RLsite: Integrating 3D-CNN and BiLSTM for RNA-ligand binding site prediction

doi:10.1088/1674-1056/adea9b

Abstract Accurate identification of RNA-ligand binding sites is essential for elucidating RNA function and advancing structure-based drug discovery. Here, we present RLsite, a novel deep learning framework that integrates energy-, structure- and sequence-based features to predict nucleotide-level binding sites with high accuracy. RLsite leverages energy-based three-dimensional representations, obtained from atomic probe interactions using a pre-trained ITScore-NL potential, and models their contextual features through a 3D convolutional neural network (3D-CNN) augmented with self-attention. In parallel, structure-based features, including network properties, Laplacian norm, and solvent-accessible surface area, together with sequence-based evolutionary constraint scores, are mapped along the RNA sequence and used as sequential descriptors. These descriptors are modeled using a bidirectional long short-term memory (BiLSTM) network enhanced with multi-head self-attention. By effectively fusing these complementary modalities, RLsite achieves robust and precise binding site prediction. Extensive evaluations across four diverse RNA-ligand benchmark datasets demonstrate that RLsite consistently outperforms state-of-the-art methods in terms of precision, recall, Matthews correlation coefficient (MCC), area under the curve (AUC), and overall robustness. Notably, on a particularly challenging test set composed of RNA structures containing junctions, RLsite surpasses the second-best method by 7.3% in precision, 3.4% in recall, 7.5% in MCC, and 10.8% in AUC, highlighting its potential as a powerful tool for RNA-targeted molecular design.

Keywords: RNA-ligand binding sites prediction deep learning self-attention

Received: 06 May 2025
Revised: 22 June 2025
Accepted manuscript online: 02 July 2025

PACS:	87.14.gn	(RNA)
	87.15.A-	(Theory, modeling, and computer simulation)
	87.15.B-	(Structure of biomolecules)

Fund: Project supported by the National Natural Science Foundation of China (Grant No. 12204118) and the Guizhou University Talent Fund (Grant No. [2022]30).

Corresponding Authors: Yuyu Feng
E-mail: fengyy@gzu.edu.cn

Cite this article:

Yan Zou(邹艳), Lang Yang(杨浪), Yanhui Liu(刘艳辉), and Yuyu Feng(冯玉宇) RLsite: Integrating 3D-CNN and BiLSTM for RNA-ligand binding site prediction 2025 Chin. Phys. B 34 088709

[1] Cao Y, Liu H C, Shannon S Lu, Krysten A Jones, Anitha P Govind, Okunola Jeyifous, Christine Q Simmons, Negar Tabatabaei,William N Green, Jimmy. L Holder Jr., Soroush Tahmasebi, Alfred L George Jr. and Bryan C Dickinson 2023 Nat. Commun. 14 6827
[2] Singh S, Sinha T and Panda A C 2024 Wiley Interdisciplinary Reviews: RNA 15 e1820
[3] Delaunay S, Helm M and Frye M 2024 Nat. Rev. Genet. 25 104
[4] Peng X, Liao W, Lin X, Lilley D M J and Huang L 2023 Nucleic Acids Res. 51 2904
[5] Truong L, Kooshapur H, Dey S K, Li X, Tjandra N, Jaffrey S R and Ferré-D’Amaré A R 2022 Nat. Chem. Biol. 18 191
[6] Li T, He J H, Cao H, Zhang Y, Chen J, Xiao Y and Huang S Y 2025 Nat. Biotechnol. 43 97
[7] Yang C, Song X, Feng Y, Zhao G and Liu Y 2023 J. Phys.: Condens. Matter 35 265101
[8] Song L, Yu S X,Wang X X, Tan Y L and Tan Z J 2022 Commun. Theor. Phys. 74 075602
[9] He X L, Wang J, Wang J and Xiao Y 2020 Chin. Phys. B 29 078702
[10] Zhu Y R, Zhu L Y, Wang X and Jin H C 2022 Cell Death Dis. 13 644
[11] Toden S and Goel A 2022 Br. J. Cancer 126 351
[12] Pardi N, Hogan M J, Porter F W and Weissman D 2018 Nat. Rev. Drug Discov. 17 261
[13] Disney M D 2019 J. Am. Chem. Soc. 141 6776
[14] Yu A M, Choi Y H and Tu M J 2020 Pharmacol Rev. 27 862
[15] Zhao R Y, Fu J H, Zhu L J, Chen Y and Liu B 2020 J. Hematol Oncol. 15 14
[16] de Souza Neto L R, Moreira-Filho J T, Neves B J, Maidana R L B R, Guimaräes A C R, Furnham N, Andrade C H and Silva F P Jr 2020 Front. Chem. 8 93
[17] Xu W and Kang C 2025 J. Med. Chem. 68 5000
[18] Ursu A, Childs-Disney J L, Andrews R J, O’Leary C A, Meyer S M, Angelbello A J, Moss W N and Disney M D 2020 Chem. Soc. Rev. 49 7252
[19] Velagapudi S P, Cameron M D, Haga C L, Rosenberg L H, Lafitte M, Duckett D R, Phinney D G and Disney M D 2016 Proc. Natl. Acad. Sci. USA 113 5898
[20] Feng Y Y, Yan Y M, He J H, Tao H Y, Wu Q L and Huang S Y 2022 Drug Discov Today 27 838
[21] Feng Y, Zhang K, Wu Q and Huang S Y 2021 J. Chem. Inf. Model. 61 4771
[22] Sun L Z, Jiang Y W, Zhou Y Z and Chen S J 2020 J. Chem. Theory Comput. 16 7173
[23] Detering C and Varani G 2004 J. Med. Chem. 47 4188
[24] Ruiz-Carmona S, Alvarez-Garcia D, Foloppe N, Beatriz Garmendia- Doval A, Juhos S, Schmidtke P, Barril X, Hubbard R E and David Morley S 2014 PLoS Comput. Biol. 10 e1003571
[25] Therese Lang P, Brozell S R, Mukherjee S, Pettersen E F, Meng E C, Thomas V, Rizzo R C, Case, James T L and Kuntz I D 2009 RNA 15 1219
[26] Guilbert C and James T L 2008 J. Chem. Inf. Model. 48 1257
[27] Zeng P, Li J, Ma W and Cui Q 2015 Sci. Rep. 5 9179
[28] Zeng P and Cui Q 2016 Sci. Rep. 6 19016
[29] Wang K, Jian Y, Wang H, Zeng C and Zhao Y 2018 Bioinformatics 34 3131
[30] Su H, Peng Z and Yang J 2021 Bioinformatics 37 36
[31] Wang K, Zhou R, Wu Y and Li M 2023 Brief Bioinform 24 bbac486
[32] Gao J, Liu H, Zhuo C, Zeng C and Zhao Y 2024 J. Chem. Inf. Model. 64 6979
[33] Berman H M, Westbrook J, Feng Z, Gilliland G, Bhat T N, Weissig H, Shindyalov I N and Bourne P E 2000 Nucleic Acids Res. 28 235
[34] Gong S, Zhang C and Zhang Y 2019 Bioinformatics 35 4459
[35] Li W and Adam G 2006 Bioinformatics 22 1658
[36] Altschul S F, Gish W, Miller W, Myers E W and Lipman D J 1990 J. Mol. Biol. 215 403
[37] Fu L, Niu B, Zhu Z, Wu S and Li W 2012 Bioinformatics 28 3150
[38] Huang Y, Niu B, Gao Y, Fu L and Li W 2010 Bioinformatics 26 680
[39] Feng Y and Huang S Y 2020 J. Chem. Inf. Model. 60 6698
[40] Amitai G, Shemesh A, Sitbon E, et al. 2004 J. Mol. Biol. 344 1135
[41] Bonnel N and Marteau P F 2012 IEEEACM Transactions on Computational Biology and Bioinformatics 9 1451
[42] Sun S, Wu Q, Peng Z and Yang J 2019 Bioinformatics 35 1686
[43] Zhang Z, Scott Schwartz, LukasWagner andWebb Miller 2000 J. Comput. Biol. 7 203
[44] Chen K, Thomas Litfin, Jaswinder Singh, Zhan J and Zhou Y Q 2024 Genomics, Proteomics & Bioinformatics 22 qzae018
[45] Marks D S, Hopf T A and Sander C 2012 Nat. Biotechnol. 30 1072
[46] Jian Y, Wang X, Qiu J, Wang H, Liu Z, Zhao Y and Zeng C 2019 BMC Bioinformatics 20 497
[47] Ekeberg M, Lövkvist C, Lan Y, Weigt M and Aurell E 2013 Phys. Rev. E Stat Nonlin Soft Matter Phys. 87 012707
[48] Zhou P, Xie X, Lin Z and Yan S. 2024 IEEE Trans Pattern Anal Mach Intell. 46 6486
[49] He K M, Zhang X Y, Ren S Q and Sun J 2015 IEEE International Conference on Computer Vision (ICCV) 1026
[50] Flinders J, DeFina S C, Brackett D M, Baugh C, Wilson C and Dieckmann T 2004 Chembiochem. 5 62
[51] Fan P, Suri A K, Fiala R, Live D and Patel D J 1996 J. Mol. Biol. 258 480
[52] Jiang L, Majumdar A, Hu W, Jaishree TJ, Xu W and Patel DJ 1999 Structure 7 817
[53] Zeller M J, Favorov O, Li K, Nuthanakanti A, Hussein D, Michaud A, Lafontaine D A, Busan S, Serganov A, Aubé J and Weeks K M 2022 Proc. Natl. Acad. Sci. USA 119 e2122660119
[54] Biesiada M, Pachulska-Wieczorek K, Adamiak R W and Purzycka K J 2016 Methods 103 120
[55] Boniecki M J, Lach G, Dawson W K, Tomala K, Lukasz P, Soltysinski T, Rother K M and Bujnicki J M 2016 Nucleic Acids Res. 44 e63
[56] Eastman P, Galvelis R, Peláez R P, Abreu C R A, Farr S E, Gallicchio E, Gorenko A, Henry M M, Hu F, Huang J, Krämer A, Michel J, Mitchell J A, Pande V S, Rodrigues J P, Rodriguez-Guerra J, Simmonett A C, Singh S, Swails J, Turner P,Wang Y, Zhang I, Chodera J D, De Fabritiis G and Markland T E 2024 J. Phys. Chem. B 128 109

[1]	Trajectory tracking on the optimal path of two-dimensional quadratic barrier escaping Zengxuan Zhao(赵曾轩), Xiuying Zhang(张秀颖), Pengchen Zhao(赵鹏琛), Chunyang Wang(王春阳), Chunlei Xia(夏春雷), Mushtaq Rana Imran, and Joelous Malamula Nyasulu. Chin. Phys. B, 2025, 34(5): 050205.
[2]	Deep learning-enabled inverse design of polarization-selective structural color based on coding metasurface Haolin Yang(杨昊霖), Bo Ni(倪波), Junhong Guo(郭俊宏), Hua Zhou(周华), and Jianhua Chang(常建华). Chin. Phys. B, 2025, 34(5): 050702.
[3]	Learning complex nonlinear physical systems using wavelet neural operators Yanan Guo(郭亚楠), Xiaoqun Cao(曹小群), Hongze Leng(冷洪泽), and Junqiang Song(宋君强). Chin. Phys. B, 2025, 34(3): 034702.
[4]	Accurate prediction of essential proteins using ensemble machine learning Dezhi Lu(鲁德志), Hao Wu(吴淏), Yutong Hou(侯俞彤), Yuncheng Wu(吴云成), Yuanyuan Liu(刘媛媛), and Jinwu Wang(王金武). Chin. Phys. B, 2025, 34(1): 018901.
[5]	A large language model-powered literature review for high-angle annular dark field imaging Wenhao Yuan(袁文浩), Cheng Peng(彭程), and Qian He(何迁). Chin. Phys. B, 2024, 33(9): 098703.
[6]	High-quality ghost imaging based on undersampled natural-order Hadamard source Kang Liu(刘炕), Cheng Zhou(周成), Jipeng Huang(黄继鹏), Hongwu Qin(秦宏伍), Xuan Liu(刘轩), Xinwei Li(李鑫伟), and Lijun Song(宋立军). Chin. Phys. B, 2024, 33(9): 094204.
[7]	Properties of radiation defects and threshold energy of displacement in zirconium hydride obtained by new deep-learning potential Xi Wang(王玺), Meng Tang(唐孟), Ming-Xuan Jiang(蒋明璇), Yang-Chun Chen(陈阳春), Zhi-Xiao Liu(刘智骁), and Hui-Qiu Deng(邓辉球). Chin. Phys. B, 2024, 33(7): 076103.
[8]	Image segmentation of exfoliated two-dimensional materials by generative adversarial network-based data augmentation Xiaoyu Cheng(程晓昱), Chenxue Xie(解晨雪), Yulun Liu(刘宇伦), Ruixue Bai(白瑞雪), Nanhai Xiao(肖南海), Yanbo Ren(任琰博), Xilin Zhang(张喜林), Hui Ma(马惠), and Chongyun Jiang(蒋崇云). Chin. Phys. B, 2024, 33(3): 030703.
[9]	Generation of orbital angular momentum hologram using a modified U-net Zhi-Gang Zheng(郑志刚), Fei-Fei Han(韩菲菲), Le Wang(王乐), and Sheng-Mei Zhao(赵生妹). Chin. Phys. B, 2024, 33(3): 034207.
[10]	Quantum state estimation based on deep learning Haowen Xiao(肖皓文) and Zhiguang Han(韩枝光). Chin. Phys. B, 2024, 33(12): 120307.
[11]	A deep learning method based on prior knowledge with dual training for solving FPK equation Denghui Peng(彭登辉), Shenlong Wang(王神龙), and Yuanchen Huang(黄元辰). Chin. Phys. B, 2024, 33(1): 010202.
[12]	Crysformer: An attention-based graph neural network for properties prediction of crystals Tian Wang(王田), Jiahui Chen(陈家辉), Jing Teng(滕婧), Jingang Shi(史金钢),Xinhua Zeng(曾新华), and Hichem Snoussi. Chin. Phys. B, 2023, 32(9): 090703.
[13]	Classification and structural characteristics of amorphous materials based on interpretable deep learning Jiamei Cui(崔佳梅), Yunjie Li(李韵洁), Cai Zhao(赵偲), and Wen Zheng(郑文). Chin. Phys. B, 2023, 32(9): 096101.
[14]	Disruption prediction based on fusion feature extractor on J-TEXT Wei Zheng(郑玮), Fengming Xue(薛凤鸣), Zhongyong Chen(陈忠勇), Chengshuo Shen(沈呈硕), Xinkun Ai(艾鑫坤), Yu Zhong(钟昱), Nengchao Wang(王能超), Ming Zhang(张明),Yonghua Ding(丁永华), Zhipeng Chen(陈志鹏), Zhoujun Yang(杨州军), and Yuan Pan(潘垣). Chin. Phys. B, 2023, 32(7): 075203.
[15]	Modeling differential car-following behavior under normal and rainy conditions: A memory-based deep learning method with attention mechanism Hai-Jian Bai(柏海舰), Chen-Chen Guo(过晨晨), Heng Ding(丁恒), Li-Yang Wei(卫立阳), Ting Sun(孙婷), and Xing-Yu Chen(陈星宇). Chin. Phys. B, 2023, 32(6): 060507.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

RLsite: Integrating 3D-CNN and BiLSTM for RNA-ligand binding site prediction

Cite this article:

Online attention