tooluniverse 0.2.0__py3-none-any.whl → 1.0.0__py3-none-any.whl

tooluniverse/data/packages/categorized_tools.txt

@@ -0,0 +1,206 @@
+"name": "ASE (Atomic Simulation Environment)"
+"name": "AnnData"
+"name": "Arboreto"
+"name": "BioPandas"
+"name": "Biopython"
+"name": "Biotite"
+"name": "COBRApy"
+"name": "COBRApy"
+"name": "Cellpose"
+"name": "Clair3"
+"name": "Cooler"
+"name": "DScribe"
+"name": "DeepChem"
+"name": "DeepPurpose"
+"name": "DeepXDE"
+"name": "Descriptastorus"
+"name": "DiffDock"
+"name": "FAN-C"
+"name": "Faiss"
+"name": "Flask"
+"name": "FlowIO"
+"name": "FlowKit"
+"name": "FlowUtils"
+"name": "GSEApy"
+"name": "Hyperopt"
+"name": "JCVI"
+"name": "MAGeCK"
+"name": "MDAnalysis"
+"name": "Matplotlib"
+"name": "MuData"
+"name": "NetworkX"
+"name": "NumPy"
+"name": "Numba"
+"name": "OpenBabel"
+"name": "OpenCV"
+"name": "OpenChem"
+"name": "OpenMM"
+"name": "PDBFixer"
+"name": "PLIP"
+"name": "PlantCV"
+"name": "ProDy"
+"name": "PyDESeq2"
+"name": "PyKalman"
+"name": "PyLiftover"
+"name": "PyMassSpec"
+"name": "PyMed"
+"name": "PyPDF2"
+"name": "PyRanges"
+"name": "PySCF"
+"name": "PyScreener"
+"name": "PyTDC"
+"name": "PyTorch Geometric"
+"name": "PyTorch"
+"name": "RDKit"
+"name": "ReportLab"
+"name": "Requests"
+"name": "Scanpy"
+"name": "SchNetPack"
+"name": "SciPy"
+"name": "Scrublet"
+"name": "Seaborn"
+"name": "SymPy"
+"name": "TileDB"
+"name": "TileDB-SOMA"
+"name": "UMAP"
+"name": "ViennaRNA"
+"name": "arxiv"
+"name": "cellxgene-census"
+"name": "cryosparc-tools"
+"name": "cyvcf2"
+"name": "deepTools"
+"name": "get_anndata_info"
+"name": "get_arboreto_info"
+"name": "get_arxiv_info"
+"name": "get_ase_info"
+"name": "get_biopandas_info"
+"name": "get_biopython_info"
+"name": "get_biotite_info"
+"name": "get_cellpose_info"
+"name": "get_cellxgene_census_info"
+"name": "get_clair3_info"
+"name": "get_cobra_info"
+"name": "get_cobrapy_info"
+"name": "get_cooler_info"
+"name": "get_cryosparc_tools_info"
+"name": "get_cyvcf2_info"
+"name": "get_deepchem_info"
+"name": "get_deeppurpose_info"
+"name": "get_deeptools_info"
+"name": "get_deepxde_info"
+"name": "get_descriptastorus_info"
+"name": "get_diffdock_info"
+"name": "get_dscribe_info"
+"name": "get_faiss_info"
+"name": "get_fanc_info"
+"name": "get_flask_info"
+"name": "get_flowio_info"
+"name": "get_flowkit_info"
+"name": "get_flowutils_info"
+"name": "get_gget_info"
+"name": "get_googlesearch_python_info"
+"name": "get_gseapy_info"
+"name": "get_h5py_info"
+"name": "get_harmony_pytorch_info"
+"name": "get_hmmlearn_info"
+"name": "get_hyperopt_info"
+"name": "get_igraph_info"
+"name": "get_jcvi_info"
+"name": "get_khmer_info"
+"name": "get_lifelines_info"
+"name": "get_loompy_info"
+"name": "get_mageck_info"
+"name": "get_matplotlib_info"
+"name": "get_mdanalysis_info"
+"name": "get_msprime_info"
+"name": "get_mudata_info"
+"name": "get_networkx_info"
+"name": "get_numba_info"
+"name": "get_numpy_info"
+"name": "get_openbabel_info"
+"name": "get_openchem_info"
+"name": "get_opencv_info"
+"name": "get_openmm_info"
+"name": "get_optlang_info"
+"name": "get_pandas_info"
+"name": "get_pdbfixer_info"
+"name": "get_plantcv_info"
+"name": "get_plip_info"
+"name": "get_poliastro_info"
+"name": "get_prody_info"
+"name": "get_pybedtools_info"
+"name": "get_pybigwig_info"
+"name": "get_pybigwig_info"
+"name": "get_pydeseq2_info"
+"name": "get_pyfaidx_info"
+"name": "get_pykalman_info"
+"name": "get_pyliftover_info"
+"name": "get_pymassspec_info"
+"name": "get_pymed_info"
+"name": "get_pymzml_info"
+"name": "get_pypdf2_info"
+"name": "get_pyranges_info"
+"name": "get_pysam_info"
+"name": "get_pyscenic_info"
+"name": "get_pyscf_info"
+"name": "get_pyscreener_info"
+"name": "get_pytdc_info"
+"name": "get_python_libsbml_info"
+"name": "get_pytorch_info"
+"name": "get_rdkit_info"
+"name": "get_reportlab_info"
+"name": "get_requests_info"
+"name": "get_ruptures_info"
+"name": "get_scanpy_info"
+"name": "get_schnetpack_info"
+"name": "get_scholarly_info"
+"name": "get_scikit_bio_info"
+"name": "get_scikit_image_info"
+"name": "get_scikit_learn_info"
+"name": "get_scipy_info"
+"name": "get_scrublet_info"
+"name": "get_scvelo_info"
+"name": "get_seaborn_info"
+"name": "get_souporcell_info"
+"name": "get_statsmodels_info"
+"name": "get_sympy_info"
+"name": "get_tiledb_info"
+"name": "get_tiledbsoma_info"
+"name": "get_torch_geometric_info"
+"name": "get_tqdm_info"
+"name": "get_trackpy_info"
+"name": "get_tskit_info"
+"name": "get_umap_learn_info"
+"name": "get_viennarna_info"
+"name": "gget"
+"name": "googlesearch-python"
+"name": "h5py"
+"name": "harmony-pytorch"
+"name": "hmmlearn"
+"name": "igraph"
+"name": "khmer"
+"name": "lifelines"
+"name": "loompy"
+"name": "msprime"
+"name": "optlang"
+"name": "pandas"
+"name": "poliastro"
+"name": "pyBigWig"
+"name": "pyBigWig"
+"name": "pySCENIC"
+"name": "pybedtools"
+"name": "pyfaidx"
+"name": "pymzML"
+"name": "pysam"
+"name": "python-libsbml"
+"name": "ruptures"
+"name": "scVelo"
+"name": "scholarly"
+"name": "scikit-bio"
+"name": "scikit-image"
+"name": "scikit-learn"
+"name": "souporcell"
+"name": "statsmodels"
+"name": "tqdm"
+"name": "trackpy"
+"name": "tskit"

tooluniverse/data/packages/cheminformatics_tools.json

@@ -0,0 +1,347 @@
+[
+  {
+    "type": "PackageTool",
+    "name": "get_rdkit_info",
+    "description": "Get comprehensive information about RDKit – cheminformatics and machine learning toolkit",
+    "parameter": {
+      "type": "object",
+      "properties": {
+        "include_examples": {
+          "type": "boolean",
+          "description": "Whether to include usage examples and quick start guide",
+          "default": true
+        }
+      }
+    },
+    "package_name": "rdkit",
+    "local_info": {
+      "name": "RDKit",
+      "description": "Collection of cheminformatics and machine learning tools. Provides functionality for molecular manipulation, descriptor calculation, molecular fingerprinting, and machine learning on chemical data.",
+      "category": "Cheminformatics",
+      "import_name": "rdkit",
+      "popularity": 90,
+      "keywords": [
+        "cheminformatics",
+        "molecular descriptors",
+        "SMILES",
+        "molecular fingerprints",
+        "drug discovery"
+      ],
+      "documentation": "https://www.rdkit.org/docs/",
+      "repository": "https://github.com/rdkit/rdkit",
+      "installation": {
+        "pip": "pip install rdkit",
+        "conda": "conda install -c conda-forge rdkit"
+      },
+      "usage_example": "from rdkit import Chem\nfrom rdkit.Chem import Descriptors, rdMolDescriptors\n\n# Create molecule from SMILES\nmol = Chem.MolFromSmiles('CCO')  # Ethanol\n\n# Calculate molecular descriptors\nmw = Descriptors.MolWt(mol)\nlogp = Descriptors.MolLogP(mol)\nprint(f'Molecular weight: {mw:.2f}')\nprint(f'LogP: {logp:.2f}')\n\n# Generate molecular fingerprint\nfp = rdMolDescriptors.GetMorganFingerprintAsBitVect(mol, 2)\nprint(f'Fingerprint: {fp.ToBitString()[:20]}...')",
+      "quick_start": [
+        "Install: conda install -c conda-forge rdkit",
+        "Create molecule: mol = Chem.MolFromSmiles('CCO')",
+        "Descriptors: Descriptors.MolWt(mol), Descriptors.MolLogP(mol)",
+        "Fingerprints: rdMolDescriptors.GetMorganFingerprintAsBitVect()",
+        "Substructure: mol.HasSubstructMatch(pattern)"
+      ]
+    }
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_openbabel_info",
+    "description": "Get comprehensive information about OpenBabel – chemical format conversion and analysis",
+    "parameter": {
+      "type": "object",
+      "properties": {
+        "include_examples": {
+          "type": "boolean",
+          "description": "Whether to include usage examples and quick start guide",
+          "default": true
+        }
+      }
+    },
+    "package_name": "openbabel",
+    "local_info": {
+      "name": "OpenBabel",
+      "description": "Chemical toolbox designed to convert, filter, and analyze chemical data. Supports reading and writing over 110 chemical file formats and provides extensive molecular manipulation capabilities.",
+      "category": "Cheminformatics",
+      "import_name": "openbabel",
+      "popularity": 75,
+      "keywords": [
+        "chemical file formats",
+        "format conversion",
+        "molecular structure",
+        "SMILES",
+        "SDF"
+      ],
+      "documentation": "http://openbabel.org/docs/dev/",
+      "repository": "https://github.com/openbabel/openbabel",
+      "installation": {
+        "pip": "pip install openbabel-wheel",
+        "conda": "conda install -c conda-forge openbabel"
+      },
+      "usage_example": "from openbabel import openbabel as ob\n\n# Create molecule\nmol = ob.OBMol()\n# Add atoms and bonds programmatically\n# or read from file\n\n# Convert between formats\nconv = ob.OBConversion()\nconv.SetInAndOutFormats('smi', 'sdf')\nconv.Convert(mol, mol)  # Convert SMILES to SDF\n\n# Calculate properties\nprint(f'Molecular weight: {mol.GetMolWt()}')\nprint(f'Formula: {mol.GetFormula()}')",
+      "quick_start": [
+        "Install: conda install -c conda-forge openbabel",
+        "Import: from openbabel import openbabel as ob",
+        "Create: mol = ob.OBMol()",
+        "Convert: conv = ob.OBConversion(); conv.SetInAndOutFormats()",
+        "Properties: mol.GetMolWt(), mol.GetFormula()"
+      ]
+    }
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_deepchem_info",
+    "description": "Get comprehensive information about DeepChem – an open-source toolkit that brings advanced AI/ML techniques to drug discovery, materials science and quantum chemistry.",
+    "parameter": {
+      "type": "object",
+      "properties": {
+        "include_examples": {
+          "type": "boolean",
+          "description": "Whether to include usage examples and quick start guide",
+          "default": true
+        }
+      }
+    },
+    "package_name": "deepchem",
+    "local_info": {
+      "name": "DeepChem",
+      "description": "A powerful Python library providing state-of-the-art deep-learning models, featurizers and workflows for chemistry, biology, materials science and beyond.",
+      "category": "AI for Science / Cheminformatics",
+      "import_name": "deepchem",
+      "popularity": 80,
+      "keywords": [
+        "drug discovery",
+        "molecular machine learning",
+        "graph neural networks",
+        "molecular descriptors",
+        "materials"
+      ],
+      "documentation": "https://deepchem.io/docs/",
+      "repository": "https://github.com/deepchem/deepchem",
+      "installation": {
+        "pip": "pip install deepchem",
+        "conda": "conda install -c conda-forge deepchem"
+      },
+      "usage_example": "import deepchem as dc\nfrom deepchem.models import GraphConvModel\n\ntasks, datasets, _ = dc.molnet.load_delaney(featurizer='GraphConv')\ntrain, valid, test = datasets\nmodel = GraphConvModel(len(tasks), mode='regression')\nmodel.fit(train, nb_epoch=50)\nprint(model.evaluate(test, metrics=[dc.metrics.Metric(dc.metrics.pearson_r)]))",
+      "quick_start": [
+        "Install: pip install deepchem",
+        "Load data: tasks, datasets, _ = dc.molnet.load_tox21()",
+        "Create model: model = dc.models.GraphConvModel(n_tasks)",
+        "Train: model.fit(train_dataset)",
+        "Evaluate: model.evaluate(test_dataset)"
+      ]
+    }
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_dscribe_info",
+    "description": "Get comprehensive information about DScribe – a library for generating machine-learning descriptors for materials and molecules.",
+    "parameter": {
+      "type": "object",
+      "properties": {
+        "include_examples": {
+          "type": "boolean",
+          "description": "Whether to include usage examples and quick start guide",
+          "default": true
+        }
+      }
+    },
+    "package_name": "dscribe",
+    "local_info": {
+      "name": "DScribe",
+      "description": "Python package that turns atomic structures into fixed-size numerical fingerprints (descriptors) for machine learning, similarity analysis and visualisation.",
+      "category": "AI for Science / Materials Descriptors",
+      "import_name": "dscribe",
+      "popularity": 50,
+      "keywords": [
+        "molecular descriptors",
+        "materials descriptors",
+        "machine learning",
+        "SOAP",
+        "atomic structures"
+      ],
+      "documentation": "https://singroup.github.io/dscribe/latest/",
+      "repository": "https://github.com/SINGROUP/dscribe",
+      "installation": {
+        "pip": "pip install dscribe",
+        "conda": "conda install -c conda-forge dscribe"
+      },
+      "usage_example": "from ase.build import molecule\nfrom dscribe.descriptors import SOAP\nimport numpy as np\n\natoms = molecule('CH4')\nsoap = SOAP(species=['C', 'H'], rcut=5.0, nmax=8, lmax=6)\nvec = soap.create(atoms)\nprint(np.linalg.norm(vec))",
+      "quick_start": [
+        "Install: pip install dscribe",
+        "Import: from dscribe.descriptors import SOAP",
+        "Create descriptor: soap = SOAP(species=['C', 'H'])",
+        "Generate: vec = soap.create(atoms)",
+        "Use for ML: Train models with descriptor vectors"
+      ]
+    }
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_cobra_info",
+    "description": "Get comprehensive information about COBRApy – constraint-based metabolic modeling",
+    "parameter": {
+      "type": "object",
+      "properties": {
+        "include_examples": {
+          "type": "boolean",
+          "description": "Whether to include usage examples and quick start guide",
+          "default": true
+        }
+      }
+    },
+    "package_name": "cobra",
+    "local_info": {
+      "name": "COBRApy",
+      "description": "Constraint-Based Reconstruction and Analysis package for Python. Provides tools for building, analyzing, and manipulating genome-scale metabolic models.",
+      "category": "Systems Biology",
+      "import_name": "cobra",
+      "popularity": 80,
+      "keywords": [
+        "metabolic modeling",
+        "systems biology",
+        "flux balance analysis",
+        "genome-scale models",
+        "constraint-based"
+      ],
+      "documentation": "https://cobrapy.readthedocs.io/",
+      "repository": "https://github.com/opencobra/cobrapy",
+      "installation": {
+        "pip": "pip install cobra",
+        "conda": "conda install -c bioconda cobra"
+      },
+      "usage_example": "import cobra\nfrom cobra.test import create_test_model\n\n# Load or create a model\nmodel = create_test_model('textbook')\n\n# Optimize the model\nsolution = model.optimize()\nprint(f'Objective value: {solution.objective_value}')\nprint(f'Status: {solution.status}')\n\n# Analyze reactions\nfor reaction in model.reactions[:5]:\n    print(f'{reaction.id}: {reaction.reaction}')",
+      "quick_start": [
+        "Install: pip install cobra",
+        "Load model: model = cobra.io.read_sbml_model('model.xml')",
+        "Optimize: solution = model.optimize()",
+        "Analyze: Check fluxes, reactions, metabolites",
+        "Modify: Add/remove reactions, change bounds"
+      ]
+    }
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_openchem_info",
+    "description": "Get comprehensive information about OpenChem – deep learning toolkit for drug discovery",
+    "parameter": {
+      "type": "object",
+      "properties": {
+        "info_type": {
+          "type": "string",
+          "enum": [
+            "overview",
+            "installation",
+            "usage",
+            "documentation"
+          ],
+          "description": "Type of information to retrieve about OpenChem"
+        }
+      },
+      "required": [
+        "info_type"
+      ]
+    },
+    "package_name": "openchem",
+    "local_info": {
+      "name": "OpenChem",
+      "description": "Deep learning toolkit for computational chemistry and drug discovery. Provides implementations of state-of-the-art molecular property prediction models, molecular generation, and optimization algorithms.",
+      "category": "Drug Discovery / Machine Learning",
+      "import_name": "openchem",
+      "popularity": 70,
+      "keywords": [
+        "drug discovery",
+        "molecular properties",
+        "deep learning",
+        "molecular generation",
+        "QSAR"
+      ],
+      "documentation": "https://github.com/Mariewelt/OpenChem",
+      "repository": "https://github.com/Mariewelt/OpenChem",
+      "installation": {
+        "pip": "pip install openchem",
+        "conda": "conda install -c conda-forge openchem"
+      },
+      "usage_example": "# OpenChem deep learning for drug discovery\n# This demonstrates molecular property prediction concepts\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.metrics import mean_squared_error, r2_score\nimport tempfile\nimport os\nfrom collections import defaultdict\n\nprint('OpenChem - Deep Learning for Drug Discovery')\nprint('=' * 45)\n\n# Overview of OpenChem capabilities\nprint('OpenChem Features:')\nprint('• Molecular property prediction (ADMET, bioactivity)')\nprint('• Graph neural networks for molecules')\nprint('• Molecular generation and optimization')\nprint('• Multi-task learning for drug discovery')\nprint('• Molecular descriptors and fingerprints')\nprint('• Integration with PyTorch and other ML frameworks')\n\nprint('\\nSupported Molecular Representations:')\nprint('• SMILES strings')\nprint('• Molecular graphs')\nprint('• 3D conformations')\nprint('• Molecular fingerprints (ECFP, MACCS, etc.)')\nprint('• Physicochemical descriptors')\n\n# Simulate molecular dataset\nprint('\\n=== Molecular Dataset Simulation ===')\n\nnp.random.seed(42)\n\n# Generate synthetic molecular data\nn_molecules = 1000\nprint(f'Generating {n_molecules} synthetic molecules...')\n\n# Molecular descriptors (simplified)\ndescriptor_names = [\n    'molecular_weight', 'logP', 'num_donors', 'num_acceptors',\n    'tpsa', 'num_rotatable_bonds', 'num_aromatic_rings',\n    'formal_charge', 'num_heteroatoms', 'fraction_csp3'\n]\n\n# Generate realistic molecular descriptors\nmolecular_data = []\nfor i in range(n_molecules):\n    # Molecular weight: 150-600 Da (drug-like range)\n    mw = np.random.normal(350, 100)\n    mw = np.clip(mw, 150, 600)\n    \n    # LogP: -2 to 6 (lipophilicity)\n    logP = np.random.normal(2.5, 1.5)\n    logP = np.clip(logP, -2, 6)\n    \n    # Hydrogen bond donors: 0-5\n    donors = np.random.poisson(2)\n    donors = np.clip(donors, 0, 5)\n    \n    # Hydrogen bond acceptors: 0-10\n    acceptors = np.random.poisson(4)\n    acceptors = np.clip(acceptors, 0, 10)\n    \n    # Topological polar surface area: 0-200 Ų\n    tpsa = np.random.gamma(2, 30)\n    tpsa = np.clip(tpsa, 0, 200)\n    \n    # Rotatable bonds: 0-15\n    rot_bonds = np.random.poisson(5)\n    rot_bonds = np.clip(rot_bonds, 0, 15)\n    \n    # Aromatic rings: 0-4\n    aromatic_rings = np.random.poisson(2)\n    aromatic_rings = np.clip(aromatic_rings, 0, 4)\n    \n    # Formal charge: typically 0, sometimes ±1\n    formal_charge = np.random.choice([0, 0, 0, 0, 1, -1])\n    \n    # Heteroatoms: 1-8\n    heteroatoms = np.random.poisson(3) + 1\n    heteroatoms = np.clip(heteroatoms, 1, 8)\n    \n    # Fraction sp3 carbons: 0-1\n    frac_csp3 = np.random.beta(2, 2)\n    \n    molecule = {\n        'id': f'MOL_{i:04d}',\n        'molecular_weight': mw,\n        'logP': logP,\n        'num_donors': donors,\n        'num_acceptors': acceptors,\n        'tpsa': tpsa,\n        'num_rotatable_bonds': rot_bonds,\n        'num_aromatic_rings': aromatic_rings,\n        'formal_charge': formal_charge,\n        'num_heteroatoms': heteroatoms,\n        'fraction_csp3': frac_csp3\n    }\n    \n    molecular_data.append(molecule)\n\n# Convert to DataFrame\ndf = pd.DataFrame(molecular_data)\nprint(f'Generated molecular dataset: {df.shape}')\nprint(f'Descriptors: {len(descriptor_names)}')\n\n# Show basic statistics\nprint('\\nDataset statistics:')\nprint(df[descriptor_names].describe().round(2))\n\n# Generate target properties\nprint('\\n=== Target Property Generation ===')\n\n# Simulate bioactivity (IC50 values)\nprint('Generating bioactivity data (IC50 values)...')\n\ndef calculate_bioactivity(row):\n    \"\"\"Simulate bioactivity based on molecular descriptors\"\"\"\n    # Lipinski's rule of five compliance\n    lipinski_score = 0\n    if row['molecular_weight'] <= 500: lipinski_score += 1\n    if row['logP'] <= 5: lipinski_score += 1\n    if row['num_donors'] <= 5: lipinski_score += 1\n    if row['num_acceptors'] <= 10: lipinski_score += 1\n    \n    # Base activity influenced by Lipinski compliance\n    base_activity = 5.0 + (lipinski_score - 2.0) * 1.5\n    \n    # Additional molecular factors\n    tpsa_factor = -0.01 * max(0, row['tpsa'] - 90)  # Penalty for high TPSA\n    flexibility_factor = -0.1 * max(0, row['num_rotatable_bonds'] - 7)  # Penalty for high flexibility\n    aromatic_factor = 0.3 * min(row['num_aromatic_rings'], 3)  # Bonus for aromatics (up to 3)\n    \n    # Combined activity (pIC50)\n    activity = base_activity + tpsa_factor + flexibility_factor + aromatic_factor\n    \n    # Add some noise\n    activity += np.random.normal(0, 0.5)\n    \n    # Ensure reasonable range (4-9 pIC50)\n    activity = np.clip(activity, 4.0, 9.0)\n    \n    return activity\n\n# Calculate bioactivity\ndf['pIC50'] = df.apply(calculate_bioactivity, axis=1)\n\n# Generate additional properties\nprint('Generating ADMET properties...')\n\n# Solubility (LogS)\ndef calculate_solubility(row):\n    \"\"\"Simulate aqueous solubility\"\"\"\n    # Lipophilicity penalty\n    logP_penalty = -0.5 * max(0, row['logP'] - 2)\n    \n    # Molecular weight penalty\n    mw_penalty = -0.005 * max(0, row['molecular_weight'] - 300)\n    \n    # TPSA bonus (polar surface area helps solubility)\n    tpsa_bonus = 0.01 * min(row['tpsa'], 100)\n    \n    # Base solubility\n    base_solubility = -2.0\n    \n    solubility = base_solubility + logP_penalty + mw_penalty + tpsa_bonus\n    solubility += np.random.normal(0, 0.3)\n    \n    return np.clip(solubility, -6.0, 1.0)\n\ndf['logS'] = df.apply(calculate_solubility, axis=1)\n\n# Permeability (Caco-2)\ndef calculate_permeability(row):\n    \"\"\"Simulate cell permeability\"\"\"\n    # LogP correlation\n    logP_factor = 0.3 * row['logP']\n    \n    # TPSA penalty\n    tpsa_penalty = -0.02 * row['tpsa']\n    \n    # Molecular weight penalty\n    mw_penalty = -0.003 * row['molecular_weight']\n    \n    # Base permeability (log Papp)\n    base_perm = -4.5\n    \n    permeability = base_perm + logP_factor + tpsa_penalty + mw_penalty\n    permeability += np.random.normal(0, 0.4)\n    \n    return np.clip(permeability, -7.0, -3.0)\n\ndf['log_Papp'] = df.apply(calculate_permeability, axis=1)\n\n# Half-life (t1/2)\ndef calculate_half_life(row):\n    \"\"\"Simulate metabolic stability\"\"\"\n    # Molecular complexity factor\n    complexity = row['num_rotatable_bonds'] + row['num_heteroatoms']\n    complexity_factor = -0.05 * complexity\n    \n    # Aromatic stabilization\n    aromatic_factor = 0.1 * row['num_aromatic_rings']\n    \n    # Base half-life (log hours)\n    base_t_half = 1.0\n    \n    t_half = base_t_half + complexity_factor + aromatic_factor\n    t_half += np.random.normal(0, 0.3)\n    \n    return np.clip(t_half, -1.0, 3.0)\n\ndf['log_t_half'] = df.apply(calculate_half_life, axis=1)\n\nprint(f'Generated properties: pIC50, logS, log_Papp, log_t_half')\nprint(f'Property value ranges:')\nfor prop in ['pIC50', 'logS', 'log_Papp', 'log_t_half']:\n    print(f'  {prop}: {df[prop].min():.2f} to {df[prop].max():.2f}')\n\n# Apply drug-likeness filters\nprint('\\n=== Drug-likeness Analysis ===')\n\ndef lipinski_filter(row):\n    \"\"\"Apply Lipinski's Rule of Five\"\"\"\n    violations = 0\n    if row['molecular_weight'] > 500: violations += 1\n    if row['logP'] > 5: violations += 1\n    if row['num_donors'] > 5: violations += 1\n    if row['num_acceptors'] > 10: violations += 1\n    return violations\n\ndef veber_filter(row):\n    \"\"\"Apply Veber's rules for oral bioavailability\"\"\"\n    violations = 0\n    if row['tpsa'] > 140: violations += 1\n    if row['num_rotatable_bonds'] > 10: violations += 1\n    return violations\n\ndf['lipinski_violations'] = df.apply(lipinski_filter, axis=1)\ndf['veber_violations'] = df.apply(veber_filter, axis=1)\ndf['drug_like'] = (df['lipinski_violations'] == 0) & (df['veber_violations'] == 0)\n\nprint(f'Drug-likeness analysis:')\nprint(f'  Lipinski compliant (0 violations): {(df[\"lipinski_violations\"] == 0).sum()}')\nprint(f'  Veber compliant (0 violations): {(df[\"veber_violations\"] == 0).sum()}')\nprint(f'  Overall drug-like: {df[\"drug_like\"].sum()}')\nprint(f'  Drug-like percentage: {df[\"drug_like\"].mean():.1%}')\n\n# Machine learning model training\nprint('\\n=== Machine Learning Model Training ===')\n\n# Prepare features and targets\nfeature_cols = descriptor_names\ntarget_cols = ['pIC50', 'logS', 'log_Papp', 'log_t_half']\n\nX = df[feature_cols].values\ny = df[target_cols].values\n\nprint(f'Feature matrix shape: {X.shape}')\nprint(f'Target matrix shape: {y.shape}')\n\n# Split data\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, test_size=0.2, random_state=42\n)\n\nprint(f'Training set: {X_train.shape[0]} molecules')\nprint(f'Test set: {X_test.shape[0]} molecules')\n\n# Train models for each property\nmodels = {}\nperformance = {}\n\nfor i, target_name in enumerate(target_cols):\n    print(f'\\nTraining model for {target_name}...')\n    \n    # Random Forest model\n    model = RandomForestRegressor(n_estimators=100, random_state=42)\n    model.fit(X_train, y_train[:, i])\n    \n    # Predictions\n    y_pred_train = model.predict(X_train)\n    y_pred_test = model.predict(X_test)\n    \n    # Performance metrics\n    train_r2 = r2_score(y_train[:, i], y_pred_train)\n    test_r2 = r2_score(y_test[:, i], y_pred_test)\n    train_rmse = np.sqrt(mean_squared_error(y_train[:, i], y_pred_train))\n    test_rmse = np.sqrt(mean_squared_error(y_test[:, i], y_pred_test))\n    \n    models[target_name] = model\n    performance[target_name] = {\n        'train_r2': train_r2,\n        'test_r2': test_r2,\n        'train_rmse': train_rmse,\n        'test_rmse': test_rmse,\n        'predictions': y_pred_test,\n        'true_values': y_test[:, i]\n    }\n    \n    print(f'  Training R²: {train_r2:.3f}')\n    print(f'  Test R²: {test_r2:.3f}')\n    print(f'  Test RMSE: {test_rmse:.3f}')\n\n# Feature importance analysis\nprint('\\n=== Feature Importance Analysis ===')\n\nfeature_importance = pd.DataFrame({\n    'feature': feature_cols,\n    **{target: models[target].feature_importances_ for target in target_cols}\n})\n\nprint('Top features for each property:')\nfor target in target_cols:\n    top_features = feature_importance.nlargest(3, target)\n    print(f'\\n{target}:')\n    for _, row in top_features.iterrows():\n        print(f'  {row[\"feature\"]}: {row[target]:.3f}')\n\n# Virtual screening simulation\nprint('\\n=== Virtual Screening Simulation ===')\n\n# Generate new molecules for screening\nn_screening = 10000\nprint(f'Generating {n_screening} molecules for virtual screening...')\n\nscreening_data = []\nfor i in range(n_screening):\n    # Generate random molecular descriptors\n    mw = np.random.normal(350, 120)\n    mw = np.clip(mw, 100, 700)\n    \n    logP = np.random.normal(2.5, 2.0)\n    logP = np.clip(logP, -3, 7)\n    \n    donors = np.random.poisson(2)\n    donors = np.clip(donors, 0, 8)\n    \n    acceptors = np.random.poisson(4)\n    acceptors = np.clip(acceptors, 0, 15)\n    \n    tpsa = np.random.gamma(2, 35)\n    tpsa = np.clip(tpsa, 0, 250)\n    \n    rot_bonds = np.random.poisson(6)\n    rot_bonds = np.clip(rot_bonds, 0, 20)\n    \n    aromatic_rings = np.random.poisson(2)\n    aromatic_rings = np.clip(aromatic_rings, 0, 5)\n    \n    formal_charge = np.random.choice([0, 0, 0, 0, 1, -1])\n    \n    heteroatoms = np.random.poisson(4) + 1\n    heteroatoms = np.clip(heteroatoms, 1, 12)\n    \n    frac_csp3 = np.random.beta(2, 2)\n    \n    screening_data.append([\n        mw, logP, donors, acceptors, tpsa, rot_bonds,\n        aromatic_rings, formal_charge, heteroatoms, frac_csp3\n    ])\n\nX_screening = np.array(screening_data)\n\n# Predict properties for screening library\nprint('Predicting properties for screening library...')\nscreening_predictions = {}\n\nfor target in target_cols:\n    predictions = models[target].predict(X_screening)\n    screening_predictions[target] = predictions\n\n# Apply filters for hit identification\nprint('\\nApplying screening filters...')\n\n# Create screening DataFrame\nscreening_df = pd.DataFrame(X_screening, columns=feature_cols)\nfor target in target_cols:\n    screening_df[f'pred_{target}'] = screening_predictions[target]\n\n# Apply drug-likeness filters\nscreening_df['lipinski_violations'] = screening_df.apply(lipinski_filter, axis=1)\nscreening_df['veber_violations'] = screening_df.apply(veber_filter, axis=1)\nscreening_df['drug_like'] = (\n    (screening_df['lipinski_violations'] == 0) & \n    (screening_df['veber_violations'] == 0)\n)\n\n# Activity filters\nactivity_threshold = 6.5  # pIC50 > 6.5 (IC50 < 316 nM)\nsolubility_threshold = -4.0  # logS > -4 (> 0.1 mM)\npermeability_threshold = -5.5  # log Papp > -5.5\n\nhits = screening_df[\n    (screening_df['pred_pIC50'] > activity_threshold) &\n    (screening_df['pred_logS'] > solubility_threshold) &\n    (screening_df['pred_log_Papp'] > permeability_threshold) &\n    (screening_df['drug_like'] == True)\n]\n\nprint(f'Screening results:')\nprint(f'  Total molecules: {len(screening_df):,}')\nprint(f'  Drug-like molecules: {screening_df[\"drug_like\"].sum():,}')\nprint(f'  Active hits (pIC50 > {activity_threshold}): {(screening_df[\"pred_pIC50\"] > activity_threshold).sum():,}')\nprint(f'  Final hits (all criteria): {len(hits):,}')\nprint(f'  Hit rate: {len(hits) / len(screening_df):.1%}')\n\nif len(hits) > 0:\n    print(f'\\nTop 5 hits:')\n    top_hits = hits.nlargest(5, 'pred_pIC50')\n    for idx, hit in top_hits.iterrows():\n        print(f'  Hit {idx}: pIC50={hit[\"pred_pIC50\"]:.2f}, '\n              f'logS={hit[\"pred_logS\"]:.2f}, MW={hit[\"molecular_weight\"]:.0f}')\n\n# Visualization\nprint('\\n=== Visualization ===')\n\nfig, axes = plt.subplots(2, 2, figsize=(15, 12))\n\n# 1. Property predictions vs true values\nfor i, target in enumerate(['pIC50', 'logS']):\n    ax = axes[0, i]\n    perf = performance[target]\n    \n    ax.scatter(perf['true_values'], perf['predictions'], alpha=0.6, s=20)\n    \n    # Perfect prediction line\n    min_val = min(perf['true_values'].min(), perf['predictions'].min())\n    max_val = max(perf['true_values'].max(), perf['predictions'].max())\n    ax.plot([min_val, max_val], [min_val, max_val], 'r--', alpha=0.8)\n    \n    ax.set_xlabel(f'True {target}')\n    ax.set_ylabel(f'Predicted {target}')\n    ax.set_title(f'{target} Prediction (R² = {perf[\"test_r2\"]:.3f})')\n    ax.grid(True, alpha=0.3)\n\n# 2. Feature importance heatmap\nax = axes[1, 0]\nimportance_matrix = feature_importance[target_cols].values.T\nim = ax.imshow(importance_matrix, cmap='viridis', aspect='auto')\nax.set_xticks(range(len(feature_cols)))\nax.set_xticklabels(feature_cols, rotation=45, ha='right')\nax.set_yticks(range(len(target_cols)))\nax.set_yticklabels(target_cols)\nax.set_title('Feature Importance Heatmap')\nplt.colorbar(im, ax=ax)\n\n# 3. Virtual screening results\nax = axes[1, 1]\nax.scatter(screening_df['pred_pIC50'], screening_df['pred_logS'], \n          alpha=0.3, s=10, color='lightblue', label='All molecules')\nif len(hits) > 0:\n    ax.scatter(hits['pred_pIC50'], hits['pred_logS'], \n              alpha=0.8, s=30, color='red', label=f'Hits ({len(hits)})')\n\nax.axvline(x=activity_threshold, color='green', linestyle='--', alpha=0.7, \n          label=f'pIC50 > {activity_threshold}')\nax.axhline(y=solubility_threshold, color='orange', linestyle='--', alpha=0.7, \n          label=f'logS > {solubility_threshold}')\n\nax.set_xlabel('Predicted pIC50')\nax.set_ylabel('Predicted logS')\nax.set_title('Virtual Screening Results')\nax.legend()\nax.grid(True, alpha=0.3)\n\nplt.tight_layout()\n\n# Save visualization\nwith tempfile.NamedTemporaryFile(suffix='.png', delete=False) as tmp:\n    plt.savefig(tmp.name, dpi=150, bbox_inches='tight')\n    viz_file = tmp.name\n\nplt.close()\nprint(f'Analysis visualization saved to: {viz_file}')\n\n# Summary report\nprint('\\n' + '=' * 45)\nprint('OPENCHEM DRUG DISCOVERY SUMMARY')\nprint('=' * 45)\nprint(f'Molecules analyzed: {len(df):,}')\nprint(f'Properties predicted: {len(target_cols)}')\nprint(f'Drug-like molecules: {df[\"drug_like\"].sum():,} ({df[\"drug_like\"].mean():.1%})')\nprint(f'\\nModel performance (test R²):')\nfor target in target_cols:\n    print(f'  {target}: {performance[target][\"test_r2\"]:.3f}')\nprint(f'\\nVirtual screening:')\nprint(f'  Molecules screened: {len(screening_df):,}')\nprint(f'  Hits identified: {len(hits):,}')\nprint(f'  Hit rate: {len(hits) / len(screening_df):.2%}')\n\n# Cleanup\nos.unlink(viz_file)\nprint('\\nDemo complete - temporary files cleaned up')\n\nprint('\\nOpenChem provides:')\nprint('• Multi-task molecular property prediction')\nprint('• Graph neural networks for molecules')\nprint('• Molecular generation and optimization')\nprint('• ADMET property prediction')\nprint('• Virtual screening capabilities')\nprint('• Integration with PyTorch')\nprint('• Pre-trained models and datasets')\n\nprint('\\nTypical OpenChem workflow:')\nprint('1. Load molecular dataset (SMILES, SDF)')\nprint('2. Generate molecular representations')\nprint('3. Train/load prediction models')\nprint('4. Predict properties for new molecules')\nprint('5. Apply filters for drug discovery')",
+      "quick_start": [
+        "Install: pip install openchem",
+        "Import: from openchem.models import build_model",
+        "Data: Load SMILES and properties",
+        "Model: Configure and train neural network",
+        "Predict: Apply model to new molecules",
+        "Filter: Apply drug-likeness criteria"
+      ]
+    }
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_molvs_info",
+    "description": "Get information about the molvs package. Molecule validation and standardization",
+    "package_name": "molvs",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_chembl_webresource_client_info",
+    "description": "Get information about the chembl-webresource-client package. Python client for ChEMBL web services",
+    "package_name": "chembl-webresource-client",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_pubchempy_info",
+    "description": "Get information about the pubchempy package. Python interface for PubChem REST API",
+    "package_name": "pubchempy",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_mordred_info",
+    "description": "Get information about the mordred package. Molecular descriptor calculator",
+    "package_name": "mordred",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_datamol_info",
+    "description": "Get information about the datamol package. Molecular manipulation made easy",
+    "package_name": "datamol",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_molfeat_info",
+    "description": "Get information about the molfeat package. Simple and robust molecular featurization",
+    "package_name": "molfeat",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  }
+]

tooluniverse/data/packages/earth_sciences_tools.json

@@ -0,0 +1,74 @@
+[
+  {
+    "type": "PackageTool",
+    "name": "get_xesmf_info",
+    "description": "Get information about the xesmf package. Universal regridder for geospatial data",
+    "package_name": "xesmf",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_rasterio_info",
+    "description": "Get information about the rasterio package. Access to geospatial raster data",
+    "package_name": "rasterio",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_geopandas_info",
+    "description": "Get information about the geopandas package. Geospatial data manipulation and analysis",
+    "package_name": "geopandas",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_cartopy_info",
+    "description": "Get information about the cartopy package. Cartographic projections and geospatial data processing",
+    "package_name": "cartopy",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_netcdf4_info",
+    "description": "Get information about the netcdf4 package. Python interface to netCDF C library",
+    "package_name": "netcdf4",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  },
+  {
+    "type": "PackageTool",
+    "name": "get_cftime_info",
+    "description": "Get information about the cftime package. Time-handling functionality from netcdf4-python",
+    "package_name": "cftime",
+    "parameter": {
+      "type": "object",
+      "properties": {},
+      "required": []
+    },
+    "required": []
+  }
+]