CENTRO DE INVESTIGACION Y DESARROLLO EN INMUNOLOGIA Y ENFERMEDADES INFECCIOSAS
Unidad Ejecutora - UE
congresos y reuniones científicas
MIXTUREpy: A machine learning based method for immuno content characterization of tumor samples in python has been accepted for ORAL presentation
ROCHA, DARIO; CHIODI, GUSTAVO; FERNÁNDEZ, ELMER ANDRÉS; MIRANDA, MATIAS; BOSSIO, ALEJANDRA; GIROTTI, MARÍA ROMINA; PRATO, LAURA; MAHMOUD, YAMIL
Congreso; 10th Argentinian Congress of Bioinformatics and Computational Biology (10CAB2C); 2019
RNA sequencing (RNASeq) and microarray data has proved to efficient high-throughput techniques to robustly characterize the presence and quantity of RNA in tumor biopsies at a given time. The use of such data to computationally estimate the composition of the tumor immune infiltrate and to infer the immunological phenotypes of those cells has proven to be an unvaluable tool. Given the significant impact of anti-cancer immunotherapies and the role of the associated immune tumor microenvironment (ITME) on its prognosis and therapy response, the estimation of the immune cell-type content in the tumor is crucial for designing effective strategies to understand and treat cancer. Current digital estimation of the ITME cell mixture content can be performed using different analytical tools. However, current methods tend to over-estimate the number of cell-types present in the sample, thus under-estimating true proportions, biasing the results. Here a noise-constrained recursive feature selection for support vector regression, MIXTUREpy, that overcomes such limitations is presenetd. MIXTUREpy deconvolutes cell-type proportions of bulk tumor samples for both RNA microarray or RNA-Seq platforms from a leukocyte validated gene signature. We evaluated MIXTURE over simulated and benchmark data sets. It overcomes competitive methods in terms of accuracy on the true number of present cell-types and proportions estimates with increased robustness to estimation bias- It also shows superior robustness to collinearity problems. The tool, implemented in Python, allows the immuno content cell-type estimation as well as provide several visualization and analytical capabilities to associate the ITME components with clinical and outcome cohort information.