MPMirjana Pavlović

Mirjana Pavlović

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mirjana Pavlović has a total of 49 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Connecting COVID-19 with Autoimmunity

    by Aritra Ghosh, Mirjana D. Pavlovic, Maria M. Larrondo-Petrie

  • Open Access

    Revolutionizing Vaccine Development for COVID-19: A Review of AI-Based Approaches

    by Aritra Ghosh, Maria M. Larrondo-Petrie, Mirjana Pavlovic

    The evolvement of COVID-19 vaccines is rapidly being revolutionized using artificial intelligence-based technologies. Small compounds, peptides, and epitopes are collected to develop new therapeutics. These substances can also guide artificial intelligence-based modeling, screening, or creation. Machine learning techniques are used to leverage pre-existing data for COVID-19 drug detection and vaccine advancement, while artificial intelligence-based models are used for these purposes. Models based on artificial intelligence are used to evaluate and recognize the best candidate targets for future therapeutic development. Artificial intelligence-based strategies can be used to address issues with the safety and efficacy of COVID-19 vaccine candidates, as well as issues with manufacturing, storage, and logistics. Because antigenic peptides are effective at eliciting immune responses, artificial intelligence algorithms can assist in identifying the most promising COVID-19 vaccine candidates. Following COVID-19 vaccination, the first phase of the vaccine-induced immune response occurs when major histocompatibility complex (MHC) class II molecules (typically bind peptides of 12–25 amino acids) recognize antigenic peptides. Therefore, AI-based models are used to identify the best COVID-19 vaccine candidates and ensure the efficacy and safety of vaccine-induced immune responses. This study explores the use of artificial intelligence-based approaches to address logistics, manufacturing, storage, safety, and effectiveness issues associated with several COVID-19 vaccine candidates. Additionally, we will evaluate potential targets for next-generation treatments and examine the role that artificial intelligence-based models can play in identifying the most promising COVID-19 vaccine candidates, while also considering the effectiveness of antigenic peptides in triggering immune responses. The aim of this project is to gain insights into how artificial intelligence-based approaches could revolutionize the development of COVID-19 vaccines and how they can be leveraged to address challenges associated with vaccine development. In this work, we highlight potential barriers and solutions and focus on recent improvements in using artificial intelligence to produce COVID-19 drugs and vaccines, as well as the prospects for intelligent training in COVID-19 treatment discovery.


  • Open Access

    The Impact of COVID-19 Vaccination on Autoimmune Disorders: A Descriptive Analysis

    by Aritra Ghosh, Maria M. Larrondo-Petrie, Mirjana Pavlovic

    The COVID-19 pandemic has had a substantial impact on global health, notably the virus's association with autoimmune illnesses. Autoimmune illnesses occur when the immune system of the body targets healthy cells, causing damage and inflammation. The potential impact of COVID-19 on autoimmune disorders, the hazards of COVID-19 vaccinations for persons with autoimmune diseases, and the potential risks of COVID-19 vaccines are all discussed in this essay. COVID-19 can cause autoimmune illnesses by causing inflammation, organ and tissue damage, and molecular mimicry, in which the immune system mistakenly assaults healthy cells for the virus. However, not everyone infected with COVID-19 develops autoimmune disorders. While some research has found a link between COVID-19 and autoimmune illnesses, this does not always suggest causation. Other factors, such as genetics and environment, may also play a role in the emergence of autoimmune illnesses. COVID-19 can aggravate existing autoimmune disorders by causing the immune system to attack healthy cells, making management more difficult and increasing the risk of consequences. People with autoimmune disorders, on the other hand, may not be at a higher risk of severe COVID-19 than the general population. Some research has found that persons with autoimmune disorders are more likely to have severe COVID-19, whereas others have found no difference. COVID-19 vaccinations may represent dangers to persons with autoimmune illnesses since they contain antigens that can activate the immune system. Furthermore, due to their already overactive immune systems, some vaccines may not perform as well for people with autoimmune disorders, and some people with autoimmune diseases may have severe reactions to immunizations, producing inflammation and other symptoms. COVID-19 may not be any more hazardous to those with autoimmune illnesses than it is to the general population. The connection between COVID-19 and autoimmune disorders is complicated and under investigation. While some research implies that people with autoimmune disorders have a higher risk of severe COVID-19, others demonstrate no difference in death rates between them and the general population. There are also counterarguments that COVID-19 can induce and exacerbate autoimmune disorders, as well as worries about COVID-19 vaccine hazards for people who have autoimmune diseases. More research is required to completely understand the influence of COVID-19 on autoimmune illnesses, as well as the dangers and benefits of vaccinations for these people.

  • Open Access

    Rational Vaccine Design for SARS-CoV-2 Virus—A Systematic Review

    by Aritra Ghosh, Mirjana Pavlovic, Maria M. Larrondo-Petrie

    The COVID-19 pandemic has significantly impacted global health and economies, necessitating the development of effective vaccines against the novel virus. Understanding the structure and function of SARS-CoV-2 is crucial for rational vaccine design. The virus consists of several key proteins, including the spike protein, envelope protein, membrane protein, and nucleocapsid protein. The spike protein plays a crucial role in host cell entry by binding to the angiotensin-converting enzyme 2 (ACE2) receptor on human cells. The replication of the virus within host cells is facilitated by various viral proteins, such as the RNA-dependent RNA polymerase (RdRp) and the main protease (Mpro). Rational vaccine design strategies for SARS-CoV-2 primarily focus on targeting the spike protein due to its role in host cell entry. However, developing vaccines against this protein is challenging due to its highly mutable nature and potential conformational changes. Alternative strategies involve using other viral proteins, such as the nucleocapsid protein, which is conserved and essential for viral replication. Considering T-cell responses in vaccine design is also vital as they play a vital role in controlling viral infections. Vaccines that elicit both antibody and T-cell responses are more likely to provide robust and durable immunity against SARS-CoV-2. Advancements in rational vaccine design for SARS-CoV-2 include mRNA-based vaccines, viral vector-based vaccines, and protein subunit vaccines. However, challenges remain in developing a universally effective vaccine, including the emergence of new SARS-CoV-2 variants and mutations that may affect the efficacy of existing vaccines. In conclusion, rational vaccine design for SARS-CoV-2 requires a comprehensive understanding of the virus's structure and function, targeting key viral proteins, and considering T-cell responses.


  • Open Access

    Revolutionizing Vaccine Development for COVID-19: A Review of AI-Based Approaches

    by Aritra Ghosh, Maria M. Petrie, Mirjana Pavlović

    AI-based approaches are increasingly being used to revolutionize vaccine development for COVID-19. Small molecules, peptides, and epitopes are being collected for therapy discovery, which could also direct AI-based models, screening, or generation [1]. AI-based models are being used for drug discovery and vaccine development, and pre-existing data is being leveraged through machine learning approaches for COVID-19 drug discovery and vaccine development [1]. The best candidate targets for future treatment development are being identified and evaluated using AI-based models [1]. AI-based approaches can be used to overcome challenges in manufacturing, storage, logistics, and safety and efficacy issues related to different vaccine candidates for COVID-19 [2]. AI algorithms can help identify the best vaccine candidates for COVID-19 while considering the efficiency of antigenic peptides for immune response generation [2]. The presentation of antigenic peptides by major histocompatibility complex (MHC) class II molecules is the first step after COVID-19 vaccine administration for any vaccine-induced immune response [2]. Thus, AI-based models are being used to identify the best vaccine candidates for COVID-19 and to ensure that the vaccine-induced immune response is efficient and safe. The utilization of AI-based methods to address logistical, manufacturing, storage, safety, and efficacy issues regarding several COVID-19 vaccine candidates will be examined in this study. Additionally, while considering the effectiveness of antigenic peptides for the induction of an immune response, we will determine the best potential targets for the next treatment development and assess how AI-based models can help discover the best vaccine candidates for COVID-19. This research ultimately intends to offer insights into how AI-based techniques can transform COVID-19 vaccine development and how they can be applied to address vaccine development issues. In this paper, we focus on recent advances in using artificial intelligence to develop COVID-19 drugs and vaccines, as well as the potential of intelligent training in discovering COVID-19 therapeutics, highlighting potential challenges and solutions.


  • Top Cited Papers
    Open Access

    The Molecular Basis and Clinical Consequences of Chronic Inflammation in Prostatic Diseases: Prostatitis, Benign Prostatic Hyperplasia, and Prostate Cancer

    by Saheed Oluwasina Oseni, Corey Naar, Mirjana Pavlović, Waseem Asghar, James X. Hartmann, Gregg B. Fields, Nwadiuto Esiobu, James Kumi-Diaka

    Chronic inflammation is now recognized as one of the major risk factors and molecular hallmarks of chronic prostatitis, benign prostatic hyperplasia (BPH), and prostate tumorigenesis. However, the molecular mechanisms by which chronic inflammation signaling contributes to the pathogenesis of these prostate diseases are poorly understood. Previous efforts to therapeutically target the upstream (e.g., TLRs and IL1-Rs) and downstream (e.g., NF-κB subunits and cytokines) inflammatory signaling molecules in people with these conditions have been clinically ambiguous and unsatisfactory, hence fostering the recent paradigm shift towards unraveling and understanding the functional roles and clinical significance of the novel and relatively underexplored inflammatory molecules and pathways that could become potential therapeutic targets in managing prostatic diseases. In this review article, we exclusively discuss the causal and molecular drivers of prostatitis, BPH, and prostate tumorigenesis, as well as the potential impacts of microbiome dysbiosis and chronic inflammation in promoting prostate pathologies. We specifically focus on the importance of some of the underexplored druggable inflammatory molecules, by discussing how their aberrant signaling could promote prostate cancer (PCa) stemness, neuroendocrine differentiation, castration resistance, metabolic reprogramming, and immunosuppression. The potential contribution of the IL1R-TLR-IRAK-NF-κBs signaling molecules and NLR/inflammasomes in prostate pathologies, as well as the prospective benefits of selectively targeting the midstream molecules in the various inflammatory cascades, are also discussed. Though this review concentrates more on PCa, we envision that the information could be applied to other prostate diseases. In conclusion, we have underlined the molecular mechanisms and signaling pathways that may need to be targeted and/or further investigated to better understand the association between chronic inflammation and prostate diseases.


  • Open Access

    Predicting residues involved in anti-DNA autoantibodies with limited neural networks

    by Rachel St. Clair, Michael Teti, Mirjana Pavlovic, William Hahn, Elan Barenholtz

    Computer-aided rational vaccine design (RVD) and synthetic pharmacology are rapidly developing fields that leverage existing datasets for developing compounds of interest. Computational proteomics utilizes algorithms and models to probe proteins for functional prediction. A potentially strong target for computational approach is autoimmune antibodies, which are the result of broken tolerance in the immune system where it cannot distinguish “self” from “non-self” resulting in attack of its own structures (proteins and DNA, mainly). The information on structure, function, and pathogenicity of autoantibodies may assist in engineering RVD against autoimmune diseases. Current computational approaches exploit large datasets curated with extensive domain knowledge, most of which include the need for many resources and have been applied indirectly to problems of interest for DNA, RNA, and monomer protein binding. We present a novel method for discovering potential binding sites. We employed long short-term memory (LSTM) models trained on FASTA primary sequences to predict protein binding in DNA-binding hydrolytic antibodies (abzymes). We also employed CNN models applied to the same dataset for comparison with LSTM. While the CNN model outperformed the LSTM on the primary task of binding prediction, analysis of internal model representations of both models showed that the LSTM models recovered sub-sequences that were strongly correlated with sites known to be involved in binding. These results demonstrate that analysis of internal processes of LSTM models may serve as a powerful tool for primary sequence analysis. Graphical abstract


  • Open Access

    Predicting Residues Involved in Anti-DNA Autoantibodies with Limited Neural Networks

    by Rachel St.Clair, Michael Teti, Mirjana Pavlovic, William Hahn, Elan Barenholtz

    Computer-aided rational vaccine design (RVD) and synthetic pharmacology are rapidly developing fields that leverage existing datasets for developing compounds of interest. Computational proteomics utilizes algorithms and models to probe proteins for functional prediction. A potentially strong target for such a computational approach is autoimmune antibodies which are the result of broken tolerance in the immune system where it cannot distinguish “self” from “non-self” resulting in attack of its own structures (proteins and DNA, mainly). The information on structure, function and pathogenicity of autoantibodies may assist in engineering RVD against autoimmune diseases. Current computational approaches exploit large datasets curated with extensive domain knowledge, most of which include the need for many computational resources and have been applied indirectly to problems of interest for DNA, RNA, and monomer protein binding. Here, we present a novel method for discovering potential binding sites. We employed long short-term memory (LSTM) models trained on FASTA primary sequences directly to predict protein binding in DNA-binding hydrolytic antibodies (abzymes). We also employed CNN models applied to the same dataset. While the CNN model outperformed the LSTM on the primary task of binding prediction, analysis of internal model representations of both models showed that the LSTM models highlighted sub-sequences that were more strongly correlated with sites known to be involved in binding. These results demonstrate that analysis of internal processes of recurrent neural network models may serve as a powerful tool for primary sequence analysis.

  • Strategies in Ebola virus disease (EVD) diagnostics at the point of care

    by Chad T. Coarsey, Nwadiuto Esiobu, Ramswamy Narayanan, Mirjana Pavlovic, Hadi Shafiee, Waseem Asghar

    Ebola virus disease (EVD) is a devastating, highly infectious illness with a high mortality rate. The disease is endemic to regions of Central and West Africa, where there is limited laboratory infrastructure and trained staff. The recent 2014 West African EVD outbreak has been unprecedented in case numbers and fatalities, and has proven that such regional outbreaks can become a potential threat to global public health, as it became the source for the subsequent transmission events in Spain and the USA. The urgent need for rapid and affordable means of detecting Ebola is crucial to control the spread of EVD and prevent devastating fatalities. Current diagnostic techniques include molecular diagnostics and other serological and antigen detection assays; which can be time-consuming, laboratory-based, often require trained personnel and specialized equipment. In this review, we discuss the various Ebola detection techniques currently in use, and highlight the potential future directions pertinent to the development and adoption of novel point-of-care diagnostic tools. Finally, a case is made for the need to develop novel microfluidic technologies and versatile rapid detection platforms for early detection of EVD.


  • Open Access

    Comparison and Analysis of Different Methods for Purification of Autoimmune Antibody Reactive with Single Stranded DNA: A Pilot Study

    by Mirjana Pavlovic, Mirjana Pavlovic Anna Kats, Michelle Cavallo Ran Chen, James X Hartmann

    Purpose: We have compared a two-step affinity purification method, previously developed in house, which utilizes biotinylated oligo-deoxythymidine (dT) bound streptavidin (SA) M-280 magnetic beads and protein G Dynabeads®, with Melon™ Gel, another two step commercial method, for the isolation and purification of human anti-DNA autoantibodies reactive with single stranded DNA (ssDNA), in order to determine which method is more applicable for analysis of antibody subclasses and, potentially subclass functional activities. Results: Although Melon Gel allowed for faster anti-ssDNA autoantibody purification and higher recovery rate, its final product was of lower purity than that of the magnetic bead method, as confirmed with nanogram silver staining method following PhastGelTM non-reducing SDS-PAGE. The polyclonal nature of anti-ssDNA autoantibodies produced by patients with Systemic Lupus Erythematosus (SLE) has been determined and compared with normal human, and B-Chronic Lymphocytic Leucosis-(B-CLL) anti-ssDNA autoantibodies. Characterization of isolated antibodies by isoelectric focusing, western blot analysis and ELISA confirmed them to be human IgGs and detected the presence of all four IgG antibody subclasses with different participation. Additionally, Lab-on chip (Agilent 2100) method, revealed the presence of different MW patterns within lupus IgG subclasses, not detectable by SDS PAGE, which were not consistent with patterns seen in sera of control or in individuals with B-CLL. Conclusions: The results obtained suggest incomparably better purity of antibodies isolated via the magnetic bead method vs. Melon-gel. SDS-PAGE and Lab-on-chip analyses of antibodies revealed the presence of different IgG patterns within human lupus anti-ssDNA autoantibody subclasses than those observed in healthy individuals and B-CLL patients. These patterns may be associated with SLE disease pathogenesis and highlight the importance of further molecular, structural, and functional studies of lupus anti-ssDNA antibodies.