PROJECT SUMMARY One-third of all women of reproductive age will experience nonmenstrual pelvic pain at some point in their lives and one-third of outpatient visits to gynecologists in the U.S. are for evaluation of abnormal uterine bleeding. For many women, these symptoms accompany infertility which is reported in ~10% of all US women and even higher percentages worldwide. For almost all of these women, these conditions result in a diagnostic odyssey wherein women struggle through multiple physicians over many years for a definitive diagnosis, frequently culminating in invasive laparoscopy or hysteroscopy with dilation and curettage (D&C) for definitive diagnosis. To reduce the burden of diagnosis and enable early treatment, MDDx, Inc. is developing the first biomarker- based diagnostic test to enable minimally invasive simultaneous diagnosis of four of the most common causes which together result in chronic pain, uterine bleeding and infertility: adenomyosis, endometrial polyps, leiomyoma, and endometriosis. MDDx, Inc. has been leveraging access to >12 years of longitudinally collected and deeply annotated biobanked uterine lavage samples from the Gynecologic Cancer Translational Research Program (Icahn School of Medicine at Mount Sinai; New York, NY and Nuvance Health; Danbury, CT) to identify diagnostic autoantibodies (AAb) that could serve as diagnostic biomarkers for these benign gynecological diseases. By performing AAb profiling against the entire human proteome and applying our novel machine-learning based method for classification of molecular profiles we have determined that there is a common set of ~200 biomarkers that could be used to diagnose women with adenomyosis, endometrial polyps, leiomyoma, or endometriosis. The goal of Phase I is to finalize and validate the optimized set of ~200 diagnostic AAbs, while Phase II will focus on validation of the commercial diagnostic assay. In Aim 1 we will expand our proprietary database of uterine lavage autoantibody profiles to ensure that we have a sample size (~935) that will enable us to confidently apply our machine learning approaches to identifying the minimal panel of AAbs for the diagnostic. We will use this enhanced database to identify a prototype panel of ~200 AAbs for construction of classification scoring functions to distinguish between adenomyosis, endometrial polyps, leiomyoma, and endometriosis. In Aim 2 we will perform a blinded validation and performance study using an independent set of 300 uterine lavage samples to provide proof-of- concept for clinically useful sensitivity and specificity prior to large scale prospective validation in Phase II. Successful completion of this Phase I program will identify the optimized panel of AAbs for an affordable, laboratory-based diagnostic test that will significantly reduce the number of women who will need to undergo laparoscopy or hysteroscopy with D&C for definitive diagnosis, enabling early treatment of disease and reducing the s...