I.S. Panchenko1, V.V. Rodionov2, O.V. Burmenskaya2, V.V. Kometova2, V.K. Bozhenko3, M.G. Sharafutdinov1, S.V. Panchenko1, L.V. Matveeva1
1Ulyanovsk State University, Ulyanovsk
2National Medical Research Center of Obstetrics, Gynecology and Perinatology named after Acad. V.I. Kulakov, Moscow
3Russian Scientific Center of X-ray Radiology, Moscow
Panchenko I.S. – Assistant Professor of the Department of Oncology and Radiodiagnostics named after O.P. Modnikov
Lev Tolstoy St., 42, 432063, Ulyanovsk, Russian Federation, tel.: +7 (8422) 32-39-05, e-mail: pan91ch@yandex.ru, ORCID ID: 0000-0001-7923-4317
Abstract. The study presents a Shiny application for automatic classification of patients with triple-negative breast cancer (TNBC) into four clusters with different prognosis of overall survival. The classification is based on the expression of six genes (AR, MKi67, FOXA1, MMP11, SCGB2A2, MIA) and is implemented using a discriminant function with unique coefficients for each cluster. The application allows researchers to quickly and accurately determine the patient’s belonging to a certain group, which can be useful for a personalized approach to treatment. We demonstrate the effectiveness of the application on real data, showing its high accuracy (95%) and speed (< 0.1 sec). The application is available online and can be used in clinical practice and scientific research.
Key words: triple-negative breast cancer (TNBC), classification, Shiny application.