RnaBench: A Comprehensive Library for In Silico RNA Modelling

RNA is a crucial regulator in living organisms and malfunctions can lead to severe diseases. To explore RNA-based therapeutics and applications, computational structure prediction and design approaches play a vital role. Among these approaches, deep learning (DL) algorithms show great promise. However, the adoption of DL methods in the RNA community is limited due to various challenges. DL practitioners often underestimate data homologies, causing skepticism in the field. Additionally, the absence of standardized benchmarks hampers result comparison, while tackling low level tasks requires significant effort. Moreover, assessing performance and visualizing results prove to be non-trivial and task-dependent. To address these obstacles, we introduce RnaBench (RnB), an open-source RNA library designed specifically for the development of deep learning algorithms that mitigate the challenges during data generation, evaluation, and visualization. It provides meticulously curated homology-aware RNA datasets and standardized RNA benchmarks, including a pioneering RNA design benchmark suite featuring a novel real-world RNA design problem. Furthermore, RnB offers baseline algorithms, both existing and novel performance measures, as well as data utilities and a comprehensive visualization module, all accessible through a user-friendly interface. By leveraging RnB, DL practitioners can rapidly develop innovative algorithms, potentially revolutionizing the field of computational RNA research.To address these obstacles, we introduce RnaBench (RnB), an open-source RNA library designed specifically for the development of deep learning algorithms that mitigate the challenges during data generation, evaluation, and visualization. It provides meticulously curated homology-aware RNA datasets and standardized RNA benchmarks, including a pioneering RNA design benchmark suite featuring a novel real-world RNA design problem. Furthermore, RnB offers baseline algorithms, both existing and novel performance measures, as well as data utilities and a comprehensive visualization module, all accessible through a user-friendly interface. By leveraging RnB, DL practitioners can rapidly develop innovative algorithms, potentially revolutionizing the field of computational RNA research.