TFcomb identifies transcription factor combinations for cellular reprogramming based on single-cell multiomics data

Reprogramming cell state transitions provides the potential for cell engineering and regenerative therapy for many diseases. Finding the reprogramming transcription factors (TFs) and their combinations that can direct the desired state transition is crucial for the task. Computational methods have been developed to identify such reprogramming TFs. However, most of them can only generate a ranked list of individual TFs and ignore the identification of TF combinations. Even for individual reprogramming TF identification, current methods often fail to put the real effective reprogramming TFs at the top of their rankings. To address these challenges, we developed TFcomb, a computational method that leverages single-cell multiomics data to identify reprogramming TFs and TF combinations that can direct cell state transitions. We modeled the task of finding reprogramming TFs and their combinations as an inverse problem to enable searching for answers in very high dimensional space, and used Tikhonov regularization to guarantee the generalization ability of solutions. For the coefficient matrix of the model, we designed a graph attention network to augment gene regulatory networks built with single-cell RNA-seq and ATAC-seq data. Benchmarking experiments on data of human embryonic stem cells demonstrated superior performance of TFcomb against existing methods for identifying individual TFs. We curated datasets of multiple cell reprogramming cases and demonstrated that TFcomb can efficiently identify reprogramming TF combinations from a vast pool of potential combinations. We applied TFcomb on a dataset of mouse hair follicle development and found key TFs in cell differentiation. All experiments showed that TFcomb is powerful in identifying reprogramming TFs and TF combinations from single-cell datasets to empower future cell engineering.