code and data you can use

Tools & data

Software from the lab and its collaborators, and the datasets we have released with Scientific Data.

Software

GENTLE

BMC Bioinformatics, 2023

Generates features and builds classifiers from T cell repertoire cancer data. Runs as a web app or locally in Python.

PathSingle

BioData Mining, 2024

Pathway activity scores for single-cell data that place T cells in their cell states.

YADA

Current Bioinformatics, 2025

Reference-free deconvolution of bulk RNA sequencing data into cell-type proportions.

PathWeigh

IWBBIO, 2022

Pathway activity scores from RNA-seq, following the behavior of biochemical pathway cascades.

AIRR-ML 2025 solution

Winning entry, AIRR-ML 2025 challenge

Predicts disease state from immune repertoires across eight datasets, matching a model to each dataset.

PhenoNet

Bioinformatics, 2014

Identifies the networks most associated with a disease phenotype.

Datasets

Pre-treatment TCR repertoires in colorectal cancer

Scientific Data, 2025

Data access is described in the paper's data availability statement.

TCR repertoires in ovarian cancer and healthy donors

Scientific Data, 2025

Data access is described in the paper's data availability statement.

Murine TCR repertoires over time after immunotherapy

Scientific Data, 2023

Data access is described in the paper's data availability statement.

Transcriptome of the medicinal leech central nervous system

Scientific Data, 2015

Data access is described in the paper's data availability statement.