The present study by González et al. explores the use of steady state and dynamic multi-omics data from human liver cell lines to further determine the affecting factors in mRNA translation rates. HepG2 and Huh7 human liver cell lines were maintained for the experiment and a complimentary technique of ribosomal sequencing (ribo-seq), polysome profiling followed by RNA-seq, and protein synthesis rate determination with pSILAC. Ribo-seq allowed for the tracking of ribosomal progression over time and a stable estimation of elongation speed of the transcript, and polysome profiling allowed for the determination of the mean ribosome load per mRNA synthesized. The study confirmed a weak correlation between the level of mRNA present and the observed protein output, and thus reinforces the need to understand study translation mechanisms beyond transcript abundance. Additional findings note the initiation phase of translation as the rate-limiting step for transcription rates, and the limited explanation for observed translation rates offered by known determinants including codon usage and UTR elements. The study further highlights the need for machine learning to be utilized in analyzing rich datasets to better understand how mRNA structure and sequence determines protein output.