Combining BulkFormer and TabPFN to predict post-transplant function from kidney biopsies during normothermic machine perfusion or cold storage

Generating predictions from transcriptomic data poses unique challenges due to the high number of genes, and often small sample size. BulkFormer and TabPFN have emerged as leading transformer-based foundation models for bulk transcriptomic and tabular data respectively. We explore an artificial intelligence pipeline using BulkFormer-TabPFN v2.5 which generates zero-shot predictions from RNA-Seq count data without retraining. This was tested on three cohorts of biopsies taken from donated human kidneys. BulkFormer-TabPFN could predict delayed kidney function using RNA-Seq counts from kidneys undergoing ex-situ normothermic machine perfusion (NMP; c-statistic = 0.82, 95% CI 0.67–0.97). Predictive discrimination was optimised under the following conditions: BulkFormer-TabPFN versus TabPFN alone, maximum absolute aggregation of BulkFormer gene-level embeddings. Cold storage biopsies showed poor predictive performance. BulkFormer-TabPFN predictions were modified by cytokine filter treatment during ex-situ NMP, suggesting they could be a dynamic surrogate endpoint for novel therapeutics, which is intrinsically linked to post-transplant outcome. This demonstrates for the first time synergistic benefits of these foundation models, to generate zero-shot predictions without model retraining. Although this work is exploratory, the provided code provides a blueprint to replicate generating predictions from RNA-Seq count data, which could be applied in a wide range of biomedical contexts within and beyond organ transplantation.