pycircdb 0.1.0__tar.gz

pycircdb-0.1.0/PKG-INFO

@@ -0,0 +1,31 @@
+Metadata-Version: 2.4
+Name: pycircdb
+Version: 0.1.0
+Summary: pycircdb: integrated circRNA database annotation for computational workflows.
+Author-email: Barry Digby <b.digby237@gmail.com>
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+Requires-Dist: apache-hamilton[lsp]>=1.90.0
+Requires-Dist: boto3>=1.42.89
+Requires-Dist: click>=8.3.2
+Requires-Dist: polars>=1.39.3
+Requires-Dist: pyyaml>=6.0.3
+Requires-Dist: rich-click>=1.9.7
+Requires-Dist: sf-hamilton[lsp]>=1.89.0
+
+# pycircdb
+
+A command-line tool for identifying and annotating circRNA interactions.
+
+## Installation
+
+```bash
+pip install pycircdb
+```
+
+## Usage
+
+```bash
+pycircdb --help
+```
+

pycircdb-0.1.0/README.md

@@ -0,0 +1,16 @@
+# pycircdb
+
+A command-line tool for identifying and annotating circRNA interactions.
+
+## Installation
+
+```bash
+pip install pycircdb
+```
+
+## Usage
+
+```bash
+pycircdb --help
+```
+

pycircdb-0.1.0/config.py

@@ -0,0 +1,116 @@
+import json
+import shutil
+import rich_click as click
+from rich.console import Console, Group
+from rich.panel import Panel
+from rich.text import Text
+from rich.table import Table
+from rich import box
+from pathlib import Path
+from typing import List, Optional, TypedDict, Union
+
+console = Console(stderr=True, highlight=False)
+CONFIG_DIR = Path(__file__).parent.absolute()
+
+DEFAULT_CONFIG_DATA = {
+    "global_parameters": {
+        "max_tasks": 1,
+        "output_dir": "results/"
+    },
+    "samples": {
+        "sample_1": {
+            "file_path": "path/to/sample1.txt",
+            "reference": "hg38",
+            "zero_based": True
+        }
+    }
+}
+
+class ToolConfig(TypedDict, total=False):
+    input: List[str]
+    reference: Union[str, List[str], None]
+    zero_based: Union[bool, List[bool], None]
+    max_tasks: int
+
+def create_config(name: str):
+    """Generate a default configuration file."""
+    output_path = Path.cwd() / f"{name}.json"
+    with open(output_path, "w") as f:
+        json.dump(DEFAULT_CONFIG_DATA, f, indent=4)
+    click.echo(f"Created default configuration file at {output_path}")
+
+def load_config(user_config_path: Optional[str] = None, verbose: int = 1) -> ToolConfig:
+    """
+    Load default config and override with a user config file if provided.
+    """
+    config: ToolConfig = {}
+
+    # Load defaults directly from memory
+    config.update(DEFAULT_CONFIG_DATA)
+
+    # Load user config if provided
+    if user_config_path:
+        user_path = Path(user_config_path)
+        if user_path.is_file():
+            with user_path.open() as f:
+                user_config = json.load(f) or {}
+                config.update(user_config)
+
+    # Verbosity check
+    if verbose >= 1:
+        display_path = str(Path(user_config_path).resolve()) if user_config_path else 'defaults'
+        console.print(Text(f"✓ Configuration File Loaded: {display_path}", style="bold green"))
+
+    return config
+
+def print_config_panel(config: ToolConfig, user_config_path: Optional[str] = None):
+    """Prints the rich panel for the workflow configuration."""
+    global_table = Table(show_header=True, header_style="bold cyan", box=box.ROUNDED, expand=True)
+    global_params = config.get("global_parameters", {})
+    for key in global_params.keys():
+        global_table.add_column(str(key), justify="center", style="magenta")
+    if global_params:
+        global_table.add_row(*[str(val) for val in global_params.values()])
+        
+    sample_table = Table(show_header=True, header_style="bold blue", box=box.ROUNDED, expand=True)
+    sample_table.add_column("Sample Name", style="bold green")
+    sample_table.add_column("Input File", style="yellow")
+    sample_table.add_column("Ref", style="cyan", justify="center")
+    sample_table.add_column("0-based", style="magenta", justify="center")
+
+    for sample_name, sample_info in config.get("samples", {}).items():
+        sample_table.add_row(
+            sample_name,
+            str(sample_info.get("input", sample_info.get("file_path", ""))),
+            str(sample_info.get("reference", "")),
+            str(sample_info.get("zero_based", ""))
+        )
+
+    db_table = Table(show_header=True, header_style="bold yellow", box=box.ROUNDED, expand=True)
+    db_table.add_column("Annotation DB", style="cyan")
+    db_table.add_column("FASTA DB", style="magenta")
+    db_table.add_column("miRNA Algorithms", style="green")
+
+    ann_dbs = config.get("annotate_databases", ["arraystar", "circbank", "circbase", "circpedia", "circrna_db", "cscd", "exorbase"])
+    fas_dbs = config.get("fasta_databases", ["arraystar", "circbank", "circbase", "circpedia", "circrna_db", "cscd"])
+    mir_algs = config.get("mirna_algorithms", ["miranda", "pita", "targetscan"])
+
+    max_len = max(len(ann_dbs), len(fas_dbs), len(mir_algs))
+    for i in range(max_len):
+        a = ann_dbs[i] if i < len(ann_dbs) else ""
+        f = fas_dbs[i] if i < len(fas_dbs) else ""
+        m = mir_algs[i] if i < len(mir_algs) else ""
+        db_table.add_row(a, f, m)
+        
+    panel_group = Group(
+        Text("Global Parameters:", style="bold white"),
+        global_table,
+        Text(""),
+        Text("Samples:", style="bold white"),
+        sample_table,
+        Text(""),
+        Text("Databases & Algorithms:", style="bold white"),
+        db_table
+    )
+
+    console.print(Panel(panel_group, title="[bold white]Workflow Configuration[/bold white]", border_style="green", expand=False))

pycircdb-0.1.0/main.py

@@ -0,0 +1,331 @@
+import json
+import shutil
+from pathlib import Path
+import rich_click as click
+from typing import Tuple, List, Optional
+from config import create_config, load_config, print_config_panel
+
+# Workflow stuff
+from hamilton import driver
+from hamilton.execution import executors
+
+from utils.connect_s3.download_annotation_tables import fetch_annotation_tables
+from utils.connect_s3.download_sequence_tables import fetch_sequence_tables
+from utils.connect_s3.download_mirna_tables import fetch_mirna_tables
+from utils.connect_s3.download_rbp_tables import fetch_rbp_tables
+
+import utils.detect_inputs.detect_inputs_driver as instantiate_lookup_driver
+import utils.annotate.annotate_driver as annotation_driver
+import utils.fasta.sequence_driver as sequence_driver
+import utils.mirna.mirna_driver as mirna_driver
+import utils.rbp.rbp_driver as rbp_driver
+from rich.console import Console
+
+console = Console(stderr=True, highlight=False)
+
+@click.group(chain=True, context_settings=dict(help_option_names=['-h', '--help']))
+@click.option(
+    "-c",
+    "--config",
+    type=click.Path(exists=True, dir_okay=False, readable=True),
+    required=False,
+    help="Path to the JSON config file containing workflow parameters."
+)
+@click.option(
+    "-v",
+    "--verbose",
+    type=click.IntRange(0, 2),
+    default=1,
+    help="Verbosity level: 0 (silent), 1 (high-level, default), 2 (all outputs)."
+)
+@click.pass_context
+def cli(ctx, config, verbose):
+    """Main CLI tool."""
+    ctx.ensure_object(dict)
+    
+    ctx.obj['verbose'] = verbose
+    
+    if config:
+        cfg = load_config(config, verbose=verbose)
+        if not cfg.get('samples'):
+            raise click.UsageError("Configuration file must contain a 'samples' dictionary.")
+        cfg.update({'verbose': verbose})
+        ctx.obj['cfg'] = cfg
+    else:
+        ctx.obj['cfg'] = None
+    ctx.obj['lookup_dict'] = None
+
+
+@cli.result_callback()
+@click.pass_context
+def process_pipeline(ctx, processors, config, verbose):
+    """Execute all processors returned by subcommands after parsing args."""
+    cfg = ctx.obj.get('cfg')
+    if cfg:
+        # Populate missing config for printing correctly
+        if 'annotate_databases' not in cfg:
+            cfg['annotate_databases'] = ['arraystar', 'circbank', 'circbase', 'circpedia', 'circrna_db', 'cscd', 'exorbase']
+        if 'fasta_databases' not in cfg:
+            cfg['fasta_databases'] = ['arraystar', 'circbank', 'circbase', 'circpedia', 'circrna_db', 'cscd']
+        if 'mirna_algorithms' not in cfg:
+            cfg['mirna_algorithms'] = ['miranda', 'pita', 'targetscan']
+            
+        if verbose >= 2:
+            print_config_panel(cfg, config)
+            
+    for processor in processors:
+        processor()
+
+@cli.command('annotate')
+@click.option(
+    "-d",
+    "--database",
+    type=str,
+    required=False,
+    default="arraystar,circbank,circbase,circpedia,circRNA_DB,CSCD,exorbase",
+    show_default=True,
+    help="Comma-separated list of databases to use."
+)
+@click.pass_context
+def annotate(ctx, database):
+    """Annotate circRNAs using a JSON configuration file."""
+    cfg = ctx.obj.get('cfg')
+    if not cfg:
+        raise click.UsageError("A config file must be provided via -c/--config before subcommands (e.g., main.py -c config.json annotate)")
+
+    if database:
+        valid_dbs = {'arraystar', 'circbank', 'circbase', 'circpedia', 'circrna_db', 'cscd', 'exorbase'}
+        parsed_dbs = [d.strip().lower() for d in database.split(',')]
+        invalid_dbs = [d for d in parsed_dbs if d not in valid_dbs]
+        if invalid_dbs:
+            raise click.BadParameter(f"Invalid databases provided: {', '.join(invalid_dbs)}. Valid options are: {', '.join(sorted(valid_dbs))}")
+        cfg['annotate_databases'] = parsed_dbs
+    else:
+        cfg['annotate_databases'] = ["arraystar", "circbank", "circbase", "circpedia", "circrna_db", "cscd", "exorbase"]
+
+    def processor():
+        lookup_dict = ctx.obj.get('lookup_dict')
+        ctx.obj['lookup_dict'] = run_annotation(lookup_dict=lookup_dict, **cfg)
+    return processor
+
+
+@cli.command('fasta')
+@click.option(
+    "-d",
+    "--database",
+    type=str,
+    required=False,
+    default="arraystar,circbank,circbase,circpedia,circRNA_DB,CSCD",
+    show_default=True,
+    help="Comma-separated list of databases to use."
+)
+@click.pass_context
+def fasta(ctx, database):
+    """Output circRNA sequences in FASTA format."""
+    cfg = ctx.obj.get('cfg')
+    if not cfg:
+        raise click.UsageError("A config file must be provided via -c/--config")
+
+    if database:
+        valid_dbs = {'arraystar', 'circbank', 'circbase', 'circpedia', 'circrna_db', 'cscd'}
+        parsed_dbs = [d.strip().lower() for d in database.split(',')]
+        invalid_dbs = [d for d in parsed_dbs if d not in valid_dbs]
+        if invalid_dbs:
+            raise click.BadParameter(f"Invalid databases provided: {', '.join(invalid_dbs)}. Valid options are: {', '.join(sorted(valid_dbs))}")
+        cfg['fasta_databases'] = parsed_dbs
+    else:
+        cfg['fasta_databases'] = ["arraystar", "circbank", "circbase", "circpedia", "circrna_db", "cscd"]
+
+    def processor():
+        lookup_dict = ctx.obj.get('lookup_dict')
+        ctx.obj['lookup_dict'] = run_fasta(lookup_dict=lookup_dict, **cfg)
+    return processor
+
+
+@cli.command('mirna')
+@click.option(
+    "-a",
+    "--algorithm",
+    type=str,
+    required=False,
+    default="miRanda,PITA,TargetScan",
+    show_default=True,
+    help="Comma-separated list of algorithms to use."
+)
+@click.pass_context
+def mirna(ctx, algorithm):
+    """Output miRNA interactions for identified circRNAs."""
+    cfg = ctx.obj.get('cfg')
+    if not cfg:
+        raise click.UsageError("A config file must be provided via -c/--config")
+
+    if algorithm:
+        valid_algs = {'miranda', 'pita', 'targetscan'}
+        parsed_algs = [a.strip() for a in algorithm.split(',')]
+        invalid_algs = [a for a in parsed_algs if a.lower() not in valid_algs]
+        if invalid_algs:
+            raise click.BadParameter(f"Invalid algorithms provided: {', '.join(invalid_algs)}. Valid options are: miRanda, PITA, TargetScan")
+        # Keep original case for 'contains' check, or use lowercase for case-insensitive check
+        cfg['mirna_algorithms'] = parsed_algs
+    else:
+        cfg['mirna_algorithms'] = ["miRanda", "PITA", "TargetScan"]
+
+    def processor():
+        lookup_dict = ctx.obj.get('lookup_dict')
+        run_mirna(lookup_dict=lookup_dict, **cfg)
+    return processor
+
+
+@cli.command('rbp')
+@click.pass_context
+def rbp(ctx):
+    """Output RBP interactions for identified circRNAs."""
+    cfg = ctx.obj.get('cfg')
+    if not cfg:
+        raise click.UsageError("A config file must be provided via -c/--config")
+
+    def processor():
+        lookup_dict = ctx.obj.get('lookup_dict')
+        run_rbp(lookup_dict=lookup_dict, **cfg)
+    return processor
+
+def run_annotation(lookup_dict=None, **kwargs):
+    """Run the annotation workflow."""
+
+    # Lookup tables
+    if lookup_dict is None:
+        lookup_dict = instantiate_lookup_driver.instantiate_driver(kwargs, verbose=kwargs.get('verbose', 1))
+
+    tmp_dir = kwargs.get("global_parameters", {}).get("tmp_dir", "tmp")
+
+    # Filter lookup dictionary if databases option is provided
+    databases = kwargs.get("annotate_databases")
+    if databases:
+        filtered_lookup_dict = {}
+        for sample, db_dict in lookup_dict.items():
+            filtered_lookup_dict[sample] = {k: v for k, v in db_dict.items() if k.lower() in databases}
+    else:
+        filtered_lookup_dict = lookup_dict
+
+    # Pull annotation tables
+    annotation_tables = fetch_annotation_tables(filtered_lookup_dict, tmp_dir_path=tmp_dir, verbose=kwargs.get("verbose", 1))
+
+    # Annotate + write to file in parallel
+    dr = (
+        driver.Builder()
+        .enable_dynamic_execution(allow_experimental_mode=True)
+        .with_local_executor(executors.SynchronousLocalTaskExecutor())
+        .with_remote_executor(executors.MultiThreadingExecutor(max_tasks=kwargs.get("global_parameters", {}).get("max_tasks", 1)))
+        .with_modules(annotation_driver)
+        .build()
+    )
+    
+    dr.execute(
+        ['close_annotation'],
+        inputs={'config': kwargs, 'annotation_tables': annotation_tables, 'lookup_results': filtered_lookup_dict}
+    )
+    
+    return lookup_dict
+
+
+def run_fasta(lookup_dict=None, **kwargs):
+    """Generate FASTA output from circRNA sequences.
+    
+    Args:
+        lookup_dict: Optional pre-computed lookup results. If None, will be generated from scratch.
+        **kwargs: Configuration parameters.
+    """
+    # Generate lookup tables if not provided (i.e., fasta running standalone)
+    if lookup_dict is None:
+        lookup_dict = instantiate_lookup_driver.instantiate_driver(kwargs, verbose=kwargs.get("verbose", 1))
+
+    databases = kwargs.get("fasta_databases")
+    if databases:
+        filtered_lookup_dict = {}
+        for sample, db_dict in lookup_dict.items():
+            filtered_lookup_dict[sample] = {k: v for k, v in db_dict.items() if k.lower() in databases}
+    else:
+        filtered_lookup_dict = lookup_dict
+
+    tmp_dir = kwargs.get("global_parameters", {}).get("tmp_dir", "tmp")
+    sequence_tables = fetch_sequence_tables(filtered_lookup_dict, tmp_dir_path=tmp_dir, verbose=kwargs.get("verbose", 1))
+
+    dr = (
+        driver.Builder()
+        .enable_dynamic_execution(allow_experimental_mode=True)
+        .with_local_executor(executors.SynchronousLocalTaskExecutor())
+        .with_remote_executor(executors.MultiThreadingExecutor(max_tasks=kwargs.get("global_parameters", {}).get("max_tasks", 1)))
+        .with_modules(sequence_driver)
+        .build()
+    )
+
+    dr.execute(
+        ['close_sequence'],
+        inputs={'config': kwargs, 'lookup_dict': filtered_lookup_dict, 'sequence_tables': sequence_tables}
+    )
+
+    return lookup_dict
+
+
+def run_mirna(lookup_dict=None, **kwargs):
+    """Output miRNA interactions for identified circRNAs.
+
+    Args:
+        lookup_dict: Optional pre-computed lookup results. If None, will be generated from scratch.
+        **kwargs: Configuration parameters.
+    """
+    if lookup_dict is None:
+        lookup_dict = instantiate_lookup_driver.instantiate_driver(kwargs, verbose=kwargs.get("verbose", 1))
+
+
+    tmp_dir = kwargs.get("global_parameters", {}).get("tmp_dir", "tmp")
+    mirna_tables = fetch_mirna_tables(lookup_dict, tmp_dir_path=tmp_dir, verbose=kwargs.get("verbose", 1))
+
+    dr = (
+        driver.Builder()
+        .enable_dynamic_execution(allow_experimental_mode=True)
+        .with_local_executor(executors.SynchronousLocalTaskExecutor())
+        .with_remote_executor(executors.MultiThreadingExecutor(max_tasks=kwargs.get("global_parameters", {}).get("max_tasks", 1)))
+        .with_modules(mirna_driver)
+        .build()
+    )
+    dr.execute(
+        ['close_mirna'],
+        inputs={'config': kwargs, 'lookup_dict': lookup_dict, 'mirna_tables': mirna_tables}
+    )
+
+
+def run_rbp(lookup_dict=None, **kwargs):
+    """Output RBP interactions for identified circRNAs.
+
+    Args:
+        lookup_dict: Optional pre-computed lookup results. If None, will be generated from scratch.
+        **kwargs: Configuration parameters.
+    """
+    if lookup_dict is None:
+        lookup_dict = instantiate_lookup_driver.instantiate_driver(kwargs, verbose=kwargs.get("verbose", 1))
+
+
+    tmp_dir = kwargs.get("global_parameters", {}).get("tmp_dir", "tmp")
+    rbp_tables = fetch_rbp_tables(lookup_dict, tmp_dir_path=tmp_dir, verbose=kwargs.get("verbose", 1))
+
+    dr = (
+        driver.Builder()
+        .enable_dynamic_execution(allow_experimental_mode=True)
+        .with_local_executor(executors.SynchronousLocalTaskExecutor())
+        .with_remote_executor(executors.MultiThreadingExecutor(max_tasks=kwargs.get("global_parameters", {}).get("max_tasks", 1)))
+        .with_modules(rbp_driver)
+        .build()
+    )
+    dr.execute(
+        ['close_rbp'],
+        inputs={'config': kwargs, 'lookup_dict': lookup_dict, 'rbp_tables': rbp_tables}
+    )
+
+
+def run_tool(**kwargs):
+    """Deprecated: Use run_annotation() instead."""
+    run_annotation(**kwargs)
+
+if __name__ == "__main__":
+    cli()

pycircdb-0.1.0/pycircdb.egg-info/PKG-INFO

@@ -0,0 +1,31 @@
+Metadata-Version: 2.4
+Name: pycircdb
+Version: 0.1.0
+Summary: pycircdb: integrated circRNA database annotation for computational workflows.
+Author-email: Barry Digby <b.digby237@gmail.com>
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+Requires-Dist: apache-hamilton[lsp]>=1.90.0
+Requires-Dist: boto3>=1.42.89
+Requires-Dist: click>=8.3.2
+Requires-Dist: polars>=1.39.3
+Requires-Dist: pyyaml>=6.0.3
+Requires-Dist: rich-click>=1.9.7
+Requires-Dist: sf-hamilton[lsp]>=1.89.0
+
+# pycircdb
+
+A command-line tool for identifying and annotating circRNA interactions.
+
+## Installation
+
+```bash
+pip install pycircdb
+```
+
+## Usage
+
+```bash
+pycircdb --help
+```
+

pycircdb-0.1.0/pycircdb.egg-info/SOURCES.txt

@@ -0,0 +1,29 @@
+README.md
+config.py
+main.py
+pyproject.toml
+pycircdb.egg-info/PKG-INFO
+pycircdb.egg-info/SOURCES.txt
+pycircdb.egg-info/dependency_links.txt
+pycircdb.egg-info/entry_points.txt
+pycircdb.egg-info/requires.txt
+pycircdb.egg-info/top_level.txt
+sequence_tables/extract_sequences.py
+sequence_tables/split_cscd_by_chr.py
+utils/__init__.py
+utils/md5sum_check.py
+utils/output_mapping.py
+utils/annotate/annotate_driver.py
+utils/annotate/annotate_subdag.py
+utils/annotate/annotate_subdriver.py
+utils/connect_s3/download_annotation_tables.py
+utils/connect_s3/download_lookup_tables.py
+utils/connect_s3/download_mirna_tables.py
+utils/connect_s3/download_rbp_tables.py
+utils/connect_s3/download_sequence_tables.py
+utils/detect_inputs/detect_inputs_driver.py
+utils/detect_inputs/detect_inputs_subdag.py
+utils/fasta/sequence_driver.py
+utils/fasta/sequence_subdag.py
+utils/mirna/mirna_driver.py
+utils/rbp/rbp_driver.py

pycircdb-0.1.0/pycircdb.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

pycircdb-0.1.0/pycircdb.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pycircdb = main:cli

pycircdb-0.1.0/pycircdb.egg-info/requires.txt

@@ -0,0 +1,7 @@
+apache-hamilton[lsp]>=1.90.0
+boto3>=1.42.89
+click>=8.3.2
+polars>=1.39.3
+pyyaml>=6.0.3
+rich-click>=1.9.7
+sf-hamilton[lsp]>=1.89.0

pycircdb-0.1.0/pycircdb.egg-info/top_level.txt

@@ -0,0 +1,12 @@
+assets
+build
+config
+db_tables
+dist
+lookup_tables
+main
+results
+sequence_tables
+test
+tmp
+utils

pycircdb-0.1.0/pyproject.toml

@@ -0,0 +1,47 @@
+[project]
+name = "pycircdb"
+version = "0.1.0"
+description = "pycircdb: integrated circRNA database annotation for computational workflows."
+readme = "README.md"
+authors = [{ name = "Barry Digby", email = "b.digby237@gmail.com" }]
+requires-python = ">=3.14"
+dependencies = [
+    "apache-hamilton[lsp]>=1.90.0",
+    "boto3>=1.42.89",
+    "click>=8.3.2",
+    "polars>=1.39.3",
+    "pyyaml>=6.0.3",
+    "rich-click>=1.9.7",
+    "sf-hamilton[lsp]>=1.89.0",
+]
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["*", "assets", "utils", "utils.*"]
+
+[tool.setuptools]
+py-modules = ["main", "config"]
+
+[tool.setuptools.package-data]
+"*" = ["assets/*.csv"]
+
+[dependency-groups]
+dev = [
+    "pytest>=9.0.3",
+    "pytest-cov>=7.1.0",
+]
+
+[tool.pytest.ini_options]
+addopts = "--cov=utils --cov=config --cov-report=term-missing --cov-report=html"
+testpaths = ["tests"]
+
+[tool.coverage.run]
+source = ["utils", "config.py", "main.py"]
+omit = ["tests/*", "venv/*"]
+[project.scripts]
+pycircdb = "main:cli"
+