Artificial Intelligence Applied to Gene Expression Testing (IVIGET) to Predict Trivalent Inactivated Influenza Vaccine Immunogenicity in HIV Infected Children.
Nicola Cotugno, Veronica Santilli, Giuseppe Rubens Pascucci, Emma Concetta Manno, Lesley De Armas, Suresh Pallikkuth, Annalisa Deodati, Donato Amodio, Paola Zangari, Sonia Zicari, Alessandra Ruggiero, Martina Fortin, Christina Bromley, Rajendra Pahwa, Paolo Rossi, Savita Pahwa, Paolo Palma
Author Information
Nicola Cotugno: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Veronica Santilli: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Giuseppe Rubens Pascucci: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Emma Concetta Manno: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Lesley De Armas: Miami Center for AIDS Research, Department of Microbiology and Immunology, Miller School of Medicine, University of Miami, Miami, FL, United States.
Suresh Pallikkuth: Miami Center for AIDS Research, Department of Microbiology and Immunology, Miller School of Medicine, University of Miami, Miami, FL, United States.
Annalisa Deodati: Academic Department of Pediatrics (DPUO), Research Unit of Growth Disorders, Bambino Gesù Children's Hospital, Rome, Italy.
Donato Amodio: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Paola Zangari: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Sonia Zicari: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Alessandra Ruggiero: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Martina Fortin: BioStat Solutions, Inc., Frederick, MD, United States.
Christina Bromley: BioStat Solutions, Inc., Frederick, MD, United States.
Rajendra Pahwa: Miami Center for AIDS Research, Department of Microbiology and Immunology, Miller School of Medicine, University of Miami, Miami, FL, United States.
Paolo Rossi: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
Savita Pahwa: Miami Center for AIDS Research, Department of Microbiology and Immunology, Miller School of Medicine, University of Miami, Miami, FL, United States.
Paolo Palma: Academic Department of Pediatrics (DPUO), Research Unit of Congenital and Perinatal Infections, Bambino Gesù Children's Hospital, Rome, Italy.
The number of patients affected by chronic diseases with special vaccination needs is burgeoning. In this scenario, predictive markers of immunogenicity, as well as signatures of immune responses are typically missing even though it would especially improve the identification of personalized immunization practices in these populations. We aimed to develop a predictive score of immunogenicity to Influenza Trivalent Inactivated Vaccination (TIV) by applying deep machine learning algorithms using transcriptional data from sort-purified lymphocyte subsets after stimulation. Peripheral blood mononuclear cells (PBMCs) collected before TIV from 23 vertically HIV infected children under ART and virally controlled were stimulated with p09/H1N1 peptides (stim) or left unstimulated (med). A multiplexed-qPCR for 96 genes was made on fixed numbers of 3 B cell subsets, 3 T cell subsets and total PBMCs. The ability to respond to TIV was assessed through hemagglutination Inhibition Assay (HIV) and ELIspot and patients were classified as Responders (R) and Non Responders (NR). A predictive modeling framework was applied to the data set in order to define genes and conditions with the higher predicted probability able to inform the final score. Twelve NR and 11 R were analyzed for gene expression differences in all subsets and 3 conditions [med, stim or Δ (stim-med)]. Differentially expressed genes between R and NR were selected and tested with the Adaptive Boosting Model to build a prediction score. The score obtained from subsets revealed the best prediction score from 46 genes from 5 different subsets and conditions. Calculating a combined score based on these 5 categories, we achieved a model accuracy of 95.6% and only one misclassified patient. These data show how a predictive bioinformatic model applied to transcriptional analysis deriving from stimulated lymphocytes subsets may predict poor or protective vaccination immune response in vulnerable populations, such as HIV-infected individuals. Future studies on larger cohorts are needed to validate such strategy in the context of vaccination trials.
