PURPOSE OF REVIEW: The aim of this study was to evaluate the relationship between infection with SARS-CoV-2 and autoimmunity. RECENT FINDINGS: Coronavirus disease 2019 (COVID-19) is an infectious disease caused by severe acute respiratory syndrome (SARS) associated coronavirus 2 (SARS-CoV-2). Although most of the infected individuals are asymptomatic, a proportion of patients with COVID-19 develop severe disease with multiple organ injuries. Evidence suggests that some medications used to treat autoimmune rheumatologic diseases might have therapeutic effect in patients with severe COVID-19 infections, drawing attention to the relationship between COVID-19 and autoimmune diseases. COVID-19 shares similarities with autoimmune diseases in clinical manifestations, immune responses and pathogenic mechanisms. Robust immune reactions participate in the pathogenesis of both disease conditions. Autoantibodies as a hallmark of autoimmune diseases can also be detected in COVID-19 patients. Moreover, some patients have been reported to develop autoimmune diseases, such as Guillain--Barre syndrome or systemic lupus erythematosus, after COVID-19 infection. It is speculated that SARS-CoV-2 can disturb self-tolerance and trigger autoimmune responses through cross-reactivity with host cells. The infection risk and prognosis of COVID-19 in patients with autoimmune diseases remains controversial, but patient adherence to medication regimens to prevent autoimmune disease flares is strongly recommended. SUMMARY: We present a review of the association between COVID-19 and autoimmune diseases, focusing on similarities in immune responses, cross-reactivity of SARS-CoV-2, the development of autoimmune diseases in COVID-19 patients and the risk of COVID-19 infection in patients with preexisting autoimmune conditions.

COVID-19 and autoimmune diseases.

Drug discovery aims at finding new compounds with specific chemical properties for the treatment of diseases. In the last years, the approach used in this search presents an important component in computer science with the skyrocketing of machine learning techniques due to its democratization. With the objectives set by the Precision Medicine initiative and the new challenges generated, it is necessary to establish robust, standard and reproducible computational methodologies to achieve the objectives set. Currently, predictive models based on Machine Learning have gained great importance in the step prior to preclinical studies. This stage manages to drastically reduce costs and research times in the discovery of new drugs. This review article focuses on how these new methodologies are being used in recent years of research. Analyzing the state of the art in this field will give us an idea of where cheminformatics will be developed in the short term, the limitations it presents and the positive results it has achieved. This review will focus mainly on the methods used to model the molecular data, as well as the biological problems addressed and the Machine Learning algorithms used for drug discovery in recent years.

A review on machine learning approaches and trends in drug discovery.

Robotics and automation provide potentially paradigm shifting improvements in the way materials are synthesized and characterized, generating large, complex data sets that are ideal for modeling and analysis by modern machine learning (ML) methods. Nanomaterials have not yet fully captured the benefits of automation, so lag behind in the application of ML methods of data analysis. Here, some key developments in, and roadblocks to the application of ML methods are reviewed to model and predict potentially adverse biological and environmental effects of nanomaterials. This work focuses on the diverse ways a range of ML algorithms are applied to understand and predict nanomaterials properties, provides examples of the application of traditional ML and deep learning methods to nanosafety, and provides context and future perspectives on developments that are likely to occur, or need to occur in the near future that allow artificial intelligence to make a deeper contribution to nanosafety.

Role of Artificial Intelligence and Machine Learning in Nanosafety.

Machine Learning (ML) techniques have been applied in the field of nanotoxicology with very encouraging results. Adverse effects of nanoforms are affected by multiple features described by theoretical descriptors, nano-specific measured properties, and experimental conditions. ML has been proven very helpful in this field in order to gain an insight into features effecting toxicity, predicting possible adverse effects as part of proactive risk analysis, and informing safe design. At this juncture, it is important to document and categorize the work that has been carried out. This study investigates and bookmarks ML methodologies used to predict nano (eco)-toxicological outcomes in nanotoxicology during the last decade. It provides a review of the sequenced steps involved in implementing an ML model, from data pre-processing, to model implementation, model validation, and applicability domain. The review gathers and presents the step-wise information on techniques and procedures of existing models that can be used readily to assemble new nanotoxicological in silico studies and accelerates the regulation of in silico tools in nanotoxicology. ML applications in nanotoxicology comprise an active and diverse collection of ongoing efforts, although it is still in their early steps toward a scientific accord, subsequent guidelines, and regulation adoption. This study is an important bookend to a decade of ML applications to nanotoxicology and serves as a useful guide to further in silico applications.

https://www.mdpi.com/2079-4991/10/1/116/pdf

Practices and Trends of Machine Learning Application in Nanotoxicology.

Artificial intelligence (AI) and machine learning, in particular, have gained significant interest in many fields, including pharmaceutical sciences. The enormous growth of data from several sources, the recent advances in various analytical tools, and the continuous developments in machine learning algorithms have resulted in a rapid increase in new machine learning applications in different areas of pharmaceutical sciences. This review summarizes the past, present, and potential future impacts of machine learning technologies on different areas of pharmaceutical sciences, including drug design and discovery, preformulation, and formulation. The machine learning methods commonly used in pharmaceutical sciences are discussed, with a specific emphasis on artificial neural networks due to their capability to model the nonlinear relationships that are commonly encountered in pharmaceutical research. AI and machine learning technologies in common day-to-day pharma needs as well as industrial and regulatory insights are reviewed. Beyond traditional potentials of implementing digital technologies using machine learning in the development of more efficient, fast, and economical solutions in pharmaceutical sciences are also discussed.

/pdf/digital-pharmaceutical-sciences-tlwt1h0bi1.pdf

Digital Pharmaceutical Sciences.

Prediction reliability of QSAR models: an overview of various validation tools

A novel quantitative read-across tool designed purposefully to fill the existing gaps in nanosafety data

The application of in silico methods in the risk assessment of metal oxide nanoparticles (MNPs) and data gap filling has found profound usability. Followed by the success of periodic table-based descriptors in the modeling study, we have reported here a pool of second generation periodic table descriptors for better understanding the mechanism of toxicity of MNPs towards three species, namely, E. coli, a human keratinocyte cell line (HaCaT) and zebrafish embryos. These descriptors are easily derived from the molecular formula and periodic table in no time and can be used in models with a prediction ability similar to or even better than those involving quantum chemical descriptors and physicochemical indices. Employing the developed 1st and 2nd generation periodic table-based descriptors, we have developed single species quantitative structure–toxicity relationship (QSTR) models and interspecies quantitative structure–toxicity–toxicity relationship (i-QSTTR) models to understand the relationship of the toxicities of metal oxide nanoparticles with different species along with the identification of the major mechanism(s) for such toxicities. These models further helped in extrapolating toxicity when the data for one species are available and the data for other species are unavailable. Further, we have made predictions for a set of 42 true external MNPs, employing all three QSTR models individually, the toxicity data for all three species using a two-stage prediction confidence check through the applicability domain and the “prediction reliability indicator”. The developed models interpreted that the oxidation state of the metal, the electronegativity of the metal oxide and the core count of the metal play substantial roles in the toxicity mediation of the MNPs irrespective of the species and response. Along with the first generation descriptors, the newly developed second generation periodic table-based descriptors can encode the toxicity features of MNPs efficiently as compared to classical quantum chemical descriptors involving time-consuming computations and physicochemical descriptors involving experimental tests.

Second generation periodic table-based descriptors to encode toxicity of metal oxide nanoparticles to multiple species: QSTR modeling for exploration of toxicity mechanisms

Dengue, zika and chikungunya have severe public health concerns in several countries. Human modification of the natural environment continues to create habitats in which mosquitoes, vectors of a wide variety of human and animal pathogens, thrive, which can bring about an enormous negative impact on public health if not controlled properly. Quantitative structure–activity relationship (QSAR) modeling has been applied in this work with the aim of exploring features contributing to promising larvicidal properties against the vector Aedes aegypti (Diptera: Culicidae). A dataset of 61 plant derived compounds reported in previous literature was used in this present study. A genetic algorithm (GA) was used for QSAR model development employing the “Double Cross Validation” (DCV) tool available at http://teqip.jdvu.ac.in/QSAR_Tools/. The DCV tool removes any bias in descriptor selection from a fixed composition of a training set and often provides an optimum solution in terms of predictivity. Simple topological descriptors, the “Extended Topochemical Atom” (ETA) indices developed by the present authors' group, were used for model development. These descriptors do not require pretreatment of molecular structures by conformational analysis or energy minimization before model development, thus saving computational time and resources. They also avoid ambiguities with respect to the existence of compounds in various conformational states leading to the loss of predictive capability in QSAR models. A number of models were generated from GA, and further, the descriptors appearing in the best model obtained from GA were subjected to partial least squares (PLS) regression to obtain the final robust model. The developed model was validated extensively using different validation metrics to check the reliability and predictivity of the model for enhancing confidence in QSAR predictions. Based on the insights obtained from the PLS model, we can conclude that the presence of hydrogen bond acceptor atoms, the presence of multiple bonds as well as sufficient lipophilicity and a limited polar surface area play crucial roles in regulating the activity of the compounds.

/pdf/chemometric-modeling-of-larvicidal-activity-of-plant-derived-5llzvc0bsi.pdf

Chemometric modeling of larvicidal activity of plant derived compounds against zika virus vectorAedes aegypti: application of ETA indices

As of 2 September 2020, the 2019 novel coronavirus or SARS CoV-2 has been responsible for more than 2,56,02,665 infections and 8,52,768 deaths worldwide. There has been an urgent need of newer drug discovery to tackle the situation. Severe acute respiratory syndrome-associated coronavirus 3C-like protease (or 3CLpro) is a potential target as anti-SARS agents as it plays a vital role in the viral life cycle. This study aims at developing a quantitative structure-activity relationship (QSAR) model against a group of 3CLpro inhibitors to study their structural requirements for their inhibitory activity. Further, molecular docking studies were carried out which helped in the justification of the QSAR findings. Moreover, molecular dynamics simulation study was performed for selected compounds to check the stability of interactions as suggested by the docking analysis. The current QSAR model was further used in the prediction and screening of large databases within a short time.Communicated by Ramaswamy H. Sarma.

Priyanka De

Papers

Prediction reliability of QSAR models: an overview of various validation tools

A novel quantitative read-across tool designed purposefully to fill the existing gaps in nanosafety data

Second generation periodic table-based descriptors to encode toxicity of metal oxide nanoparticles to multiple species: QSTR modeling for exploration of toxicity mechanisms

Chemometric modeling of larvicidal activity of plant derived compounds against zika virus vectorAedes aegypti: application of ETA indices

In silico modeling for quick prediction of inhibitory activity against 3CLpro enzyme in SARS CoV diseases