resources/META-INF/galaxy-operator.json
1{"categories": ["Galaxy", "Bioinformatics", "Sequences"], "description": "Count observed k-mer composition in each DNA sequence.", "documentation": {"example_job": "name: Count observed k-mer composition in each DNA sequence.\nsteps:\n- id: read\n operator: read_item@1.0\n inputs: {}\n params:\n uri: context:/galaxy/extended/emboss_compseq.txt\n view: bytes\n- id: process\n operator: galaxy_emboss_compseq@1.0\n inputs:\n source: read\n params: {}\noutputs:\n result: process\n", "inputs": {"source": "UTF-8 bytes stream. All sliding frames; emits observed ACGT words in lexical order. Windows containing ambiguities are omitted from both counts and denominator. No expected-frequency or external composition tables. FASTA UTF-8 bytes input; one result bytes stream. At most 8 MiB characters per sequence, 100000 sequence records; strict parameters and cancellation. Normalized FASTA uses unwrapped sequence lines. This is a documented subset of the Galaxy EMBOSS wrapper, not the EMBOSS CLI."}, "outputs": {"result": "Count observed k-mer composition in each DNA sequence. All sliding frames; emits observed ACGT words in lexical order. Windows containing ambiguities are omitted from both counts and denominator. No expected-frequency or external composition tables. FASTA UTF-8 bytes input; one result bytes stream. At most 8 MiB characters per sequence, 100000 sequence records; strict parameters and cancellation. Normalized FASTA uses unwrapped sequence lines. This is a documented subset of the Galaxy EMBOSS wrapper, not the EMBOSS CLI."}, "parameters": {"word": {"description": "Overlapping DNA k-mer size.", "example": 2, "help": "Overlapping DNA k-mer size. All sliding frames; emits observed ACGT words in lexical order. Windows containing ambiguities are omitted from both counts and denominator. No expected-frequency or external composition tables. FASTA UTF-8 bytes input; one result bytes stream. At most 8 MiB characters per sequence, 100000 sequence records; strict parameters and cancellation. Normalized FASTA uses unwrapped sequence lines. This is a documented subset of the Galaxy EMBOSS wrapper, not the EMBOSS CLI."}}}, "entrypoint": "xstream.galaxy.EmbossCompseq", "fixture": {"data": ">x\nACGT\n", "expected": "sequence\tword\tcount\tfraction\nx\tAC\t1\t0.333333\nx\tCG\t1\t0.333333\nx\tGT\t1\t0.333333\n", "params": {}}, "icon": {"color": "#5265ad", "path": "M4 3h12l4 4v14H4zM8 11h8M8 15h8m-8 4h5"}, "implementation": "SequenceEdits", "inputs": {"source": {"formats": [], "representations": ["bytes"]}}, "name": "galaxy_emboss_compseq", "parameters": {"additionalProperties": false, "properties": {"word": {"default": 2, "description": "Overlapping DNA k-mer size.", "maximum": 8, "minimum": 1, "type": "integer"}}, "required": [], "type": "object"}, "params": {}, "scope": "All sliding frames; emits observed ACGT words in lexical order. Windows containing ambiguities are omitted from both counts and denominator. No expected-frequency or external composition tables. FASTA UTF-8 bytes input; one result bytes stream. At most 8 MiB characters per sequence, 100000 sequence records; strict parameters and cancellation. Normalized FASTA uses unwrapped sequence lines. This is a documented subset of the Galaxy EMBOSS wrapper, not the EMBOSS CLI.", "upstream": {"path": "tools/emboss_5/emboss_compseq.xml", "repository": "https://github.com/galaxyproject/tools-iuc"}, "version": "1.0"}