A Neural Network Approach for the Analysis of Reproducible Ribo–Seq Profiles

In recent years, the Ribosome profiling technique (Ribo–seq) has emerged as a powerful method for globally monitoring translation process in vivo at single nucleotide resolution. Based on deep sequencing of mRNA fragments, Ribo–seq allows to obtain profiles that reflect time spent by ribosomes translating each part an open reading frame. Unfortunately, produced this can vary significantly different experimental setups, being characterized poor reproducibility. To address problem, we have employed statistical identification highly reproducible profiles, which was tested set E. coli genes. State-of-the-art artificial neural network models been used validate quality sequences. Moreover, new insights into dynamics ribosome provided through analysis obtained