COVID-19 disease severity and symptoms can vary considerably among infected patients. Even though most studies investigating COVID-19 have focused on patients with a severe form of the disease, investigations of asymptomatic infection have provided new insights into patient-specific immunological features that protect patients from COVID-19 symptoms. Recent studies have shown an association between common human leukocyte antigen (HLA) alleles such and asymptomatic COVID-19 infections. Here we utilize machine learning in conjunction with explainable AI (XAI) to identify alleles in five HLA loci that can be either “protective” or “atrisk” for symptomatic COVID-19. Data from the public online HLA-COVID database (composed of 3238 samples) was used for training and validation of multiple ML classification models to identify the top performing model. The model was then further processed with XAI via SHAP (SHapley Additive exPlanations) to identify the “protective” and “at-risk” HLA alleles. We determined that HLA-B *07:02, *40:01, and *15:01 are associated with asymptomatic disease, i.e., are protective and HLA-B* 44:01, 39:06, and 51:01 are associated with symptomatic disease i.e., place the individual at greater risk. This study provides a proof-of-concept study for utilizing machine learning to provide valuable insights for Covid-19 patients. These findings can be translated into algorithms that can help physicians personalize COVID-19 treatment and achieve better clinical outcomes.

The advancements in next-generation sequencing have made it possible to effectively detect somatic mutations, which has led to the development of personalized neoantigen cancer vaccines that are tailored to the unique variants found in a patient's cancer. These vaccines can provide significant clinical benefit by leveraging the patient's immune response to eliminate malignant cells. However, determining the optimal vaccine dose for each patient is a challenge due to the heterogeneity of tumors. To address this challenge, we formulate a mathematical dose optimization problem based on a previous mathematical model that encompasses the immune response cascade produced by the vaccine in a patient. We propose an optimization approach to identify the optimal personalized vaccine doses, considering a fixed vaccination schedule, while simultaneously minimizing the overall number of tumor and activated T cells. To validate our approach, we perform in silico experiments on six real-world clinical trial patients with advanced melanoma. We compare the results of applying an optimal vaccine dose to those of a suboptimal dose (the dose used in the clinical trial and its deviations). Our simulations reveal that an optimal vaccine regimen of higher initial doses and lower final doses may lead to a reduction in tumor size for certain patients. Our mathematical dose optimization offers a promising approach to determining an optimal vaccine dose for each patient and improving clinical outcomes.

Cancer vaccines are an important component of the cancer immunotherapy toolkit enhancing immune response to malignant cells by activating CD4+ and CD8+ T cells. Multiple successful clinical applications of cancer vaccines have shown good safety and efficacy. Despite the notable progress, significant challenges remain in obtaining consistent immune responses across heterogeneous patient populations, as well as various cancers. We present a mechanistic mathematical model describing key interactions of a personalized neoantigen cancer vaccine with an individual patient's immune system. Specifically, the model considers the vaccine concentration of tumor-specific antigen peptides and adjuvant, the patient's major histocompatibility complexes I and II copy numbers, tumor size, T cells, and antigen presenting cells. We parametrized the model using patient-specific data from a clinical study in which individualized cancer vaccines were used to treat six melanoma patients. Model simulations predicted both immune responses, represented by T cell counts, to the vaccine as well as clinical outcome (determined as change of tumor size). This model, although complex, can be used to describe, simulate, and predict the behavior of the human immune system to a personalized cancer vaccine.

The development of neutralizing anti-drug-antibodies to the Factor VIII protein-therapeutic is currently the most significant impediment to the effective management of hemophilia A. Common non-synonymous single nucleotide polymorphisms (ns-SNPs) in the F8 gene occur as six haplotypes in the human population (denoted H1 to H6) of which H3 and H4 have been associated with an increased risk of developing anti-drug antibodies. There is evidence that CD4+ T-cell response is essential for the development of anti-drug antibodies and such a response requires the presentation of the peptides by the MHC-class-II (MHC-II) molecules of the patient. We measured the binding and half-life of peptide-MHC-II complexes using synthetic peptides from regions of the Factor VIII protein where ns-SNPs occur and showed that these wild type peptides form stable complexes with six common MHC-II alleles, representing 46.5% of the North American population. Next, we compared the affinities computed by NetMHCIIpan, a neural network-based algorithm for MHC-II peptide binding prediction, to the experimentally measured values and concluded that these are in good agreement (area under the ROC-curve of 0.778 to 0.972 for the six MHC-II variants). Using a computational binding predictor, we were able to expand our analysis to (a) include all wild type peptides spanning each polymorphic position; and (b) consider more MHC-II variants, thus allowing for a better estimation of the risk for clinical manifestation of anti-drug antibodies in the entire population (or a specific sub-population). Analysis of these computational data confirmed that peptides which have the wild type sequence at positions where the polymorphisms associated with haplotypes H3, H4 and H5 occur bind MHC-II proteins significantly more than a negative control. Taken together, the experimental and computational results suggest that wild type peptides from polymorphic regions of FVIII constitute potential T-cell epitopes and thus could explain the increased incidence of anti-drug antibodies in hemophilia A patients with haplotypes H3 and H4.

MOTIVATION: Systematic Evolution of Ligands by EXponential Enrichment (SELEX) represents a state-of-the-art technology to isolate single-stranded (ribo)nucleic acid fragments, named aptamers, which bind to a molecule (or molecules) of interest via specific structural regions induced by their sequence-dependent fold. This powerful method has applications in designing protein inhibitors, molecular detection systems, therapeutic drugs and antibody replacement among others. However, full understanding and consequently optimal utilization of the process has lagged behind its wide application due to the lack of dedicated computational approaches. At the same time, the combination of SELEX with novel sequencing technologies is beginning to provide the data that will allow the examination of a variety of properties of the selection process. RESULTS: To close this gap we developed, Aptamotif, a computational method for the identification of sequence-structure motifs in SELEX-derived aptamers. To increase the chances of identifying functional motifs, Aptamotif uses an ensemble-based approach. We validated the method using two published aptamer datasets containing experimentally determined motifs of increasing complexity. We were able to recreate the author's findings to a high degree, thus proving the capability of our approach to identify binding motifs in SELEX data. Additionally, using our new experimental dataset, we illustrate the application of Aptamotif to elucidate several properties of the selection process.