[ { "id": "fastp", "name": "fastp", "article": "10.1093\/bioinformatics\/bty560", "website": "https:\/\/github.com\/OpenGene\/fastp", "git": "https:\/\/github.com\/OpenGene\/fastp", "description": "A tool designed to provide fast all-in-one preprocessing for FastQ files.", "version": "0.23.4", "documentation": "https:\/\/github.com\/OpenGene\/fastp", "multiqc": "fastp", "commands": [ { "name": "fastp_PE", "cname": "Fastp PE", "command": "fastp", "category": "quality", "output_dir": "fastp_PE", "inputs": [ { "name": "read", "type": "reads" }, { "name": "read2", "type": "reads" } ], "outputs": [ { "name": "report_html", "type": "html", "file": "fastp_report_{sample}.html", "description": "Rapport HTML du pr\u00e9processing effectu\u00e9" }, { "name": "report_json", "type": "json", "file": "fastp_report_{sample}fastp.json", "description": "Rapport JSON du pr\u00e9processing effectu\u00e9" }, { "name": "read_preprocessed", "type": "reads", "file": "{sample}_1.fq.gz", "description": "Reads R1 pr\u00e9process\u00e9s" }, { "name": "read2_preprocessed", "type": "reads", "file": "{sample}_2.fq.gz", "description": "Reads R2 pr\u00e9process\u00e9s" } ], "options": [ { "name": "fastp_threads", "prefix": "--thread", "type": "numeric", "value": 4, "min": 1, "max": "NA", "step": 1, "label": "Number of threads to use" }, { "name": "fastp_complexity_threshold", "prefix": "--complexity_threshold", "type": "numeric", "value": 30, "min": 1, "max": "NA", "step": 1, "label": "The threshold for low complexity filter (0~100)" }, { "name": "fastp_report_title", "prefix": "--report_title", "type": "text", "value": "fastp report", "label": "fastp report title" }, { "name": "fastp_adapter_detection_PE", "type": "checkbox", "value": true, "label": "adapter sequence auto-detection is disabled by default since the adapters can be trimmed by overlap analysis. However, you can specify --detect_adapter_for_pe to enable it" }, { "name": "fastp_adapter_sequence", "prefix": "--adapter_sequence", "type": "text", "value": "", "label": "The adapter for read1. For SE data, if not specified, the adapter will be auto-detected. For PE data, this is used if R1\/R2 are found not overlapped." }, { "name": "fastp_adapter_sequence_R2_PE", "prefix": "--adapter_sequence_r2", "type": "text", "value": "", "label": "the adapter for read2 (PE data only). This is used if R1\/R2 are found not overlapped. If not specified, it will be the same as " }, { "name": "fastp_P_PE", "prefix": "-P", "type": "numeric", "value": 20, "min": 1, "max": "NA", "step": 1, "label": "For example, if you set -P 100, only 1\/100 reads will be used for counting, and if you set -P 1, all reads will be used and slower." }, { "name": "fastp_correction_PE", "type": "checkbox", "value": true, "label": "Enable base correction in overlapped regions" }, { "name": "fastp_low_complexity_filter", "type": "checkbox", "value": true, "label": "Enable low complexity filter. The complexity is defined as the percentage of base that is different from its next base (base[i] != base[i+1])." }, { "name": "fastp_overrepresentation_analysis", "type": "checkbox", "value": true, "label": "enable overrepresented sequence analysis." }, { "name": "fastp_dedup_PE", "prefix": "--dedup", "type": "checkbox", "value": true, "label": "deduplication for FASTQ data" } ] }, { "name": "fastp_SE", "cname": "Fastp SE", "command": "fastp", "category": "quality", "output_dir": "fastp_SE", "inputs": [ { "name": "read", "type": "reads" } ], "outputs": [ { "name": "report_html", "type": "html", "file": "fastp_report_{sample}.html", "description": "Rapport HTML du pr\u00e9processing effectu\u00e9" }, { "name": "report_json", "type": "json", "file": "fastp_report_{sample}fastp.json", "description": "Rapport JSON du pr\u00e9processing effectu\u00e9" }, { "name": "read_preprocessed", "type": "reads", "file": "{sample}.fq.gz", "description": "Reads pr\u00e9process\u00e9s" } ], "options": [ { "name": "fastp_threads", "prefix": "--thread", "type": "numeric", "value": 4, "min": 1, "max": "NA", "step": 1, "label": "Number of threads to use" }, { "name": "fastp_complexity_threshold", "prefix": "--complexity_threshold", "type": "numeric", "value": 30, "min": 1, "max": "NA", "step": 1, "label": "The threshold for low complexity filter (0~100)" }, { "name": "fastp_report_title", "prefix": "--report_title", "type": "text", "value": "fastp report", "label": "fastp report title" }, { "name": "fastp_adapter_sequence", "prefix": "--adapter_sequence", "type": "text", "value": "", "label": "The adapter for read1. For SE data, if not specified, the adapter will be auto-detected. For PE data, this is used if R1\/R2 are found not overlapped." }, { "name": "fastp_P_SE", "prefix": "-P", "type": "numeric", "value": 20, "min": 1, "max": "NA", "step": 1, "label": "For example, if you set -P 100, only 1\/100 reads will be used for counting, and if you set -P 1, all reads will be used and slower." }, { "name": "fastp_low_complexity_filter", "type": "checkbox", "value": true, "label": "Enable low complexity filter. The complexity is defined as the percentage of base that is different from its next base (base[i] != base[i+1])." }, { "name": "fastp_overrepresentation_analysis", "type": "checkbox", "value": true, "label": "enable overrepresented sequence analysis." } ] } ], "install": [], "citations": { "fastp": [ "Shifu Chen, Yanqing Zhou, Yaru Chen, Jia Gu, fastp: an ultra-fast all-in-one FASTQ preprocessor, Bioinformatics, Volume 34, Issue 17, 01 September 2018, Pages i884-i890, https:\/\/doi.org\/10.1093\/bioinformatics\/bty560" ] }, "yaml": "{\n id: fastp,\n name: fastp,\n article: 10.1093\/bioinformatics\/bty560,\n website: \"https:\/\/github.com\/OpenGene\/fastp\",\n git: \"https:\/\/github.com\/OpenGene\/fastp\",\n description: \"A tool designed to provide fast all-in-one preprocessing for FastQ files.\",\n version: \"0.23.4\",\n documentation: \"https:\/\/github.com\/OpenGene\/fastp\",\n multiqc: \"fastp\",\n commands:\n [\n {\n name: fastp_PE,\n cname: \"Fastp PE\",\n command: fastp,\n category: \"quality\",\n output_dir: fastp_PE,\n inputs: [{ name: read, type: \"reads\" }, { name: read2, type: \"reads\" }],\n outputs: [\n { name: report_html, type: \"html\", file: \"fastp_report_{sample}.html\", description: \"Rapport HTML du pr\u00e9processing effectu\u00e9\" },\n { name: report_json, type: \"json\", file: \"fastp_report_{sample}fastp.json\", description: \"Rapport JSON du pr\u00e9processing effectu\u00e9\" },\n { name: read_preprocessed, type: \"reads\", file: \"{sample}_1.fq.gz\", description: \"Reads R1 pr\u00e9process\u00e9s\" },\n { name: read2_preprocessed, type: \"reads\", file: \"{sample}_2.fq.gz\", description: \"Reads R2 pr\u00e9process\u00e9s\" },\n ],\n options:\n [\n {\n name: fastp_threads,\n prefix: --thread,\n type: numeric,\n value: 4,\n min: 1,\n max: NA,\n step: 1,\n label: \"Number of threads to use\",\n },\n {\n name: fastp_complexity_threshold,\n prefix: --complexity_threshold,\n type: numeric,\n value: 30,\n min: 1,\n max: NA,\n step: 1,\n label: \"The threshold for low complexity filter (0~100)\",\n },\n {\n name: fastp_report_title,\n prefix: --report_title,\n type: text,\n value: \"fastp report\",\n label: \"fastp report title\",\n },\n {\n name: \"fastp_adapter_detection_PE\",\n type: \"checkbox\",\n value: TRUE,\n label: \"adapter sequence auto-detection is disabled by default since the adapters can be trimmed by overlap analysis. However, you can specify --detect_adapter_for_pe to enable it\",\n },\n {\n name: fastp_adapter_sequence,\n prefix: --adapter_sequence,\n type: text,\n value: \"\",\n label: \"The adapter for read1. For SE data, if not specified, the adapter will be auto-detected. For PE data, this is used if R1\/R2 are found not overlapped.\"\n },\n {\n name: fastp_adapter_sequence_R2_PE,\n prefix: --adapter_sequence_r2,\n type: text,\n value: \"\",\n label: \"the adapter for read2 (PE data only). This is used if R1\/R2 are found not overlapped. If not specified, it will be the same as \"\n },\n {\n name: fastp_P_PE,\n prefix: -P,\n type: numeric,\n value: 20,\n min: 1,\n max: NA,\n step: 1,\n label: \"For example, if you set -P 100, only 1\/100 reads will be used for counting, and if you set -P 1, all reads will be used and slower.\",\n },\n {\n name: \"fastp_correction_PE\",\n type: \"checkbox\",\n value: TRUE,\n label: \"Enable base correction in overlapped regions\",\n },\n {\n name: \"fastp_low_complexity_filter\",\n type: \"checkbox\",\n value: TRUE,\n label: \"Enable low complexity filter. The complexity is defined as the percentage of base that is different from its next base (base[i] != base[i+1]).\",\n },\n {\n name: \"fastp_overrepresentation_analysis\",\n type: \"checkbox\",\n value: TRUE,\n label: \"enable overrepresented sequence analysis.\",\n },\n {\n name: \"fastp_dedup_PE\",\n prefix: --dedup,\n type: \"checkbox\",\n value: TRUE,\n label: \"deduplication for FASTQ data\",\n },\n ],\n },\n {\n name: fastp_SE,\n cname: \"Fastp SE\",\n command: fastp,\n category: \"quality\",\n output_dir: fastp_SE,\n inputs: [{ name: read, type: \"reads\" }],\n outputs: [\n { name: report_html, type: \"html\", file: \"fastp_report_{sample}.html\", description: \"Rapport HTML du pr\u00e9processing effectu\u00e9\" },\n { name: report_json, type: \"json\", file: \"fastp_report_{sample}fastp.json\", description: \"Rapport JSON du pr\u00e9processing effectu\u00e9\" },\n { name: read_preprocessed, type: \"reads\", file: \"{sample}.fq.gz\", description: \"Reads pr\u00e9process\u00e9s\" },\n ],\n options:\n [\n {\n name: fastp_threads,\n prefix: --thread,\n type: numeric,\n value: 4,\n min: 1,\n max: NA,\n step: 1,\n label: \"Number of threads to use\",\n },\n {\n name: fastp_complexity_threshold,\n prefix: --complexity_threshold,\n type: numeric,\n value: 30,\n min: 1,\n max: NA,\n step: 1,\n label: \"The threshold for low complexity filter (0~100)\",\n },\n {\n name: fastp_report_title,\n prefix: --report_title,\n type: text,\n value: \"fastp report\",\n label: \"fastp report title\",\n },\n {\n name: fastp_adapter_sequence,\n prefix: --adapter_sequence,\n type: text,\n value: \"\",\n label: \"The adapter for read1. For SE data, if not specified, the adapter will be auto-detected. For PE data, this is used if R1\/R2 are found not overlapped.\"\n },\n {\n name: fastp_P_SE,\n prefix: -P,\n type: numeric,\n value: 20,\n min: 1,\n max: NA,\n step: 1,\n label: \"For example, if you set -P 100, only 1\/100 reads will be used for counting, and if you set -P 1, all reads will be used and slower.\",\n },\n {\n name: \"fastp_low_complexity_filter\",\n type: \"checkbox\",\n value: TRUE,\n label: \"Enable low complexity filter. The complexity is defined as the percentage of base that is different from its next base (base[i] != base[i+1]).\",\n },\n {\n name: \"fastp_overrepresentation_analysis\",\n type: \"checkbox\",\n value: TRUE,\n label: \"enable overrepresented sequence analysis.\",\n },\n ],\n },\n ],\n install: {\n # fastp: [\n # \"wget https:\/\/github.com\/OpenGene\/fastp\/archive\/v0.23.0.tar.gz\",\n # \"tar -xvzf v0.23.0.tar.gz\",\n # \"cd fastp-0.23.0\",\n # \"make\",\n # \"mv fastp \/opt\/biotools\/bin\/fastp\",\n # \"cd ..\",\n # \"rm -r fastp-0.23.0 v0.23.0.tar.gz \"\n # ]\n },\n citations: {\n fastp: [\n \"Shifu Chen, Yanqing Zhou, Yaru Chen, Jia Gu, fastp: an ultra-fast all-in-one FASTQ preprocessor, Bioinformatics, Volume 34, Issue 17, 01 September 2018, Pages i884-i890, https:\/\/doi.org\/10.1093\/bioinformatics\/bty560\"\n ]\n }\n}\n" } ]