README.md

In elmerfer/MIXTURE: MIXTURE: a nu-SVR based recursive feature extraction mdoel with noise constraints for molecular signature deconvolution of bulk tumor tissues

A noise constrained Recursive Feature Extraction algorithm for robust deconvolution of cell-types mixture from molecular signatures

Since the significant impact of immunotherapy in cancer, the estimation of the immune cell-type proportions present in a tumor becomes crucial. Currently, the deconvolution of the cell mixture content of a tumor is carried out by different analytic tools, yet the accuracy of inferred cell type proportions has room for improvement. We improve tumor immune environment characterization developing MIXTURE, an analytical method based on a noise constrained recursive variable selection for a support vector regression. Please Get the biorxiv 2018 manuscript or the Briefings in Bioinformatics 2020 manuscript and/or the benchmark analysis in Journal of Biomedical Informatics 2023

NOTE:

The MIXTURE shiny App is now available

The RUN_MIXTURE code was tested on Linux, Windows and Mac.

New! MIXTURE in Python

Getting Started

Installation

install.packages("devtools")
library(devtools)
install_github("elmerfer/MIXTURE")

Running MIXTURE

This example tends to estimate the same pure cell-types from LM22 signature matrix from Newman et al.. The LM22 matrix was stored as an RData obj for convinience and provided as data

library(MIXTURE)
##Load signature matrix
data(LM22)
##  Run the self test on LM22 signature
mix.test <- MIXTURE(expressionMatrix = LM22,          #N x ncol(signatureMatrix) gene expresion matrix to evaluate 
                                                      ##rownames(M) should be the GeneSymbols
              signatureMatrix = LM22,                 #the gene signature matrix (W) such that M = W*betas' 
                                                      #(i.e the LM22 from Newman et al)
              iter = 1000,                            #iterations for the statistical test (null distribution)
              functionMixture = nu.svm.robust.RFE,    #cibersort, nu.svm.robust.rfe, ls.rfe.abbas, 
              useCores = 10L,                         #cores for parallel processing/ if using windows set to 1
              verbose = TRUE,                         #TRUE or FALSE messages  
              nullDist = "PopulationBased",           #"none" or "PopulationBased" if the statistical test should
                                                      #be performed
              fileSave = "MIXTURE_FILE_LM22.xlsx")    #EXCEL file name to store the results 

save(mix.test, file = "MIXTURE_FILE_LM22.RData") #save full list as an RData object.

Documentation

MIXTURE vignette

Wiki

Authors

• Elmer Andrés Fernández - Initial work - Profile - [CIDIE]- CONICET - Fundación para el Progreso de la Medicina - FPM
• Agustin Nava -Manteiner - CONICET

Collaborators

• Dario Rocha -- - *Testing and application on TCGA Data
• Yamil Mahamoud -- IBYME-CONICET. Application on Cancer immunotherapy
• Joaquin Merlo -- IBYME-CONICET. Application on Cancer immunotherapy

How to cite

Unveiling the immune infiltrate modulation in cancer and response to immunotherapy by MIXTURE—an enhanced deconvolution method Elmer A Fernández, Yamil D Mahmoud, Florencia Veigas, Darío Rocha, Matías Miranda, Joaquín Merlo, Mónica Balzarini, Hugo D Lujan, Gabriel A Rabinovich, María Romina Girotti Briefings in Bioinformatics, bbaa317, [https://doi.org/10.1093/bib/bbaa317] Published: 16 December 2020

Novel evaluation approach for molecular signature-based deconvolution methods. Agustín Nava, Daniela Alves da Quinta, Laura Prato, María Romina Girotti, Gabriel Moron, Andrea S. Llera, Elmer A. Fernández. May 2023, Journal of Biomedical Informatics 142(5):104387 DOI: 10.1016/j.jbi.2023.104387

License

This project is licensed under the MIT License - see the LICENSE.md file for details

elmerfer/MIXTURE documentation built on Aug. 20, 2024, 8:03 p.m.