FunVIP 0.3.22.2__tar.gz → 0.3.23__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {funvip-0.3.22.2 → funvip-0.3.23}/FunVIP.egg-info/PKG-INFO +1 -1
- {funvip-0.3.22.2 → funvip-0.3.23}/PKG-INFO +1 -1
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/cleanup-blastdb-volumes.py +162 -162
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/get_species_taxids.sh +152 -152
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/legacy_blast.pl +1359 -1359
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/update_blastdb.pl +1069 -1069
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/tree_interpretation.py +19 -1
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/validate_input.py +951 -951
- {funvip-0.3.22.2 → funvip-0.3.23}/pyproject.toml +1 -1
- {funvip-0.3.22.2 → funvip-0.3.23}/FunVIP.egg-info/SOURCES.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/FunVIP.egg-info/dependency_links.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/FunVIP.egg-info/entry_points.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/FunVIP.egg-info/requires.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/FunVIP.egg-info/top_level.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/LICENSE +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/MANIFEST.in +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/README.md +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/FunVIP_GUI.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/__init__.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/data/Option_manager.xlsx +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/data/__init__.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/data/genus_line.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/Uninstall-ncbi-blast-2.12.0+.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/blastn.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/makeblastdb.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/nghttp2.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/doc/README.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/FastTree_Windows/FastTree.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/Documentation/Gblocks_documentation.html +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/Gblocks.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/more_alignments/cox2.pir +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/more_alignments/cytb.pir +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/more_alignments/nad3.pir +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/more_alignments/nad5.pir +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/nad3.pir +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/Gblocks_Windows_0.91b/Gblocks_0.91b/paths +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/MAFFT_LICENSE +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/MAFFT_Windows.zip +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/RAxML_Windows/GPL-3.0.txt +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/RAxML_Windows/README +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/RAxML_Windows/raxmlHPC-PTHREADS-AVX2.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/__init__.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/iqtree/bin/iqtree2-click.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/iqtree/bin/iqtree2.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/iqtree/bin/libiomp5md.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/iqtree/example.cf +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/iqtree/example.nex +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/iqtree/example.phy +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/iqtree/models.nex +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/LICENSE.md +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/README.md +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/busybox.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/cygbz2-1.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/cyggcc_s-seh-1.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/cyggomp-1.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/cygstdc++-6.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/cygwin1.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/cygz.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/bin/mmseqs.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/examples/QUERY.fasta +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM10.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM100.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM110.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM120.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM130.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM140.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM150.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM160.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM170.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM180.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM190.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM20.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM30.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM40.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM50.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM60.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM70.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM80.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/PAM90.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/VTML10.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/VTML120.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/VTML160.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/VTML20.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/VTML40.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/VTML80.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum100.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum30.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum35.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum40.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum45.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum50.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum55.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum60.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum62.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum65.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum70.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum75.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum80.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum85.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum90.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/blosum95.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/matrices/nucleotide.out +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/mmseqs.bat +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/mmseqs_Windows/util/bash-completion.sh +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/AUTHORS +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/CHANGELOG +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/LICENSE +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/README +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/bin/libgcc_s_dw2-1.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/bin/libstdc++-6.dll +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/bin/trimal.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/check_codon_alignments.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/compare_trimmed_msas.sh +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/generateRandomAlignmentsUsingAsSeedRealAlignments.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/generate_trimmed_msas.sh +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/get_sequence_representative_from_alignment.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/get_sequences_gaps_ratio.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/remove_shorter_sequences.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/selective_trimming_for_dNdS_analyses.based_neighbours.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/scripts/set_manual_boundaries.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/alignment.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/alignment.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/alignment.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/autAlignment.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/autAlignment.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/compareFiles.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/compareFiles.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/compareFiles.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/defines.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/main.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/makefile +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/makefile.MacOS +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/readAl.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/readal.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/rwAlignment.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/rwAlignment.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/sequencesMatrix.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/sequencesMatrix.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/sequencesMatrix.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/similarityMatrix.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/similarityMatrix.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/similarityMatrix.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statAl.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statal.exe +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsConservation.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsConservation.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsConservation.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsFiles.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsFiles.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsGaps.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsGaps.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/statisticsGaps.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/utils.cpp +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/utils.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/utils.o +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/trimal.v1.4/trimAl/source/values.h +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/main.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/preset/.gitignore +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/preset/accurate.yaml +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/preset/fast.yaml +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/.gitignore +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__init__.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/CATV_pipe.cpython-310.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/CAT_V.cpython-310.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/CAT_V.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/CAT_V_pipe.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/__init__.cpython-310.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/__init__.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/align.cpython-310.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/cluster.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/dataset.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/ext.cpython-310.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/ext.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/hasher.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/initialize.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/io.cpython-310.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/io.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/logger.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/modeltest.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/multigene.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/ncbi.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/opt_generator.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/reporter.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/search.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/tool.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/validation.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/__pycache__/visualize.cpython-39.pyc +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/align.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/cluster.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/command.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/concatenate.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/dataset.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/ext.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/hasher.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/initialize.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/logger.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/logics.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/modeltest.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/ncbi.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/opt_generator.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/reporter.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/save.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/search.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/templates/template.html +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/tool.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/tree.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/tree_interpretation_pipe.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/trim.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/validate_option.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/validation.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/src/version.py +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/test_dataset/penicillium/DB/DB_Penicillium.xlsx +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/test_dataset/penicillium/Options.config +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/test_dataset/penicillium/Query/Query.xlsx +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/test_dataset/penicillium/preset.yaml +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/test_dataset/terrei/DB/FunVIP_Aspergillus_db.xlsx +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/test_dataset/terrei/Query/FunVIP_Aspergillus_query.xlsx +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/funvip/test_dataset/terrei/preset.yaml +0 -0
- {funvip-0.3.22.2 → funvip-0.3.23}/setup.cfg +0 -0
{funvip-0.3.22.2 → funvip-0.3.23}/funvip/external/BLAST_Windows/bin/cleanup-blastdb-volumes.py
RENAMED
|
@@ -1,162 +1,162 @@
|
|
|
1
|
-
#!/usr/bin/env python3
|
|
2
|
-
"""
|
|
3
|
-
# $Id: cleanup-blastdb-volumes.py 590894 2019-08-07 14:59:53Z camacho $
|
|
4
|
-
# ===========================================================================
|
|
5
|
-
#
|
|
6
|
-
# PUBLIC DOMAIN NOTICE
|
|
7
|
-
# National Center for Biotechnology Information
|
|
8
|
-
#
|
|
9
|
-
# This software/database is a "United States Government Work" under the
|
|
10
|
-
# terms of the United States Copyright Act. It was written as part of
|
|
11
|
-
# the author's official duties as a United States Government employee and
|
|
12
|
-
# thus cannot be copyrighted. This software/database is freely available
|
|
13
|
-
# to the public for use. The National Library of Medicine and the U.S.
|
|
14
|
-
# Government have not placed any restriction on its use or reproduction.
|
|
15
|
-
#
|
|
16
|
-
# Although all reasonable efforts have been taken to ensure the accuracy
|
|
17
|
-
# and reliability of the software and data, the NLM and the U.S.
|
|
18
|
-
# Government do not and cannot warrant the performance or results that
|
|
19
|
-
# may be obtained by using this software or data. The NLM and the U.S.
|
|
20
|
-
# Government disclaim all warranties, express or implied, including
|
|
21
|
-
# warranties of performance, merchantability or fitness for any particular
|
|
22
|
-
# purpose.
|
|
23
|
-
#
|
|
24
|
-
# Please cite the author in any work or product based on this material.
|
|
25
|
-
#
|
|
26
|
-
# ===========================================================================
|
|
27
|
-
#
|
|
28
|
-
# Author: Christiam Camacho
|
|
29
|
-
#
|
|
30
|
-
# File Description:
|
|
31
|
-
# Script to remove needless BLAST database files.
|
|
32
|
-
#
|
|
33
|
-
# ===========================================================================
|
|
34
|
-
"""
|
|
35
|
-
import argparse, os, configparser
|
|
36
|
-
import unittest, tempfile
|
|
37
|
-
from pathlib import Path
|
|
38
|
-
from glob import glob
|
|
39
|
-
|
|
40
|
-
VERSION = '1.0'
|
|
41
|
-
DESC = r""" Remove needless BLAST database volumes. """
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
class Tester(unittest.TestCase):
|
|
45
|
-
""" Testing class for this script. """
|
|
46
|
-
|
|
47
|
-
def test_blastdb_config_invalid(self):
|
|
48
|
-
rv = get_blastdb_from_ncbi_config("/dev/null")
|
|
49
|
-
self.assertIsNone(rv)
|
|
50
|
-
|
|
51
|
-
def test_blastdb_config(self):
|
|
52
|
-
config = configparser.ConfigParser()
|
|
53
|
-
expected = "/blast/db/blast"
|
|
54
|
-
config['BLAST'] = {'BLASTDB': expected}
|
|
55
|
-
tf = tempfile.NamedTemporaryFile(mode="wt")
|
|
56
|
-
config.write(tf)
|
|
57
|
-
tf.flush()
|
|
58
|
-
rv = get_blastdb_from_ncbi_config(tf.name)
|
|
59
|
-
self.assertEqual(expected, rv)
|
|
60
|
-
|
|
61
|
-
def test_blastdb_finder(self):
|
|
62
|
-
tal = tempfile.NamedTemporaryFile(suffix=".pin")
|
|
63
|
-
dbname = find_blastdb(tal.name[:-4], True)
|
|
64
|
-
self.assertEqual(dbname, tal.name[:-4])
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
def find_blastdb(name: str, is_prot: bool) -> str:
|
|
68
|
-
""" Returns full path to BLAST database or None. """
|
|
69
|
-
alias_file = "{}.{}al".format(name, "p" if is_prot else "n")
|
|
70
|
-
index_file = "{}.{}in".format(name, "p" if is_prot else "n")
|
|
71
|
-
if os.path.exists(alias_file) or os.path.exists(index_file):
|
|
72
|
-
return name
|
|
73
|
-
|
|
74
|
-
if "BLASTDB" in os.environ:
|
|
75
|
-
alf = os.path.join(os.environ["BLASTDB"], alias_file)
|
|
76
|
-
idxf = os.path.join(os.environ["BLASTDB"], index_file)
|
|
77
|
-
if os.path.exists(alf) or os.path.exists(idxf):
|
|
78
|
-
return os.path.join(os.environ["BLASTDB"], name)
|
|
79
|
-
|
|
80
|
-
paths = [ os.getcwd(), str(Path.home()) ]
|
|
81
|
-
if "NCBI" in os.environ:
|
|
82
|
-
paths.append(os.path.join(os.environ["NCBI"]))
|
|
83
|
-
|
|
84
|
-
for path in paths:
|
|
85
|
-
for fname in [ ".ncbirc", "ncbi.ini" ]:
|
|
86
|
-
ncbirc = os.path.join(path, fname)
|
|
87
|
-
if os.path.exists(ncbirc):
|
|
88
|
-
blastdb = get_blastdb_from_ncbi_config(ncbirc)
|
|
89
|
-
if blastdb is not None:
|
|
90
|
-
alf = os.path.join(blastdb, alias_file)
|
|
91
|
-
idxf = os.path.join(blastdb, index_file)
|
|
92
|
-
if os.path.exists(alf) or os.path.exists(idxf):
|
|
93
|
-
return os.path.join(blastdb, name)
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
def get_blastdb_from_ncbi_config(config_file: str) -> str:
|
|
97
|
-
""" Return the BLASTDB setting from the NCBI configuration file or None. """
|
|
98
|
-
config = configparser.ConfigParser()
|
|
99
|
-
config.read(config_file)
|
|
100
|
-
if 'BLAST' in config and 'BLASTDB' in config['BLAST']:
|
|
101
|
-
return config['BLAST']['BLASTDB']
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
def main():
|
|
105
|
-
""" Entry point into this program. """
|
|
106
|
-
parser = create_arg_parser()
|
|
107
|
-
args = parser.parse_args()
|
|
108
|
-
|
|
109
|
-
ext = args.dbtype[0]
|
|
110
|
-
db = find_blastdb(args.db, ext == 'p')
|
|
111
|
-
if db == None:
|
|
112
|
-
print("Cannot find {} {} BLAST database".
|
|
113
|
-
format("protein" if ext == 'p' else "nucleotide", args.db),
|
|
114
|
-
file=sys.stderr)
|
|
115
|
-
return 1
|
|
116
|
-
|
|
117
|
-
alias_file = "{}.{}al".format(db, ext)
|
|
118
|
-
if not os.path.exists(alias_file):
|
|
119
|
-
return 1
|
|
120
|
-
|
|
121
|
-
with open(alias_file, "rt") as al:
|
|
122
|
-
for line in al:
|
|
123
|
-
if not line.startswith("DBLIST"):
|
|
124
|
-
continue
|
|
125
|
-
vols = list(map(lambda x: x.replace('"', ''), line.split()[1:]))
|
|
126
|
-
for existing_vols in sorted(glob("{}.*.{}in".format(db, ext))):
|
|
127
|
-
vol_name = os.path.basename(existing_vols)[:-4]
|
|
128
|
-
if vol_name in vols:
|
|
129
|
-
continue
|
|
130
|
-
if args.dry_run:
|
|
131
|
-
print("Will remove extra volume {}".format(existing_vols[:-4]))
|
|
132
|
-
to_rm = glob("{}??".format(existing_vols[:-2]))
|
|
133
|
-
to_rm += glob("{}.tar.gz.md5".format(existing_vols[:-4]))
|
|
134
|
-
for f in to_rm:
|
|
135
|
-
if not args.dry_run:
|
|
136
|
-
os.unlink(f)
|
|
137
|
-
print("Removed {}".format(f))
|
|
138
|
-
elif args.verbose > 0:
|
|
139
|
-
print("Will remove {}".format(f))
|
|
140
|
-
|
|
141
|
-
return 0
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
def create_arg_parser():
|
|
145
|
-
""" Create the command line options parser object for this script. """
|
|
146
|
-
parser = argparse.ArgumentParser(description=DESC)
|
|
147
|
-
parser.add_argument("-db", required=True, help="BLAST database name")
|
|
148
|
-
parser.add_argument("-dbtype", help="Molecule type", required=True,
|
|
149
|
-
choices=["prot", "nucl"])
|
|
150
|
-
parser.add_argument("-dry-run", action='store_true',
|
|
151
|
-
help="Do not delete any files, just list them")
|
|
152
|
-
parser.add_argument('-version', action='version',
|
|
153
|
-
version='%(prog)s ' + VERSION)
|
|
154
|
-
parser.add_argument("-verbose", action="count", default=0,
|
|
155
|
-
help="Increase output verbosity")
|
|
156
|
-
return parser
|
|
157
|
-
|
|
158
|
-
|
|
159
|
-
if __name__ == "__main__":
|
|
160
|
-
import sys
|
|
161
|
-
sys.exit(main())
|
|
162
|
-
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
"""
|
|
3
|
+
# $Id: cleanup-blastdb-volumes.py 590894 2019-08-07 14:59:53Z camacho $
|
|
4
|
+
# ===========================================================================
|
|
5
|
+
#
|
|
6
|
+
# PUBLIC DOMAIN NOTICE
|
|
7
|
+
# National Center for Biotechnology Information
|
|
8
|
+
#
|
|
9
|
+
# This software/database is a "United States Government Work" under the
|
|
10
|
+
# terms of the United States Copyright Act. It was written as part of
|
|
11
|
+
# the author's official duties as a United States Government employee and
|
|
12
|
+
# thus cannot be copyrighted. This software/database is freely available
|
|
13
|
+
# to the public for use. The National Library of Medicine and the U.S.
|
|
14
|
+
# Government have not placed any restriction on its use or reproduction.
|
|
15
|
+
#
|
|
16
|
+
# Although all reasonable efforts have been taken to ensure the accuracy
|
|
17
|
+
# and reliability of the software and data, the NLM and the U.S.
|
|
18
|
+
# Government do not and cannot warrant the performance or results that
|
|
19
|
+
# may be obtained by using this software or data. The NLM and the U.S.
|
|
20
|
+
# Government disclaim all warranties, express or implied, including
|
|
21
|
+
# warranties of performance, merchantability or fitness for any particular
|
|
22
|
+
# purpose.
|
|
23
|
+
#
|
|
24
|
+
# Please cite the author in any work or product based on this material.
|
|
25
|
+
#
|
|
26
|
+
# ===========================================================================
|
|
27
|
+
#
|
|
28
|
+
# Author: Christiam Camacho
|
|
29
|
+
#
|
|
30
|
+
# File Description:
|
|
31
|
+
# Script to remove needless BLAST database files.
|
|
32
|
+
#
|
|
33
|
+
# ===========================================================================
|
|
34
|
+
"""
|
|
35
|
+
import argparse, os, configparser
|
|
36
|
+
import unittest, tempfile
|
|
37
|
+
from pathlib import Path
|
|
38
|
+
from glob import glob
|
|
39
|
+
|
|
40
|
+
VERSION = '1.0'
|
|
41
|
+
DESC = r""" Remove needless BLAST database volumes. """
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
class Tester(unittest.TestCase):
|
|
45
|
+
""" Testing class for this script. """
|
|
46
|
+
|
|
47
|
+
def test_blastdb_config_invalid(self):
|
|
48
|
+
rv = get_blastdb_from_ncbi_config("/dev/null")
|
|
49
|
+
self.assertIsNone(rv)
|
|
50
|
+
|
|
51
|
+
def test_blastdb_config(self):
|
|
52
|
+
config = configparser.ConfigParser()
|
|
53
|
+
expected = "/blast/db/blast"
|
|
54
|
+
config['BLAST'] = {'BLASTDB': expected}
|
|
55
|
+
tf = tempfile.NamedTemporaryFile(mode="wt")
|
|
56
|
+
config.write(tf)
|
|
57
|
+
tf.flush()
|
|
58
|
+
rv = get_blastdb_from_ncbi_config(tf.name)
|
|
59
|
+
self.assertEqual(expected, rv)
|
|
60
|
+
|
|
61
|
+
def test_blastdb_finder(self):
|
|
62
|
+
tal = tempfile.NamedTemporaryFile(suffix=".pin")
|
|
63
|
+
dbname = find_blastdb(tal.name[:-4], True)
|
|
64
|
+
self.assertEqual(dbname, tal.name[:-4])
|
|
65
|
+
|
|
66
|
+
|
|
67
|
+
def find_blastdb(name: str, is_prot: bool) -> str:
|
|
68
|
+
""" Returns full path to BLAST database or None. """
|
|
69
|
+
alias_file = "{}.{}al".format(name, "p" if is_prot else "n")
|
|
70
|
+
index_file = "{}.{}in".format(name, "p" if is_prot else "n")
|
|
71
|
+
if os.path.exists(alias_file) or os.path.exists(index_file):
|
|
72
|
+
return name
|
|
73
|
+
|
|
74
|
+
if "BLASTDB" in os.environ:
|
|
75
|
+
alf = os.path.join(os.environ["BLASTDB"], alias_file)
|
|
76
|
+
idxf = os.path.join(os.environ["BLASTDB"], index_file)
|
|
77
|
+
if os.path.exists(alf) or os.path.exists(idxf):
|
|
78
|
+
return os.path.join(os.environ["BLASTDB"], name)
|
|
79
|
+
|
|
80
|
+
paths = [ os.getcwd(), str(Path.home()) ]
|
|
81
|
+
if "NCBI" in os.environ:
|
|
82
|
+
paths.append(os.path.join(os.environ["NCBI"]))
|
|
83
|
+
|
|
84
|
+
for path in paths:
|
|
85
|
+
for fname in [ ".ncbirc", "ncbi.ini" ]:
|
|
86
|
+
ncbirc = os.path.join(path, fname)
|
|
87
|
+
if os.path.exists(ncbirc):
|
|
88
|
+
blastdb = get_blastdb_from_ncbi_config(ncbirc)
|
|
89
|
+
if blastdb is not None:
|
|
90
|
+
alf = os.path.join(blastdb, alias_file)
|
|
91
|
+
idxf = os.path.join(blastdb, index_file)
|
|
92
|
+
if os.path.exists(alf) or os.path.exists(idxf):
|
|
93
|
+
return os.path.join(blastdb, name)
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
def get_blastdb_from_ncbi_config(config_file: str) -> str:
|
|
97
|
+
""" Return the BLASTDB setting from the NCBI configuration file or None. """
|
|
98
|
+
config = configparser.ConfigParser()
|
|
99
|
+
config.read(config_file)
|
|
100
|
+
if 'BLAST' in config and 'BLASTDB' in config['BLAST']:
|
|
101
|
+
return config['BLAST']['BLASTDB']
|
|
102
|
+
|
|
103
|
+
|
|
104
|
+
def main():
|
|
105
|
+
""" Entry point into this program. """
|
|
106
|
+
parser = create_arg_parser()
|
|
107
|
+
args = parser.parse_args()
|
|
108
|
+
|
|
109
|
+
ext = args.dbtype[0]
|
|
110
|
+
db = find_blastdb(args.db, ext == 'p')
|
|
111
|
+
if db == None:
|
|
112
|
+
print("Cannot find {} {} BLAST database".
|
|
113
|
+
format("protein" if ext == 'p' else "nucleotide", args.db),
|
|
114
|
+
file=sys.stderr)
|
|
115
|
+
return 1
|
|
116
|
+
|
|
117
|
+
alias_file = "{}.{}al".format(db, ext)
|
|
118
|
+
if not os.path.exists(alias_file):
|
|
119
|
+
return 1
|
|
120
|
+
|
|
121
|
+
with open(alias_file, "rt") as al:
|
|
122
|
+
for line in al:
|
|
123
|
+
if not line.startswith("DBLIST"):
|
|
124
|
+
continue
|
|
125
|
+
vols = list(map(lambda x: x.replace('"', ''), line.split()[1:]))
|
|
126
|
+
for existing_vols in sorted(glob("{}.*.{}in".format(db, ext))):
|
|
127
|
+
vol_name = os.path.basename(existing_vols)[:-4]
|
|
128
|
+
if vol_name in vols:
|
|
129
|
+
continue
|
|
130
|
+
if args.dry_run:
|
|
131
|
+
print("Will remove extra volume {}".format(existing_vols[:-4]))
|
|
132
|
+
to_rm = glob("{}??".format(existing_vols[:-2]))
|
|
133
|
+
to_rm += glob("{}.tar.gz.md5".format(existing_vols[:-4]))
|
|
134
|
+
for f in to_rm:
|
|
135
|
+
if not args.dry_run:
|
|
136
|
+
os.unlink(f)
|
|
137
|
+
print("Removed {}".format(f))
|
|
138
|
+
elif args.verbose > 0:
|
|
139
|
+
print("Will remove {}".format(f))
|
|
140
|
+
|
|
141
|
+
return 0
|
|
142
|
+
|
|
143
|
+
|
|
144
|
+
def create_arg_parser():
|
|
145
|
+
""" Create the command line options parser object for this script. """
|
|
146
|
+
parser = argparse.ArgumentParser(description=DESC)
|
|
147
|
+
parser.add_argument("-db", required=True, help="BLAST database name")
|
|
148
|
+
parser.add_argument("-dbtype", help="Molecule type", required=True,
|
|
149
|
+
choices=["prot", "nucl"])
|
|
150
|
+
parser.add_argument("-dry-run", action='store_true',
|
|
151
|
+
help="Do not delete any files, just list them")
|
|
152
|
+
parser.add_argument('-version', action='version',
|
|
153
|
+
version='%(prog)s ' + VERSION)
|
|
154
|
+
parser.add_argument("-verbose", action="count", default=0,
|
|
155
|
+
help="Increase output verbosity")
|
|
156
|
+
return parser
|
|
157
|
+
|
|
158
|
+
|
|
159
|
+
if __name__ == "__main__":
|
|
160
|
+
import sys
|
|
161
|
+
sys.exit(main())
|
|
162
|
+
|
|
@@ -1,152 +1,152 @@
|
|
|
1
|
-
#!/bin/bash
|
|
2
|
-
# $Id: get_species_taxids.sh 631039 2021-05-12 14:35:54Z fongah2 $
|
|
3
|
-
# ===========================================================================
|
|
4
|
-
#
|
|
5
|
-
# PUBLIC DOMAIN NOTICE
|
|
6
|
-
# National Center for Biotechnology Information
|
|
7
|
-
#
|
|
8
|
-
# This software/database is a "United States Government Work" under the
|
|
9
|
-
# terms of the United States Copyright Act. It was written as part of
|
|
10
|
-
# the author's official duties as a United States Government employee and
|
|
11
|
-
# thus cannot be copyrighted. This software/database is freely available
|
|
12
|
-
# to the public for use. The National Library of Medicine and the U.S.
|
|
13
|
-
# Government have not placed any restriction on its use or reproduction.
|
|
14
|
-
#
|
|
15
|
-
# Although all reasonable efforts have been taken to ensure the accuracy
|
|
16
|
-
# and reliability of the software and data, the NLM and the U.S.
|
|
17
|
-
# Government do not and cannot warrant the performance or results that
|
|
18
|
-
# may be obtained by using this software or data. The NLM and the U.S.
|
|
19
|
-
# Government disclaim all warranties, express or implied, including
|
|
20
|
-
# warranties of performance, merchantability or fitness for any particular
|
|
21
|
-
# purpose.
|
|
22
|
-
#
|
|
23
|
-
# Please cite the author in any work or product based on this material.
|
|
24
|
-
#
|
|
25
|
-
# ===========================================================================
|
|
26
|
-
#
|
|
27
|
-
# Author: Amelia Fong
|
|
28
|
-
#
|
|
29
|
-
# File Description:
|
|
30
|
-
# Script to convert NCBI taxonomy IDs or text into taxonomy IDs suitable for
|
|
31
|
-
# filtering BLAST searches.
|
|
32
|
-
#
|
|
33
|
-
# N.B.: Depends on EDirect (https://www.ncbi.nlm.nih.gov/books/NBK179288/)
|
|
34
|
-
#
|
|
35
|
-
# ===========================================================================
|
|
36
|
-
|
|
37
|
-
export PATH=/bin:/usr/bin:/am/ncbiapdata/bin:$HOME/edirect:$PATH
|
|
38
|
-
set -uo pipefail
|
|
39
|
-
|
|
40
|
-
TOO_MANY_MATCHES=500
|
|
41
|
-
OUTPUT=`mktemp`
|
|
42
|
-
TMP=`mktemp`
|
|
43
|
-
trap " /bin/rm -fr $OUTPUT $TMP" INT QUIT EXIT HUP KILL ALRM
|
|
44
|
-
|
|
45
|
-
usage() {
|
|
46
|
-
echo "$0 usage:";
|
|
47
|
-
echo -e "\t-t <taxonomy ID>\n\t\tGet taxonomy IDs at or below input taxonomy ID level";
|
|
48
|
-
echo -e "\t-n <Scientific Name, Common Name or Keyword>\n\t\tGet taxonomy information for organism";
|
|
49
|
-
exit 0;
|
|
50
|
-
}
|
|
51
|
-
|
|
52
|
-
error_exit() {
|
|
53
|
-
msg=$1
|
|
54
|
-
exit_code=${2:-1}
|
|
55
|
-
>&2 echo $msg;
|
|
56
|
-
exit $exit_code;
|
|
57
|
-
}
|
|
58
|
-
|
|
59
|
-
check_deps() {
|
|
60
|
-
for app in esearch efetch esummary; do
|
|
61
|
-
command -v $app >/dev/null 2>&1 || error_exit "Cannot find Entrez EDirect $app tool, please see installation in https://www.ncbi.nlm.nih.gov/books/NBK179288/"
|
|
62
|
-
done
|
|
63
|
-
}
|
|
64
|
-
|
|
65
|
-
check_deps
|
|
66
|
-
|
|
67
|
-
TAXID=""
|
|
68
|
-
NAME=""
|
|
69
|
-
while getopts "ht::n::o::" OPT; do
|
|
70
|
-
case $OPT in
|
|
71
|
-
h)
|
|
72
|
-
usage
|
|
73
|
-
;;
|
|
74
|
-
t)
|
|
75
|
-
TAXID=${OPTARG}
|
|
76
|
-
;;
|
|
77
|
-
n)
|
|
78
|
-
NAME=${OPTARG}
|
|
79
|
-
;;
|
|
80
|
-
esac
|
|
81
|
-
done
|
|
82
|
-
|
|
83
|
-
if [ -z "${TAXID}" ] && [ -z "${NAME}" ]; then
|
|
84
|
-
usage
|
|
85
|
-
fi
|
|
86
|
-
if [ ! -z "${TAXID}" ] && [ ! -z "${NAME}" ]; then
|
|
87
|
-
echo -e "Input Error: -t is incompatible with -n\n"
|
|
88
|
-
usage
|
|
89
|
-
fi
|
|
90
|
-
|
|
91
|
-
if [ ! -z "${TAXID}" ]; then
|
|
92
|
-
esearch -db taxonomy -query "txid$TAXID[orgn]" > $OUTPUT
|
|
93
|
-
if [ $? -ne 0 ]; then
|
|
94
|
-
error_exit "esearch error" $?
|
|
95
|
-
fi
|
|
96
|
-
|
|
97
|
-
efetch -format uid < $OUTPUT > $TMP
|
|
98
|
-
if [ $? -ne 0 ]; then
|
|
99
|
-
error_exit "efetch error" $?
|
|
100
|
-
fi
|
|
101
|
-
|
|
102
|
-
if [ ! -s $TMP ]; then
|
|
103
|
-
error_exit "Taxonomy ID not found"
|
|
104
|
-
fi
|
|
105
|
-
|
|
106
|
-
sort -n $TMP > $OUTPUT
|
|
107
|
-
fi
|
|
108
|
-
|
|
109
|
-
if [ ! -z "${NAME}" ]; then
|
|
110
|
-
|
|
111
|
-
esearch -db taxonomy -query "$NAME[All Names]" > $OUTPUT
|
|
112
|
-
if [ $? -ne 0 ]; then
|
|
113
|
-
error_exit "esearch error" $?
|
|
114
|
-
fi
|
|
115
|
-
|
|
116
|
-
NUM_RESULTS=$(grep "<Count>" $OUTPUT | sed -e 's,.*<Count>\([^<]*\)</Count>.*,\1,g')
|
|
117
|
-
|
|
118
|
-
if [ $NUM_RESULTS -eq 0 ]; then
|
|
119
|
-
CORRECT_NAME=$(espell -db taxonomy -query "$NAME" | grep "<CorrectedQuery>" | sed -e 's,.*<CorrectedQuery>\([^<]*\)</CorrectedQuery>.*,\1,g')
|
|
120
|
-
|
|
121
|
-
if [ ! -z "${CORRECT_NAME}" ]; then
|
|
122
|
-
error_exit "No matches found for \"$NAME\". Did you mean \"$CORRECT_NAME\"?"
|
|
123
|
-
fi
|
|
124
|
-
|
|
125
|
-
esearch -db taxonomy -query "$NAME[Name Tokens]" > $OUTPUT
|
|
126
|
-
if [ $? -ne 0 ]; then
|
|
127
|
-
error_exit "esearch error"
|
|
128
|
-
fi
|
|
129
|
-
NUM_RESULTS=$(grep "<Count>" $OUTPUT | sed -e 's,.*<Count>\([^<]*\)</Count>.*,\1,g')
|
|
130
|
-
if [ $NUM_RESULTS -gt $TOO_MANY_MATCHES ]; then
|
|
131
|
-
error_exit "More than $TOO_MANY_MATCHES matches found, please refine your search."
|
|
132
|
-
fi
|
|
133
|
-
if [ $NUM_RESULTS -eq 0 ]; then
|
|
134
|
-
error_exit "No matches for \"$NAME\"."
|
|
135
|
-
fi
|
|
136
|
-
fi
|
|
137
|
-
|
|
138
|
-
esummary -mode json < $OUTPUT > $TMP
|
|
139
|
-
|
|
140
|
-
if [ $? -ne 0 ]; then
|
|
141
|
-
error_exit "esummary error" $?
|
|
142
|
-
fi
|
|
143
|
-
|
|
144
|
-
cat $TMP | tr ',|{' '\n' | \
|
|
145
|
-
grep 'uid\|rank\|division\|scientificname\|commonname' | \
|
|
146
|
-
grep -v "uids\|genbankdivision" | tr '"\|,' " " | tr -s ' ' | \
|
|
147
|
-
sed 's/ uid/Taxid/g;s/name/ name/g' | awk '/Taxid/{print ""}1' > $OUTPUT
|
|
148
|
-
|
|
149
|
-
echo -e "\n$NUM_RESULTS matche(s) found.\n" >> $OUTPUT
|
|
150
|
-
fi
|
|
151
|
-
|
|
152
|
-
cat $OUTPUT
|
|
1
|
+
#!/bin/bash
|
|
2
|
+
# $Id: get_species_taxids.sh 631039 2021-05-12 14:35:54Z fongah2 $
|
|
3
|
+
# ===========================================================================
|
|
4
|
+
#
|
|
5
|
+
# PUBLIC DOMAIN NOTICE
|
|
6
|
+
# National Center for Biotechnology Information
|
|
7
|
+
#
|
|
8
|
+
# This software/database is a "United States Government Work" under the
|
|
9
|
+
# terms of the United States Copyright Act. It was written as part of
|
|
10
|
+
# the author's official duties as a United States Government employee and
|
|
11
|
+
# thus cannot be copyrighted. This software/database is freely available
|
|
12
|
+
# to the public for use. The National Library of Medicine and the U.S.
|
|
13
|
+
# Government have not placed any restriction on its use or reproduction.
|
|
14
|
+
#
|
|
15
|
+
# Although all reasonable efforts have been taken to ensure the accuracy
|
|
16
|
+
# and reliability of the software and data, the NLM and the U.S.
|
|
17
|
+
# Government do not and cannot warrant the performance or results that
|
|
18
|
+
# may be obtained by using this software or data. The NLM and the U.S.
|
|
19
|
+
# Government disclaim all warranties, express or implied, including
|
|
20
|
+
# warranties of performance, merchantability or fitness for any particular
|
|
21
|
+
# purpose.
|
|
22
|
+
#
|
|
23
|
+
# Please cite the author in any work or product based on this material.
|
|
24
|
+
#
|
|
25
|
+
# ===========================================================================
|
|
26
|
+
#
|
|
27
|
+
# Author: Amelia Fong
|
|
28
|
+
#
|
|
29
|
+
# File Description:
|
|
30
|
+
# Script to convert NCBI taxonomy IDs or text into taxonomy IDs suitable for
|
|
31
|
+
# filtering BLAST searches.
|
|
32
|
+
#
|
|
33
|
+
# N.B.: Depends on EDirect (https://www.ncbi.nlm.nih.gov/books/NBK179288/)
|
|
34
|
+
#
|
|
35
|
+
# ===========================================================================
|
|
36
|
+
|
|
37
|
+
export PATH=/bin:/usr/bin:/am/ncbiapdata/bin:$HOME/edirect:$PATH
|
|
38
|
+
set -uo pipefail
|
|
39
|
+
|
|
40
|
+
TOO_MANY_MATCHES=500
|
|
41
|
+
OUTPUT=`mktemp`
|
|
42
|
+
TMP=`mktemp`
|
|
43
|
+
trap " /bin/rm -fr $OUTPUT $TMP" INT QUIT EXIT HUP KILL ALRM
|
|
44
|
+
|
|
45
|
+
usage() {
|
|
46
|
+
echo "$0 usage:";
|
|
47
|
+
echo -e "\t-t <taxonomy ID>\n\t\tGet taxonomy IDs at or below input taxonomy ID level";
|
|
48
|
+
echo -e "\t-n <Scientific Name, Common Name or Keyword>\n\t\tGet taxonomy information for organism";
|
|
49
|
+
exit 0;
|
|
50
|
+
}
|
|
51
|
+
|
|
52
|
+
error_exit() {
|
|
53
|
+
msg=$1
|
|
54
|
+
exit_code=${2:-1}
|
|
55
|
+
>&2 echo $msg;
|
|
56
|
+
exit $exit_code;
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
check_deps() {
|
|
60
|
+
for app in esearch efetch esummary; do
|
|
61
|
+
command -v $app >/dev/null 2>&1 || error_exit "Cannot find Entrez EDirect $app tool, please see installation in https://www.ncbi.nlm.nih.gov/books/NBK179288/"
|
|
62
|
+
done
|
|
63
|
+
}
|
|
64
|
+
|
|
65
|
+
check_deps
|
|
66
|
+
|
|
67
|
+
TAXID=""
|
|
68
|
+
NAME=""
|
|
69
|
+
while getopts "ht::n::o::" OPT; do
|
|
70
|
+
case $OPT in
|
|
71
|
+
h)
|
|
72
|
+
usage
|
|
73
|
+
;;
|
|
74
|
+
t)
|
|
75
|
+
TAXID=${OPTARG}
|
|
76
|
+
;;
|
|
77
|
+
n)
|
|
78
|
+
NAME=${OPTARG}
|
|
79
|
+
;;
|
|
80
|
+
esac
|
|
81
|
+
done
|
|
82
|
+
|
|
83
|
+
if [ -z "${TAXID}" ] && [ -z "${NAME}" ]; then
|
|
84
|
+
usage
|
|
85
|
+
fi
|
|
86
|
+
if [ ! -z "${TAXID}" ] && [ ! -z "${NAME}" ]; then
|
|
87
|
+
echo -e "Input Error: -t is incompatible with -n\n"
|
|
88
|
+
usage
|
|
89
|
+
fi
|
|
90
|
+
|
|
91
|
+
if [ ! -z "${TAXID}" ]; then
|
|
92
|
+
esearch -db taxonomy -query "txid$TAXID[orgn]" > $OUTPUT
|
|
93
|
+
if [ $? -ne 0 ]; then
|
|
94
|
+
error_exit "esearch error" $?
|
|
95
|
+
fi
|
|
96
|
+
|
|
97
|
+
efetch -format uid < $OUTPUT > $TMP
|
|
98
|
+
if [ $? -ne 0 ]; then
|
|
99
|
+
error_exit "efetch error" $?
|
|
100
|
+
fi
|
|
101
|
+
|
|
102
|
+
if [ ! -s $TMP ]; then
|
|
103
|
+
error_exit "Taxonomy ID not found"
|
|
104
|
+
fi
|
|
105
|
+
|
|
106
|
+
sort -n $TMP > $OUTPUT
|
|
107
|
+
fi
|
|
108
|
+
|
|
109
|
+
if [ ! -z "${NAME}" ]; then
|
|
110
|
+
|
|
111
|
+
esearch -db taxonomy -query "$NAME[All Names]" > $OUTPUT
|
|
112
|
+
if [ $? -ne 0 ]; then
|
|
113
|
+
error_exit "esearch error" $?
|
|
114
|
+
fi
|
|
115
|
+
|
|
116
|
+
NUM_RESULTS=$(grep "<Count>" $OUTPUT | sed -e 's,.*<Count>\([^<]*\)</Count>.*,\1,g')
|
|
117
|
+
|
|
118
|
+
if [ $NUM_RESULTS -eq 0 ]; then
|
|
119
|
+
CORRECT_NAME=$(espell -db taxonomy -query "$NAME" | grep "<CorrectedQuery>" | sed -e 's,.*<CorrectedQuery>\([^<]*\)</CorrectedQuery>.*,\1,g')
|
|
120
|
+
|
|
121
|
+
if [ ! -z "${CORRECT_NAME}" ]; then
|
|
122
|
+
error_exit "No matches found for \"$NAME\". Did you mean \"$CORRECT_NAME\"?"
|
|
123
|
+
fi
|
|
124
|
+
|
|
125
|
+
esearch -db taxonomy -query "$NAME[Name Tokens]" > $OUTPUT
|
|
126
|
+
if [ $? -ne 0 ]; then
|
|
127
|
+
error_exit "esearch error"
|
|
128
|
+
fi
|
|
129
|
+
NUM_RESULTS=$(grep "<Count>" $OUTPUT | sed -e 's,.*<Count>\([^<]*\)</Count>.*,\1,g')
|
|
130
|
+
if [ $NUM_RESULTS -gt $TOO_MANY_MATCHES ]; then
|
|
131
|
+
error_exit "More than $TOO_MANY_MATCHES matches found, please refine your search."
|
|
132
|
+
fi
|
|
133
|
+
if [ $NUM_RESULTS -eq 0 ]; then
|
|
134
|
+
error_exit "No matches for \"$NAME\"."
|
|
135
|
+
fi
|
|
136
|
+
fi
|
|
137
|
+
|
|
138
|
+
esummary -mode json < $OUTPUT > $TMP
|
|
139
|
+
|
|
140
|
+
if [ $? -ne 0 ]; then
|
|
141
|
+
error_exit "esummary error" $?
|
|
142
|
+
fi
|
|
143
|
+
|
|
144
|
+
cat $TMP | tr ',|{' '\n' | \
|
|
145
|
+
grep 'uid\|rank\|division\|scientificname\|commonname' | \
|
|
146
|
+
grep -v "uids\|genbankdivision" | tr '"\|,' " " | tr -s ' ' | \
|
|
147
|
+
sed 's/ uid/Taxid/g;s/name/ name/g' | awk '/Taxid/{print ""}1' > $OUTPUT
|
|
148
|
+
|
|
149
|
+
echo -e "\n$NUM_RESULTS matche(s) found.\n" >> $OUTPUT
|
|
150
|
+
fi
|
|
151
|
+
|
|
152
|
+
cat $OUTPUT
|