ANDREA 0.1.0__py3-none-any.whl

andrea/__init__.py

@@ -0,0 +1,5 @@
+"""ANDREA package root."""
+
+from .config import __author__, __version__
+
+__all__ = ["__author__", "__version__"]

andrea/__main__.py

@@ -0,0 +1,15 @@
+"""Entry point for the ANDREA CLI."""
+
+from rich import print
+
+from andrea.cli.app import app
+from andrea.config import HEADER
+
+
+def main() -> None:
+    print(HEADER)
+    app()
+
+
+if __name__ == "__main__":
+    main()

andrea/catalog_inference_tools/__init__.py

@@ -0,0 +1 @@
+"""Packaged inference tool catalog (schemas + toolspec-driven wrappers metadata)."""

andrea/catalog_inference_tools/input_specs/cell_cell_interactions.json

@@ -0,0 +1,64 @@
+{
+  "schema_version": "1.0",
+  "key": "cell_cell_interactions",
+  "file_kind": "tsv",
+  "description": "Cell-cell interaction TSV: directed ligand-receptor effects between public expression columns.",
+  "example": "source_column\ttarget_column\tsource_group\ttarget_group\tligand\treceptor\tscore\tsign\teffect\nspot_1\tspot_2\tA\tB\tL1\tR1\t1.0\t+\t5.2",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 9,
+  "first_column_role": "none",
+  "required_columns": [
+    "source_column",
+    "target_column",
+    "source_group",
+    "target_group",
+    "ligand",
+    "receptor",
+    "score",
+    "sign",
+    "effect"
+  ],
+  "column_types": {
+    "source_column": "string",
+    "target_column": "string",
+    "source_group": "string",
+    "target_group": "string",
+    "ligand": "string",
+    "receptor": "string",
+    "score": "float",
+    "sign": "string",
+    "effect": "float"
+  },
+  "cross_checks": [
+    {
+      "kind": "column_subset_expression_columns",
+      "column": "source_column"
+    },
+    {
+      "kind": "column_subset_expression_columns",
+      "column": "target_column"
+    },
+    {
+      "kind": "column_subset_expression_genes",
+      "column": "ligand"
+    },
+    {
+      "kind": "column_subset_expression_genes",
+      "column": "receptor"
+    },
+    {
+      "kind": "column_subset_extra_column",
+      "column": "source_group",
+      "other_input": "groups",
+      "other_column": "cluster"
+    },
+    {
+      "kind": "column_subset_extra_column",
+      "column": "target_group",
+      "other_input": "groups",
+      "other_column": "cluster"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/chromatin_accessibility.json

@@ -0,0 +1,20 @@
+{
+  "schema_version": "1.0",
+  "key": "chromatin_accessibility",
+  "file_kind": "tsv",
+  "description": "Chromatin accessibility matrix TSV: first column contains chromatin region identifiers and remaining columns match expression column identifiers.",
+  "example": "region\tspot_1\tspot_2\nregion_1\t0\t2\nregion_2\t1\t0",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "none",
+  "unique_first_column": true,
+  "data_columns_type": "float",
+  "data_numeric_min_fraction": 1.0,
+  "cross_checks": [
+    {
+      "kind": "data_columns_match_expression_columns"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/chromatin_regions.json

@@ -0,0 +1,23 @@
+{
+  "schema_version": "1.0",
+  "key": "chromatin_regions",
+  "file_kind": "tsv",
+  "description": "Chromatin region metadata TSV: one row per public chromatin region with stable region id, numeric region index and semicolon-separated linked expression genes.",
+  "example": "region\tregion_index\tlinked_genes\nregion_1\t1\tG1;G2\nregion_2\t2\tG3",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 3,
+  "first_column_role": "none",
+  "required_columns": [
+    "region",
+    "region_index",
+    "linked_genes"
+  ],
+  "unique_first_column": true,
+  "column_types": {
+    "region": "string",
+    "region_index": "float",
+    "linked_genes": "string"
+  }
+}

andrea/catalog_inference_tools/input_specs/cluster_identities.json

@@ -0,0 +1,30 @@
+{
+  "schema_version": "1.0",
+  "key": "cluster_identities",
+  "file_kind": "tsv",
+  "description": "Cluster identity TSV: maps cluster IDs to human-readable cluster annotations, with an optional integer order column for methods that display or rank clusters along a known ordering.",
+  "example": "cluster\tannotation\torder\nA\tcortex\t1\nB\tendodermis\t2",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "none",
+  "required_columns": [
+    "cluster",
+    "annotation"
+  ],
+  "unique_first_column": true,
+  "column_types": {
+    "cluster": "string",
+    "annotation": "string",
+    "order": "int"
+  },
+  "cross_checks": [
+    {
+      "kind": "column_subset_extra_column",
+      "column": "cluster",
+      "other_input": "groups",
+      "other_column": "cluster"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/cluster_markers.json

@@ -0,0 +1,35 @@
+{
+  "schema_version": "1.0",
+  "key": "cluster_markers",
+  "file_kind": "tsv",
+  "description": "Cluster marker TSV: Seurat FindAllMarkers-style marker table with one row per upregulated marker gene and a cluster assignment for that marker.",
+  "example": "geneID\tp_val\tavg_logFC\tpct.1\tpct.2\tp_val_adj\tcluster\tgene\nG1\t0.001\t0.8\t0.7\t0.2\t0.01\tA\tG1\nG2\t0.002\t0.6\t0.6\t0.1\t0.02\tB\tG2",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 4,
+  "first_column_role": "none",
+  "required_columns": [
+    "cluster",
+    "gene",
+    "p_val_adj"
+  ],
+  "column_types": {
+    "cluster": "string",
+    "gene": "string",
+    "p_val_adj": "float",
+    "avg_logFC": "float"
+  },
+  "cross_checks": [
+    {
+      "kind": "column_subset_expression_genes",
+      "column": "gene"
+    },
+    {
+      "kind": "column_subset_extra_column",
+      "column": "cluster",
+      "other_input": "groups",
+      "other_column": "cluster"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/column_descriptors.json

@@ -0,0 +1,25 @@
+{
+  "schema_version": "1.0",
+  "key": "column_descriptors",
+  "file_kind": "tsv",
+  "description": "Column descriptor TSV: first column maps expression column identifiers to one or more categorical descriptor columns such as batch, donor, condition, cell type, timepoint or perturbation.",
+  "example": "column\tbatch\tcondition\ncell_1\tbatch_a\tcontrol\ncell_2\tbatch_b\tstimulated",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "expression_column_id",
+  "unique_first_column": true,
+  "data_columns_type": "any",
+  "data_numeric_min_fraction": 0.0,
+  "required_columns": [],
+  "column_types": {},
+  "cross_checks": [
+    {
+      "kind": "first_column_subset_expression_columns"
+    },
+    {
+      "kind": "row_count_matches_expression_columns"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/column_phenotypes.json

@@ -0,0 +1,29 @@
+{
+  "schema_version": "1.0",
+  "key": "column_phenotypes",
+  "file_kind": "tsv",
+  "description": "Ordered column phenotype TSV: first column maps expression column identifiers to a phenotype/state label, and order gives the integer phenotype order used by methods that model transitions between phenotypes.",
+  "example": "column\tphenotype\torder\ncell_1\tIP\t0\ncell_2\tIP\t0\ncell_3\tD12\t1",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 3,
+  "first_column_role": "expression_column_id",
+  "required_columns": [
+    "phenotype",
+    "order"
+  ],
+  "unique_first_column": true,
+  "column_types": {
+    "phenotype": "string",
+    "order": "int"
+  },
+  "cross_checks": [
+    {
+      "kind": "first_column_subset_expression_columns"
+    },
+    {
+      "kind": "row_count_matches_expression_columns"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/enrichment_background.json

@@ -0,0 +1,9 @@
+{
+  "schema_version": "1.0",
+  "key": "enrichment_background",
+  "file_kind": "txt_list",
+  "description": "Enrichment background gene list: one gene identifier per line, used as a user-provided background universe for enrichment analyses.",
+  "example": "G1\nG2\nG3",
+  "min_rows": 1,
+  "cross_checks": []
+}

andrea/catalog_inference_tools/input_specs/expression_matrix.json

@@ -0,0 +1,30 @@
+{
+  "schema_version": "1.0",
+  "key": "expression_matrix",
+  "file_kind": "tsv",
+  "description": "Expression matrix TSV. Header row required. First column is gene identifier and remaining columns are samples/cells.",
+  "example": "gene\tcell_1\tcell_2\nG1\t0.12\t0.20\nG2\t1.30\t0.95",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "gene_id",
+  "first_column_disallowed_names": [
+    "cell",
+    "cells",
+    "sample",
+    "samples",
+    "timepoint",
+    "timepoints",
+    "perturbation",
+    "perturbations",
+    "cluster",
+    "pseudotime"
+  ],
+  "unique_first_column": true,
+  "data_columns_type": "float",
+  "data_numeric_min_fraction": 1.0,
+  "required_columns": [],
+  "column_types": {},
+  "cross_checks": []
+}

andrea/catalog_inference_tools/input_specs/grnboost_network.json

@@ -0,0 +1,32 @@
+{
+  "schema_version": "1.0",
+  "key": "grnboost_network",
+  "file_kind": "tsv",
+  "description": "Precomputed GRNBoost2 network TSV: directed regulator-target edges with raw GRNBoost2 importance scores, used by tools that can skip de novo GRNBoost2 inference.",
+  "example": "source\ttarget\tscore\nTF1\tG1\t0.82\nTF2\tG2\t0.41",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 3,
+  "first_column_role": "none",
+  "required_columns": [
+    "source",
+    "target",
+    "score"
+  ],
+  "column_types": {
+    "source": "string",
+    "target": "string",
+    "score": "float"
+  },
+  "cross_checks": [
+    {
+      "kind": "column_subset_expression_genes",
+      "column": "source"
+    },
+    {
+      "kind": "column_subset_expression_genes",
+      "column": "target"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/groups.json

@@ -0,0 +1,20 @@
+{
+  "schema_version": "1.0",
+  "key": "groups",
+  "file_kind": "tsv",
+  "description": "Groups TSV: first column maps expression column identifiers to a cluster/group label.",
+  "example": "column\tcluster\nS1\tA\nS2\tB",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "expression_column_id",
+  "required_columns": ["cluster"],
+  "unique_first_column": true,
+  "column_types": {
+    "cluster": "string"
+  },
+  "cross_checks": [
+    {"kind": "first_column_subset_expression_columns"}
+  ]
+}

andrea/catalog_inference_tools/input_specs/interventions.json

@@ -0,0 +1,32 @@
+{
+  "schema_version": "1.0",
+  "key": "interventions",
+  "file_kind": "tsv",
+  "description": "Intervention TSV: one row per intervention definition, including the perturbed target gene and intervention effect.",
+  "example": "intervention\ttarget\teffect\tsign\tdose\nknockdown_G1\tG1\tknockdown\t-1\t1.0\noverexpress_G2\tG2\toverexpression\t1\t1.0",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 3,
+  "first_column_role": "none",
+  "required_columns": [
+    "intervention",
+    "target",
+    "effect"
+  ],
+  "unique_first_column": true,
+  "column_types": {
+    "intervention": "string",
+    "target": "string",
+    "effect": "string",
+    "sign": "int",
+    "dose": "float",
+    "timepoint": "float"
+  },
+  "cross_checks": [
+    {
+      "kind": "column_subset_expression_genes",
+      "column": "target"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/lineage_tree.json

@@ -0,0 +1,18 @@
+{
+  "schema_version": "1.0",
+  "key": "lineage_tree",
+  "file_kind": "tsv",
+  "description": "Lineage tree TSV with child, parent, gain_rate and loss_rate. Every group must appear as a child; root groups use parent '__root__' with gain_rate=0 and loss_rate=0.",
+  "example": "child\tparent\tgain_rate\tloss_rate\nC1\t__root__\t0\t0\nC2\tC1\t0.2\t0.1",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "required_columns": ["child", "parent", "gain_rate", "loss_rate"],
+  "column_types": {
+    "child": "string",
+    "parent": "string",
+    "gain_rate": "float",
+    "loss_rate": "float"
+  },
+  "cross_checks": []
+}

andrea/catalog_inference_tools/input_specs/perturbation_design.json

@@ -0,0 +1,39 @@
+{
+  "schema_version": "1.0",
+  "key": "perturbation_design",
+  "file_kind": "tsv",
+  "description": "Perturbation design TSV: first column maps expression column identifiers to experimental condition metadata for perturbational datasets.",
+  "example": "column\tcondition\tperturbation\ttarget\tdose\ttimepoint\treplicate\ncell_1\tcontrol\tnone\t\t0\t0\tr1\ncell_2\tknockdown_G1\tknockdown\tG1\t1\t24\tr1",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "expression_column_id",
+  "required_columns": [
+    "condition"
+  ],
+  "unique_first_column": true,
+  "data_columns_type": "any",
+  "data_numeric_min_fraction": 0.0,
+  "column_types": {
+    "condition": "string",
+    "perturbation": "string",
+    "target": "string",
+    "dose": "float",
+    "timepoint": "float",
+    "replicate": "string",
+    "control": "bool"
+  },
+  "cross_checks": [
+    {
+      "kind": "first_column_subset_expression_columns"
+    },
+    {
+      "kind": "row_count_matches_expression_columns"
+    },
+    {
+      "kind": "column_subset_expression_genes",
+      "column": "target"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/prior_grn.json

@@ -0,0 +1,20 @@
+{
+  "schema_version": "1.0",
+  "key": "prior_grn",
+  "file_kind": "tsv",
+  "description": "Global prior GRN edges with source regulator, target gene and score. Nonzero scores indicate known or putative regulatory connections; sign and magnitude may be meaningful to tools that estimate regulator activity from priors.",
+  "example": "source\ttarget\tscore\nTF1\tG1\t1\nTF2\tG2\t-1",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "required_columns": ["source", "target", "score"],
+  "column_types": {
+    "source": "string",
+    "target": "string",
+    "score": "float"
+  },
+  "cross_checks": [
+    {"kind": "column_subset_expression_genes", "column": "source"},
+    {"kind": "column_subset_expression_genes", "column": "target"}
+  ]
+}

andrea/catalog_inference_tools/input_specs/prior_grn_by_group.json

@@ -0,0 +1,27 @@
+{
+  "schema_version": "1.0",
+  "key": "prior_grn_by_group",
+  "file_kind": "tsv",
+  "description": "Group-specific prior GRN edges with group, source, target and score.",
+  "example": "group\tsource\ttarget\tscore\nA\tG1\tG2\t0.82\nB\tG1\tG3\t0.41",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "required_columns": ["group", "source", "target", "score"],
+  "column_types": {
+    "group": "string",
+    "source": "string",
+    "target": "string",
+    "score": "float"
+  },
+  "cross_checks": [
+    {"kind": "column_subset_expression_genes", "column": "source"},
+    {"kind": "column_subset_expression_genes", "column": "target"},
+    {
+      "kind": "column_subset_extra_column",
+      "column": "group",
+      "other_input": "groups",
+      "other_column": "cluster"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/pseudotime.json

@@ -0,0 +1,27 @@
+{
+  "schema_version": "1.0",
+  "key": "pseudotime",
+  "file_kind": "tsv",
+  "description": "Pseudotime TSV: first column maps expression column identifiers to a numeric pseudotime value.",
+  "example": "column\tpseudotime\ncell_1\t0.0\ncell_2\t0.4\ncell_3\t1.0",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "expression_column_id",
+  "required_columns": [
+    "pseudotime"
+  ],
+  "unique_first_column": true,
+  "column_types": {
+    "pseudotime": "float"
+  },
+  "cross_checks": [
+    {
+      "kind": "first_column_subset_expression_columns"
+    },
+    {
+      "kind": "row_count_matches_expression_columns"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/replicates.json

@@ -0,0 +1,31 @@
+{
+  "schema_version": "1.0",
+  "key": "replicates",
+  "file_kind": "tsv",
+  "description": "Replicate TSV: first column maps expression column identifiers to biological or technical replicate labels.",
+  "example": "column\treplicate\tbatch\nsample_1\tr1\tbatch_a\nsample_2\tr2\tbatch_a\nsample_3\tr1\tbatch_b",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "expression_column_id",
+  "required_columns": [
+    "replicate"
+  ],
+  "unique_first_column": true,
+  "data_columns_type": "any",
+  "data_numeric_min_fraction": 0.0,
+  "column_types": {
+    "replicate": "string",
+    "batch": "string",
+    "condition": "string"
+  },
+  "cross_checks": [
+    {
+      "kind": "first_column_subset_expression_columns"
+    },
+    {
+      "kind": "row_count_matches_expression_columns"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/spatial_coordinates.json

@@ -0,0 +1,32 @@
+{
+  "schema_version": "1.0",
+  "key": "spatial_coordinates",
+  "file_kind": "tsv",
+  "description": "Spatial coordinate TSV: first column maps expression column identifiers to numeric spatial coordinates used by spatial transcriptomics methods.",
+  "example": "column\tx\ty\nspot_1\t0.0\t1.2\nspot_2\t0.5\t1.4",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 3,
+  "first_column_role": "expression_column_id",
+  "required_columns": [
+    "x",
+    "y"
+  ],
+  "unique_first_column": true,
+  "data_columns_type": "float",
+  "data_numeric_min_fraction": 1.0,
+  "column_types": {
+    "x": "float",
+    "y": "float",
+    "z": "float"
+  },
+  "cross_checks": [
+    {
+      "kind": "first_column_subset_expression_columns"
+    },
+    {
+      "kind": "row_count_matches_expression_columns"
+    }
+  ]
+}

andrea/catalog_inference_tools/input_specs/terms_of_interest.json

@@ -0,0 +1,9 @@
+{
+  "schema_version": "1.0",
+  "key": "terms_of_interest",
+  "file_kind": "txt_list",
+  "description": "Terms of interest list: one ontology term, ontology ID or plain-language keyword per line, used by methods that prioritize regulators against expected functions or biological themes.",
+  "example": "root\nGO:0009819\nvascular",
+  "min_rows": 1,
+  "cross_checks": []
+}

andrea/catalog_inference_tools/input_specs/tf_list.json

@@ -0,0 +1,11 @@
+{
+  "schema_version": "1.0",
+  "key": "tf_list",
+  "file_kind": "txt_list",
+  "description": "TF list text file. One TF identifier per line.",
+  "example": "SOX2\nMYC\nTP53",
+  "min_rows": 1,
+  "cross_checks": [
+    {"kind": "line_subset_expression_genes"}
+  ]
+}

andrea/catalog_inference_tools/input_specs/timepoints.json

@@ -0,0 +1,28 @@
+{
+  "schema_version": "1.0",
+  "key": "timepoints",
+  "file_kind": "tsv",
+  "description": "Timepoint TSV: first column maps expression column identifiers to observed time coordinates or ordered sampling times.",
+  "example": "column\ttimepoint\nsample_1\t0\nsample_2\t6\nsample_3\t12",
+  "delimiter": "\t",
+  "header": true,
+  "min_rows": 1,
+  "min_columns": 2,
+  "first_column_role": "expression_column_id",
+  "required_columns": [
+    "timepoint"
+  ],
+  "unique_first_column": true,
+  "column_types": {
+    "timepoint": "float",
+    "timepoint_label": "string"
+  },
+  "cross_checks": [
+    {
+      "kind": "first_column_subset_expression_columns"
+    },
+    {
+      "kind": "row_count_matches_expression_columns"
+    }
+  ]
+}