Evolutionary Optimization of COVID-19 Vaccine Distribution With Evolutionary Demands

Vaccination uptake has become the key factor that will determine our success in containing the coronavirus pneumonia (COVID-19) pandemic. Efficient distribution of vaccines to inoculation spots is crucial to curtailing the spread of the novel COVID-19 pandemic. Normally, in a big city, a huge number of vaccines need to be transported from central depot(s) through a set of satellites to widely scattered inoculation spots by special-purpose vehicles every day. Such a large two-echelon vehicle routing problem is computationally difficult. Moreover, the demands for vaccines evolve with the epidemic spread over time, and the actual demands are hard to determine early and exactly, which not only increases the problem difficulty but also prolongs the distribution time. Based on our practical experience of COVID-19 vaccine distribution in China, we present a hybrid machine learning and evolutionary computation method, which first uses a fuzzy deep learning model to forecast the demands for vaccines for each next day, such that we can predistribute the forecasted number of vaccines to the satellites in advance;after obtaining the actual demands, it uses an evolutionary algorithm (EA) to route vehicles to distribute vaccines from the satellites/depots to the inoculation spots on each day. The EA saves historical problem instances and their high-quality solutions in a knowledge base, so as to capture inherent relationship between evolving problem inputs to solutions;when solving a new problem instance on each day, the EA utilizes historical solutions that perform well on the similar instances to improve initial solution quality and, hence, accelerate convergence. Computational results on real-world instances of vaccine distribution demonstrate that the proposed method can produce solutions with significantly shorter distribution time compared to state-of-the-arts and, hence, contribute to accelerating the achievement of herd immunity.

An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19

In this work, we propose to use a state-of-the-art evolutionary algorithm to set the discretization thresholds for gene expression profiles, using feedback from a classifier in order to maximize the accuracy of the predictions based on the discretized gene expression levels, while at the same time minimizing the number of different profiles obtained, to ease the understanding of the expert. The methodology is applied to a dataset containing COVID-19 patients that developed either mild or severe symptoms. The results show that the evolutionary approach performs better than a traditional discretization based on statistical analysis, and that it does preserve the sense-making necessary for practitioners to trust the results. © 2022 Owner/Author.

Evolutionary Optimization of COVID-19 Vaccine Distribution with Evolutionary Demands

Vaccination uptake has become the key factor that will determine our success in containing the COVID-19 pandemic. Efficient distribution of vaccines to inoculation spots is crucial to curtailing the spread of the novel coronavirus pneumonia (COVID-19) pandemic. Normally, in a big city, a huge number of vaccines need to be transported from central depot(s) through a set of satellites to widely-scattered inoculation spots by special-purpose vehicles every day. Such a large two-echelon vehicle routing problem is computationally difficult. Moreover, the demands for vaccines evolve with the epidemic spread over time, and the actual demands are hard to determine early and exactly, which not only increases the problem difficulty but also prolongs the distribution time. Based on our practical experience of COVID-19 vaccine distribution in China, we present a hybrid machine learning and evolutionary computation method, which first uses a fuzzy deep learning model to forecast the demands for vaccines for each next day, such that we can pre-distribute the forecasted number of vaccines to the satellites in advance;after obtaining the actual demands, it uses an evolutionary algorithm (EA) to route vehicles to distribute vaccines from the satellites/depots to the inoculation spots on each day. The EA saves historical problem instances and their high-quality solutions in a knowledge base, so as to capture inherent relationship between evolving problem inputs to solutions;when solving a new problem instance on each day, the EA utilizes historical solutions that perform well on the similar instances to improve initial solution quality and hence accelerate convergence. Computational results on real-world instances of vaccine distribution demonstrate that the proposed method can produce solutions with significantly shorter distribution time compared to state-of-the-arts, and hence contribute to accelerating the achievement of herd immunity. IEEE

Human/SARS-CoV-2 genome-scale metabolic modeling to discover potential antiviral targets for COVID-19.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has caused a substantial increase in mortality and economic and social disruption. The absence of US Food and Drug Administration-approved drugs for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) highlights the need for new therapeutic drugs to combat COVID-19. METHODS: The present study proposed a fuzzy hierarchical optimization framework for identifying potential antiviral targets for COVID-19. The objectives in the decision-making problem were not only to evaluate the elimination of the virus growth, but also to minimize side effects causing treatment. The identified candidate targets could promote processes of drug discovery and development. SIGNIFICANT FINDINGS: Our gene-centric method revealed that dihydroorotate dehydrogenase (DHODH) inhibition could reduce viral biomass growth and metabolic deviation by 99.4% and 65.6%, respectively, and increase cell viability by 70.4%. We also identified two-target combinations that could completely block viral biomass growth and more effectively prevent metabolic deviation. We also discovered that the inhibition of two antiviral metabolites, cytidine triphosphate (CTP) and uridine-5'-triphosphate (UTP), exhibits effects similar to those of molnupiravir, which is undergoing phase III clinical trials. Our predictions also indicate that CTP and UTP inhibition blocks viral RNA replication through a similar mechanism to that of molnupiravir.