Dataset simulation with LIgO

For simulation of AIRR datasets with user-defined signals, immuneML uses LIgO. It supports simulation on both repertoire and receptor level. It can be used from immuneML through LigoSim instruction.

For more details on the decisions behind simulation, see the Methods section of the original paper:

Chernigovskaya, M., Pavlović, M., Kanduri, C., et al. (2025). Simulation of adaptive immune receptors and repertoires with complex immune information to guide the development and benchmarking of AIRR machine learning. Nucleic Acids Research, 53(3), gkaf025. https://doi.org/10.1093/nar/gkaf025

See LIgO tutorials below:

• YAML specification of the LigoSim instruction for introducing immune signals
• How to simulate co-occuring immune signals
• Paired chain simulations in LIgO
• Simulation with custom signal functions