SIGMA (sigma-omics)

SIGMA is a spectral interface graph model for quantitative metabolic field analysis of tumor interfaces. It constructs a spatial Gaussian graph from tissue coordinates, transforms tumor/non-tumor annotations into an interface-aware prior field, and decomposes spatial metabolomics representations into low-frequency tissue background and high-frequency boundary-associated residual components. A spectral residual graph convolutional network then learns boundary-enriched metabolic fields under weak pathological supervision. Matched spatial transcriptomic profiles can be used for auxiliary alignment and biological interpretation but are not required for the separate SM-only weak-anchor workflow.

SIGMA returns a continuous tumor-associated field, an inferred boundary, and a signed-distance coordinate for ranking and quantifying interface-associated metabolic features. The scientific definitions and default parameters are preserved from the HBC515 and HCC reference implementations.

Install

After the first PyPI release:

pip install sigma-omics

The distribution name is sigma-omics; the Python import remains sigma_spatial.

Install from source

pip install -e .

Quick start

import scanpy as sc
from sigma_spatial import run_sigma

adata = sc.read_h5ad("sample.h5ad")
result = run_sigma(
    adata,
    anchor_key="sigma_anchor",        # 1=tumor, 0=non-tumor, NaN=unknown
    representation_key="X_harmony",  # validated auxiliary representation
    random_state=0,
)

# Main outputs
result.obs[["sigma_region_probability", "sigma_boundary", "sigma_d_signed"]]

For SM-only data, use the separately validated HCC-derived entry point:

from sigma_spatial import run_sigma_weak_anchor

result = run_sigma_weak_anchor(
    adata,
    anchor_key="sigma_anchor",
    already_log=True,
    random_state=0,
)

This path preserves the executed HCC P1/P4 loss without introducing an RNA target. See docs/input_format.md and docs/output_schema.md.

Scope

The package should contain reusable SIGMA computation only. Manuscript-specific simulation, benchmarking, GO enrichment, plotting, and sample-specific analyses should live under examples/ or a separate analysis repository.

Project links

Data verified by PyPI on Aug 17, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.2.1)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for Bingxue from gravatar.com Bingxue

Credits

Author: Bingxue Du

GitHub Statistics

Data verified by PyPI on Aug 17, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT

Requires

Python >=3.10

Provides Extra

dev plot

Tags

graph neural network mass spectrometry imaging spatial metabolomics spatial omics tumor boundary

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sigma_omics-0.1.1.tar.gz (27.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sigma_omics-0.1.1-py3-none-any.whl (22.5 kB view details)

Uploaded Python 3

File details

Details for the file sigma_omics-0.1.1.tar.gz.

File metadata

  • Download URL: sigma_omics-0.1.1.tar.gz
  • Upload date:
  • Size: 27.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for sigma_omics-0.1.1.tar.gz
Algorithm Hash digest
SHA256 f7a1049ce6d9c28ea7fec64b8e54caa9e542940bbceed638f1998caf353f0bb0
MD5 ae8080210e0700242705372fcf944a60
BLAKE2b-256 4e69e838a909a2d806f73cd075bc165d27c2e133cc0618a632d16a1512ed7cab

See more details on using hashes here.

Provenance

The following attestation bundles were made for sigma_omics-0.1.1.tar.gz:

Publisher: publish.yml on Elsa-bingxue/SIGMA

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file sigma_omics-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: sigma_omics-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 22.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for sigma_omics-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 be512386322d0e68390f15c54d48c15b9a7cc86abd642a0e24b070e2053f9ce2
MD5 e3df08ff316090b327708bb10c71b4a4
BLAKE2b-256 ab1a54a9af62bdb8533f51057e6e91ae1323bbe2b65db2483579ee9ae4cf718f

See more details on using hashes here.

Provenance

The following attestation bundles were made for sigma_omics-0.1.1-py3-none-any.whl:

Publisher: publish.yml on Elsa-bingxue/SIGMA

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.2.1

2 files

0.2.0

2 files

This release

0.1.1 This release

2 files

Pre-release

0.1.0a1

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page