Accurate de novo transcription unit annotation from run-on and sequencing data

Functional element annotations are critical tools used to provide insight into the molecular processes governing cell development, differentiation, and disease. Run-on and sequencing assays measure the production of nascent RNAs and can provide an effective data source for discovering functional elements. However, the accurate inference of functional elements from run-on sequencing data remains an open problem because the signal is noisy and challenging to model. Here we investigated computational approaches that convert run-on and sequencing data into annotations representing transcription units, including genes and non-coding RNAs. We developed a convolutional neural network, called convolutional discovery of gene anatomy using PRO-seq (CGAP), trained to identify different anatomical features of a transcription unit, which were then stitched together into transcript annotations using a hidden Markov model (HMM). Comparison with existing methods showed a significant performance improvement using our novel CGAP-HMM approach. We developed a voting system that ensembles the top three annotation strategies, resulting in large and significant improvements in transcription unit annotation accuracy over the best performing individual method. Finally, we also explore a conditional generative adversarial network (cGAN) as a possible alternative approach to transcription unit annotation. Collectively our work provides novel tools for de novo transcription unit annotation from run-on and sequencing data that are accurate enough to be useful in many applications.Author summary: Understanding how transcriptional elements (e.g., genes) are organized and expressed is fundamental to biology and medicine. Our DNA contains thousands of transcriptional elements, but pinpointing exactly where each begins and ends (a process called genome annotation) remains technically challenging, especially for newly sequenced organisms. One powerful experimental approach, called precision nuclear run-on and sequencing (PRO-seq), captures RNA polymerase (the molecular machine that reads DNA to produce RNA) as it works across the genome, generating a characteristic “signal fingerprint” at each active transcriptional element.