torchcell

TorchCell overview: literature and public databases feed an ontology and a knowledge graph (a); reference data and experiment data (b); persistent entities, the encoder, perturbation, and decoder path, and contingent observations (c)

Documentation: https://mjvolk3.github.io/torchcell/

Database: https://torchcell-database.ncsa.illinois.edu:7473/browser/ (Neo4j Browser over the served TorchCell knowledge graph)

Database releases and compatibility: https://mjvolk3.github.io/torchcell/database/compatibility.html

Datasets: https://mjvolk3.github.io/torchcell/datasets/index.html

Dataset downloads (the tc-data API): https://mjvolk3.github.io/torchcell/guide/downloads.html

Download a dataset

Built datasets are served as versioned archives (the records LMDB plus its build manifest) by the tc-data endpoint on the database host, with Swagger at /docs. Each page below is one supported query over the knowledge graph and bundles the datasets it returns: what the experiments measured, one stored record each, the value distributions, the query, and the download commands.

Page	Datasets (records)
Gene essentiality and single-mutant fitness	Gene essentiality, SGD (1,329) Single-mutant fitness, Costanzo 2016 (20,484)
Amino acids and betaxanthin	Amino acids, Mulleder 2016 (4,678) Amine peaks, Cooper 2010 (4,313) Betaxanthin, Cachera 2023 (4,719)

With an endpoint URL and a key (see Downloading datasets), a loader fetches its archive instead of building. Export the two variables in the shell:

export TC_DATA_URL=http://torchcell-database.ncsa.illinois.edu:8724
export TC_DATA_API_KEY=<your key>

or put the same two lines, without export, in a .env file in your project and load it before constructing a loader:

from dotenv import load_dotenv

load_dotenv()  # reads the .env beside this script or in a parent directory

from torchcell.datasets.scerevisiae.mulleder2016 import AminoAcidMulleder2016Dataset

dataset = AminoAcidMulleder2016Dataset(root="data/torchcell/amino_acid_mulleder2016")

The loader reads the two variables from the process environment and does not read .env itself. With TC_DATA_URL unset it builds from the publisher's files instead.

The full collection served by the knowledge graph (51 datasets, 52.7 million experiments at release 2026.09.21) is listed on the Datasets page.

Metadata

Release files for torchcell 1.8.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for torchcell 1.8.2
File	Size	Uploaded
torchcell-1.8.2.tar.gz	4.7 MB	Oct 17, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for torchcell 1.8.2
File	Interpreter	ABI	Platform	Reset
torchcell-1.8.2-py3-none-any.whl 5.3 MB Oct 17, 2026	Python 3	none	any	Details

Total release size: 10.1 MB

Release files / torchcell-1.8.2.tar.gz

Download URL	torchcell-1.8.2.tar.gz
Size	4.7 MB
Tags	Source
SHA-256 checksum How to use checksums	`947179e4fc119c8c50de72873119ff54f7c7b254e2c3d3ca8adbdb65957dc7f9`
BLAKE2b-256 checksum How to use checksums	`eb89804ade38f05b081887a4aec657b8553725002d18ce93491984bdebfc74dc`
Upload date	Oct 17, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/Mjvolk3/torchcell
Publishing commit: github.com/Mjvolk3/torchcell/tree/a64164832ee666b77c4b64ac23fcacb772da0c2a

Workflow

Publishing configuration: github.com/Mjvolk3/torchcell/blob/a64164832ee666b77c4b64ac23fcacb772da0c2a/.github/workflows/semantic-release.yaml
Publishing logs: github.com/Mjvolk3/torchcell/actions/runs/39012701718/attempts/1

Artifact

Subject: torchcell-1.8.2.tar.gz
SHA-256 checksum: 947179e4fc119c8c50de72873119ff54f7c7b254e2c3d3ca8adbdb65957dc7f9 Verifying attestations

Release files / torchcell-1.8.2-py3-none-any.whl

Download URL	torchcell-1.8.2-py3-none-any.whl
Size	5.3 MB
Tags	Python 3
SHA-256 checksum How to use checksums	`0de987d6354f309dacf27e7b4c60c830ddf43fdf0dd08b686066ea4bfd119ad8`
BLAKE2b-256 checksum How to use checksums	`c3f6f571e65e250f916a6e3c8cb10f57ade2f99fb33fc721fcc39e44d125b092`
Upload date	Oct 17, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/Mjvolk3/torchcell
Publishing commit: github.com/Mjvolk3/torchcell/tree/a64164832ee666b77c4b64ac23fcacb772da0c2a

Workflow

Publishing configuration: github.com/Mjvolk3/torchcell/blob/a64164832ee666b77c4b64ac23fcacb772da0c2a/.github/workflows/semantic-release.yaml
Publishing logs: github.com/Mjvolk3/torchcell/actions/runs/39012701718/attempts/1

Artifact

Subject: torchcell-1.8.2-py3-none-any.whl
SHA-256 checksum: 0de987d6354f309dacf27e7b4c60c830ddf43fdf0dd08b686066ea4bfd119ad8 Verifying attestations