

The main purpose of this topic is to provide an excellent classification method for predicting the disease based on the key aspect of the disease. Here, we used a multiclass variable database for the prediction;also the methods, random forest and linear SVC, are used for the classification. Furthermore, based on the confusion matrix, we can know the outcome of the prediction model. In this, all the results are discussed using the confusion matrix. Infectious diseases such as nCOVID-19 cause serious damage to the human body’s immune system. It recently emerged from China and affects neighbors’ country and flu-like symptoms initially manifest in 89.9%. The disease spreads faster than SARS-CoV and MERS-CoV, and soon, the disease begins to spread from one person to another, with high fever (101.4 F), inhalation or dyspnea, sore throat, sneezing and coughing. In India, as of January 31, 2020, the number of cases was one, and on March 28, 2020, the outrage began to rise to 909. In addition, COVID is also caused by pneumonia-related illnesses. So far, such epidemics have been studied and diagnosed by reverse transcriptase poly-merase chain reaction (RT-PCR) and serology laboratory testing. Chest X-ray or computed tomography helps identify damaged and white cells in the affected body, identifying pathogens, and the presence of abundant metagenomic sequence in RNA is a major clinical challenge. Since the vaccine has not yet been announced, the current treatment is supplemental care. In this study, we compared machine learning classification methods such as NN, SVM, MLP, RF and KNN, which are widely used in the healthcare sector to diagnose disease by X-ray. Doctors often prescribe chest radiography to diagnose and/or predict infections, since we have read numerous articles on coronavirus. Further, in the clinical perspective, machine learning plays a vital role in solving the problem of prognosis and, thanks to treatment monitoring, there are effective mechanisms. In the presence of airborne diseases, we need an effective tool such as machine learning to investigate this, because nCOVID is transmitted by sneezing or coughing and/or other pulmonary syndrome. Therefore, this review summarizes the current outbreaks of coronavirus and its closely related lung viruses such as influenza and pneumonia, medical-based machine learning (MML) techniques and comparative analysis of MML for infectious diseases. © Springer International Publishing AG 2018.

The pragmatism of technological advancements post-covid in civil engineering education

This research focuses primarily on the ontology and adaptability of various tools and technologies for the post-COVID (2019 novel coronavirus) scenario in Civil Engineering Education (CEE). Initially, a gamut of tools and technologies used in Civil Engineering education is discerned. The applicability and versatility (flexibility in adaptation) of these tools and technologies are thoroughly studied for post-COVID scenarios and the suitability of the same is perceived. In this research, five major technologies such as Building Information Modeling (BIM), Virtual Reality (VR), Augmented Reality (AR), Online Study System (OSS) comprises Micro and Macro Learning, Structured and Unstructured Learning including storytelling, gamification is instantiated for Civil Engineering Education. Comprehensive analogies of these technologies are exemplified to reinforce the applicability and adaptability in post-COVID CEE.

Early intervention is the key to success in COVID-19 control (preprint)

New Zealand responded to the COVID-19 pandemic with a combination of border restrictions and an Alert Level system that included strict stay-at-home orders. These interventions were successful in containing the outbreak and ultimately eliminating community transmission of COVID-19. The timing of interventions is crucial to their success. Delaying interventions for too long may both reduce their effectiveness and mean that they need to be maintained for a longer period of time. Here, we use a stochastic branching process model of COVID-19 transmission and control to simulate the epidemic trajectory in New Zealand and the effect of its interventions during its COVID-19 outbreak in March-April 2020. We use the model to calculate key outcomes, including the peak load on the contact tracing system, the total number of reported COVID-19 cases and deaths, and the probability of elimination within a specified time frame. We investigate the sensitivity of these outcomes to variations in the timing of the interventions. We find that a delay to the introduction of Alert Level 4 controls results in considerably worse outcomes. Changes in the timing of border measures have a smaller effect. We conclude that the rapid response in introducing stay-at-home orders was crucial in reducing the number of cases and deaths and increasing the probability of elimination.