Prediction of parsimonious and temporally sensitive sets of cell fate engineering transcription factors with IMCell
Su, E. Y.; Ly, B.; Cahan, P.
Show abstract
Transcription factor (TF) cocktails used in cell identity reprogramming protocols have largely been developed from experimental approaches. A handful of computational approaches have been reported, though have not been widely adopted by the scientific community. To standardize their use and assess their performance, we built CompForce, a platform that integrates these tools. Using CompForce, we found that existing computational methods offer modest improvements over differential expression on both synthetic and literature-curated data, and that their lackluster and inconsistent performance could be attributed to a reliance on local centrality metrics. To improve upon these methods, we developed IMCell, a prediction method that is inspired by the influence maximization problem. Unlike existing tools, IMCell returns optimized TF sets rather than ranked TF lists. We demonstrate that IMCell vastly out-performs existing tools, and further extend it to dynamic, stepwise contexts. The tools presented here are available in the R packages CompForce and IMCell.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- scDesign2: a transparent simulator that generates high-fidelity single-cell gene expression count data with gene correlations captured 95%
- Robustness and applicability of functional genomics tools on scRNA-seq data 95%
- Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing data 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.