omix 0.1.0__tar.gz

omix-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Heather MacGregor
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

omix-0.1.0/PKG-INFO

@@ -0,0 +1,138 @@
+Metadata-Version: 2.4
+Name: omix
+Version: 0.1.0
+Summary: A modular Python package for fetching, enriching, and analyzing omics metadata and publications.
+Author-email: Heather MacGregor <user@example.com>
+License: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31
+Requires-Dist: beautifulsoup4>=4.12
+Requires-Dist: pandas>=2.0
+Requires-Dist: pypdf2>=3.0
+Requires-Dist: urllib3>=2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.0
+Requires-Dist: click>=8.0
+Requires-Dist: aiohttp>=3.8
+Requires-Dist: biopython>=1.81
+Requires-Dist: geopy>=2.0
+Requires-Dist: rapidfuzz>=3.0
+Requires-Dist: tqdm>=4.0
+Provides-Extra: llm
+Requires-Dist: openai>=1.0; extra == "llm"
+Requires-Dist: transformers>=4.30; extra == "llm"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: httpx; extra == "dev"
+Dynamic: license-file
+
+# omix
+
+A Python package that:
+
+- Fetches comprehensive metadata from public databases (ENA, and soon others).
+- Enriches coordinates, dates, host/environment categories, and experimental protocols.
+- Searches across multiple publication sources (Crossref, Europe PMC, NCBI, Semantic Scholar, etc.).
+- Extracts methodology from full‑text using LLMs (optional).
+- Validates findings against reference databases (e.g., primer databases for 16S).
+- Works for **any omics** via plugins.
+
+## Installation
+
+```bash
+pip install omix
+# with LLM support:
+pip install omix[llm]
+```
+
+## Quick Start
+
+### Command Line
+
+```bash
+# Enrich a metadata file with ENA data
+omix fetch-metadata samples.tsv --email you@example.com
+
+# Fetch publications for one or more accessions
+omix fetch-publications PRJNA864623 --omics 16S --api-key $LLM_KEY
+
+# Run the full metadata cleaning and enrichment pipeline
+omix run-pipeline metadata.csv -o enriched.csv
+
+# NEW: Unified pipeline (metadata + publications + validation + integration)
+omix enrich-with-publications samples.csv -o enriched_complete.csv --config config.yaml
+```
+
+### Unified Metadata + Publications Pipeline
+
+The `enrich-with-publications` command provides an end-to-end workflow:
+
+1. **Metadata Enrichment**: Fetches comprehensive data from ENA (sequences, samples, runs)
+2. **Publication Discovery**: Searches across 12+ publication APIs (Crossref, EuropePMC, NCBI, Semantic Scholar, arXiv, bioRxiv, CORE, DataCite, DOAJ, PLOS, Unpaywall, Zenodo)
+3. **Publication Validation**: Filters to only include publications with direct accession mentions
+4. **Integration**: Merges publication counts and DOIs into the enriched metadata
+
+Output includes all ENA metadata fields plus:
+- `publication_count`: Number of validated publications per study
+- `publication_dois`: Semicolon-separated list of publication DOIs
+
+```bash
+# Basic usage
+omix enrich-with-publications input.csv -o output.csv
+
+# With debug config for faster testing
+omix enrich-with-publications input.csv -o output.csv --config config.debug.yaml
+
+# Skip validation (keep all publications found)
+omix enrich-with-publications input.csv -o output.csv --no-validate
+
+# With LLM-based methodology extraction
+omix enrich-with-publications input.csv -o output.csv --api-key $LLM_KEY
+```
+
+### Python API
+
+```python
+from omix import Config
+from omix.metadata.file_workflow import enrich_metadata_from_path
+import asyncio
+
+config = Config(email="you@example.com")
+df = asyncio.run(enrich_metadata_from_path("samples.csv", config=config))
+print(df.head())
+```
+
+## Configuration
+
+`omix` can be configured via a YAML file:
+
+```yaml
+credentials:
+  email: "your.email@example.com"
+  ena_email: "ena@example.com"
+  llm_api_key: "sk-..."
+  ncbi_api_key: "..."
+
+apis:
+  sequence:
+    ena:
+      enabled: true
+      max_concurrent: 5
+      batch_size: 100
+      cache_ttl_days: 30
+      fetch_phases: true
+
+metadata:
+  sample_id_column: "#sampleid"
+  exclude_host: false
+
+paths:
+  cache_dir: ".cache"
+  logs_dir: "logs"
+  primer_db: null
+```
+
+Pass it with `--config my_config.yaml` or set environment variables like `OMIX_EMAIL`.

omix-0.1.0/README.md

@@ -0,0 +1,107 @@
+# omix
+
+A Python package that:
+
+- Fetches comprehensive metadata from public databases (ENA, and soon others).
+- Enriches coordinates, dates, host/environment categories, and experimental protocols.
+- Searches across multiple publication sources (Crossref, Europe PMC, NCBI, Semantic Scholar, etc.).
+- Extracts methodology from full‑text using LLMs (optional).
+- Validates findings against reference databases (e.g., primer databases for 16S).
+- Works for **any omics** via plugins.
+
+## Installation
+
+```bash
+pip install omix
+# with LLM support:
+pip install omix[llm]
+```
+
+## Quick Start
+
+### Command Line
+
+```bash
+# Enrich a metadata file with ENA data
+omix fetch-metadata samples.tsv --email you@example.com
+
+# Fetch publications for one or more accessions
+omix fetch-publications PRJNA864623 --omics 16S --api-key $LLM_KEY
+
+# Run the full metadata cleaning and enrichment pipeline
+omix run-pipeline metadata.csv -o enriched.csv
+
+# NEW: Unified pipeline (metadata + publications + validation + integration)
+omix enrich-with-publications samples.csv -o enriched_complete.csv --config config.yaml
+```
+
+### Unified Metadata + Publications Pipeline
+
+The `enrich-with-publications` command provides an end-to-end workflow:
+
+1. **Metadata Enrichment**: Fetches comprehensive data from ENA (sequences, samples, runs)
+2. **Publication Discovery**: Searches across 12+ publication APIs (Crossref, EuropePMC, NCBI, Semantic Scholar, arXiv, bioRxiv, CORE, DataCite, DOAJ, PLOS, Unpaywall, Zenodo)
+3. **Publication Validation**: Filters to only include publications with direct accession mentions
+4. **Integration**: Merges publication counts and DOIs into the enriched metadata
+
+Output includes all ENA metadata fields plus:
+- `publication_count`: Number of validated publications per study
+- `publication_dois`: Semicolon-separated list of publication DOIs
+
+```bash
+# Basic usage
+omix enrich-with-publications input.csv -o output.csv
+
+# With debug config for faster testing
+omix enrich-with-publications input.csv -o output.csv --config config.debug.yaml
+
+# Skip validation (keep all publications found)
+omix enrich-with-publications input.csv -o output.csv --no-validate
+
+# With LLM-based methodology extraction
+omix enrich-with-publications input.csv -o output.csv --api-key $LLM_KEY
+```
+
+### Python API
+
+```python
+from omix import Config
+from omix.metadata.file_workflow import enrich_metadata_from_path
+import asyncio
+
+config = Config(email="you@example.com")
+df = asyncio.run(enrich_metadata_from_path("samples.csv", config=config))
+print(df.head())
+```
+
+## Configuration
+
+`omix` can be configured via a YAML file:
+
+```yaml
+credentials:
+  email: "your.email@example.com"
+  ena_email: "ena@example.com"
+  llm_api_key: "sk-..."
+  ncbi_api_key: "..."
+
+apis:
+  sequence:
+    ena:
+      enabled: true
+      max_concurrent: 5
+      batch_size: 100
+      cache_ttl_days: 30
+      fetch_phases: true
+
+metadata:
+  sample_id_column: "#sampleid"
+  exclude_host: false
+
+paths:
+  cache_dir: ".cache"
+  logs_dir: "logs"
+  primer_db: null
+```
+
+Pass it with `--config my_config.yaml` or set environment variables like `OMIX_EMAIL`.

omix-0.1.0/omix/__init__.py

@@ -0,0 +1,13 @@
+"""
+omix: A modular Python package for fetching, enriching, and analyzing
+omics metadata and publications.
+
+Usage:
+    from omix import Config
+    config = Config(email="you@example.com")
+"""
+
+__version__ = "0.1.0"
+
+from .config import Config, load_config
+from .logging_utils import setup_logging, get_logger