Early multi-omic signatures and machine learning models predict cardiomyocyte differentiation efficiency and enable robust hPSC differentiation to cardiomyocytes

Protocols for generating cardiomyocytes (CMs) from human pluripotent stem cells (hPSCs) have existed for nearly two decades, yet manufacturing variability in terminal cell identity continues to limit clinical translation. To uncover the origin of fate divergence during hPSC-CM differentiation, we performed temporal transcriptomics, proteomics, and metabolomics of high and low efficiency differentiations. We identified significant early multi-omic divergence between differentiation batches and key pathways underlying fate divergence at critical differentiation stages included Wnt, MAPK, and glucose metabolism. Machine learning models trained on early candidate gene markers predicted hPSC-CM purity better than models using canonical cardiac development markers. Lastly, multi-omic insights informed perturbations, including Wnt and MAPK inhibition, which produced higher CM purities and yields. Our results showcase multi-omic analysis coupled with machine learning models as a powerful tool to identify cell fate determinants and enable robust manufacturing of complex cell products such as hPSC-derived cell therapies. Overall design: We differentiated human pluripotent stem cells (hPSCs) to cardiomyocytes (CMs) and temporally profiled differentiations that resulted in high or low cardiomyocyte purity on Day 16 (cTnT+ cells by flow cytometry). For the multi-omic collection experiment, we used the WTC11 hiPSC line and collected samples on Days 0, 2, 4, 6, 8, 10, 13, and 16. Each replicate is a well replicate of the same differentiation. W52 = high purity CM differentiation and W69 = low CM purity. For the RNAsequencing only collection experiment, we used the WTC11 (W), H9 (H), and IMR90-4 (I) hPSC lines and collected early step-matched differentiation samples from high and low purity CM differentiations. This included sample collection on D0 (+CHIR), D2/D3 (+IWP2), D4/D5 (-IWP2), and D6/7 (+INS). There are no well replicates here with differentiations. Replication is done at the differentiation level across cell lines (n=3 differentiations each for high and low CM purity - one in each cell line). W69 = low purity CM and W81 = high purity CM differentiation. I55 = high purity CM and I75 = low purity CM differentiation. H55 = low purity CM and H58 = high purity CM differentiation.