updated dockerfile, added details section

Author: agusinac

R/bray.R

@@ -2,6 +2,8 @@
 #'
 #' @description 
 #' Calculates the Bray-Curtis dissimilarity of a \link[Matrix]{sparseMatrix} pairwise for each column. 
+#' 
+#' @details
 #' The Bray-Curtis dissimilarity between two samples \eqn{A} and \eqn{B}, each of length \eqn{n}, is defined as:
 #'
 #' \eqn{d(A,B) = \frac{\sum_{i}^n |A_i - B_i|}{\sum_{i}^n (A_i + B_i)}}

R/canberra.R

@@ -2,6 +2,8 @@
 #'
 #' @description 
 #' Calculates the Canberra dissimilarity of a \link[Matrix]{sparseMatrix} pairwise for each column.
+#' 
+#' @details
 #' The Canberra dissimilarity between two samples \eqn{A} and \eqn{B}, each of length \eqn{n}, is defined as:
 #'
 #' \eqn{d(A,B) = \frac{1 / NZ} \sum_{i}^n \frac{|A_i - B_i|}{|A_i| + |B_i|}}

R/cosine.R

@@ -2,6 +2,8 @@
 #'
 #' @description 
 #' Calculates the cosine disimilarity of a \link[Matrix]{sparseMatrix} pairwise for each column.
+#' 
+#' @details
 #' The cosine dissimilarity between two samples \eqn{A} and \eqn{B}, each of length \eqn{n}, is defined as:
 #'
 #' \eqn{d(A,B) = 1 - \frac{\sum_{i}^n A_i B_i}{\sqrt{\sum_{i}^n A_i^2} \sqrt{\sum_{i}^n B_i^2}} }

R/jaccard.R

@@ -2,6 +2,8 @@
 #'
 #' @description 
 #' Calculates the Jaccard dissimilarity of a \link[Matrix]{sparseMatrix} pairwise for each column.
+#' 
+#' @details
 #' The weighted Jaccard disimilarity between two samples \eqn{A} and \eqn{B}, each of length \eqn{n}, is defined as:
 #'
 #' \eqn{d(A,B) = 1 - \frac{ \sum_{i}^{n} \min(A_i, B_i) }{ \sum_{i}^{n} \max(A_i, B_i) }}

R/jsd.R

@@ -2,13 +2,15 @@
 #'
 #' @description
 #' Calculates the Jensen-Shannon divergence of a \link[Matrix]{sparseMatrix} pairwise for each column.
+#' 
+#' @details
 #' The Jensen-Shannon divergence between two probability distributions \eqn{A} and \eqn{B}, each of length \eqn{n}, is defined as:
 #'
 #' \eqn{ d(A, B) = \frac{1}{2} D_{KL}(A \parallel M) + \frac{1}{2} D_{KL}(B \parallel M) }
 #'
 #' where \eqn{M = \frac{1}{2} (A + B)} is the mixture distribution,
 #' and \eqn{D_{KL}} is the Kullback-Leibler divergence.
-#' When weighted is set to FALSE, counts are changed to relative abundances.
+#' When weighted is set to FALSE, counts are replaced by presence/absence data.
 #'
 #' @param x A \link[Matrix]{sparseMatrix}.
 #' @param weighted A boolean value, to use counts or relative abundances (default: TRUE).

R/manhattan.R

@@ -2,6 +2,8 @@
 #'
 #' @description 
 #' Calculates the Manhattan dissimilarity of a \link[Matrix]{sparseMatrix} pairwise for each column.
+#' 
+#' @details
 #' The Manhattan dissimilarity between two samples \eqn{A} and \eqn{B}, each of length \eqn{n}, is defined as:
 #'
 #' \eqn{d(A, B) = \sum_{i}^n |A_i - B_i|}

R/omics-class.R

@@ -841,7 +841,7 @@ omics <- R6::R6Class(
     #'
     #' obj$feature_subset(Kingdom == "Bacteria")
     #' dist <- obj$distance(metric = "bray")
-    #' @seealso \link{ordination_plot}, \link{plot_pairwise_stats}, \link{pairwise_anosim}, \link{pairwise_adonis}
+    #' @seealso \link{bray}, \link{canberra}, \link{cosine}, \link{jaccard}, \link{jsd}, \link{manhattan}, \link{unifrac}
     distance = function(metric, normalized = TRUE, weighted = TRUE, threads = 1) {
 
       ## Error handling

R/unifrac.R

@@ -1,32 +1,29 @@
 #' Compute UniFrac Dissimilarity from a Sparse Matrix.
 #'
 #' @description Calculates the UniFrac dissimilarity between samples based on phylogenetic branch lengths and abundance or presence/absence data.
-#' The UniFrac distance between two samples \eqn{A} and \eqn{B}, with phylogenetic tree edges \eqn{i = 1 \ldots n} of lengths \eqn{L_i}, is computed differently depending on the \code{weighted} and \code{normalized} flags:
-#' Weighted UniFrac:
-#' \eqn{d(A,B) = \frac{\sum_{i}^n L_i |A_i - B_i|}{\sum_{i}^n L_i (A_i + B_i)}}
-#' Normalized Weighted UniFrac:
-#' \eqn{d(A,B) = \sum_{i}^n L_i |A_i - B_i|}
-#' where \eqn{A_i} and \eqn{B_i} are the abundance weights for branch \eqn{i} computed by propagating tip abundances to internal nodes.
-#'
-#' Unweighted UniFrac (always normalized): 
-#' \eqn{d(A,B) = \frac{\sum_{i}^n L_i |A'_i - B'_i|}{\sum_{i}^n L_i \max(A'_i, B'_i)}}
-#'
-#' where \eqn{A'_i} and \eqn{B'_i} are binary indicators (presence/absence) on branches \eqn{i}, derived by propagating tip presence to internal nodes.
-#' When \code{weighted = FALSE}, input counts are first converted to presence/absence before distance computation.
-#'
+#' 
+#' @details
+#' The UniFrac distance between two samples \eqn{A} and \eqn{B}, with phylogenetic tree edges \eqn{i = 1 \ldots n} of lengths \eqn{L_i}, is computed differently depending on the \code{weighted} and \code{normalized} flags. 
+#' When \code{weighted = FALSE}, input counts are first converted to presence/absence data.
+#' \describe{
+#'  \item{Weighted UniFrac (\code{normalized = FALSE} and \code{weighted = TRUE}):}{
+#'      \eqn{d(A,B) = \frac{\sum_{i}^n L_i |A_i - B_i|}{\sum_{i}^n L_i (A_i + B_i)}}
+#'  }
+#'  \item{Normalized Weighted UniFrac (\code{normalized = TRUE} and \code{weighted = TRUE}):}{
+#'      \eqn{d(A,B) = \sum_{i}^n L_i |A_i - B_i|}
+#'  }
+#'  \item{Unweighted UniFrac (\code{weighted = FALSE}, unweighted is always normalized):}{
+#'      \eqn{d(A,B) = \frac{\sum_{i}^n L_i |A_i - B_i|}{\sum_{i}^n L_i \max(A_i, B_i)}}
+#'  }
+#'}
 #' @param x A \link[Matrix]{sparseMatrix} of strictly positive counts or presence/absence data.
 #' @param tree A `phylo` class tree.
 #' @param weighted Logical indicating whether to compute weighted (abundance) or unweighted (presence/absence) UniFrac (default: TRUE).
 #' @param normalized Logical indicating whether to normalize weighted UniFrac distances to be between 0 and 1 (default: TRUE). Unweighted UniFrac is always normalized.
 #' @param threads Integer number of threads to use for parallel computation (default: 1).
 #' @return A symmetric matrix of pairwise UniFrac distances between columns of \code{x}.
 #' @references
-#' Lozupone, C., Hamady, M., Kelley, S. T., & Knight, R. (2007). Quantitative and qualitative beta diversity measures lead to different insights into factors that structure microbial communities. Applied and Environmental Microbiology, 73(5), 1576–1585.
-#'
 #' Lozupone, C., & Knight, R. (2005). UniFrac: a new phylogenetic method for comparing microbial communities. Applied and Environmental Microbiology, 71(12), 8228–8235.
-#'
-#' Lozupone, C., & Knight, R. (2008). Species divergence and the measurement of microbial diversity. FEMS Microbiology Reviews, 32(4), 557–578.
-#'
 #' @examples 
 #' library("OmicFlow")
 #'

README.md

@@ -162,20 +162,5 @@ res <- taxa$DFE(
 res$volcano_plot
 ```
 
-### Run autoflow via docker 🐳
-For additional options please run `autoflow -h`
-```bash
-docker pull agusinac/autoflow:1.3.2
-
-docker run -it --rm -v \
-    "$(pwd)":/data \             # Mount the data in a temporary directory
-    -w /data \                   # set working directory
-    -u $(id -u):$(id -g) \       # non-root user
-    agusinac/autoflow:1.3.2 \
-    autoflow \                   # autoflow R script
-    -b /data/biom_with_taxonomy_hdf5.biom \
-    -m /data/metadata.tsv
-```
-
 ## Support
-If you are having issues, please [create a ticket](https://github.com/agusinac/OmicFlow/issues)
+If you are having issues, please [create a ticket](https://github.com/agusinac/OmicFlow/issues)

docker/Dockerfile

@@ -1,6 +1,6 @@
 #------------------------------------------------------------------------------------#
 #
-#   Created by Alem Gusinac, last modified at 16-10-2025
+#   Created by Alem Gusinac, last modified at 24-10-2025
 #
 #   It builds on top of a slim ubuntu (70MB) base
 #
@@ -53,6 +53,10 @@ RUN echo "deb https://cloud.r-project.org/bin/linux/ubuntu focal-cran40/" >> /et
 RUN apt-get update && apt-get upgrade -y && apt-get clean
 RUN apt-get update && apt-get install -y r-base
 
+# Install ggplot2 3.5.2 explicitly before other packages
+RUN R -e "install.packages('remotes', repos='https://cloud.r-project.org')"
+RUN R -e "remotes::install_version('ggplot2', version='3.5.2', repos='https://cloud.r-project.org')"
+
 # Copy requirements
 COPY install2.r .
 COPY installBioc.r .
@@ -62,11 +66,9 @@ RUN R -e "install.packages('docopt', dependencies=TRUE)"
 
 # Essential R dependencies
 RUN Rscript install2.r --error --skipinstalled \
-    remotes \
     pak \
     BiocManager \
     b64 \
-    ggplot2 \
     cli \
     DT \
     downloadthis \
@@ -95,4 +97,4 @@ ARG USER_GID=$USER_UID
 
 # Create the user
 RUN groupadd --gid $USER_GID $USERNAME \
-    && useradd --uid $USER_UID --gid $USER_GID -m $USERNAME \
+    && useradd --uid $USER_UID --gid $USER_GID -m $USERNAME