upd NextITS to 1.1.0

image_development/Dockerfile_nextits

@@ -9,7 +9,7 @@
 # docker build --target test --tag nextits-test --file NextITS.dockerfile .
 
 ## Build stage 1 (Rust and Cargo)
-FROM rust:1.89.0-slim AS rust
+FROM rust:1.92.0-slim AS rust
 RUN cargo install runiq sd
 
 # Stage 2 (Nextflow - minimal stage)
@@ -58,14 +58,18 @@ RUN    R -e 'BiocManager::install("Biostrings", ask = FALSE)' \
     && R -e 'BiocManager::install("phyloseq",   ask = FALSE)' \
     && rm -rf /tmp/downloaded_packages
 
-RUN    install2.r --error --skipinstalled geodist phytools ggdendro gridExtra \
-    && R -e 'ok <- tryCatch({ remotes::install_github("mikemc/speedyseq"); TRUE }, error=function(e){ message(e); FALSE }); \
-          if (!ok || !requireNamespace("speedyseq", quietly=TRUE)) quit(status=1)' \
-    && R -e 'ok <- tryCatch({ remotes::install_github("vmikk/metagMisc"); TRUE }, error=function(e){ message(e); FALSE }); \
-          if (!ok || !requireNamespace("metagMisc", quietly=TRUE)) quit(status=1)' \
-    && R -e 'ok <- tryCatch({ remotes::install_cran("qs2", type = "source", configure.args = "--with-simd=AVX2"); TRUE }, error=function(e){ message(e); FALSE }); \
-          if (!ok || !requireNamespace("qs2", quietly=TRUE)) quit(status=1)' \
-    && rm -rf /tmp/downloaded_packages
+RUN    install2.r --error --skipinstalled \
+    geodist \
+    phytools \
+    ggdendro \
+    gridExtra \
+  && R -e 'ok <- tryCatch({ remotes::install_github("mikemc/speedyseq"); TRUE }, error=function(e){ message(e); FALSE }); \
+        if (!ok || !requireNamespace("speedyseq", quietly=TRUE)) quit(status=1)' \
+  && R -e 'ok <- tryCatch({ remotes::install_github("vmikk/metagMisc"); TRUE }, error=function(e){ message(e); FALSE }); \
+        if (!ok || !requireNamespace("metagMisc", quietly=TRUE)) quit(status=1)' \
+  && R -e 'ok <- tryCatch({ remotes::install_cran("qs", type = "source", configure.args = "--with-simd=AVX2"); TRUE }, error=function(e){ message(e); FALSE }); \
+        if (!ok || !requireNamespace("qs", quietly=TRUE)) quit(status=1)' \
+  && rm -rf /tmp/downloaded_packages
 
 ## Install conda
 RUN mkdir -p /opt/software \
@@ -97,23 +101,23 @@ RUN cd /opt/software \
 RUN /opt/software/conda/bin/mamba install -y \
     "lima>=2.13.0" \
     "pbtk>=3.5.0" \
-    "vsearch>=2.30.0" \
-    "swarm>=3.1.5" \
-    "seqkit>=2.10.1" \
-    "seqfu>=1.22.3" \
+    "vsearch>=2.30.3" \
+    "swarm>=3.1.6" \
+    "seqkit>=2.12.0" \
+    "seqfu>=1.23.0" \
     "fastp>=1.0.1" \
     "blast>=2.17.0" \
     "bioawk" \
-    "miller>=6.13.0" \
+    "miller>=6.16.0" \
     "xsv>=0.13.0" \
     "bedtools>=2.31.1" \
-    "parallel>=20250622" \
-    "csvtk>=0.34.0" \
-    "cutadapt>=5.1" \
+    "parallel>=20251122" \
+    "csvtk>=0.36.0" \
+    "cutadapt>=5.2" \
     "itsx>=1.1.3" \
-    "bbmap>=39.33" \
-    "ripgrep>=14.1.1" \
-    "fd-find>=10.2.0" \
+    "bbmap>=39.52" \
+    "ripgrep>=15.1.0" \
+    "fd-find>=10.3.0" \
     "mmseqs2" \
     "mamba" \
   && /opt/software/conda/bin/conda clean --all --yes
@@ -128,7 +132,7 @@ RUN cd /opt/software \
     && wget https://github.com/vmikk/seqhasher/releases/download/1.1.2/seqhasher \
     && chmod +x seqhasher \
     && mv seqhasher /opt/software/conda/bin/ \
-    && wget https://github.com/vmikk/phredsort/releases/download/1.3.0/phredsort \
+    && wget https://github.com/vmikk/phredsort/releases/download/1.4.0/phredsort \
     && chmod +x phredsort \
     && mv phredsort /opt/software/conda/bin/ \
     && wget https://github.com/vmikk/ucs/releases/download/0.8.0/ucs \
@@ -144,7 +148,7 @@ RUN git clone --depth 1 https://github.com/indraniel/fqgrep \
   && rm -r fqgrep
 
 ## rush
-RUN wget https://github.com/shenwei356/rush/releases/download/v0.7.0/rush_linux_amd64.tar.gz \
+RUN wget https://github.com/shenwei356/rush/releases/download/v0.8.0/rush_linux_amd64.tar.gz \
   && tar -xzf rush_linux_amd64.tar.gz \
   && mv rush /opt/software/conda/bin/ \
   && rm rush_linux_amd64.tar.gz
@@ -179,7 +183,7 @@ RUN cd /opt/software \
 
 ## Install DuckDB
 RUN cd /opt/software \
-    && curl -L https://github.com/duckdb/duckdb/releases/download/v1.3.2/duckdb_cli-linux-amd64.zip -o duckdb_cli-linux-amd64.zip \
+    && curl -L https://github.com/duckdb/duckdb/releases/download/v1.4.3/duckdb_cli-linux-amd64.zip -o duckdb_cli-linux-amd64.zip \
     && unzip duckdb_cli-linux-amd64.zip -d /opt/software/conda/bin/ \
     && rm duckdb_cli-linux-amd64.zip
 
@@ -221,7 +225,7 @@ ENTRYPOINT ["/opt/software/entrypoint.sh"]
 FROM main AS test
 
 # Set environment variable for R version testing
-ENV R_VERSION=4.5.1
+ENV R_VERSION=4.5.2
 
 RUN echo "=== Testing R installation and packages ===" \
   && R --quiet -e "stopifnot(getRversion() == '${R_VERSION}')" \
@@ -230,7 +234,7 @@ RUN echo "=== Testing R installation and packages ===" \
     'required_packages <- c("optparse", "data.table", "arrow", "duckdb",' \
     '                      "plyr", "dplyr", "ggplot2", "openxlsx", "yaml",' \
     '                      "Biostrings", "DECIPHER", "dada2", "phyloseq",' \
-    '                      "metagMisc", "qs2")' \
+    '                      "metagMisc", "qs")' \
     '' \
     'for(pkg in required_packages) {' \
     '  cat("Testing package:", pkg, "... ")' \
@@ -268,4 +272,5 @@ RUN echo "=== Testing R installation and packages ===" \
             echo "FAILED - $tool not found in PATH" && exit 1; \
           fi; \
      done \
-  && echo "=== All tests passed! Container looks ready for use ==="
+  && echo "=== All tests passed! Container looks ready for use ==="
+

src/pipecraft-core/service_scripts/NextITS/CHANGELOG.md

@@ -7,7 +7,7 @@ For version numbering, we use the following convention: `MAJOR.MINOR.PATCH`.
 Each element increases numerically (e.g., `1.9.0` -> `1.10.0` -> `1.11.0`).  
 
 
-## [1.1.0] - 2025-xx-xx
+## [1.1.0] - 2026-01-22
 
 - Fixed handling of unknown barcode combinations (in `dual asymmetric` mode); thanks to Alice Retter for reporting  
 - Refactored and optimized the tag-jump removal step  
@@ -18,6 +18,8 @@ Each element increases numerically (e.g., `1.9.0` -> `1.10.0` -> `1.11.0`).
     - `lima_remove_unknown` (default, `false`; if `true`, unknown barcode combinations are removed from demultiplexed data)  
     - `chunking_n` (number of chunks to split the dataset into prior to clustering)  
     - `chunking_id` (minimum sequence identity used for splitting the dataset into chunks)  
+    - `chimera_methods` (specifies which chimera removal methods to use - "ref" for reference-based, "denovo" for de novo, or "ref,denovo" for both; could be also "none" or `null` to disable chimera removal)  
+    - `tj` (specifies whether to run tag-jump removal - "true" or "false")  
 - Added DADA2 denoising (`--preclustering dada2`; also works with `--clustering none`)
 - Implemented automated documentation for analysis procedures (generates `README_Step1_Methods.txt` and `README_Step2_Methods.txt` in the `pipeline_info` directory)  
 - Refactored parameter validation (using `nf-schema` plugin)  

src/pipecraft-core/service_scripts/NextITS/CITATION.cff

@@ -11,7 +11,7 @@ authors:
 - family-names: "Tedersoo"
   given-names: "Leho"
   orcid: "https://orcid.org/0000-0002-1635-1249"
-version: 1.0.0
+version: 1.1.0
 doi: 10.5281/zenodo.15074881
 date-released: 2025-03-24
 url: "https://github.com/vmikk/NextITS"