[ { "id": "busco", "name": "Busco", "description": "Based on evolutionarily-informed expectations of gene content of near-universal single-copy orthologs, BUSCO metric is complementary to technical metrics like N50.", "version": "5.4.7", "website": "https:\/\/busco.ezlab.org\/", "git": "https:\/\/gitlab.com\/ezlab\/busco", "documentation": "https:\/\/busco.ezlab.org\/busco_userguide.html", "article": "10.1007\/978-1-4939-9173-0_14", "multiqc": "busco", "commands": [ { "name": "busco", "cname": "BUSCO", "category": "post_assembly", "command": "busco", "output_dir": "busco", "inputs": [ { "name": "fasta_seq", "file": "seq.fasta", "type": "contigs", "description": "Input sequence file in FASTA format. Can be an assembled genome or transcriptome (DNA), or protein sequences from an annotated gene set." } ], "outputs": [ { "name": "log", "file": "busco.log", "type": "txt", "description": "Full log of Busco execution" } ], "options": [ { "name": "busco_mode", "prefix": "-m", "value": "geno", "choices": [ { "geno": "geno" }, { "tran": "tran" }, { "prot": "prot" } ], "label": "Specify which BUSCO analysis mode to run.", "type": "select" }, { "name": "busco_threads", "prefix": "-c", "value": 4, "min": 1, "max": 60, "step": 1, "label": "Specify the number (N=integer) of threads\/cores ", "type": "numeric" }, { "name": "busco_lineage", "prefix": "-l", "value": "metazoa_odb10", "choices": [ { "autodetect_full": "--auto-lineage" }, { "autodetect_prok": "--auto-lineage-prok" }, { "autodetect_euka": "--auto-lineage-euk" }, { "acidobacteria_odb10": "acidobacteria_odb10" }, { "actinobacteria_phylum_odb10": "actinobacteria_phylum_odb10" }, { "aquificae_odb10": "aquificae_odb10" }, { "bacteroidetes-chlorobi_group_odb10": "bacteroidetes-chlorobi_group_odb10" }, { "chlamydiae_odb10": "chlamydiae_odb10" }, { "chloroflexi_odb10": "chloroflexi_odb10" }, { "cyanobacteria_odb10": "cyanobacteria_odb10" }, { "firmicutes_odb10": "firmicutes_odb10" }, { "fusobacteria_odb10": "fusobacteria_odb10" }, { "planctomycetes_odb10": "planctomycetes_odb10" }, { "proteobacteria_odb10": "proteobacteria_odb10" }, { "spirochaetes_odb10": "spirochaetes_odb10" }, { "synergistetes_odb10": "synergistetes_odb10" }, { "tenericutes_odb10": "tenericutes_odb10" }, { "thermotogae_odb10": "thermotogae_odb10" }, { "verrucomicrobia_odb10": "verrucomicrobia_odb10" }, { "thaumarchaeota_odb10": "thaumarchaeota_odb10" }, { "thermoprotei_odb10": "thermoprotei_odb10" }, { "euryarchaeota_odb10": "euryarchaeota_odb10" }, { "alveolata_odb10": "alveolata_odb10" }, { "euglenozoa_odb10": "euglenozoa_odb10" }, { "fungi_odb10": "fungi_odb10" }, { "metazoa_odb10": "metazoa_odb10" }, { "stramenopiles_odb10": "stramenopiles_odb10" }, { "viridiplantae_odb10": "viridiplantae_odb10" } ], "label": "clade specific information to identify BUSCO genes in the analysed sequence.", "type": "select" } ] } ], "install": [], "citations": { "busco": [ "Seppey M., Manni M., Zdobnov E.M. (2019) BUSCO: Assessing Genome Assembly and Annotation Completeness. In: Kollmar M. (eds) Gene Prediction. Methods in Molecular Biology, vol 1962. Humana, New York, NY. 2019 doi.org\/10.1007\/978-1-4939-9173-0_14 . PMID:31020564" ], "blast": [ "Camacho, C., Coulouris, G., Avagyan, V. et al. BLAST+: architecture and applications. BMC Bioinformatics 10, 421 (2009). https:\/\/doi.org\/10.1186\/1471-2105-10-421" ], "augustus": [ "Oliver Keller, Martin Kollmar, Mario Stanke, Stephan Waack, A novel hybrid gene prediction method employing protein multiple sequence alignments, Bioinformatics, Volume 27, Issue 6, 15 March 2011, Pages 757-763, https:\/\/doi.org\/10.1093\/bioinformatics\/btr010" ] }, "yaml": "{\n id: \"busco\",\n name: \"Busco\",\n description: \"Based on evolutionarily-informed expectations of gene content of near-universal single-copy orthologs, BUSCO metric is complementary to technical metrics like N50.\",\n version: \"5.4.7\",\n website: \"https:\/\/busco.ezlab.org\/\",\n git: \"https:\/\/gitlab.com\/ezlab\/busco\",\n documentation: \"https:\/\/busco.ezlab.org\/busco_userguide.html\",\n article: \"10.1007\/978-1-4939-9173-0_14\",\n multiqc: \"busco\",\n commands:\n [\n {\n name: \"busco\",\n cname: \"BUSCO\",\n category: \"post_assembly\",\n command: \"busco\",\n output_dir: \"busco\",\n inputs:\n [\n {\n name: \"fasta_seq\",\n file: \"seq.fasta\",\n type: \"contigs\",\n description: \"Input sequence file in FASTA format. Can be an assembled genome or transcriptome (DNA), or protein sequences from an annotated gene set.\",\n },\n ],\n outputs: [\n #{\n # name: \"summary\",\n # file: \"short_summary.*.txt\", # filename depend on parameters (lineage, ... ?)\n # type: \"txt\",\n # description: \"Plain text summary of the results in BUSCO notation.\",\n #},\n {\n name: \"log\",\n file: \"busco.log\",\n type: \"txt\",\n description: \"Full log of Busco execution\",\n },\n ],\n options:\n [\n {\n name: \"busco_mode\",\n prefix: \"-m\",\n value: \"geno\",\n choices: [geno: \"geno\", tran: \"tran\", prot: \"prot\"],\n label: \"Specify which BUSCO analysis mode to run.\",\n type: \"select\",\n },\n {\n name: \"busco_threads\",\n prefix: \"-c\",\n value: 4,\n min: 1,\n max: 60,\n step: 1,\n label: \"Specify the number (N=integer) of threads\/cores \",\n type: \"numeric\",\n },\n {\n name: \"busco_lineage\",\n prefix: \"-l\",\n value: \"metazoa_odb10\",\n choices:\n [\n autodetect_full: \"--auto-lineage\",\n autodetect_prok: \"--auto-lineage-prok\",\n autodetect_euka: \"--auto-lineage-euk\",\n acidobacteria_odb10: \"acidobacteria_odb10\",\n actinobacteria_phylum_odb10: \"actinobacteria_phylum_odb10\",\n aquificae_odb10: \"aquificae_odb10\",\n bacteroidetes-chlorobi_group_odb10: \"bacteroidetes-chlorobi_group_odb10\",\n chlamydiae_odb10: \"chlamydiae_odb10\",\n chloroflexi_odb10: \"chloroflexi_odb10\",\n cyanobacteria_odb10: \"cyanobacteria_odb10\",\n firmicutes_odb10: \"firmicutes_odb10\",\n fusobacteria_odb10: \"fusobacteria_odb10\",\n planctomycetes_odb10: \"planctomycetes_odb10\",\n proteobacteria_odb10: \"proteobacteria_odb10\",\n spirochaetes_odb10: \"spirochaetes_odb10\",\n synergistetes_odb10: \"synergistetes_odb10\",\n tenericutes_odb10: \"tenericutes_odb10\",\n thermotogae_odb10: \"thermotogae_odb10\",\n verrucomicrobia_odb10: \"verrucomicrobia_odb10\",\n thaumarchaeota_odb10: \"thaumarchaeota_odb10\",\n thermoprotei_odb10: \"thermoprotei_odb10\",\n euryarchaeota_odb10: \"euryarchaeota_odb10\",\n alveolata_odb10: \"alveolata_odb10\",\n euglenozoa_odb10: \"euglenozoa_odb10\",\n fungi_odb10: \"fungi_odb10\",\n metazoa_odb10: \"metazoa_odb10\",\n stramenopiles_odb10: \"stramenopiles_odb10\",\n viridiplantae_odb10: \"viridiplantae_odb10\",\n ],\n label: \"clade specific information to identify BUSCO genes in the analysed sequence.\",\n type: \"select\",\n },\n ],\n },\n ],\n install:\n {\n # biopython: [\n # \"pip3 install biopython==1.76\"\n # ],\n # blast: [\n # \"cd \/opt\/biotools\/\",\n # \"wget -O ncbi-blast-2.12.0+.tar.gz https:\/\/ftp.ncbi.nlm.nih.gov\/blast\/executables\/blast+\/2.12.0\/ncbi-blast-2.12.0+-x64-linux.tar.gz\",\n # \"tar -xvzf ncbi-blast-2.12.0+.tar.gz\",\n # \"ENV PATH $PATH:\/opt\/biotools\/ncbi-blast-2.12.0+\/bin\"\n # ],\n # augustus: [\n # \"apt-get -y update\",\n # \"apt-get -y install augustus=3.2.3+dfsg-1\",\n # \"ENV AUGUSTUS_CONFIG_PATH \/usr\/share\/augustus\/config\"\n # ],\n # prodigal: [\n # \"cd \/opt\/biotools\/bin\",\n # \"wget -O prodigal https:\/\/github.com\/hyattpd\/Prodigal\/releases\/download\/v2.6.3\/prodigal.linux\",\n # \"chmod +x prodigal\"\n # ],\n # HMMER: [\n # \"cd \/opt\/biotools\",\n # \"wget http:\/\/eddylab.org\/software\/hmmer\/hmmer-3.2.1.tar.gz\",\n # \"tar -xvzf hmmer-3.2.1.tar.gz\",\n # \"cd hmmer-3.2.1\",\n # \".\/configure --prefix \/opt\/biotools\/\",\n # \"make -j 10\",\n # \"make install\",\n # \"cd easel; make install\",\n # \"cd \/opt\/biotools\",\n # \"rm -r hmmer-3.2.1.tar.gz hmmer-3.2.1\"\n # ],\n # sepp: [\n # \"cd \/opt\/biotools\",\n # \"wget -O sepp-4.3.10.tar.gz https:\/\/github.com\/smirarab\/sepp\/archive\/4.3.10.tar.gz\",\n # \"tar -xvzf sepp-4.3.10.tar.gz\",\n # \"cd sepp-4.3.10\",\n # \"python3 setup.py config -c\",\n # \"python3 setup.py install\",\n # \"cd .. && rm -r sepp-4.3.10 sepp-4.3.10.tar.gz\"\n # ],\n # busco: [\n # \"cd \/opt\/biotools\",\n # \"wget https:\/\/gitlab.com\/ezlab\/busco\/-\/archive\/4.1.3\/busco-4.1.3.tar.gz\",\n # \"tar -xvzf busco-4.1.3.tar.gz\",\n # \"cd busco-4.1.3\",\n # \"python3 setup.py install\",\n # \"cd ..\",\n # \"echo '[tblastn]\\\\npath = \/opt\/biotools\/ncbi-blast-2.12.0+\/bin\/\\\\ncommand = tblastn\\\\n' > busco_config.ini\",\n # \"echo '[makeblastdb]\\\\npath = \/opt\/biotools\/ncbi-blast-2.12.0+\/bin\/\\\\ncommand = makeblastdb\\\\n' >> busco_config.ini\",\n # \"echo '[augustus]\\\\npath = \/usr\/bin\/\\\\ncommand = augustus\\\\n' >> busco_config.ini\",\n # \"echo '[etraining]\\\\npath = \/usr\/bin\/\\\\ncommand = etraining\\\\n' >> busco_config.ini\",\n # \"echo '[gff2gbSmallDNA.pl]\\\\npath = \/usr\/share\/augustus\/scripts\/\\\\ncommand = gff2gbSmallDNA.pl\\\\n' >> busco_config.ini\",\n # \"echo '[new_species.pl]\\\\npath = \/usr\/share\/augustus\/scripts\/\\\\ncommand = new_species.pl\\\\n' >> busco_config.ini\",\n # \"echo '[optimize_augustus.pl]\\\\npath = \/usr\/share\/augustus\/scripts\/\\\\ncommand = optimize_augustus.pl\\\\n' >> busco_config.ini\",\n # \"echo '[hmmsearch]\\\\npath = \/opt\/biotools\/bin\/\\\\ncommand = hmmsearch\\\\n' >> busco_config.ini\",\n # \"echo '[sepp]\\\\npath = \/usr\/local\/bin\/\\\\ncommand = run_sepp.py\\\\n' >> busco_config.ini\",\n # \"echo '[prodigal]\\\\npath = \/opt\/biotools\/bin\/\\\\ncommand = prodigal\\\\n\\\\n' >> busco_config.ini\",\n # \"echo '[busco_run]' >> busco_config.ini\",\n # \"ENV BUSCO_CONFIG_FILE \/opt\/biotools\/busco_config.ini\"\n # ],\n },\n citations:\n {\n busco: [\n \"Seppey M., Manni M., Zdobnov E.M. (2019) BUSCO: Assessing Genome Assembly and Annotation Completeness. In: Kollmar M. (eds) Gene Prediction. Methods in Molecular Biology, vol 1962. Humana, New York, NY. 2019 doi.org\/10.1007\/978-1-4939-9173-0_14 . PMID:31020564\",\n ],\n blast: [\n \"Camacho, C., Coulouris, G., Avagyan, V. et al. BLAST+: architecture and applications. BMC Bioinformatics 10, 421 (2009). https:\/\/doi.org\/10.1186\/1471-2105-10-421\"\n ],\n augustus: [\n \"Oliver Keller, Martin Kollmar, Mario Stanke, Stephan Waack, A novel hybrid gene prediction method employing protein multiple sequence alignments, Bioinformatics, Volume 27, Issue 6, 15 March 2011, Pages 757-763, https:\/\/doi.org\/10.1093\/bioinformatics\/btr010\"\n ],\n },\n}\n" } ]