tcren

tcren — structure-based prediction of TCR–epitope recognition

python

TCRen predicts which epitopes a T-cell receptor recognises from a single TCR–peptide–MHC structure (experimental or modelled). It extracts the TCR–peptide contact map and scores every candidate peptide with a residue-level statistical potential derived from contact preferences in TCR:pMHC crystal structures — answering not "what fancy complex can a model draw?" but "is this binding physically plausible?".

This is a documented, tested, CLI-driven Python library. TCR chains are annotated with the sibling arda; MHC chains are mapped and the groove partitioned against a curated reference; structures are oriented into one canonical frame; and the original contact maps, potential, and scores are reproduced numerically (validated against committed oracles to floating-point precision).

While the original tcren focused on TCR:peptide contacts, the new version brings in features to score TCR:MHC and peptide:MHC interactions, required to get full picture of TCR:pMHC binding mechanics and estimate ddG values.

Install

pip install tcren          # from PyPI — binary wheels ship the C++ extension; pulls in arda-mapper

For development (editable install, conda env with the build toolchain, and the reference data fetched into data/):

bash setup.sh              # creates the `tcren` conda env, installs arda + tcren, fetches data/
conda activate tcren

tcren ships a small pybind11/C++ extension (tcren._align) for the MHC-pseudosequence fitting-alignment hot path, built on install by scikit-build-core (a Biopython fallback runs if it is not built). TCR annotation is provided by arda, a runtime dependency published to PyPI as arda-mapper (it imports as arda); pip/setup.sh pull it automatically. setup.sh also runs tcren fetch-data to populate data/ with the reference structure sets (Native2026, Canonical2026) used by orient/superimpose (set TCREN_NO_FETCH=1 to skip).

Command line

# Full pipeline: annotate -> superimpose -> resmarkup / canonical Cα / contacts -> per-interface
# energies (TCRen for TCR↔peptide, MJ for TCR↔MHC and peptide↔MHC) + total
tcren pipeline -s complex.pdb -o scores.csv

# Configurable per-interface potential: swap a bundled name (tcren|mj|keskin), a CSV, or
# None for any interface; default reproduces the built-in per-interface families exactly.
tcren pipeline -s complex.pdb -o scores.csv --tcr-mhc-potential keskin

# Opt-in TCR framework regions: --regions {all,cdr,cdr+fr} chooses which TCR regions
# contribute on the TCR side (cdr = CDR1-3 only; cdr+fr adds FR1-3; all = unfiltered, default).
tcren score -s complex.pdb -c candidates.txt -o ranked.csv --regions cdr+fr

# Percentile-rank the native (or candidate) peptide's TCRen energy against a random pMHC
# background — small rank_pct = the peptide scores among the best binders.
tcren rank -s complex.pdb -o rank.csv

# Fast ΔΔG of peptide point mutations (virtual-matrix path: no atoms move, no re-docking).
tcren ddg -s complex.pdb -o ddg.csv

# Binder vs non-binder P(binder) from AF-orthogonal interface geometry + the CDR1/2-vs-CDR3a
# TCRen term — ranks candidate TCRs against a fixed pMHC, beating AlphaFold/TCRmodel2 confidence
# (denoised AUC 0.928 vs 0.872) with no external tool. See tcren.binder.binder_score.
tcren binder -s complex.pdb -o binder.csv

# End-to-end candidate-epitope scoring from a structure
tcren score -s complex.pdb -c candidates.txt -o ranked.csv

# Substitute a peptide and refine its pose (knowledge-based MC scored by the DOPE atom-level
# statistical potential — independent of the TCRen/MJ scoring potentials, restrained to the input).
# Not physics relaxation — use Rosetta FlexPepDock for that.
tcren refine -s complex.pdb -o refined/ --substitute KQWLVWLFL

# Structures: any of .pdb / .cif / .pdb.gz / .cif.gz, a directory, or a .tar.gz batch
tcren contacts -s batch.tar.gz -o contacts.csv --interface tcr_peptide

# Per-residue markup: TCR (CDR/FR) + MHC groove (helix/floor) + peptide in one table.
# --regions all|tcr|mhc|peptide filters; --pseudo also marks NetMHCpan groove residues (MPS).
tcren annotate -s complex.cif.gz -o markup.csv --regions mhc --pseudo

# Superimpose structure(s) onto the canonical frame, by MHC, against the canonical database
# (data/Canonical2026, fetched at install). Detects MHC class + species and averages the
# superposition over every database structure of that class/species. Chains -> A=Vα B=Vβ
# C=peptide D=MHCα E=MHCβ/β2m. -s takes a file / directory / .tar.gz / glob; -o is a directory,
# or a single structure file (one input) whose extension must match --mmCIF/--compress; -t threads.
tcren superimpose -s complex.pdb -o oriented.pdb           # single file
tcren superimpose -s 'data/*.pdb' -o oriented/ -t 8        # glob -> directory, threaded

# Build a canonical database from native complexes (how Canonical2026 is produced). Annotation
# is one batched mmseqs call; -t threads only the structural alignment + write.
tcren orient -s data/Native2026 -o data/Canonical2026 -t 8

# Structure outputs are plain .pdb by default; add --mmCIF for .cif and --compress for .gz.
tcren superimpose -s complex.pdb -o oriented/ --mmCIF --compress   # -> oriented/<id>.cif.gz

# Fetch recent TCR-pMHC structures from RCSB -> data/pdb_recent (mmCIF .cif.gz, 5-chain validated)
tcren fetch-recent --discover --after 2024-01-01

# Build the MHC reference once (IMGT/HLA + mouse H-2; cached, not committed)
tcren build-mhc-ref

tcren info
tcren --install-completion        # shell tab-completion (bash/zsh/fish)

tcren orient and tcren superimpose need the reference sets in data/ (Native2026, Canonical2026); setup.sh fetches them at install via tcren fetch-data (re-run it any time).

Library

from tcren import run_pipeline, parse_structure, import_structure, ContactMap, score_peptides
from tcren.annotation import classify_chains
from tcren.potential import tcren

# One call: annotate -> superimpose -> contacts -> per-interface energies + total
res = run_pipeline("complex.pdb")              # res.scores, res.markup, res.contacts, res.oriented

# Oracle facade: one structure -> a bundle of ready-to-tabulate frames for the paper
# notebooks (scores, percentile rank, ΔΔG alanine scan, markup, contacts). Configurable
# per-interface potentials and TCR-region selection are forwarded to every milestone.
from tcren import summarize_structure
bundle = summarize_structure("complex.pdb", alanine=True)   # bundle["scores"], ["rank"], ["ddg"], …

# …or the individual steps:
s = parse_structure("complex.pdb.gz")          # also .cif/.cif.gz; import_structure trims the C-gene
classify_chains(s, organism="human")           # TRA/TRB via arda, peptide, MHC
cm = ContactMap.from_structure(s)              # 5 Å contacts + interface partitioning
ranked = score_peptides(cm, ["KQWLVWLFL", "RLLHPHHPL"], tcren())

Batch inputs, gzip, archives

from tcren.structure import iter_structures
for pdb_id, structure in iter_structures("batch.tar.gz"):   # file | directory | .tar.gz
    classify_chains(structure, organism="human")
    ...

Canonical orientation, contacts, docking geometry

from tcren.mhc import annotate_mhc
from tcren.orient import canonicalize_structure, superimpose, docking_angles
from tcren.contacts import multi_contacts, ContactDefinition

annotate_mhc(s)
oriented, info = canonicalize_structure(s)     # frame: z=MHC→TCR, y=peptide, x=thin; chains A–E
oriented, info = superimpose(s)                # orient onto data/Canonical2026 by MHC (class+species ensemble)
layers = multi_contacts(s, ContactDefinition(d1=5, d2=8, d3=12))   # heavy-atom / Cβ / Cα
d = docking_angles(s)                          # crossing (~20–70° αβ) + incident angle

2D complementarity maps & region-pair contacts

from tcren.project2d import (project_structure, residue_markup_table, contacts_table,
                             region_pair_summary)
from tcren.viz import render_complementarity_map, view_pocket_cdr

proj = project_structure(s)                                   # canonical groove plane
svg  = render_complementarity_map(residue_markup_table(s, proj),
                                  contacts=contacts_table(s, threshold=5.0))
region_pair_summary(s, kind="closest")        # contacts per region pair + bond types (cb/ca too)
view_pocket_cdr(s).show()                      # interactive 3D pocket + CDR overlay (py3Dmol)

Data

Structures live in the Hugging Face dataset isalgo/tcren_structures, all gzipped:

folder	contents
`Native2022`	the 2022 paper set (oracle)
`Native2026`	the comprehensive 2026 TCR:pMHC set the current potential is derived from
`Canonical2026`	`Native2026` re-oriented into the canonical frame (`tcren orient`)

tcren reads .pdb/.cif/.pdb.gz/.cif.gz and .tar.gz batches; an installed library lazily fetches the canonical reference structures from the Hub when orienting a new complex. The root data/ holds Native2026 (+ Canonical2026, gitignored, fetched on demand), PDB_date.tsv, orient_metadata.json, and TCRen_potential.csv — the current potential derived from the Native2026 set (use it with tcren score -p data/TCRen_potential.csv).

Notebooks

Runnable examples under notebooks/ (rendered in the docs):

complementarity_map_2d — 2D interface maps, multiple structural + map views of 1ao7
contact_thresholds_and_bondtypes — region-pair contact counts (closest/Cβ/Cα) + bond types
canonical_frame_figures — canonical-frame QC across the Native2026 set
pymol_canonical_figures — ray-traced PyMOL panels (overlay, groove, interface) by class/species
mhc_pseudosequence_mps — NetMHCpan MHC pseudosequence (MPS) residues vs. peptide contacts
example_gil_a02_rs_motif — GILGFVFTL/HLA-A*02 and the public CDR3β Arg–Ser motif
natcompsci2022/ — full reproduction of the Nat Comput Sci 2022 analyses

Performance

Per-stage timings on a TCR-pMHC complex (1ao7), Apple M3, single thread (RUN_BENCHMARK=1 pytest -k benchmark -s to reproduce):

stage	time	notes
parse a gzipped structure	~19 ms	`.pdb.gz` / `.cif.gz`
contact map (5 Å, cKDTree)	~9 ms	per structure
score 1000 candidate peptides	~8 ms	~8 µs/peptide (vectorised)
annotate (TCR + MHC), batched	~213 ms/structure	one mmseqs2 call for the whole set; vs ~1.5 s/structure unbatched
peak RSS, single-structure pipeline	~195 MB

Annotation is the only network/compute-heavy step and is always batched (one mmseqs2 search over all chains; mmseqs2 parallelises internally — never per-structure, never Python-threaded). Threads are used only for the embarrassingly-parallel, mmseqs-free stages (structural alignment, write, rendering): tcren orient -t N.

Tests

pytest -m "not slow"          # unit + fast regression (the CI gate)
pytest                        # add the arda/mmseqs-backed regression tests
RUN_BENCHMARK=1 pytest -k benchmark -s

Methods appendix

The coordinate-level extensions — backbone-preserving peptide substitution and the potential-guided Monte-Carlo refinement kernel (energy function, the restraint-necessity argument, sampler, and citations) — are written up in the technical appendix appendix/tcren.tex (built with make -C appendix → appendix/tcren.pdf).

Citing

TCRen is free for academic and non-commercial use. If you use it, please cite our latest Nature Computational Science 2024 paper:

Karnaukhov VK, Shcherbinin DS, Chugunov AO, Chudakov DM, Efremov RG, Zvyagin IV, Shugay M. Structure-based prediction of T cell receptor recognition of unseen epitopes using TCRen. Nat Comput Sci. 2024 Jul;4(7):510-521. doi: 10.1038/s43588-024-00653-0. Epub 2024 Jul 10. PMID: 38987378.

Download files

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

Source Distribution

tcren-2.1.1.tar.gz (1.2 MB view details)

Uploaded Jul 2, 2026 Source

Built Distributions

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

tcren-2.1.1-cp313-cp313-win_amd64.whl (1.5 MB view details)

Uploaded Jul 2, 2026 CPython 3.13Windows x86-64

tcren-2.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB view details)

Uploaded Jul 2, 2026 CPython 3.13manylinux: glibc 2.17+ x86-64

tcren-2.1.1-cp313-cp313-macosx_11_0_arm64.whl (1.4 MB view details)

Uploaded Jul 2, 2026 CPython 3.13macOS 11.0+ ARM64

tcren-2.1.1-cp312-cp312-win_amd64.whl (1.5 MB view details)

Uploaded Jul 2, 2026 CPython 3.12Windows x86-64

tcren-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB view details)

Uploaded Jul 2, 2026 CPython 3.12manylinux: glibc 2.17+ x86-64

tcren-2.1.1-cp312-cp312-macosx_11_0_arm64.whl (1.4 MB view details)

Uploaded Jul 2, 2026 CPython 3.12macOS 11.0+ ARM64

tcren-2.1.1-cp311-cp311-win_amd64.whl (1.5 MB view details)

Uploaded Jul 2, 2026 CPython 3.11Windows x86-64

tcren-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB view details)

Uploaded Jul 2, 2026 CPython 3.11manylinux: glibc 2.17+ x86-64

tcren-2.1.1-cp311-cp311-macosx_11_0_arm64.whl (1.4 MB view details)

Uploaded Jul 2, 2026 CPython 3.11macOS 11.0+ ARM64

tcren-2.1.1-cp310-cp310-win_amd64.whl (1.5 MB view details)

Uploaded Jul 2, 2026 CPython 3.10Windows x86-64

tcren-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB view details)

Uploaded Jul 2, 2026 CPython 3.10manylinux: glibc 2.17+ x86-64

tcren-2.1.1-cp310-cp310-macosx_11_0_arm64.whl (1.4 MB view details)

Uploaded Jul 2, 2026 CPython 3.10macOS 11.0+ ARM64

File details

Details for the file tcren-2.1.1.tar.gz.

File metadata

Download URL: tcren-2.1.1.tar.gz
Upload date: Jul 2, 2026
Size: 1.2 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1.tar.gz
Algorithm	Hash digest
SHA256	`8ddda4bdeb4d117adc1a6ec053d07f53363aeb45fccb161845f5200fbbe8bb20`
MD5	`b0f323e4610c8004e6889cf994b6a8ec`
BLAKE2b-256	`255ec337a317c7cbddfb3c8dfe90a487e20634f93f4cd3dd6ced05f0715e28b2`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1.tar.gz:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1.tar.gz
- Subject digest: 8ddda4bdeb4d117adc1a6ec053d07f53363aeb45fccb161845f5200fbbe8bb20
- Sigstore transparency entry: 2044791589
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp313-cp313-win_amd64.whl.

File metadata

Download URL: tcren-2.1.1-cp313-cp313-win_amd64.whl
Upload date: Jul 2, 2026
Size: 1.5 MB
Tags: CPython 3.13, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp313-cp313-win_amd64.whl
Algorithm	Hash digest
SHA256	`4db1b1dd144526f223a29257fd242b49083a110bd0671ab5bd9b23eb01bec15f`
MD5	`bd067e00429352e78df6ecf20439466a`
BLAKE2b-256	`bd4d872af5878792c87b89146b80a3fb7769285f941ac991ae099b506600440a`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp313-cp313-win_amd64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp313-cp313-win_amd64.whl
- Subject digest: 4db1b1dd144526f223a29257fd242b49083a110bd0671ab5bd9b23eb01bec15f
- Sigstore transparency entry: 2044792425
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: tcren-2.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Jul 2, 2026
Size: 1.6 MB
Tags: CPython 3.13, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`553de88787fe0aa82151cb62150bffba326c404ef01a6ac197a018b75b6adf07`
MD5	`4f5523614ab6563e6dae335fd16bb1ae`
BLAKE2b-256	`58cd34848e8c464df7df1a98115120d36599abe53829f73038818966c92ab0ba`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 553de88787fe0aa82151cb62150bffba326c404ef01a6ac197a018b75b6adf07
- Sigstore transparency entry: 2044792627
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp313-cp313-macosx_11_0_arm64.whl.

File metadata

Download URL: tcren-2.1.1-cp313-cp313-macosx_11_0_arm64.whl
Upload date: Jul 2, 2026
Size: 1.4 MB
Tags: CPython 3.13, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp313-cp313-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`ff7066f0e979c3b97701a2dcafd828d662e3c01dd1b50abd033568037e63a3ab`
MD5	`e70a99c7782d0604a18864587dfef74e`
BLAKE2b-256	`36fd25a5475e7250aad6bd8471f9036d39077ccbfcc2cd89216c5ba8ecb5d59c`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp313-cp313-macosx_11_0_arm64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp313-cp313-macosx_11_0_arm64.whl
- Subject digest: ff7066f0e979c3b97701a2dcafd828d662e3c01dd1b50abd033568037e63a3ab
- Sigstore transparency entry: 2044791835
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp312-cp312-win_amd64.whl.

File metadata

Download URL: tcren-2.1.1-cp312-cp312-win_amd64.whl
Upload date: Jul 2, 2026
Size: 1.5 MB
Tags: CPython 3.12, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp312-cp312-win_amd64.whl
Algorithm	Hash digest
SHA256	`8cadaf3cbef2775dfe5d72b0af21c0be3abadf46a85ed3b564b9fe00bfbfd8ee`
MD5	`e794aa4003e0245b1c54ab698cf390d1`
BLAKE2b-256	`b3e350a99e8c434476d335e8e9d04ed7cce2cc6f347934777e1788cc4f9f12da`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp312-cp312-win_amd64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp312-cp312-win_amd64.whl
- Subject digest: 8cadaf3cbef2775dfe5d72b0af21c0be3abadf46a85ed3b564b9fe00bfbfd8ee
- Sigstore transparency entry: 2044791646
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: tcren-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Jul 2, 2026
Size: 1.6 MB
Tags: CPython 3.12, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`5e16d918a258b63ab45d4c3ed693ed8c9b1df291816d2c25d12350e1e8af6120`
MD5	`7b59420cea41c31c25348b840c851a0b`
BLAKE2b-256	`ae8ece4c04caeede063d29411e9ae7a16eda2f8101d02c3992d23a4cb51309e8`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 5e16d918a258b63ab45d4c3ed693ed8c9b1df291816d2c25d12350e1e8af6120
- Sigstore transparency entry: 2044792730
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp312-cp312-macosx_11_0_arm64.whl.

File metadata

Download URL: tcren-2.1.1-cp312-cp312-macosx_11_0_arm64.whl
Upload date: Jul 2, 2026
Size: 1.4 MB
Tags: CPython 3.12, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp312-cp312-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`560a2feaf46b36b2c33cbff28b8fa19bc8227af8a84f04625ce851a1a0c2f8fc`
MD5	`a2636247d1c57edcc7447baa2aaaeaa6`
BLAKE2b-256	`e669e6002c610535ca0f4999f5b35bcffffe604c93810722a54c5da345915a76`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp312-cp312-macosx_11_0_arm64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp312-cp312-macosx_11_0_arm64.whl
- Subject digest: 560a2feaf46b36b2c33cbff28b8fa19bc8227af8a84f04625ce851a1a0c2f8fc
- Sigstore transparency entry: 2044792959
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp311-cp311-win_amd64.whl.

File metadata

Download URL: tcren-2.1.1-cp311-cp311-win_amd64.whl
Upload date: Jul 2, 2026
Size: 1.5 MB
Tags: CPython 3.11, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp311-cp311-win_amd64.whl
Algorithm	Hash digest
SHA256	`709b58c396be6fc5230e623175057b091cca801bdf280585e9d641db8e6ac8ef`
MD5	`db41363d78787bbf2e42962e559f7666`
BLAKE2b-256	`82bb585a92c92a58cdb2d812e7b396faf70738a30f217d9c13f590a9e84b3f1a`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp311-cp311-win_amd64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp311-cp311-win_amd64.whl
- Subject digest: 709b58c396be6fc5230e623175057b091cca801bdf280585e9d641db8e6ac8ef
- Sigstore transparency entry: 2044792493
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: tcren-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Jul 2, 2026
Size: 1.6 MB
Tags: CPython 3.11, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`0565b6690712ae6e191484b1bf27d58f5395cb2571148c478195c46477665496`
MD5	`e2314c4eeebd6cedf32e50fb523e32d2`
BLAKE2b-256	`32731ffdcb491261a1257d50583e2e48d661ca116808917979e60e81761f6319`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 0565b6690712ae6e191484b1bf27d58f5395cb2571148c478195c46477665496
- Sigstore transparency entry: 2044792147
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp311-cp311-macosx_11_0_arm64.whl.

File metadata

Download URL: tcren-2.1.1-cp311-cp311-macosx_11_0_arm64.whl
Upload date: Jul 2, 2026
Size: 1.4 MB
Tags: CPython 3.11, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp311-cp311-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`2fca6b32aef9aa94ad7336ae121a2403484c6a03be43d11f90f383bdae4f814e`
MD5	`b64fef2330e0ec9f756df0c5481a0a51`
BLAKE2b-256	`f2c2641bb065903d409a55c2296f963affb7fd626cf4b55b03289ba2d7eb4063`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp311-cp311-macosx_11_0_arm64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp311-cp311-macosx_11_0_arm64.whl
- Subject digest: 2fca6b32aef9aa94ad7336ae121a2403484c6a03be43d11f90f383bdae4f814e
- Sigstore transparency entry: 2044792784
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp310-cp310-win_amd64.whl.

File metadata

Download URL: tcren-2.1.1-cp310-cp310-win_amd64.whl
Upload date: Jul 2, 2026
Size: 1.5 MB
Tags: CPython 3.10, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp310-cp310-win_amd64.whl
Algorithm	Hash digest
SHA256	`5c30cbb5d70155017ca0631bffc157f84a3a1d7aab9a268b11d993a84316693e`
MD5	`3dc8b843db9ca5b3dd7dbc5b02fd99a7`
BLAKE2b-256	`0ce17eb1e3f2729bf819edf89a097037e8821a29288bd5cb5b46af2d0ed57055`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp310-cp310-win_amd64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp310-cp310-win_amd64.whl
- Subject digest: 5c30cbb5d70155017ca0631bffc157f84a3a1d7aab9a268b11d993a84316693e
- Sigstore transparency entry: 2044792225
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: tcren-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Jul 2, 2026
Size: 1.6 MB
Tags: CPython 3.10, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`6c3576aa9a83d2f4e413ab1bb65b77d2ad6da13b4e1cb5157ad04ba3549f7693`
MD5	`6d5a23039afdb90963a1307e4b8bef19`
BLAKE2b-256	`76ab9d7a2194cbe242e8d03fde6345ad6ae51288747a81a0032be677b3d8f2b8`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 6c3576aa9a83d2f4e413ab1bb65b77d2ad6da13b4e1cb5157ad04ba3549f7693
- Sigstore transparency entry: 2044791769
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

File details

Details for the file tcren-2.1.1-cp310-cp310-macosx_11_0_arm64.whl.

File metadata

Download URL: tcren-2.1.1-cp310-cp310-macosx_11_0_arm64.whl
Upload date: Jul 2, 2026
Size: 1.4 MB
Tags: CPython 3.10, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tcren-2.1.1-cp310-cp310-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`498830900df404a3423b1ba2fd506938eff013848f167b52b4c95ce88bb48b99`
MD5	`bd1b463f7f5ff10b42c6933873ca337d`
BLAKE2b-256	`b47ea3cfa99e39d3fd54acd022be09bfb5454c1baf03d32226367a95c288819e`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tcren-2.1.1-cp310-cp310-macosx_11_0_arm64.whl:

Publisher: publish.yml on antigenomics/tcren

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tcren-2.1.1-cp310-cp310-macosx_11_0_arm64.whl
- Subject digest: 498830900df404a3423b1ba2fd506938eff013848f167b52b4c95ce88bb48b99
- Sigstore transparency entry: 2044791960
- Sigstore integration time: Jul 2, 2026
Source repository:
- Permalink: antigenomics/tcren@03a91f81a573c2e136df6179669fb8ca26c198dd
- Branch / Tag: refs/tags/v2.1.1
- Owner: https://github.com/antigenomics
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@03a91f81a573c2e136df6179669fb8ca26c198dd
- Trigger Event: release

Release history Release notifications | RSS feed

2.5.0

Jul 28, 2026

2.4.0

Jul 28, 2026

2.3.2

Jul 24, 2026

2.3.1

Jul 24, 2026

2.2.3

Jul 19, 2026

2.2.2

Jul 17, 2026

2.2.1

Jul 15, 2026

2.2.0

Jul 13, 2026

2.1.2

Jul 2, 2026

This release

2.1.1

Jul 2, 2026

0.1.0

Jun 17, 2026

tcren 2.1.1

tcren — structure-based prediction of TCR–epitope recognition

Install

Command line

Library

Batch inputs, gzip, archives

Canonical orientation, contacts, docking geometry

2D complementarity maps & region-pair contacts

Data

Notebooks

Performance

Tests

Methods appendix

Citing

Project links

Key dates

1 maintainer

Credits

GitHub Statistics

License

Requires

Provides Extra

Tags

Classifiers

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

Release history Release notifications | RSS feed