{"title":"A triple-pose complex between an extended WIP motif and a C-terminal SH3 domain modulates cortactin activity.","authors":"Chana G Sokolik, Jordan H Chill","doi":"10.1016/j.jmb.2025.168984","DOIUrl":"https://doi.org/10.1016/j.jmb.2025.168984","url":null,"abstract":"<p><p>The central domain of WASp-interacting protein (WIP) interacts with the cortactin SH3 domain through a previously undefined binding motif. This interaction affects extracellular matrix (ECM) degradation and the invasive phenotype of cells. Here, using NMR-based methods, we identify the major WIP epitope modulating this binding event as residues 168-183, an unexpectedly long segment uncharacteristic of SH3 peptidic ligands. A scanning mutagenesis analysis showed that peptide binding 'hotspots' are distributed throughout the binding sequence. To uncover the structural basis of WIP-cortactin recognition we utilized edited-filtered NOESY experiments to determine the structure of the intermediate-affinity SH3/peptide complex. Analysis of the NOESY pattern suggests that the peptide sequence dictates three interchanging binding modes, two oppositely oriented canonical poses involving N-terminal interactions, corresponding to class I and class II complexes, and a non-canonical pseudo-class II pose involving C-terminal interactions. The latter pose highlights the importance of the hydrophobic surface adjacent to the canonical binding grooves and accounts for the extended binding motif. Design of mutant peptides with increased affinity based on this multi-conformational complex demonstrates how these structural insights may impact design of improved inhibitors of the WIP-cortactin interaction with potential therapeutic applications.</p>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":" ","pages":"168984"},"PeriodicalIF":4.7,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143363496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bernadeta A Pietrzak-Wawrzyńska, Agnieszka Wnuk, Karolina Przepiórska-Drońska, Andrzej Łach, Małgorzata Kajta
{"title":"Non-nuclear estrogen receptor signaling as a promising therapeutic target to reverse Alzheimer's disease-related autophagy deficits and upregulate the membrane ESR1 and ESR2 which involves DNA methylation-dependent mechanisms.","authors":"Bernadeta A Pietrzak-Wawrzyńska, Agnieszka Wnuk, Karolina Przepiórska-Drońska, Andrzej Łach, Małgorzata Kajta","doi":"10.1016/j.jmb.2025.168982","DOIUrl":"https://doi.org/10.1016/j.jmb.2025.168982","url":null,"abstract":"<p><p>Although Alzheimer's disease (AD) affects millions of individuals worldwide, there are currently no effective treatments available. Recent findings have suggested that non-nuclear estrogen receptor (ER) signaling represents promising therapeutic target for central nervous system disorders, offering potential treatments without the significant side effects associated with the activation of nuclear ERs. Because ER signaling deficiency and autophagy impairment have been linked to AD etiology, the present study aimed to selectively target non-nuclear ERs signaling pathways with PaPE-1 and identify autophagy-related mechanisms of neuroprotection in a cellular model of AD. The present study demonstrated that PaPE-1 protected mouse cortical neurons from AD pathology, as evidenced by MAP2-specific labeling. Posttreatment with PaPE-1 reversed the Aβ-evoked decrease in autophagic vesicles, and increased the levels of autophagy-related mRNAs and proteins, accompanied by hypomethylation of the Atg7 gene. Moreover, posttreatment with PaPE-1 increased the levels of membrane fraction receptors ESR1/ERα and ESR2/ERβ, which corresponds to increased Esr1 and Esr2 mRNA expression and DNA hypomethylation of specific genes. In addition to inhibiting DNA methylation of autophagy and ER-related genes, PaPE-1 did not alter global DNA methylation but stimulated HAT activity in Aβ-treated cells. In summary, PaPE-1 promoted neuroprotection against Aβ-induced toxicity that involved stimulation of autophagy, upregulation of membrane ESR1 and ESR2 and decreased DNA methylation of respective genes. The present study proposes a novel therapeutic approach against AD that is based on the selective activation of non-nuclear ER signaling to overcome Aβ-induced autophagy deficits and normalize the epigenetic status of cerebral neurons.</p>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":" ","pages":"168982"},"PeriodicalIF":4.7,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143363498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multifaceted roles of the ATG8 protein family in plant autophagy: from autophagosome biogenesis to cargo recognition.","authors":"Yixin Wu, Rui Xu, Xiaohong Zhuang","doi":"10.1016/j.jmb.2025.168981","DOIUrl":"https://doi.org/10.1016/j.jmb.2025.168981","url":null,"abstract":"<p><p>In plant cells, autophagy is an essential quality control process by forming a double-membrane structure named the autophagosome, which envelopes and transports the cargoes to the vacuole for degradation/recycling. Autophagy-related (ATG) 8, a key regulator in autophagy, exerts multifunctional roles during autophagy. ATG8 anchors on the phagophore membrane through the ATG8 conjugation system and participates in different steps during autophagosome formation. Accumulating evidence has demonstrated that ATG8 cooperates with other ATG or non-ATG proteins in autophagosome biogenesis. Meanwhile, ATG8 plays an important role in cargo recognition, which is mainly attributed by the specific interactions between ATG8 and the selective autophagy receptors (SARs) or cargos for selective autophagy. Emerging roles of ATG8 in non-canonical autophagy have been recently reported in plants for different stress adaptation. Here, we review the diverse functions of ATG8 in plants, focusing on autophagosome biogenesis and cargo recognition in canonical and non-canonical autophagy.</p>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":" ","pages":"168981"},"PeriodicalIF":4.7,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143254008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luis Valiente , Valentín Riomoros-Barahona , Juan Carlos Gil-Redondo , José R. Castón , Alejandro Valbuena , Mauricio G. Mateu
{"title":"A RNA Dodecahedral Cage Inside a Human Virus Plays a Dual Biological Role in Virion Assembly and Genome Release Control","authors":"Luis Valiente , Valentín Riomoros-Barahona , Juan Carlos Gil-Redondo , José R. Castón , Alejandro Valbuena , Mauricio G. Mateu","doi":"10.1016/j.jmb.2024.168922","DOIUrl":"10.1016/j.jmb.2024.168922","url":null,"abstract":"<div><div>Human rhinoviruses (RV) are among the most frequent human pathogens. As major causative agents of common colds they originate serious socioeconomic problems and huge expenditure every year, and they also exacerbate severe respiratory diseases. No anti-rhinoviral drugs or vaccines are available so far. Antiviral drug design may benefit from an understanding of the role during the infectious cycle of the interactions in the virion between the capsid and the viral nucleic acid. The genomic RNA inside the human RV virion forms a dodecahedral cage made of 30 double-stranded RNA elements that interact with equivalent sites at the capsid inner wall. RNA dodecahedral cages also occur in distantly related insect and plant viruses. However, the functional role(s) of the interactions between any dodecahedral cage and the capsid remained to be established. Here we describe an extensive structure–function mutational analysis of the capsid-RNA dodecahedral cage interface in the RV virion, to dissect the role of the interactions between the capsid and the cage-forming RNA duplexes in: (i) infection by RV; (ii) virus biological fitness; (iii) virion assembly; (iv) virion stability; and (v) viral RNA uncoating. The results reveal that the capsid-bound dsRNA dodecahedral cage in the human RV virion is a multifunctional structural element. Two structurally overlapping subsets of RNA duplex-capsid interactions promote virus infectivity and biological fitness by respectively facilitating virion assembly or restraining the untimely, unproductive uncoating of the viral RNA genome. These results provide new insights into virion morphogenesis and genome uncoating, and have implications for antiviral drug design.</div></div>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":"437 3","pages":"Article 168922"},"PeriodicalIF":4.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142891160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julien Minniti, Frédéric Checler, Eric Duplan , Cristine Alves da Costa
{"title":"TFinder: A Python Web Tool for Predicting Transcription Factor Binding Sites","authors":"Julien Minniti, Frédéric Checler, Eric Duplan , Cristine Alves da Costa","doi":"10.1016/j.jmb.2024.168921","DOIUrl":"10.1016/j.jmb.2024.168921","url":null,"abstract":"<div><div>Transcription is a key cell process that consists of synthesizing several copies of RNA from a gene DNA sequence. This process is highly regulated and closely linked to the ability of transcription factors to bind specifically to DNA. TFinder is an easy-to-use Python web portal allowing the identification of Individual Motifs (IM) such as Transcription Factor Binding Sites (TFBS).</div><div>Using the NCBI API, TFinder extracts either promoter or gene terminal regulatory regions, through a simple query of NCBI gene name or ID. It enables simultaneous analysis across five different species for an unlimited number of genes. TFinder searches for Individual Motifs in different formats, including IUPAC codes and JASPAR entries. Moreover, TFinder also allows de novo generations of a Position Weight Matrix (PWM) and the use of already established PWM. Finally, the data are provided in a tabular and a graph format showing the relevance and the <em>P</em>-value of the Individual Motifs found as well as their location relative to the Transcription Start Site (TSS) or the terminal region of the gene. The results are then sent by email to users facilitating the subsequent data analysis and sharing.</div><div>TFinder is written in Python and freely available on GitHub under the MIT license: <span><span>https://github.com/Jumitti/TFinder</span><svg><path></path></svg></span>. It can be accessed as a web application implemented in Streamlit at <span><span>https://tfinder-ipmc.streamlit.app</span><svg><path></path></svg></span>. Resources are available on Streamlit “Resources” tab. TFINDER strength is that it relies on an all-in-one intuitive tool allowing users inexperienced with bioinformatics tools to retrieve gene regulatory regions sequences in multiple species and to search for individual motifs in a huge number of genes.</div></div>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":"437 3","pages":"Article 168921"},"PeriodicalIF":4.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143021543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Farjana Parvin , Johan N.K. Larsson , Walker S. Jackson , Sofie Nyström , Per Hammarström
{"title":"Efficient Seeding of Cerebral Vascular Aβ-Amyloidosis by Recombinant AβM1-42 Amyloid Fibrils","authors":"Farjana Parvin , Johan N.K. Larsson , Walker S. Jackson , Sofie Nyström , Per Hammarström","doi":"10.1016/j.jmb.2024.168923","DOIUrl":"10.1016/j.jmb.2024.168923","url":null,"abstract":"<div><div>Aβ-amyloid plaques and cerebral amyloid angiopathy (CAA) in the brain are pathological hallmarks of Alzheimer’s disease (AD) and vascular dementia. The spreading of Aβ amyloidosis in the brain appears to be mediated by a seeding mechanism, where preformed fibrils (called seeds) accelerate Aβ fibril formation by bypassing the rate-determining nucleation step. Several studies have demonstrated that Aβ amyloidosis can be induced in transgenic mice, producing human Aβ, by injecting Aβ-rich brain extracts (seeds) derived from transgenic mice and human AD brains. However, studies on recombinant seeds are limited. Therefore, we investigated the seeding activity of pure recombinant human Aβ fibrils of different compositions. Seeds were inoculated into APP23 mice at the age of 3 months and were analyzed after 6 months of incubation.</div><div>Recombinant fibril seeds made from Aβ-peptides with an N-terminal methionine (<em>i.e.</em> (preformed fibrils from AβM1-42, AβM1-40, and AβM1-40 + AβM1-42) accelerated Aβ-amyloid plaque formation <em>in vivo</em> compared to non-inoculated transgenic control mice of the same age. In addition, all seeds induced CAA pathology. Interestingly, AβM1-42 containing seeds produced significantly more CAA and amyloid plaques than seeds containing pure AβM1-40, which was surprising given that APP23 mice produce approximately four-fold more Aβ1-40 substrate than Aβ1-42.</div><div>This study showed that AβM1-42 fibrils are highly potent in seeding CAA and implies that conformational templating occurs in amyloid plaque as deduced by comparative amyloid ligand staining. Our results verify that recombinant Aβ fibrils are transmissible amyloids, and that <em>in vivo</em> seeding can accelerate, and redirect Aβ amyloidosis patterns compared to spontaneous age dependent amyloidosis.</div></div>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":"437 3","pages":"Article 168923"},"PeriodicalIF":4.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142891164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhengrui Zhang , Rishi Patel , Zhao-Qing Luo , Chittaranjan Das
{"title":"Cryo-EM Detection of AMPylated Histidine Implies Covalent Catalysis in AMPylation Mediated by a Bacterial Effector","authors":"Zhengrui Zhang , Rishi Patel , Zhao-Qing Luo , Chittaranjan Das","doi":"10.1016/j.jmb.2024.168917","DOIUrl":"10.1016/j.jmb.2024.168917","url":null,"abstract":"<div><div>AMPylation is a post-translational modification (PTM) whereby adenosine monophosphate (AMP) from adenosine triphosphate (ATP) is transferred onto protein hydroxyl groups of serine, threonine, or tyrosine. Recently, an actin-dependent AMPylase namely LnaB from the bacterial pathogen <em>Legionella pneumophila</em> was found to AMPylate phosphate groups of phosphoribosylated ubiquitin and Src family kinases. LnaB represents an evolutionarily distinct family of AMPylases with conserved active site Ser-His-Glu residues. Here, we capture the structure of the LnaB-actin complex in a putative intermediate state via single-particle cryogenic electron microscopy (cryo-EM) and find that the catalytic histidine of LnaB is covalently attached to AMP through a phosphoramidate linkage at the Nδ1 atom. This observation provides direct structural evidence of histidine AMPylation as a PTM and implies the possibility of covalent catalysis in LnaB-mediated AMPylation, a mechanism distinct from known AMPylases. Subsequent biochemical studies confirm the observed AMP binding site and provide additional insights into the catalytic properties of LnaB. Together, our work highlights the power of cryo-EM in capturing labile PTMs and transient species during enzymatic reactions, while opening new avenues of mechanistic investigation into the LnaB family.</div></div>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":"437 3","pages":"Article 168917"},"PeriodicalIF":4.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142851953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andaleeb Sajid, Nandhini Ranganathan, Rajan Guha, Megumi Murakami, Shafaq Ahmed, Stewart R Durell, Suresh V Ambudkar
{"title":"Conversion of human multidrug transporter P-glycoprotein (ABCB1) from drug efflux to uptake pump: Evidence for a switch region modulating the direction of substrate transport.","authors":"Andaleeb Sajid, Nandhini Ranganathan, Rajan Guha, Megumi Murakami, Shafaq Ahmed, Stewart R Durell, Suresh V Ambudkar","doi":"10.1016/j.jmb.2025.168979","DOIUrl":"https://doi.org/10.1016/j.jmb.2025.168979","url":null,"abstract":"<p><p>The multidrug transporter P-glycoprotein (P-gp), is pivotal in exporting various chemically dissimilar amphipathic compounds including anti-cancer drugs, thus causing multidrug resistance during cancer treatment. P-gp is composed of two transmembrane domains (TMDs), each containing six homologous transmembrane helices (TMHs). Among these helices, TMH 6 and 12 align oppositely, lining a drug-binding pocket in the transmembrane region which acts as a pathway for drug efflux. Previously, we demonstrated that specific mutations within TMH 6 and 12 resulted in loss of substrate efflux and altered the transport direction from efflux to uptake for some substrates. This suggested the presence of a regulatory switch that governs the direction of transport. In this study, we sought to elucidate the mechanism of switch modulation of the uptake function by engineering several mutants via substituting specific residues in TMH 6 and 12. We discovered that the alanine substitution of four residues (V974, L975, V977, and F978) within the upper region of TMH 12, along with three residues (V334, F336, and F343) within TMH 6, was sufficient to convert P-gp from an efflux to an uptake pump. Additional mutagenesis of the residues in the middle region of TMH 12 revealed that the uptake function, like efflux, is reversible. Further studies, including molecular dynamics simulations, revealed that the switch region appears to act during the substrate translocation step. We propose that the switch region in TMH 6 and 12, which modulates the direction of transport by P-gp, provides a novel approach to selectively target P-gp-expressing cancer cells.</p>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":" ","pages":"168979"},"PeriodicalIF":4.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143121927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ki Wook Lee, Nhat Truong Pham, Hye Jung Min, Hyun Woo Park, Ji Won Lee, Han-En Lo, Na Young Kwon, Jimin Seo, Illia Shaginyan, Heeje Cho, Leyi Wei, Balachandran Manavalan, Young-Jun Jeon
{"title":"DOGpred: A Novel Deep Learning Framework for Accurate Identification of Human O-linked Threonine Glycosylation Sites.","authors":"Ki Wook Lee, Nhat Truong Pham, Hye Jung Min, Hyun Woo Park, Ji Won Lee, Han-En Lo, Na Young Kwon, Jimin Seo, Illia Shaginyan, Heeje Cho, Leyi Wei, Balachandran Manavalan, Young-Jun Jeon","doi":"10.1016/j.jmb.2025.168977","DOIUrl":"https://doi.org/10.1016/j.jmb.2025.168977","url":null,"abstract":"<p><p>O-linked glycosylation is a crucial post-transcriptional modification that regulates protein function and biological processes. Dysregulation of this process is associated with various diseases, underscoring the need to accurately identify O-linked glycosylation sites on proteins. Current experimental methods for identifying O-linked threonine glycosylation (OTG) sites are often complex and costly. Consequently, developing computational tools that predict these sites based on protein features is crucial. Such tools can complement experimental approaches, enhancing our understanding of the role of OTG dysregulation in diseases and uncovering potential therapeutic targets. In this study, we developed DOGpred, a deep learning-based predictor for precisely identifying human OTGs using high-latent feature representations. Initially, we extracted nine different conventional feature descriptors (CFDs) and nine pre-trained protein language model (PLM)-based embeddings. Notably, each feature was encoded as a 2D tensor, capturing both the sequential and inherent feature characteristics. Subsequently, we designed a stacked convolutional neural network (CNN) module to learn spatial feature representations from CFDs and a stacked recurrent neural network (RNN) module to learn temporal feature representations from PLM-based embeddings. These features were integrated using attention-based fusion mechanisms to generate high-level feature representations for final classification. Ablation analysis and independent tests demonstrated that the optimal model (DOGpred), employing a stacked 1D CNN and a stacked attention-based RNN module with cross-attention feature fusion, achieved the best performance on the training dataset and significantly outperformed machine learning-based single-feature models and state-of-the-art methods on independent datasets. Furthermore, DOGpred is publicly available at https://github.com/JeonRPM/DOGpred/ for free access and usage.</p>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":" ","pages":"168977"},"PeriodicalIF":4.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143121929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"ERNIE-ac4C: A novel deep learning model for effectively predicting N4-acetylcytidine sites.","authors":"Ronglin Lu, Jianbo Qiao, Kefei Li, Yanxi Zhao, Junru Jin, Feifei Cui, Zilong Zhang, Balachandran Manavalan, Leyi Wei","doi":"10.1016/j.jmb.2025.168978","DOIUrl":"https://doi.org/10.1016/j.jmb.2025.168978","url":null,"abstract":"<p><p>RNA modifications are known to play a critical role in gene regulation and cellular processes. Specifically, N4-acetylcytidine (ac4C) modification has emerged as a significant marker involved in mRNA translation efficiency, stability, and various diseases. Accurate identification of ac4C modification sites is essential for unraveling its functional implications. However, currently available experimental methods suffer from drawbacks such as lengthy detection times, complexity, and high costs, resulting in low efficiency and accuracy in prediction. Although several bioinformatics methods have been proposed and have advanced the prediction of ac4C modification sites, there is still ample room for improvement. In this research, we propose a novel deep learning model, ERNIE-ac4C, which combines the ERNIE-RNA language model and a two-dimensional Convolutional Neural Network (CNN). ERNIE-ac4C utilizes the fusion of sequence features and attention map features to predict ac4C modification sites. ERNIE-ac4C surpasses other state-of-the-art deep learning methods, demonstrating superior accuracy and effectiveness. The availability of the code on GitHub (https://github.com/lrlbcxdd/ERNIEac4C.git) and our openness to feedback from the research community contribute to the model's accessibility and its potential for further advancements. Our study provides valuable insights into ac4C research and enhances our understanding of the functional consequences of RNA modifications.</p>","PeriodicalId":369,"journal":{"name":"Journal of Molecular Biology","volume":" ","pages":"168978"},"PeriodicalIF":4.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143121934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}