Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/

TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

1. Definitions.

"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.

"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.

"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.

"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.

"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.

"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.

"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).

"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.

"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."

"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.

2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.

3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.

4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:

(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and

(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and

(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and

(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.

You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.

5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.

6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.

7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.

8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.

9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.

END OF TERMS AND CONDITIONS

APPENDIX: How to apply the Apache License to your work.

To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.

Copyright [yyyy] [name of copyright owner]

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

#!/usr/bin/env python3
"""
Quality Control Analysis for Single-Cell RNA-seq Data
Following scverse best practices from:
https://www.sc-best-practices.org/preprocessing_visualization/quality_control.html

This is a convenience script that runs a complete QC workflow using the
modular functions from qc_core.py and qc_plotting.py.
"""

import anndata as ad
import scanpy as sc
import sys
import os
import argparse

# Import our modular utilities
from qc_core import (
    calculate_qc_metrics,
    detect_outliers_mad,
    apply_hard_threshold,
    filter_cells,
    filter_genes,
    print_qc_summary
)
from qc_plotting import (
    plot_qc_distributions,
    plot_filtering_thresholds,
    plot_qc_after_filtering
)

print("=" * 80)
print("Single-Cell RNA-seq Quality Control Analysis")
print("=" * 80)

# Default parameters (single source of truth)
DEFAULT_MAD_COUNTS = 5
DEFAULT_MAD_GENES = 5
DEFAULT_MAD_MT = 3
DEFAULT_MT_THRESHOLD = 8
DEFAULT_MIN_CELLS = 20
DEFAULT_MT_PATTERN = 'mt-,MT-'
DEFAULT_RIBO_PATTERN = 'Rpl,Rps,RPL,RPS'
DEFAULT_HB_PATTERN = '^Hb[^(p)]|^HB[^(P)]'

# Parse command-line arguments
parser = argparse.ArgumentParser(
    description='Quality Control Analysis for Single-Cell RNA-seq Data',
    formatter_class=argparse.RawDescriptionHelpFormatter,
    epilog="""
Examples:
  python3 qc_analysis.py data.h5ad
  python3 qc_analysis.py raw_feature_bc_matrix.h5
  python3 qc_analysis.py data.h5ad --mad-counts 4 --mad-genes 4 --mad-mt 2.5
  python3 qc_analysis.py data.h5ad --mt-threshold 10 --min-cells 10
  python3 qc_analysis.py data.h5ad --mt-pattern "^mt-" --ribo-pattern "^Rpl,^Rps"
    """
)

parser.add_argument('input_file', help='Input .h5ad or .h5 file (10X Genomics format)')
parser.add_argument('--output-dir', type=str, help='Output directory (default: <input_basename>_qc_results)')
parser.add_argument('--mad-counts', type=float, default=DEFAULT_MAD_COUNTS, help=f'MAD threshold for total counts (default: {DEFAULT_MAD_COUNTS})')
parser.add_argument('--mad-genes', type=float, default=DEFAULT_MAD_GENES, help=f'MAD threshold for gene counts (default: {DEFAULT_MAD_GENES})')
parser.add_argument('--mad-mt', type=float, default=DEFAULT_MAD_MT, help=f'MAD threshold for mitochondrial percentage (default: {DEFAULT_MAD_MT})')
parser.add_argument('--mt-threshold', type=float, default=DEFAULT_MT_THRESHOLD, help=f'Hard threshold for mitochondrial percentage (default: {DEFAULT_MT_THRESHOLD})')
parser.add_argument('--min-cells', type=int, default=DEFAULT_MIN_CELLS, help=f'Minimum cells for gene filtering (default: {DEFAULT_MIN_CELLS})')
parser.add_argument('--mt-pattern', type=str, default=DEFAULT_MT_PATTERN, help=f'Comma-separated mitochondrial gene prefixes (default: "{DEFAULT_MT_PATTERN}")')
parser.add_argument('--ribo-pattern', type=str, default=DEFAULT_RIBO_PATTERN, help=f'Comma-separated ribosomal gene prefixes (default: "{DEFAULT_RIBO_PATTERN}")')
parser.add_argument('--hb-pattern', type=str, default=DEFAULT_HB_PATTERN, help=f'Hemoglobin gene regex pattern (default: "{DEFAULT_HB_PATTERN}")')

args = parser.parse_args()

# Verify input file exists
if not os.path.exists(args.input_file):
    print(f"\nError: File '{args.input_file}' not found!")
    sys.exit(1)

input_file = args.input_file
base_name = os.path.splitext(os.path.basename(input_file))[0]

# Set up output directory
if args.output_dir:
    output_dir = args.output_dir
else:
    output_dir = f"{base_name}_qc_results"

os.makedirs(output_dir, exist_ok=True)
print(f"\nOutput directory: {output_dir}")

# Display parameters
print(f"\nParameters:")
print(f"  MAD thresholds: counts={args.mad_counts}, genes={args.mad_genes}, MT%={args.mad_mt}")
print(f"  MT hard threshold: {args.mt_threshold}%")
print(f"  Min cells for gene filtering: {args.min_cells}")
print(f"  Gene patterns: MT={args.mt_pattern}, Ribo={args.ribo_pattern}")

# Load the data
print("\n[1/5] Loading data...")
file_ext = os.path.splitext(input_file)[1].lower()

if file_ext == '.h5ad':
    adata = ad.read_h5ad(input_file)
    print(f"Loaded .h5ad file: {adata.n_obs} cells × {adata.n_vars} genes")
elif file_ext == '.h5':
    adata = sc.read_10x_h5(input_file)
    print(f"Loaded 10X .h5 file: {adata.n_obs} cells × {adata.n_vars} genes")
    # Make variable names unique (10X data sometimes has duplicate gene names)
    adata.var_names_make_unique()
else:
    print(f"\nError: Unsupported file format '{file_ext}'. Expected .h5ad or .h5")
    sys.exit(1)

# Store original counts for comparison
n_cells_original = adata.n_obs
n_genes_original = adata.n_vars

# Calculate QC metrics
print("\n[2/5] Calculating QC metrics...")
calculate_qc_metrics(adata, mt_pattern=args.mt_pattern,
                     ribo_pattern=args.ribo_pattern,
                     hb_pattern=args.hb_pattern,
                     inplace=True)

print(f"  Found {adata.var['mt'].sum()} mitochondrial genes (pattern: {args.mt_pattern})")
print(f"  Found {adata.var['ribo'].sum()} ribosomal genes (pattern: {args.ribo_pattern})")
print(f"  Found {adata.var['hb'].sum()} hemoglobin genes (pattern: {args.hb_pattern})")

print_qc_summary(adata, label='QC Metrics Summary (before filtering)')

# Create before-filtering visualizations
print("\n[3/5] Creating QC visualizations...")
before_plot = os.path.join(output_dir, 'qc_metrics_before_filtering.png')
plot_qc_distributions(adata, before_plot, title='Quality Control Metrics - Before Filtering')
print(f"  Saved: {before_plot}")

# Apply MAD-based filtering
print("\n[4/5] Applying MAD-based filtering thresholds...")

# Detect outliers for each metric
adata.obs['outlier_counts'] = detect_outliers_mad(adata, 'total_counts', args.mad_counts)
adata.obs['outlier_genes'] = detect_outliers_mad(adata, 'n_genes_by_counts', args.mad_genes)
adata.obs['outlier_mt'] = detect_outliers_mad(adata, 'pct_counts_mt', args.mad_mt)

# Apply hard threshold for mitochondrial content
print(f"\n  Applying hard threshold for mitochondrial content (>{args.mt_threshold}%):")
high_mt_mask = apply_hard_threshold(adata, 'pct_counts_mt', args.mt_threshold, operator='>')

# Combine MT filters (MAD + hard threshold)
adata.obs['outlier_mt'] = adata.obs['outlier_mt'] | high_mt_mask

# Overall filtering decision
adata.obs['pass_qc'] = ~(
    adata.obs['outlier_counts'] |
    adata.obs['outlier_genes'] |
    adata.obs['outlier_mt']
)

print(f"\n  Total cells failing QC: {(~adata.obs['pass_qc']).sum()} ({(~adata.obs['pass_qc']).sum()/adata.n_obs*100:.2f}%)")
print(f"  Cells passing QC: {adata.obs['pass_qc'].sum()} ({adata.obs['pass_qc'].sum()/adata.n_obs*100:.2f}%)")

# Visualize filtering thresholds
outlier_masks = {
    'total_counts': adata.obs['outlier_counts'].values,
    'n_genes_by_counts': adata.obs['outlier_genes'].values,
    'pct_counts_mt': adata.obs['outlier_mt'].values
}

thresholds = {
    'total_counts': {'n_mads': args.mad_counts},
    'n_genes_by_counts': {'n_mads': args.mad_genes},
    'pct_counts_mt': {'n_mads': args.mad_mt, 'hard': args.mt_threshold}
}

threshold_plot = os.path.join(output_dir, 'qc_filtering_thresholds.png')
plot_filtering_thresholds(adata, outlier_masks, thresholds, threshold_plot)
print(f"\n  Saved: {threshold_plot}")

# Apply filtering
print("\n[5/5] Applying filters...")
adata_filtered = filter_cells(adata, adata.obs['pass_qc'].values, inplace=False)
print(f"  Cells after filtering: {adata_filtered.n_obs} (removed {n_cells_original - adata_filtered.n_obs})")

# Filter genes
print(f"\n  Filtering genes detected in <{args.min_cells} cells...")
filter_genes(adata_filtered, min_cells=args.min_cells, inplace=True)
print(f"  Genes after filtering: {adata_filtered.n_vars} (removed {n_genes_original - adata_filtered.n_vars})")

# Generate summary statistics
print("\n" + "=" * 80)
print("QC Summary")
print("=" * 80)

print("\nBefore filtering:")
print(f"  Cells: {n_cells_original}")
print(f"  Genes: {n_genes_original}")

print("\nAfter filtering:")
print(f"  Cells: {adata_filtered.n_obs} ({adata_filtered.n_obs/n_cells_original*100:.1f}% retained)")
print(f"  Genes: {adata_filtered.n_vars} ({adata_filtered.n_vars/n_genes_original*100:.1f}% retained)")

print_qc_summary(adata_filtered, label='\nFiltered data QC metrics')

# Create after-filtering visualizations
after_plot = os.path.join(output_dir, 'qc_metrics_after_filtering.png')
plot_qc_after_filtering(adata_filtered, after_plot)
print(f"\n  Saved: {after_plot}")

# Save filtered data
print("\nSaving filtered data...")
output_filtered = os.path.join(output_dir, f'{base_name}_filtered.h5ad')
output_with_qc = os.path.join(output_dir, f'{base_name}_with_qc.h5ad')
adata_filtered.write(output_filtered)
print(f"  Saved: {output_filtered}")

# Also save the unfiltered data with QC annotations
adata.write(output_with_qc)
print(f"  Saved: {output_with_qc} (original data with QC annotations)")

print("\n" + "=" * 80)
print("Quality Control Analysis Complete!")
print("=" * 80)
print(f"\nAll results saved to: {output_dir}/")
print("\nGenerated files:")
print("  1. qc_metrics_before_filtering.png - Initial QC visualizations")
print("  2. qc_filtering_thresholds.png - MAD-based threshold visualization")
print("  3. qc_metrics_after_filtering.png - Post-filtering QC visualizations")
print(f"  4. {base_name}_filtered.h5ad - Filtered dataset")
print(f"  5. {base_name}_with_qc.h5ad - Original dataset with QC annotations")
print("\nNext steps:")
print("  - Consider ambient RNA correction (SoupX)")
print("  - Consider doublet detection (scDblFinder)")
print("  - Proceed with normalization and downstream analysis")

#!/usr/bin/env python3
"""
Core utility functions for single-cell RNA-seq quality control.

This module provides building blocks for metrics calculation and filtering
while following scverse best practices from:
https://www.sc-best-practices.org/preprocessing_visualization/quality_control.html
"""

import anndata as ad
import scanpy as sc
import numpy as np
from scipy.stats import median_abs_deviation


def calculate_qc_metrics(adata, mt_pattern='mt-,MT-', ribo_pattern='Rpl,Rps,RPL,RPS',
                        hb_pattern='^Hb[^(p)]|^HB[^(P)]', inplace=True):
    """
    Calculate QC metrics for single-cell RNA-seq data.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix
    mt_pattern : str
        Comma-separated mitochondrial gene prefixes (default: 'mt-,MT-')
    ribo_pattern : str
        Comma-separated ribosomal gene prefixes (default: 'Rpl,Rps,RPL,RPS')
    hb_pattern : str
        Regex pattern for hemoglobin genes (default: '^Hb[^(p)]|^HB[^(P)]')
    inplace : bool
        Modify adata in place (default: True)

    Returns
    -------
    AnnData or None
        If inplace=False, returns modified AnnData. Otherwise modifies in place.
    """
    if not inplace:
        adata = adata.copy()

    # Identify gene categories
    mt_prefixes = tuple(mt_pattern.split(','))
    adata.var['mt'] = adata.var_names.str.startswith(mt_prefixes)

    ribo_prefixes = tuple(ribo_pattern.split(','))
    adata.var['ribo'] = adata.var_names.str.startswith(ribo_prefixes)

    adata.var['hb'] = adata.var_names.str.match(hb_pattern)

    # Calculate QC metrics
    sc.pp.calculate_qc_metrics(
        adata,
        qc_vars=['mt', 'ribo', 'hb'],
        percent_top=None,
        log1p=False,
        inplace=True
    )

    if not inplace:
        return adata


def detect_outliers_mad(adata, metric, n_mads, verbose=True):
    """
    Detect outliers using Median Absolute Deviation (MAD).

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix with QC metrics
    metric : str
        Column name in adata.obs to use for outlier detection
    n_mads : float
        Number of MADs to use as threshold
    verbose : bool
        Print outlier statistics (default: True)

    Returns
    -------
    np.ndarray
        Boolean mask where True indicates outliers
    """
    metric_values = adata.obs[metric]
    median = np.median(metric_values)
    mad = median_abs_deviation(metric_values)

    # Calculate bounds
    lower = median - n_mads * mad
    upper = median + n_mads * mad

    # Identify outliers
    outlier_mask = (metric_values < lower) | (metric_values > upper)

    if verbose:
        print(f"  {metric}:")
        print(f"    Median: {median:.2f}, MAD: {mad:.2f}")
        print(f"    Bounds: [{lower:.2f}, {upper:.2f}] ({n_mads} MADs)")
        print(f"    Outliers: {outlier_mask.sum()} cells ({outlier_mask.sum()/len(metric_values)*100:.2f}%)")

    return outlier_mask


def apply_hard_threshold(adata, metric, threshold, operator='>', verbose=True):
    """
    Apply a hard threshold filter.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix
    metric : str
        Column name in adata.obs to filter on
    threshold : float
        Threshold value
    operator : str
        Comparison operator: '>', '<', '>=', '<=' (default: '>')
    verbose : bool
        Print filtering statistics (default: True)

    Returns
    -------
    np.ndarray
        Boolean mask where True indicates cells to filter out
    """
    metric_values = adata.obs[metric]

    if operator == '>':
        mask = metric_values > threshold
    elif operator == '<':
        mask = metric_values < threshold
    elif operator == '>=':
        mask = metric_values >= threshold
    elif operator == '<=':
        mask = metric_values <= threshold
    else:
        raise ValueError(f"Invalid operator: {operator}. Use '>', '<', '>=', or '<='")

    if verbose:
        print(f"  {metric} {operator} {threshold}:")
        print(f"    Cells filtered: {mask.sum()} ({mask.sum()/len(metric_values)*100:.2f}%)")

    return mask


def filter_cells(adata, mask, inplace=False):
    """
    Filter cells based on a boolean mask.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix
    mask : np.ndarray or pd.Series
        Boolean mask where True indicates cells to KEEP
    inplace : bool
        Modify adata in place (default: False)

    Returns
    -------
    AnnData
        Filtered AnnData object
    """
    if inplace:
        # This is actually a bit tricky - AnnData doesn't support true inplace filtering
        # Return filtered copy which caller should reassign
        return adata[mask].copy()
    else:
        return adata[mask].copy()


def filter_genes(adata, min_cells=20, min_counts=None, inplace=True):
    """
    Filter genes based on detection thresholds.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix
    min_cells : int
        Minimum number of cells a gene must be detected in (default: 20)
    min_counts : int, optional
        Minimum total counts across all cells
    inplace : bool
        Modify adata in place (default: True)

    Returns
    -------
    AnnData or None
        If inplace=False, returns filtered AnnData
    """
    if not inplace:
        adata = adata.copy()

    if min_cells is not None:
        sc.pp.filter_genes(adata, min_cells=min_cells)

    if min_counts is not None:
        sc.pp.filter_genes(adata, min_counts=min_counts)

    if not inplace:
        return adata


def print_qc_summary(adata, label=''):
    """
    Print summary statistics for QC metrics.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix with QC metrics
    label : str
        Label to prepend to output (e.g., 'Before filtering', 'After filtering')
    """
    if label:
        print(f"\n{label}:")
    print(f"  Cells: {adata.n_obs}")
    print(f"  Genes: {adata.n_vars}")

    if 'total_counts' in adata.obs:
        print(f"  Mean counts per cell: {adata.obs['total_counts'].mean():.0f}")
        print(f"  Median counts per cell: {adata.obs['total_counts'].median():.0f}")

    if 'n_genes_by_counts' in adata.obs:
        print(f"  Mean genes per cell: {adata.obs['n_genes_by_counts'].mean():.0f}")
        print(f"  Median genes per cell: {adata.obs['n_genes_by_counts'].median():.0f}")

    if 'pct_counts_mt' in adata.obs:
        print(f"  Mean mitochondrial %: {adata.obs['pct_counts_mt'].mean():.2f}%")

    if 'pct_counts_ribo' in adata.obs:
        print(f"  Mean ribosomal %: {adata.obs['pct_counts_ribo'].mean():.2f}%")

#!/usr/bin/env python3
"""
Visualization functions for single-cell RNA-seq quality control.

This module provides plotting utilities for QC metrics and filtering thresholds.
"""

import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import median_abs_deviation


def plot_qc_distributions(adata, output_path, title='Quality Control Metrics'):
    """
    Create comprehensive QC distribution plots.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix with QC metrics
    output_path : str
        Path to save the figure
    title : str
        Figure title (default: 'Quality Control Metrics')
    """
    fig, axes = plt.subplots(3, 3, figsize=(15, 12))
    fig.suptitle(title, fontsize=16, y=0.995)

    # Row 1: Histograms
    axes[0, 0].hist(adata.obs['total_counts'], bins=100, color='steelblue', edgecolor='black')
    axes[0, 0].set_xlabel('Total counts per cell')
    axes[0, 0].set_ylabel('Number of cells')
    axes[0, 0].set_title('Distribution of Total Counts')
    axes[0, 0].axvline(adata.obs['total_counts'].median(), color='red', linestyle='--', label='Median')
    axes[0, 0].legend()

    axes[0, 1].hist(adata.obs['n_genes_by_counts'], bins=100, color='forestgreen', edgecolor='black')
    axes[0, 1].set_xlabel('Genes per cell')
    axes[0, 1].set_ylabel('Number of cells')
    axes[0, 1].set_title('Distribution of Detected Genes')
    axes[0, 1].axvline(adata.obs['n_genes_by_counts'].median(), color='red', linestyle='--', label='Median')
    axes[0, 1].legend()

    axes[0, 2].hist(adata.obs['pct_counts_mt'], bins=100, color='coral', edgecolor='black')
    axes[0, 2].set_xlabel('Mitochondrial %')
    axes[0, 2].set_ylabel('Number of cells')
    axes[0, 2].set_title('Distribution of Mitochondrial Content')
    axes[0, 2].axvline(adata.obs['pct_counts_mt'].median(), color='red', linestyle='--', label='Median')
    axes[0, 2].legend()

    # Row 2: Violin plots
    axes[1, 0].violinplot([adata.obs['total_counts']], positions=[0], showmeans=True, showmedians=True)
    axes[1, 0].set_ylabel('Total counts')
    axes[1, 0].set_title('Total Counts per Cell')
    axes[1, 0].set_xticks([])

    axes[1, 1].violinplot([adata.obs['n_genes_by_counts']], positions=[0], showmeans=True, showmedians=True)
    axes[1, 1].set_ylabel('Genes detected')
    axes[1, 1].set_title('Genes per Cell')
    axes[1, 1].set_xticks([])

    axes[1, 2].violinplot([adata.obs['pct_counts_mt']], positions=[0], showmeans=True, showmedians=True)
    axes[1, 2].set_ylabel('Mitochondrial %')
    axes[1, 2].set_title('Mitochondrial Content')
    axes[1, 2].set_xticks([])

    # Row 3: Scatter plots
    scatter1 = axes[2, 0].scatter(
        adata.obs['total_counts'],
        adata.obs['n_genes_by_counts'],
        c=adata.obs['pct_counts_mt'],
        cmap='viridis',
        alpha=0.5,
        s=10
    )
    axes[2, 0].set_xlabel('Total counts')
    axes[2, 0].set_ylabel('Genes detected')
    axes[2, 0].set_title('Counts vs Genes (colored by MT%)')
    plt.colorbar(scatter1, ax=axes[2, 0], label='MT %')

    axes[2, 1].scatter(
        adata.obs['total_counts'],
        adata.obs['pct_counts_mt'],
        alpha=0.5,
        s=10,
        color='coral'
    )
    axes[2, 1].set_xlabel('Total counts')
    axes[2, 1].set_ylabel('Mitochondrial %')
    axes[2, 1].set_title('Total Counts vs Mitochondrial %')

    axes[2, 2].scatter(
        adata.obs['n_genes_by_counts'],
        adata.obs['pct_counts_mt'],
        alpha=0.5,
        s=10,
        color='forestgreen'
    )
    axes[2, 2].set_xlabel('Genes detected')
    axes[2, 2].set_ylabel('Mitochondrial %')
    axes[2, 2].set_title('Genes vs Mitochondrial %')

    plt.tight_layout()
    plt.savefig(output_path, dpi=300, bbox_inches='tight')
    plt.close()


def plot_filtering_thresholds(adata, outlier_masks, thresholds, output_path):
    """
    Visualize filtering thresholds overlaid on distributions.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix with QC metrics
    outlier_masks : dict
        Dictionary mapping metric names to boolean outlier masks
        Example: {'total_counts': mask1, 'n_genes_by_counts': mask2, 'pct_counts_mt': mask3}
    thresholds : dict
        Dictionary with threshold information for each metric
        Example: {'total_counts': {'n_mads': 5}, 'pct_counts_mt': {'n_mads': 3, 'hard': 8}}
    output_path : str
        Path to save the figure
    """
    fig, axes = plt.subplots(1, 3, figsize=(15, 4))
    fig.suptitle('MAD-Based Filtering Thresholds', fontsize=16)

    # Helper function to plot with thresholds
    def plot_with_threshold(ax, metric, outlier_mask, n_mads, hard_threshold=None):
        data = adata.obs[metric]
        median = np.median(data)
        mad = median_abs_deviation(data)
        lower = median - n_mads * mad
        upper = median + n_mads * mad

        ax.hist(data[~outlier_mask], bins=100, alpha=0.7, label='Pass QC', color='steelblue')
        ax.hist(data[outlier_mask], bins=100, alpha=0.7, label='Fail QC', color='coral')
        ax.axvline(lower, color='red', linestyle='--', linewidth=2, label=f'Thresholds ({n_mads} MADs)')
        ax.axvline(upper, color='red', linestyle='--', linewidth=2)

        if hard_threshold is not None:
            ax.axvline(hard_threshold, color='darkred', linestyle=':', linewidth=2,
                      label=f'Hard threshold ({hard_threshold})')

        ax.set_xlabel(metric.replace('_', ' ').title())
        ax.set_ylabel('Number of cells')
        ax.legend()

    # Plot each metric
    metrics = [
        ('total_counts', 'Total Counts'),
        ('n_genes_by_counts', 'Genes Detected'),
        ('pct_counts_mt', 'Mitochondrial %')
    ]

    for idx, (metric, label) in enumerate(metrics):
        if metric in outlier_masks and metric in thresholds:
            hard = thresholds[metric].get('hard', None)
            plot_with_threshold(axes[idx], metric, outlier_masks[metric],
                              thresholds[metric]['n_mads'], hard)

    plt.tight_layout()
    plt.savefig(output_path, dpi=300, bbox_inches='tight')
    plt.close()


def plot_qc_after_filtering(adata, output_path):
    """
    Create QC plots for filtered data (simplified version without outlier overlay).

    Parameters
    ----------
    adata : AnnData
        Filtered annotated data matrix with QC metrics
    output_path : str
        Path to save the figure
    """
    fig, axes = plt.subplots(2, 3, figsize=(15, 8))
    fig.suptitle('Quality Control Metrics - After Filtering', fontsize=16, y=0.995)

    # Row 1: Histograms
    axes[0, 0].hist(adata.obs['total_counts'], bins=100, color='steelblue', edgecolor='black')
    axes[0, 0].set_xlabel('Total counts per cell')
    axes[0, 0].set_ylabel('Number of cells')
    axes[0, 0].set_title('Distribution of Total Counts')

    axes[0, 1].hist(adata.obs['n_genes_by_counts'], bins=100, color='forestgreen', edgecolor='black')
    axes[0, 1].set_xlabel('Genes per cell')
    axes[0, 1].set_ylabel('Number of cells')
    axes[0, 1].set_title('Distribution of Detected Genes')

    axes[0, 2].hist(adata.obs['pct_counts_mt'], bins=100, color='coral', edgecolor='black')
    axes[0, 2].set_xlabel('Mitochondrial %')
    axes[0, 2].set_ylabel('Number of cells')
    axes[0, 2].set_title('Distribution of Mitochondrial Content')

    # Row 2: Scatter plots
    scatter1 = axes[1, 0].scatter(
        adata.obs['total_counts'],
        adata.obs['n_genes_by_counts'],
        c=adata.obs['pct_counts_mt'],
        cmap='viridis',
        alpha=0.5,
        s=10
    )
    axes[1, 0].set_xlabel('Total counts')
    axes[1, 0].set_ylabel('Genes detected')
    axes[1, 0].set_title('Counts vs Genes (colored by MT%)')
    plt.colorbar(scatter1, ax=axes[1, 0], label='MT %')

    axes[1, 1].scatter(
        adata.obs['total_counts'],
        adata.obs['pct_counts_mt'],
        alpha=0.5,
        s=10,
        color='coral'
    )
    axes[1, 1].set_xlabel('Total counts')
    axes[1, 1].set_ylabel('Mitochondrial %')
    axes[1, 1].set_title('Total Counts vs Mitochondrial %')

    axes[1, 2].scatter(
        adata.obs['n_genes_by_counts'],
        adata.obs['pct_counts_mt'],
        alpha=0.5,
        s=10,
        color='forestgreen'
    )
    axes[1, 2].set_xlabel('Genes detected')
    axes[1, 2].set_ylabel('Mitochondrial %')
    axes[1, 2].set_title('Genes vs Mitochondrial %')

    plt.tight_layout()
    plt.savefig(output_path, dpi=300, bbox_inches='tight')
    plt.close()