Differentiable Folding for Nearest Neighbor Model Optimization
This work addresses a computational bottleneck in RNA structure prediction and design, enabling more accurate models for researchers in computational biology and bioinformatics, though it is incremental as it builds on existing differentiable folding methods.
The paper tackled the challenge of optimizing the approximately 13,000 thermodynamic parameters in the Nearest Neighbor model for RNA secondary structure prediction by using differentiable folding to compute gradients, resulting in a new parameter set that increased the average predicted probability of ground-truth sequence-structure pairs by over 23 orders of magnitude for a single RNA family.
The Nearest Neighbor model is the $\textit{de facto}$ thermodynamic model of RNA secondary structure formation and is a cornerstone of RNA structure prediction and sequence design. The current functional form (Turner 2004) contains $\approx13,000$ underlying thermodynamic parameters, and fitting these to both experimental and structural data is computationally challenging. Here, we leverage recent advances in $\textit{differentiable folding}$, a method for directly computing gradients of the RNA folding algorithms, to devise an efficient, scalable, and flexible means of parameter optimization that uses known RNA structures and thermodynamic experiments. Our method yields a significantly improved parameter set that outperforms existing baselines on all metrics, including an increase in the average predicted probability of ground-truth sequence-structure pairs for a single RNA family by over 23 orders of magnitude. Our framework provides a path towards drastically improved RNA models, enabling the flexible incorporation of new experimental data, definition of novel loss terms, large training sets, and even treatment as a module in larger deep learning pipelines. We make available a new database, RNAometer, with experimentally-determined stabilities for small RNA model systems.