Congenital heart disease (CHD) is a leading cause of infant mortality in the US and is commonly thought to arise from perturbations of transcription factors (TFs) during cardiac development. ISLET1 (ISL1) is one such TF, although it also directs differentiation of other cell types, including motor neuron progenitors (MNPs) and pancreatic islet cells. Although cellular specificity of ISL1 function is likely achieved through combinatorial interactions, its essential cardiac interacting partners are unknown. By assaying ISL1 genomic occupancy in human iPSC-derived cardiac progenitors (CPs) or MNPs and leveraging the deep learning approach BPNet, we identified cell-type-specific motifs of other TFs that predicted ISL1 occupancy in each lineage, with the NKX2.5 motif being most closely associated to ISL1 in CPs. We demonstrated ISL1 forms a protein complex with NKX2.5 in CPs, and the two regulated similar gene networks. NKX2.5 co-occupied more than half of ISL1-bound loci, and ISL1 was dependent on NKX2.5 for CP-specific localization. Furthermore, overexpression of NKX2.5 in MNPs led to ISL1 redistribution to CP-specific loci. These results reveal how ISL1 can guide differential lineage choices through a combinatorial code that dictates genomic occupancy and transcription.