[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DP58VZEKVDXMDAMZWBMX2D":3,"skill-same:01M6DP58VZEKVDXMDAMZWBMX2D":77},{"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":28,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":52,"commitSha":53,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M6DP58VZEKVDXMDAMZWBMX2D","ligandmpnn",null,"Ligand-aware protein sequence design using LigandMPNN. Use this skill when: (1) Designing sequences around small molecules, (2) Enzyme active site design, (3) Ligand binding pocket optimization, (4) Metal coordination site design, (5) Cofactor binding proteins.\nFor standard protein design, use proteinmpnn. For solubility optimization, use solublempnn.","huamu668\u002Fclawhub-openclaw-medical","huamu668","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F202473531?v=4","01M6DK1V7D7VP9PJ06Z1VXVK13","huamu","01M6DK1VBYG1BX5FT154AFZHAS",0,"MIT","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fligandmpnn\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"design","metal","Optimization","Tools","modal","site","coordination","use","active","proteins","sequence-design","binding","inverse-folding","ligand-aware","2026-11-10 10:12:30",false,"---\nname: ligandmpnn\ndescription: >\n  Ligand-aware protein sequence design using LigandMPNN.\n  Use this skill when: (1) Designing sequences around small molecules,\n  (2) Enzyme active site design,\n  (3) Ligand binding pocket optimization,\n  (4) Metal coordination site design,\n  (5) Cofactor binding proteins.\n\n  For standard protein design, use proteinmpnn.\n  For solubility optimization, use solublempnn.\nlicense: MIT\ncategory: design-tools\ntags: [sequence-design, inverse-folding, ligand-aware]\nbiomodals_script: modal_ligandmpnn.py\n---\n\n# LigandMPNN Ligand-Aware Design\n\n## Prerequisites\n\n| Requirement | Minimum | Recommended |\n|-------------|---------|-------------|\n| Python | 3.8+ | 3.10 |\n| CUDA | 11.0+ | 11.7+ |\n| GPU VRAM | 8GB | 16GB (T4) |\n| RAM | 8GB | 16GB |\n\n## How to run\n\n> **First time?** See [Installation Guide](..\u002F..\u002Fdocs\u002Finstallation.md) to set up Modal and biomodals.\n\n### Option 1: Modal (recommended)\n```bash\ncd biomodals\nmodal run modal_ligandmpnn.py \\\n  --pdb-path protein_ligand.pdb \\\n  --num-seq-per-target 16 \\\n  --sampling-temp 0.1\n```\n\n**GPU**: T4 (16GB) | **Timeout**: 600s default\n\n### Option 2: Local installation\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fdauparas\u002FLigandMPNN.git\ncd LigandMPNN\n\npython run.py \\\n  --pdb_path protein_ligand.pdb \\\n  --out_folder output\u002F \\\n  --num_seq_per_target 16\n```\n\n## Key parameters\n\n| Parameter | Default | Range | Description |\n|-----------|---------|-------|-------------|\n| `--pdb_path` | required | path | PDB with ligand |\n| `--num_seq_per_target` | 1 | 1-1000 | Sequences per structure |\n| `--sampling_temp` | \"0.1\" | \"0.0001-1.0\" | Temperature (string!) |\n| `--ligand_mpnn_use_side_chain_context` | true | bool | Use ligand context |\n\n## Ligand Specification\n\n### In PDB File\nLigand must be present as HETATM records:\n```\nATOM    ...protein atoms...\nHETATM  1  C1  LIG A 999      x.xxx  y.yyy  z.zzz  1.00  0.00           C\n```\n\n### Supported Ligand Types\n- Small molecules (HETATM)\n- Metals (Zn, Fe, Mg, Ca, etc.)\n- Cofactors (NAD, FAD, ATP)\n- DNA\u002FRNA\n\n## Output format\n\n```\noutput\u002F\n├── seqs\u002F\n│   └── protein.fa          # FASTA sequences\n└── protein_pdb\u002F\n    └── protein_0001.pdb    # PDBs with designed sequence\n```\n\n## Sample output\n\n### Successful run\n```\n$ python run.py --pdb_path enzyme_substrate.pdb --out_folder output\u002F --num_seq_per_target 8\nLoading LigandMPNN model weights...\nProcessing enzyme_substrate.pdb\nFound ligand: LIG (12 atoms)\nGenerated 8 sequences in 3.1 seconds\n\noutput\u002Fseqs\u002Fenzyme_substrate.fa:\n>enzyme_substrate_0001, score=1.45, global_score=1.38\nMKTAYIAKQRQISFVKSHFSRQLE...\n>enzyme_substrate_0002, score=1.52, global_score=1.41\nMKTAYIAKQRQISFVKSQFSRQLD...\n```\n\n**What good output looks like:**\n- Score: 1.0-2.0 (lower = more confident)\n- Ligand detected and incorporated in context\n- Active site residues preserved or optimized\n\n## Decision tree\n\n```\nShould I use LigandMPNN?\n│\n├─ What's in your binding site?\n│  ├─ Small molecule \u002F ligand → LigandMPNN ✓\n│  ├─ Metal ion (Zn, Fe, etc.) → LigandMPNN ✓\n│  ├─ Cofactor (NAD, FAD, ATP) → LigandMPNN ✓\n│  ├─ DNA\u002FRNA → LigandMPNN ✓\n│  └─ Nothing \u002F protein only → Use ProteinMPNN\n│\n├─ What type of design?\n│  ├─ Enzyme active site → LigandMPNN ✓\n│  ├─ Metal binding site → LigandMPNN ✓\n│  ├─ Protein-protein binder → Use ProteinMPNN\n│  └─ De novo scaffold → Use ProteinMPNN\n│\n└─ Priority?\n   ├─ Solubility\u002Fexpression → Consider SolubleMPNN\n   └─ Ligand context accuracy → LigandMPNN ✓\n```\n\n## Typical performance\n\n| Campaign Size | Time (T4) | Cost (Modal) | Notes |\n|---------------|-----------|--------------|-------|\n| 100 backbones × 8 seq | 15-20 min | ~$2 | Standard |\n| 500 backbones × 8 seq | 1-1.5h | ~$8 | Large campaign |\n\n**Throughput**: ~50-100 sequences\u002Fminute on T4 GPU.\n\n---\n\n## Verify\n\n```bash\ngrep -c \"^>\" output\u002Fseqs\u002F*.fa  # Should match backbone_count × num_seq_per_target\n```\n\n---\n\n## Troubleshooting\n\n**Ligand not recognized**: Check HETATM format, verify ligand residue name\n**Poor binding residues**: Increase sampling around active site\n**Missing contacts**: Verify ligand coordinates in PDB\n\n### Error interpretation\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `RuntimeError: CUDA out of memory` | Long protein or large batch | Reduce batch_size |\n| `KeyError: 'LIG'` | Ligand not found in PDB | Check HETATM records |\n| `ValueError: no ligand atoms` | Empty ligand | Verify ligand has atoms in PDB |\n\n---\n\n**Next**: Structure prediction for validation → `protein-qc` for filtering.\n","# LigandMPNN Ligand-Aware Design\n\n## Prerequisites\n\n| Requirement | Minimum | Recommended |\n|-------------|---------|-------------|\n| Python | 3.8+ | 3.10 |\n| CUDA | 11.0+ | 11.7+ |\n| GPU VRAM | 8GB | 16GB (T4) |\n| RAM | 8GB | 16GB |\n\n## How to run\n\n> **First time?** See [Installation Guide](..\u002F..\u002Fdocs\u002Finstallation.md) to set up Modal and biomodals.\n\n### Option 1: Modal (recommended)\n```bash\ncd biomodals\nmodal run modal_ligandmpnn.py \\\n  --pdb-path protein_ligand.pdb \\\n  --num-seq-per-target 16 \\\n  --sampling-temp 0.1\n```\n\n**GPU**: T4 (16GB) | **Timeout**: 600s default\n\n### Option 2: Local installation\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fdauparas\u002FLigandMPNN.git\ncd LigandMPNN\n\npython run.py \\\n  --pdb_path protein_ligand.pdb \\\n  --out_folder output\u002F \\\n  --num_seq_per_target 16\n```\n\n## Key parameters\n\n| Parameter | Default | Range | Description |\n|-----------|---------|-------|-------------|\n| `--pdb_path` | required | path | PDB with ligand |\n| `--num_seq_per_target` | 1 | 1-1000 | Sequences per structure |\n| `--sampling_temp` | \"0.1\" | \"0.0001-1.0\" | Temperature (string!) |\n| `--ligand_mpnn_use_side_chain_context` | true | bool | Use ligand context |\n\n## Ligand Specification\n\n### In PDB File\nLigand must be present as HETATM records:\n```\nATOM    ...protein atoms...\nHETATM  1  C1  LIG A 999      x.xxx  y.yyy  z.zzz  1.00  0.00           C\n```\n\n### Supported Ligand Types\n- Small molecules (HETATM)\n- Metals (Zn, Fe, Mg, Ca, etc.)\n- Cofactors (NAD, FAD, ATP)\n- DNA\u002FRNA\n\n## Output format\n\n```\noutput\u002F\n├── seqs\u002F\n│   └── protein.fa          # FASTA sequences\n└── protein_pdb\u002F\n    └── protein_0001.pdb    # PDBs with designed sequence\n```\n\n## Sample output\n\n### Successful run\n```\n$ python run.py --pdb_path enzyme_substrate.pdb --out_folder output\u002F --num_seq_per_target 8\nLoading LigandMPNN model weights...\nProcessing enzyme_substrate.pdb\nFound ligand: LIG (12 atoms)\nGenerated 8 sequences in 3.1 seconds\n\noutput\u002Fseqs\u002Fenzyme_substrate.fa:\n>enzyme_substrate_0001, score=1.45, global_score=1.38\nMKTAYIAKQRQISFVKSHFSRQLE...\n>enzyme_substrate_0002, score=1.52, global_score=1.41\nMKTAYIAKQRQISFVKSQFSRQLD...\n```\n\n**What good output looks like:**\n- Score: 1.0-2.0 (lower = more confident)\n- Ligand detected and incorporated in context\n- Active site residues preserved or optimized\n\n## Decision tree\n\n```\nShould I use LigandMPNN?\n│\n├─ What's in your binding site?\n│  ├─ Small molecule \u002F ligand → LigandMPNN ✓\n│  ├─ Metal ion (Zn, Fe, etc.) → LigandMPNN ✓\n│  ├─ Cofactor (NAD, FAD, ATP) → LigandMPNN ✓\n│  ├─ DNA\u002FRNA → LigandMPNN ✓\n│  └─ Nothing \u002F protein only → Use ProteinMPNN\n│\n├─ What type of design?\n│  ├─ Enzyme active site → LigandMPNN ✓\n│  ├─ Metal binding site → LigandMPNN ✓\n│  ├─ Protein-protein binder → Use ProteinMPNN\n│  └─ De novo scaffold → Use ProteinMPNN\n│\n└─ Priority?\n   ├─ Solubility\u002Fexpression → Consider SolubleMPNN\n   └─ Ligand context accuracy → LigandMPNN ✓\n```\n\n## Typical performance\n\n| Campaign Size | Time (T4) | Cost (Modal) | Notes |\n|---------------|-----------|--------------|-------|\n| 100 backbones × 8 seq | 15-20 min | ~$2 | Standard |\n| 500 backbones × 8 seq | 1-1.5h | ~$8 | Large campaign |\n\n**Throughput**: ~50-100 sequences\u002Fminute on T4 GPU.\n\n---\n\n## Verify\n\n```bash\ngrep -c \"^>\" output\u002Fseqs\u002F*.fa  # Should match backbone_count × num_seq_per_target\n```\n\n---\n\n## Troubleshooting\n\n**Ligand not recognized**: Check HETATM format, verify ligand residue name\n**Poor binding residues**: Increase sampling around active site\n**Missing contacts**: Verify ligand coordinates in PDB\n\n### Error interpretation\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `RuntimeError: CUDA out of memory` | Long protein or large batch | Reduce batch_size |\n| `KeyError: 'LIG'` | Ligand not found in PDB | Check HETATM records |\n| `ValueError: no ligand atoms` | Empty ligand | Verify ligand has atoms in PDB |\n\n---\n\n**Next**: Structure prediction for validation → `protein-qc` for filtering.\n",{"name":5,"tags":48,"license":15,"category":49,"description":50,"biomodals_script":51},[39,41,42],"design-tools","Ligand-aware protein sequence design using LigandMPNN. Use this skill when: (1) Designing sequences around small molecules, (2) Enzyme active site design, (3) Ligand binding pocket optimization, (4) Metal coordination site design, (5) Cofactor binding proteins.\nFor standard protein design, use proteinmpnn. For solubility optimization, use solublempnn.\n","modal_ligandmpnn.py","main","d3998984163a67a891ee8397e35adf79b14e872d","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical","https:\u002F\u002Fgithub.com\u002Fhuamu668","2026-03-12 11:49:42",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add huamu668\u002Fclawhub-openclaw-medical --skill ligandmpnn",{"tool":63,"command":64},"bunx","bunx skills add huamu668\u002Fclawhub-openclaw-medical --skill ligandmpnn",{"tool":66,"command":67},"pnpm","pnpm dlx skills add huamu668\u002Fclawhub-openclaw-medical --skill ligandmpnn","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fligandmpnn\u002FSKILL.md",true,[71],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"index.json","REFERENCE","参考文档",520,"https:\u002F\u002Fgithub.com\u002FDCx7C5\u002Fai-marketplace\u002Fblob\u002Fmain\u002Fskills\u002Fidentity-pam-privacctdiscovery\u002Findex.json",[78,98,126,146,160,175],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":43},"01M6DR3JGAEX5G5FR7TK3D8NS8","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fzarr-python\u002FSKILL.md",[],[85,86,87,88,89,90,91,92,93,94,95,96,97],"python","zarr python","storage","scientific computing","numpy","arrays","pipelines","parallel","dask","cloud","gcs","s3","integration",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":107,"publishedAt":43},"01M6DR101MEDE5XT2ZZ5VBEAA5","vaex","Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV\u002FHDF5\u002FArrow\u002FParquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fvaex\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[100,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,36,124,125],"machine learning","in memory","learning","csv","visualization","create","core","ml","big data","memory","visualizations","fit","statistics","do","build","files","operations","work",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":43},"01M6DQVMB0GBKF2W44FKXVD1P7","torch-geometric","Graph Neural Networks (PyG). Node\u002Fgraph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftorch-geometric\u002FSKILL.md",[],[133,110,134,135,136,137,138,139,140,141,142,143,144,145],"torch geometric","node","Neural","link","gat","molecular","graphs","deep","networks","graph","neural networks","deep learning","classification",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":43},"01M6DQH2GZPZKEQ140GRCJ9746","tiledbvcf","Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF\u002FBCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftiledbvcf\u002FSKILL.md",[],[148,153,154,155,156,157,158,92,159,87],"data","genomics","sample","queries","ingestion","export","capabilities",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":168,"publishedAt":43},"01M6DQD9G958EM6NHJ994D0SK1","solublempnn","Solubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli expression, (2) Optimizing solubility of designed proteins, (3) Reducing aggregation propensity, (4) Need high-yield expression, (5) Avoiding inclusion body formation.\nFor standard design, use proteinmpnn. For ligand-aware design, use ligandmpnn.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fsolublempnn\u002FSKILL.md",[166,167],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[162,169,170,36,33,32,171,29,38,172,173,5,42,41,174,39],"inclusion","yield","aggregation","solubility","proteinmpnn","expression",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":179,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":43},"01M6DQ8W91A93MGGCEEW949HBC","scvelo","RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced\u002Fspliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy\u002FscVI-tools for trajectory inference.","BSD-3-Clause","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fscvelo\u002FSKILL.md",[],[177,183,184,185,186,187,188,189,190,191,192,32,153,193,194],"RNA","single-cell","infer","cell","transitions","time","compute","velocity","scanpy","analysis","state","inference"]