predictTilState: Predict state of tumor-infiltrating CD8 T-cells from...

In GfellerLab/TILAtlas: Tumor-infiltrating CD8+ T-cell state predictor for scRNA-seq data

Description

predictTilState This function evaluates a logistic regression model to predict the state of individual CD8 tumor-infiltrating lymphocytes (mouse or human) based on their transcriptomes (scRNA-seq data)

Usage

predictTilState(tpm, ignore = F)

Arguments

tpm

expression matrix using TPM (Transcripts per Million) normalization, where rows correspond to genes and columns to single-cells. Row names must corresond to gene symbols in uppercase (e.g. LAG3, LGALS1, ANXA2). Only the following genes are necessary for the function to work: LAG3, LGALS1, ANXA2, SELL, BHLHE40, PDCD1, TIGIT, KLRK1, TCF7, LEF1, S1PR1, RPS24, EMB, IL7R, GPR18, PIK3IP1, ST6GAL1, RPS6, KLRG1, GZMA, RPS15A, RPS26, S1PR5, RPS25, RPL39, NRP2, DTX1, FBXL2, CXCR6, CCL4, HAVCR2, TMSB4X, CCL3, TOX, ADAM8, ATXN1, GLRX, LAT2, PRF1, HILPDA, SLC37A2, ST14, CCNA2, CDCA8, ITGB7, CCR7, ADAM19, ISG20, NUP43, PADI2, FANCI, NCOR2, LSM3, ORC1, DUSP4, TNFRSF4, ITGB1, CCL5, IL2RA, CD83, TNFSF11, XCL1, CRTAM, RAMP3, LAD1, LTA, PPIL1, TM4SF5, RAMP1, WRAP53, STMN1, CCNB2, KIF20A, CDCA2, FAM83D, NEIL3, PTPRC, SIVA1, 1500009L16RIK, SLC9A5

ignore

is set to TRUE, up to 10 missing genes will be imputed to 0s (NOT RECOMMENDED, UNKOWN PREDICTIVE PERFORMANCE)

Value

a two-element list containing 1) predictedState, the predicted states (naive, terminal effector, exhausted, memory-like, cycling effector or "unknown" if no class had a score above a threshold of 0.5), and 2) stateProbabilityMatrix, a matrix of number_of_cells x number_of_states (5) of probabilities of cell c belonging to class s

Author(s)

Santiago J. Carmona <[e-mail]>

Examples

data(B16CD8TILs_tpm)
x <- predictTilState(B16CD8TILs_tpm)
table(x$predictedState)
head(x$stateProbabilityMatrix)

GfellerLab/TILAtlas documentation built on May 17, 2019, 8:03 a.m.