[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MSZ1N485RTP0HCFN4T1JM":3,"skill-same:01M74MSZ1N485RTP0HCFN4T1JM":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M74MSZ1N485RTP0HCFN4T1JM","encode-ccres-database",null,"Query the ENCODE Registry of cis-Regulatory Elements (cCREs) via the SCREEN GraphQL API, or make custom queries to the ENCODE Portal REST API for experiments and files (ChIP-seq peaks, etc.). Use when you want to query regulatory annotations or raw experimental data across human cell types.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fencode_ccres_database\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: encode-ccres-database\ndescription: >\n    Query the ENCODE Registry of cis-Regulatory Elements (cCREs) via the SCREEN\n    GraphQL API, or make custom queries to the ENCODE Portal REST API for\n    experiments and files (ChIP-seq peaks, etc.). Use when you want to query\n    regulatory annotations or raw experimental data across human cell types.\n---\n\n# ENCODE Database Skill\n\nThis skill allows you to query the ENCODE Registry of cCREs (candidate\ncis-Regulatory Elements) via the SCREEN GraphQL API. It helps identify\nfunctional non-coding DNA elements (like Promoters, Enhancers, and insulators)\nby analyzing biochemical signatures (DNase, H3K4me3, H3K27ac, CTCF).\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fencode_ccres_database_LICENSE.txt does\n    not already exist in the workspace root directory then (1) prominently\n    notify the user to check the terms at\n    https:\u002F\u002Fwww.encodeproject.org\u002Fhelp\u002Frest-api\u002F, then (2) create the file\n    recording the notification text and timestamp.\n\n## Core Rules\n\n-   **Use the Wrapper**: ALWAYS execute the provided helper scripts to query the\n    database rather than accessing the database directly. The scripts\n    automatically enforce the required rate limit gracefully.\n-   **Parsing Output**: Do NOT use `cat` to read the entire JSON output file\n    into context, as it can be extremely large. You MUST use `jq` to efficiently\n    parse and extract relevant fields.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n### Quick Start\n\n```bash\n# Search cCREs by coordinates\nuv run scripts\u002Fscreen_api.py search --chromosome chr11 \\\n  --start 5205263 --end 5207263 \\\n  --output \u002Ftmp\u002Fsearch.json\n\n# Get details for a specific cCRE\nuv run scripts\u002Fscreen_api.py details EH38E2941922 \\\n  --output \u002Ftmp\u002Fdetails.json\n```\n\nAll subcommands write JSON to disk. Always save output in a temporary location\nlike `\u002Ftmp\u002F`.\n\n### Identifying High-Confidence (\"Type A\") Biosamples\n\nBiosamples in ENCODE are often categorized by their data completeness. **\"Type\nA\"** (or high-confidence) biosamples are those that have experimental data for\nall four core epigenetic markers: **DNase, H3K4me3, H3K27ac, and CTCF**.\n\nThe `biosamples` and `details` commands automatically enrich their output with\nan `is_type_a` boolean flag for each biosample.\n\n**Example: Finding high-confidence cell types**\n\n```bash\nuv run scripts\u002Fscreen_api.py biosamples --output \u002Ftmp\u002Fbiosamples.json\n# Use jq to filter for Type A biosamples\njq '.data.ccREBiosampleQuery.biosamples[] | select(.is_type_a == true) | .displayname' \u002Ftmp\u002Fbiosamples.json\n```\n\n### Parsing Output (CRITICAL)\n\n**Do NOT use `cat` to read the entire JSON output file into context, as it**\n**can be extremely large.** Instead, you MUST use `jq` to efficiently parse and\nextract the relevant fields from the JSON file saved by the script. If `jq` is\nnot available on the system, write your own Python filtering code (e.g.,\n`python3 -c \"import json...\"`) to extract the necessary data.\n\nFor a complete reference of the JSON structure returned by eachmcommand (so you\nknow which fields to query with `jq`), read\n`references\u002Fjson_output_structure.md`.\n\n### Available Commands\n\n-   `search`: Search cCREs by coordinates, accessions, or epigenetic signals.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py search \\\n        --chromosome chr11 --start 5205263 --end 5207263 \\\n        --output \u002Ftmp\u002Fsearch.json\n    ```\n\n-   `nearby-genes`: Find nearby genes for given cCRE accessions.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py nearby-genes \\\n        EH38E1516972 --output \u002Ftmp\u002Fnearby.json\n    ```\n\n-   `details`: Get detailed information and biosample-specific max Z-scores for\n    a specific cCRE.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py details EH38E2941922 \\\n        --output \u002Ftmp\u002Fdetails.json\n    ```\n\n-   `biosamples`: Get biosample metadata for an assembly.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py biosamples \\\n        --output \u002Ftmp\u002Fbiosamples.json\n    ```\n\n-   `orthologs`: Get orthologous cCREs in another assembly.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py orthologs EH38E2941922 \\\n        --output \u002Ftmp\u002Forthologs.json\n    ```\n\n-   `linked-genes`: Find linked genes via methods like HiC or eQTLs.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py linked-genes \\\n        EH38E1516972 --output \u002Ftmp\u002Flinked.json\n    ```\n\n-   `gene-expression`: Get gene expression (TPM) across all biosamples for a\n    named gene. Internally resolves the gene symbol to an Ensembl gene ID, then\n    queries per-biosample RNA-seq quantifications.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py gene-expression GAPDH \\\n        --output \u002Ftmp\u002Fgene_expr.json\n    ```\n\n-   `entex`: Get ENTEx data for a cCRE or genomic region.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py entex \\\n        --accession EH38E1310345 \\\n        --output \u002Ftmp\u002Fentex.json\n    ```\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py entex \\\n        --region chr1:1000068:1000409 \\\n        --output \u002Ftmp\u002Fentex.json\n    ```\n\n-   `gwas`: Query genome-wide association studies, SNPs, or enrichment data.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py gwas studies \\\n        --output \u002Ftmp\u002Fgwas.json\n    ```\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py gwas snps --study \\\n        Ahola-Olli_AV-27989323-Eotaxin_levels \\\n        --output \u002Ftmp\u002Fgwas_snps.json\n    ```\n\nYou can supply the `--assembly mm10` or `--assembly grch38` flag to explicitly\nrequest a specific assembly for most commands. By default, the script targets\n`grch38` but will automatically fall back to `mm10` if no results are found or\nif the query fails.\n\n## ENCODE Portal REST API (Direct Access)\n\nFor accessing raw experiments, ChIP-seq peaks, or other datasets that are not\nrepresented as cCREs in SCREEN, use the `scripts\u002Fencode_portal_api.py` script.\nIt allows custom queries to the ENCODE Portal REST API.\n\n### Usage\n\n```bash\nuv run scripts\u002Fencode_portal_api.py search \"type=Experiment&target.label=ZNF549\" --output \u002Ftmp\u002Fznf549_experiments.json\n```\n\n### Data Analysis Tips\n\nWhen analyzing `.bed` or `.bigBed` files downloaded from ENCODE, standard\nbioinformatics tools are highly recommended for finding overlaps (e.g., between\ngene promoters and peaks):\n\n-   **`bedtools`**: For fast mathematical operations on genomic intervals.\n-   **`bigBedToBed`**: For converting binary BigBed files to readable BED\n    format.\n-   **`pybedtools`**: A Python wrapper for `bedtools`.\n\nWrite custom logic if these tools are not pre-installed.\n\n## Custom Queries (SCREEN GraphQL)\n\nIf you need to make a complex GraphQL query that the script does not support,\nread `references\u002Fgraphql_schema.md` for a reference of available queries,\narguments, and return fields in the SCREEN GraphQL API.\n","# ENCODE Database Skill\n\nThis skill allows you to query the ENCODE Registry of cCREs (candidate\ncis-Regulatory Elements) via the SCREEN GraphQL API. It helps identify\nfunctional non-coding DNA elements (like Promoters, Enhancers, and insulators)\nby analyzing biochemical signatures (DNase, H3K4me3, H3K27ac, CTCF).\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fencode_ccres_database_LICENSE.txt does\n    not already exist in the workspace root directory then (1) prominently\n    notify the user to check the terms at\n    https:\u002F\u002Fwww.encodeproject.org\u002Fhelp\u002Frest-api\u002F, then (2) create the file\n    recording the notification text and timestamp.\n\n## Core Rules\n\n-   **Use the Wrapper**: ALWAYS execute the provided helper scripts to query the\n    database rather than accessing the database directly. The scripts\n    automatically enforce the required rate limit gracefully.\n-   **Parsing Output**: Do NOT use `cat` to read the entire JSON output file\n    into context, as it can be extremely large. You MUST use `jq` to efficiently\n    parse and extract relevant fields.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n### Quick Start\n\n```bash\n# Search cCREs by coordinates\nuv run scripts\u002Fscreen_api.py search --chromosome chr11 \\\n  --start 5205263 --end 5207263 \\\n  --output \u002Ftmp\u002Fsearch.json\n\n# Get details for a specific cCRE\nuv run scripts\u002Fscreen_api.py details EH38E2941922 \\\n  --output \u002Ftmp\u002Fdetails.json\n```\n\nAll subcommands write JSON to disk. Always save output in a temporary location\nlike `\u002Ftmp\u002F`.\n\n### Identifying High-Confidence (\"Type A\") Biosamples\n\nBiosamples in ENCODE are often categorized by their data completeness. **\"Type\nA\"** (or high-confidence) biosamples are those that have experimental data for\nall four core epigenetic markers: **DNase, H3K4me3, H3K27ac, and CTCF**.\n\nThe `biosamples` and `details` commands automatically enrich their output with\nan `is_type_a` boolean flag for each biosample.\n\n**Example: Finding high-confidence cell types**\n\n```bash\nuv run scripts\u002Fscreen_api.py biosamples --output \u002Ftmp\u002Fbiosamples.json\n# Use jq to filter for Type A biosamples\njq '.data.ccREBiosampleQuery.biosamples[] | select(.is_type_a == true) | .displayname' \u002Ftmp\u002Fbiosamples.json\n```\n\n### Parsing Output (CRITICAL)\n\n**Do NOT use `cat` to read the entire JSON output file into context, as it**\n**can be extremely large.** Instead, you MUST use `jq` to efficiently parse and\nextract the relevant fields from the JSON file saved by the script. If `jq` is\nnot available on the system, write your own Python filtering code (e.g.,\n`python3 -c \"import json...\"`) to extract the necessary data.\n\nFor a complete reference of the JSON structure returned by eachmcommand (so you\nknow which fields to query with `jq`), read\n`references\u002Fjson_output_structure.md`.\n\n### Available Commands\n\n-   `search`: Search cCREs by coordinates, accessions, or epigenetic signals.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py search \\\n        --chromosome chr11 --start 5205263 --end 5207263 \\\n        --output \u002Ftmp\u002Fsearch.json\n    ```\n\n-   `nearby-genes`: Find nearby genes for given cCRE accessions.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py nearby-genes \\\n        EH38E1516972 --output \u002Ftmp\u002Fnearby.json\n    ```\n\n-   `details`: Get detailed information and biosample-specific max Z-scores for\n    a specific cCRE.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py details EH38E2941922 \\\n        --output \u002Ftmp\u002Fdetails.json\n    ```\n\n-   `biosamples`: Get biosample metadata for an assembly.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py biosamples \\\n        --output \u002Ftmp\u002Fbiosamples.json\n    ```\n\n-   `orthologs`: Get orthologous cCREs in another assembly.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py orthologs EH38E2941922 \\\n        --output \u002Ftmp\u002Forthologs.json\n    ```\n\n-   `linked-genes`: Find linked genes via methods like HiC or eQTLs.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py linked-genes \\\n        EH38E1516972 --output \u002Ftmp\u002Flinked.json\n    ```\n\n-   `gene-expression`: Get gene expression (TPM) across all biosamples for a\n    named gene. Internally resolves the gene symbol to an Ensembl gene ID, then\n    queries per-biosample RNA-seq quantifications.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py gene-expression GAPDH \\\n        --output \u002Ftmp\u002Fgene_expr.json\n    ```\n\n-   `entex`: Get ENTEx data for a cCRE or genomic region.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py entex \\\n        --accession EH38E1310345 \\\n        --output \u002Ftmp\u002Fentex.json\n    ```\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py entex \\\n        --region chr1:1000068:1000409 \\\n        --output \u002Ftmp\u002Fentex.json\n    ```\n\n-   `gwas`: Query genome-wide association studies, SNPs, or enrichment data.\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py gwas studies \\\n        --output \u002Ftmp\u002Fgwas.json\n    ```\n\n    ```bash\n    uv run scripts\u002Fscreen_api.py gwas snps --study \\\n        Ahola-Olli_AV-27989323-Eotaxin_levels \\\n        --output \u002Ftmp\u002Fgwas_snps.json\n    ```\n\nYou can supply the `--assembly mm10` or `--assembly grch38` flag to explicitly\nrequest a specific assembly for most commands. By default, the script targets\n`grch38` but will automatically fall back to `mm10` if no results are found or\nif the query fails.\n\n## ENCODE Portal REST API (Direct Access)\n\nFor accessing raw experiments, ChIP-seq peaks, or other datasets that are not\nrepresented as cCREs in SCREEN, use the `scripts\u002Fencode_portal_api.py` script.\nIt allows custom queries to the ENCODE Portal REST API.\n\n### Usage\n\n```bash\nuv run scripts\u002Fencode_portal_api.py search \"type=Experiment&target.label=ZNF549\" --output \u002Ftmp\u002Fznf549_experiments.json\n```\n\n### Data Analysis Tips\n\nWhen analyzing `.bed` or `.bigBed` files downloaded from ENCODE, standard\nbioinformatics tools are highly recommended for finding overlaps (e.g., between\ngene promoters and peaks):\n\n-   **`bedtools`**: For fast mathematical operations on genomic intervals.\n-   **`bigBedToBed`**: For converting binary BigBed files to readable BED\n    format.\n-   **`pybedtools`**: A Python wrapper for `bedtools`.\n\nWrite custom logic if these tools are not pre-installed.\n\n## Custom Queries (SCREEN GraphQL)\n\nIf you need to make a complex GraphQL query that the script does not support,\nread `references\u002Fgraphql_schema.md` for a reference of available queries,\narguments, and return fields in the SCREEN GraphQL API.\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fscience-skills\u002Fencode_ccres_database",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill encode-ccres-database",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill encode-ccres-database",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill encode-ccres-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fencode_ccres_database\u002FSKILL.md",true,[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcitation.bib","REFERENCE","参考文档",7838,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fencode_ccres_database\u002Freferences\u002Fcitation.bib",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fgraphql_schema.md",4708,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fencode_ccres_database\u002Freferences\u002Fgraphql_schema.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fjson_output_structure.md",5622,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fencode_ccres_database\u002Freferences\u002Fjson_output_structure.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fencode_portal_api.py","SCRIPT","脚本",2099,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fencode_ccres_database\u002Fscripts\u002Fencode_portal_api.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fscreen_api.py",20490,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fencode_ccres_database\u002Fscripts\u002Fscreen_api.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]