RiboUnmix: Learning Shared Translational Dynamics from Biased and Noisy Ribo-seq Measurements

2026-09-30

AI Summary

This study addresses the challenge that experimental biases and noise in Ribo-seq data obscure true ribosome dynamics by proposing a probabilistic multi-dataset joint modeling framework. The method employs a negative binomial observation model coupled with a multiplicative modulation mechanism to transform cross-experiment variability into reproducible biological evidence, effectively decoupling technical effects from shared sequence signals. Validation through synthetic benchmarks and real-world data demonstrates that this framework significantly outperforms existing baseline methods. Notably, it robustly extracts highly consistent translational dynamic profiles from 114 HEK293 datasets, providing a reliable tool for the precise characterization of translational regulation.

Abstract

Ribosome profiling (Ribo-seq) measures ribosome distributions along mRNAs, but observed occupancy profiles also contain experiment-specific distortions and stochastic variability. Consequently, models that accurately predict measured profiles may reproduce technical effects rather than recover the underlying biology. We ask whether jointly modeling datasets collected under different experimental conditions can reveal shared, sequence-dependent patterns of ribosome occupancy. We introduce RiboUnmix, a probabilistic multi-dataset framework in which each expected measured profile is represented as a shared sequence-dependent signal modulated by a dataset-specific multiplicative factor. A negative-binomial observation model captures variability across replicates. We evaluate RiboUnmix on a controlled synthetic benchmark combining programmed translation kinetics, ribosome traffic, stochastic count sampling, and sequence-dependent experimental distortions. Because the underlying kinetics and distortions are known, recovery of the shared profile and dataset-specific effects can be assessed separately. Both inferred components correlate strongly with their targets, demonstrating that RiboUnmix can disentangle shared kinetic patterns from experimental effects. Across four organism-specific real-data benchmarks, RiboUnmix outperforms sequence-to-profile baselines in predicting measured profiles. Models trained independently on subsets of 114 HEK-derived datasets recover concordant shared profiles for held-out transcripts, and experiments varying the number and composition of training datasets show that the learned representation remains stable. RiboUnmix thus converts variation across experiments into evidence for reproducible sequence-dependent patterns of ribosome occupancy, supporting biological hypothesis generation from diverse Ribo-seq datasets.

Problem

• Ribosome profiling
• Ribo-seq
• translational dynamics
• experimental bias
• signal disentanglement

Innovation

• Ribo-seq
• probabilistic multi-dataset framework
• disentanglement
• negative-binomial model
• translational dynamics