Ribonucleic Acid(RNA)contact prediction holds great significance for modeling RNA 3D structures and further understanding RNA biological functions.The rapid growth of RNA sequencing data has driven the development of ...Ribonucleic Acid(RNA)contact prediction holds great significance for modeling RNA 3D structures and further understanding RNA biological functions.The rapid growth of RNA sequencing data has driven the development of diverse computational methods for RNA contact prediction,and a benchmark evaluation of these methods remains essential.In this work,we first classified RNA contact prediction methods into statistical inference-based and neural networkbased ones.We then evaluated eight state-of-the-art methods on three test sets:a sequencediverse set,a structurally non-redundant set and a CASP RNA targets set.Our evaluation shows that for identifying non-local and long-range contacts,neural network-based methods outperform statistical inference-based ones,with SPOT-RNA-2D achieving the best performance,followed by CoCoNet and RNAcontact.However,for identifying the long-range tertiary contacts,which are vital for stabilizing RNA tertiary structure,statistical inference-based methods exhibit superior performance with GREMLIN emerging as the top performer.This work provides a comprehensive benchmarking of RNA contact prediction methods,highlighting their strengths and limitations to guide further methodological improvements and applications in RNA structure modeling.展开更多
基金supported by grants from the National Natural Science Foundation of China(Grant No.12205223 to YLT,Grant No.12375038 to ZJT and Grant No.11605125 to YZS)the Department of Education of Hubei Province(Grant No.Q20221705 to YLT)。
文摘Ribonucleic Acid(RNA)contact prediction holds great significance for modeling RNA 3D structures and further understanding RNA biological functions.The rapid growth of RNA sequencing data has driven the development of diverse computational methods for RNA contact prediction,and a benchmark evaluation of these methods remains essential.In this work,we first classified RNA contact prediction methods into statistical inference-based and neural networkbased ones.We then evaluated eight state-of-the-art methods on three test sets:a sequencediverse set,a structurally non-redundant set and a CASP RNA targets set.Our evaluation shows that for identifying non-local and long-range contacts,neural network-based methods outperform statistical inference-based ones,with SPOT-RNA-2D achieving the best performance,followed by CoCoNet and RNAcontact.However,for identifying the long-range tertiary contacts,which are vital for stabilizing RNA tertiary structure,statistical inference-based methods exhibit superior performance with GREMLIN emerging as the top performer.This work provides a comprehensive benchmarking of RNA contact prediction methods,highlighting their strengths and limitations to guide further methodological improvements and applications in RNA structure modeling.
