RNA-binding proteins are vital regulators in numerous biological processes. Their disfunction can result in diverse diseases, such as cancer or neurodegenerative disorders, making the prediction of their binding sites of high importance. Deep learning (DL) has brought about a revolution in various biological domains, including the field of protein-RNA interactions. Nonetheless, several challenges persist, such as the limited availability of experimentally validated binding sites to train well-performing DL models for the majority of proteins. Here, we present a novel training approach based on transfer learning (TL) to address the issue of limited data. Employing a sophisticated and interpretable architecture, we compare the performance of our method trained using two distinct approaches: training from scratch (SCR) and utilizing TL. Additionally, we benchmark our results against the current state-of-the-art methods. Furthermore, we tackle the challenges associated with selecting appropriate input features and determining optimal interval sizes. Our results show that TL enhances model performance, particularly in datasets with minimal training data, where satisfactory results can be achieved with just a few hundred RNA binding sites. Moreover, we demonstrate that integrating both sequence and evolutionary conservation information leads to superior performance. Additionally, we showcase how incorporating an attention layer into the model facilitates the interpretation of predictions within a biologically relevant context.

• Klíčová slova
• CLIP-seq, RNA-binding protein, deep learning, interpretation, transfer learning,
• Publikační typ
• časopisecké články MeSH

Tudor staphylococcal nuclease (Tudor-SN) and Argonaute (Ago) are conserved components of the basic RNA interference (RNAi) machinery with a variety of functions including immune response and gene regulation. The RNAi machinery has been characterized in tick vectors of human and animal diseases but information is not available on the role of Tudor-SN in tick RNAi and other cellular processes. Our hypothesis is that tick Tudor-SN is part of the RNAi machinery and may be involved in innate immune response and other cellular processes. To address this hypothesis, Ixodes scapularis and I. ricinus ticks and/or cell lines were used to annotate and characterize the role of Tudor-SN in dsRNA-mediated RNAi, immune response to infection with the rickettsia Anaplasma phagocytophilum and the flaviviruses TBEV or LGTV and tick feeding. The results showed that Tudor-SN is conserved in ticks and involved in dsRNA-mediated RNAi and tick feeding but not in defense against infection with the examined viral and rickettsial pathogens. The effect of Tudor-SN gene knockdown on tick feeding could be due to down-regulation of genes that are required for protein processing and blood digestion through a mechanism that may involve selective degradation of dsRNAs enriched in G:U pairs that form as a result of adenosine-to-inosine RNA editing. These results demonstrated that Tudor-SN plays a role in tick RNAi pathway and feeding but no strong evidence for a role in innate immune responses to pathogen infection was found.

• MeSH
• Anaplasma phagocytophilum patogenita   MeSH
• buněčné linie MeSH
• Flavivirus patogenita   MeSH
• fylogeneze MeSH
• jaderné proteiny genetika   metabolismus   MeSH
• klíště genetika   parazitologie   virologie   MeSH
• konzervovaná sekvence MeSH
• křečci praví MeSH
• molekulární sekvence - údaje MeSH
• RNA interference * MeSH
• sekvence aminokyselin MeSH
• transkriptom MeSH
• zvířata MeSH
• Check Tag
• křečci praví MeSH
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Názvy látek
• jaderné proteiny MeSH