A multi-layer model for the early detection of COVID-19.

Current COVID-19 screening efforts mainly rely on reported symptoms and the potential exposure to infected individuals. Here, we developed a machine-learning model for COVID-19 detection that uses four layers of information: (i) sociodemographic characteristics of the individual, (ii) spatio-temporal patterns of the disease, (iii) medical condition and general health consumption of the individual and (iv) information reported by the individual during the testing episode. We evaluated our model on 140 682 members of Maccabi Health Services who were tested for COVID-19 at least once between February and October 2020. These individuals underwent, in total, 264 516 COVID-19 PCR tests, out of which 16 512 were positive. Our multi-layer model obtained an area under the curve (AUC) of 81.6% when evaluated over all the individuals in the dataset, and an AUC of 72.8% when only individuals who did not report any symptom were included. Furthermore, considering only information collected before the testing episode-i.e. before the individual had the chance to report on any symptom-our model could reach a considerably high AUC of 79.5%. Our ability to predict early on the outcomes of COVID-19 tests is pivotal for breaking transmission chains, and can be used for a more efficient testing policy.

Native human autoantibodies targeting GIPC1 identify differential expression in malignant tumors of the breast and ovary.

BACKGROUND: We have been studying the native humoral immune response to cancer and have isolated a library of fully human autoantibodies to a variety of malignancies. We previously described the isolation and characterization of two fully human monoclonal antibodies, 27.F7 and 27.B1, from breast cancer patients that target the protein known as GIPC1, an accessory PDZ-domain binding protein involved in regulation of G-protein signaling. Human monoclonal antibodies, 27.F7 and 27.B1, to GIPC1 demonstrate specific binding to malignant breast cancer tissue with no reactivity with normal breast tissue. METHODS: The current study employs cELISA, flow cytometry, Western blot analysis as well as immunocytochemistry, and immunohistochemistry. Data is analyzed statistically with the Fisher one-tail and two-tail tests for two independent samples. RESULTS: By screening several other cancer cell lines with 27.F7 and 27.B1 we found consistently strong staining of other human cancer cell lines including SKOV-3 (an ovarian cancer cell line). To further clarify the association of GIPC1 with breast and ovarian cancer we carefully studied 27.F7 and 27.B1 using immunocytochemical and immunohistochemical techniques. An immunohistochemical study of normal ovarian tissue, benign, borderline and malignant ovarian serous tumors, and different types of breast cancer revealed high expression of GIPC1 protein in neoplastic cells. Interestingly, antibodies 27.F7 and 27.B1 demonstrate differential staining of borderline ovarian tumors. Examination of different types of breast cancer demonstrates that the level of GIPC1 expression depends on tumor invasiveness and displays a higher expression than in benign tumors. CONCLUSION: The present pilot study demonstrates that the GIPC1 protein is overexpressed in ovarian and breast cancer, which may provide an important diagnostic and prognostic marker and will constitute the basis for further study of the role that this protein plays in malignant diseases. In addition, this study suggests that human monoclonal antibodies 27.F7 and 27.B1 should be further evaluated as potential diagnostic tools.