[ { "id": "CIAlign", "name": "CIAlign", "article": "10.7717\/peerj.12983", "website": "https:\/\/github.com\/KatyBrown\/CIAlign", "git": "https:\/\/github.com\/KatyBrown\/CIAlign", "description": "command line tool which performs various functions to clean and analyse a multiple sequence alignment (MSA)", "version": "1.0.18", "documentation": "https:\/\/github.com\/KatyBrown\/CIAlign", "multiqc": "custom", "commands": [ { "name": "CIAlign", "cname": "CIAlign clean", "command": "CIAlign ", "category": "phylogenetics", "output_dir": "CIAlign", "inputs": [ { "name": "align_file", "type": "aligned_fasta", "file": "aligned_seqs.fasta", "description": "Aligned fasta sequences" } ], "outputs": [ { "name": "cleaned_alignment", "type": "aligned_fasta", "file": "CIAlign_cleaned.fasta", "description": "cleaned alignment after all steps have been performed" } ], "options": [ { "name": "CIAlign_remove_divergent", "prefix": "--remove_divergent", "type": "checkbox", "value": false, "label": "Remove sequences with <= N proportion of positions at which the most common base \/ amino acid in the alignment is present" }, { "name": "CIAlign_remove_divergent_minperc", "prefix": "--remove_divergent_minperc", "type": "numeric", "value": 0.65, "min": 0, "max": 1, "step": 0.01, "label": "Minimum proportion of positions which should be identical to the most common base\/amino acid in order to be preserved" }, { "name": "CIAlign_remove_insertions", "prefix": "--remove_insertions", "type": "checkbox", "value": false, "label": "Remove insertions found in <= 50% of sequences from the alignment" }, { "name": "CIAlign_insertion_min_size", "prefix": "--insertion_min_size", "type": "numeric", "value": 3, "min": 1, "max": "NA", "step": 1, "label": "Only remove insertions >= this number of residues" }, { "name": "CIAlign_insertion_max_size", "prefix": "--insertion_max_size", "type": "numeric", "value": 200, "min": 1, "max": 1000, "step": 1, "label": "Only remove insertions <= this number of residues" }, { "name": "CIAlign_insertion_min_flank", "prefix": "--insertion_min_flank", "type": "numeric", "value": 5, "min": 0, "max": "NA", "step": 1, "label": "Minimum number of bases on either side of an insertion to classify it as an insertion" }, { "name": "CIAlign_crop_ends", "prefix": "--crop_ends", "type": "checkbox", "value": false, "label": "Crop the ends of sequences if they are poorly aligned" }, { "name": "CIAlign_crop_ends_mingap_perc", "prefix": "--crop_ends_mingap_perc", "type": "numeric", "value": 0.05, "min": 0, "max": 0.5, "step": 0.01, "label": "Minimum proportion of the sequence length (excluding gaps) that is the threshold for change in gap numbers." }, { "name": "CIAlign_crop_ends_redefine_perc", "prefix": "--crop_ends_redefine_perc", "type": "numeric", "value": 0.1, "min": 0, "max": 0.5, "step": 0.01, "label": "Proportion of the sequence length (excluding gaps) that is being checked for change in gap numbers to redefine start\/end." }, { "name": "CIAlign_remove_short", "prefix": "--remove_short", "type": "checkbox", "value": false, "label": "Remove sequences <= N bases \/ amino acids from the alignment" }, { "name": "CIAlign_remove_min_length", "prefix": "--crop_remove_min_length", "type": "numeric", "value": 50, "min": 0, "max": "NA", "step": 1, "label": "Sequences are removed if they are shorter than this minimum length, excluding gaps." }, { "name": "CIAlign_keep_gaponly", "prefix": "--keep_gaponly", "type": "checkbox", "value": false, "label": "Keep gap only columns in the alignment" } ] } ], "install": [], "citations": { "ete": [ "Tumescheit C, Firth AE, Brown K. 2022. CIAlign: A highly customisable command line tool to clean, interpret and visualise multiple sequence alignments. PeerJ 10:e12983 https:\/\/doi.org\/10.7717\/peerj.12983" ] }, "yaml": "{\n id: CIAlign ,\n name: CIAlign,\n article: \"10.7717\/peerj.12983\",\n website: \"https:\/\/github.com\/KatyBrown\/CIAlign\",\n git: \"https:\/\/github.com\/KatyBrown\/CIAlign\",\n description: \"command line tool which performs various functions to clean and analyse a multiple sequence alignment (MSA)\",\n version: \"1.0.18\",\n documentation: \"https:\/\/github.com\/KatyBrown\/CIAlign\",\n multiqc: \"custom\",\n commands:\n [\n {\n name: CIAlign,\n cname: \"CIAlign clean\",\n command: \"CIAlign \",\n category: \"phylogenetics\",\n output_dir: CIAlign,\n inputs: [\n { name: align_file, type: \"aligned_fasta\", file: \"aligned_seqs.fasta\", description: \"Aligned fasta sequences\"}\n ],\n outputs:\n [\n { name: cleaned_alignment, type: \"aligned_fasta\", file: \"CIAlign_cleaned.fasta\", description: \"cleaned alignment after all steps have been performed\" },\n ],\n options:\n [\n {\n name: CIAlign_remove_divergent,\n prefix: \"--remove_divergent\",\n type: checkbox,\n value: FALSE,\n label: \"Remove sequences with <= N proportion of positions at which the most common base \/ amino acid in the alignment is present\",\n },\n {\n name: CIAlign_remove_divergent_minperc,\n prefix: \"--remove_divergent_minperc\",\n type: numeric,\n value: 0.65,\n min: 0,\n max: 1,\n step: 0.01,\n label: \"Minimum proportion of positions which should be identical to the most common base\/amino acid in order to be preserved\",\n }, \n {\n name: CIAlign_remove_insertions,\n prefix: \"--remove_insertions\",\n type: checkbox,\n value: FALSE,\n label: \"Remove insertions found in <= 50% of sequences from the alignment\",\n }, \n {\n name: CIAlign_insertion_min_size,\n prefix: \"--insertion_min_size\",\n type: numeric,\n value: 3,\n min: 1,\n max: NA,\n step: 1,\n label: \"Only remove insertions >= this number of residues\",\n }, \n {\n name: CIAlign_insertion_max_size,\n prefix: \"--insertion_max_size\",\n type: numeric,\n value: 200,\n min: 1,\n max: 1000,\n step: 1,\n label: \"Only remove insertions <= this number of residues\",\n }, \n {\n name: CIAlign_insertion_min_flank,\n prefix: \"--insertion_min_flank\",\n type: numeric,\n value: 5,\n min: 0,\n max: NA,\n step: 1,\n label: \"Minimum number of bases on either side of an insertion to classify it as an insertion\",\n }, \n {\n name: CIAlign_crop_ends,\n prefix: \"--crop_ends\",\n type: checkbox,\n value: FALSE,\n label: \"Crop the ends of sequences if they are poorly aligned\",\n }, \n {\n name: CIAlign_crop_ends_mingap_perc,\n prefix: \"--crop_ends_mingap_perc\",\n type: numeric,\n value: 0.05,\n min: 0,\n max: 0.5,\n step: 0.01,\n label: \"Minimum proportion of the sequence length (excluding gaps) that is the threshold for change in gap numbers.\",\n }, \n {\n name: CIAlign_crop_ends_redefine_perc,\n prefix: \"--crop_ends_redefine_perc\",\n type: numeric,\n value: 0.1,\n min: 0,\n max: 0.5,\n step: 0.01,\n label: \"Proportion of the sequence length (excluding gaps) that is being checked for change in gap numbers to redefine start\/end.\",\n }, \n {\n name: CIAlign_remove_short,\n prefix: \"--remove_short\",\n type: checkbox,\n value: FALSE,\n label: \"Remove sequences <= N bases \/ amino acids from the alignment\",\n },\n {\n name: CIAlign_remove_min_length,\n prefix: \"--crop_remove_min_length\",\n type: numeric,\n value: 50,\n min: 0,\n max: NA,\n step: 1,\n label: \"Sequences are removed if they are shorter than this minimum length, excluding gaps.\",\n },\n {\n name: CIAlign_keep_gaponly,\n prefix: \"--keep_gaponly\",\n type: checkbox,\n value: FALSE,\n label: \"Keep gap only columns in the alignment\",\n }, \n ],\n },\n ],\n install: {\n # numpy: [\n # \"pip3 install numpy\"\n # ],\n # scipy: [\n # \"pip3 install scipy\"\n # ],\n # matplotlib: [\n # \"pip3 install matplotlib\"\n # ],\n # CIAlign : [\n # \"pip3 install cialign==1.0.15\"\n # ],\n },\n citations: {\n ete: [\n \"Tumescheit C, Firth AE, Brown K. 2022. CIAlign: A highly customisable command line tool to clean, interpret and visualise multiple sequence alignments. PeerJ 10:e12983 https:\/\/doi.org\/10.7717\/peerj.12983\"\n ],\n }\n}" } ]