Overview
This tutorial demonstrates how to run a multimodal experiment that fuses microbiota taxonomic profiles with metabolomics data. Both modalities come from the same IBD cohort (Franzosa et al., 2019) used in the single-modality tutorials.
What changes compared to single-modality experiments
A single-modality experiment uses one data source. A multimodal experiment adds one or more secondary modalities and a set of fusion strategies that control how the modalities are combined during training and prediction. The key additions are:
ModalityConfigdescribes each secondary modality (file path, sample ID column, NaN handling).MultimodalConfiggroups the secondary modalities, lists the fusion strategies to evaluate, and controls whether single-modality baselines are also produced (run_siso).FusionConfigspecifies the fusion approach (early or late) and the concrete algorithm (e.g.,CONCAT,MEAN).
The primary modality (microbiome) is still configured through microbiome_file, taxonomic_configs, and transform_configs as before. The secondary modalities are passed through multimodal_config.
Fusion strategies used in this tutorial
| Strategy | Type | Description |
|---|---|---|
| Early fusion | CONCAT | Concatenates microbiome and metabolomics features into a single feature matrix before training. |
| Late fusion | MEAN | Trains separate models on each modality, then averages their prediction probabilities. |
For a full list of available fusion strategies, see Fusion strategies.
Tutorial structure
| Page | Content |
|---|---|
| Data preparation | Where to find download and preparation scripts for both modalities. |
| Experiment configuration | Secondary modality, fusion strategies, and full experiment assembly. |
| Running the experiment | Execution and output structure. |
Source files
The complete experiment script is at example/IBD/ibd_franzosa_multimodal.py.