Machine Learning\nand Hyperspectral Imaging for Analysis\nof Human Papillomaviruses (HPV) Vaccine Self-Healing Particles

Human papillomaviruses (HPV) are known to cause a variety\nof diseases,\nincluding cervical cancer and genital warts. HPV is a highly prevalent\nvirus and is considered the most common sexually transmitted disease.\nBecause of the risks associated with HPV, Gardasil, a quadrivalent\nrecombinant vaccine, was developed by Merck & Co., Inc., Rahway,\nNJ, USA, and approved by the Food and Drug Administration (FDA) in\n2006. The second generation of the vaccine, Gardasil9, was subsequently\napproved by the FDA in 2014, providing significant protection against\nHPV. The HPV vaccine may be given as 2 or 3 doses; however, vaccine\nadministration as a single dose with a sustained release mechanism\nmay potentially offer benefits to meet emerging health needs. To explore\nthis, HPV vaccines were formulated within microporous self-healing\nparticles (SHPs) to enable potential controlled release of HPV virus-like\nparticle (VLP) antigen. Machine learning, in the form of multivariate\ncurve resolution-alternating least-squares (MCR-ALS), with Raman hyperspectral\nimaging was used to determine the molecular identity and spatial distribution\nof all relevant species within this HPV vaccine formulation. The results\nindicate that machine learning with Raman hyperspectral imaging was\nable to spatially resolve HPV VLP antigens within SHP vaccines for\nthe <i>first</i> time, providing crucial information necessary\nfor vaccine development.