The authors would like to clarify the following:
We previously developed a PTBP1 binding model based on a Hidden Markov Model (HMM) that utilized overlapping nucleotide triplets but was limited by the model’s assumption of independence. Here, we present an improved PTBP1 binding model using Transcription Factor Flexible Models (TFFMs), which relax this assumption and accommodate flexible-length motifs. The updated model shows stronger correlation with experimental binding affinities (r = −0.95) compared to the prior HMM (r = −0.91) and maintains specificity by correctly scoring non-binding RNA substrates. This work demonstrates the advantage of flexible, context-aware modeling frameworks in accurately predicting RBP-RNA interactions and provides an improved tool for studying PTBP1 binding specificity.
https://www.biorxiv.org/c...