/abaR

Automated biomarker analysis in R

Primary LanguageRGNU General Public License v3.0GPL-3.0

Automated biomarker analysis (aba)

R-CMD-check Codecov test coverage

The goals of the aba package are as follows:

  • to facilitate sound statistical modelling in clinical research
  • to provide advanced tools for biomarker-based planning of clinical trials
  • to generate publication-ready tables and figures

overview image

With the aba package, it becomes easier to fit statistical models on permuatations of covariates / predictors / outcomes / groups, to make it easier to investigate how biomarkers can be used to plan (screening / enirichment) and analyze clinical trials, and to facilitate multi-cohort validation studies when data cannot be easily shared between collaborators.

Getting started

To view tutorials and examples of how to use the package, you can visit the package website at https://ncullen93.github.io/abaR/.

You can install the development version of the aba package from GitHub with the following:

# install.packages("devtools")
devtools::install_github("ncullen93/abaR")

The typical workflow for performing statistical analysis with aba is incredibly simple:

library(aba)

df <- aba::adnimerge %>% filter(VISCODE == 'bl')

# build and fit an aba model with multiple outcomes and predictors
model <- df %>% aba_model() %>%
  set_outcomes(ConvertedToAlzheimers, CSF_ABETA_STATUS_bl) %>%
  set_predictors(
    PLASMA_ABETA_bl, PLASMA_PTAU181_bl, PLASMA_NFL_bl,
    c(PLASMA_ABETA_bl, PLASMA_PTAU181_bl, PLASMA_NFL_bl)
  ) %>%
  set_stats('glm') %>% 
  fit()

# summarise the model results (coefficients and metrics)
model_summary <- model_fit %>% summary()

You can then generate publication-ready figures in just one line of code:

fig <- model_summary %>% aba_plot_coef(palette = 'lancet')

coefficient image

Publications

Some publications whose analysis has been done partially or completely with functions from the aba package are featured here:

Cite

If you use the aba package in your work, we appreciate if you cite us. An example statement which can be added at the end of the “Statistical analysis” section of your methods is provided here:

The analysis was done in the R programming language (v4.0.3) using the Automated Biomarker Analysis for R (“aba”) package [citation].

Receiving help

The easiest way to get help is to create an issue on the github page or to send us an email with your questions.