Analysis of chimeric reads characterises the diverse targetome of AGO2-mediated regulation.

Argonaute proteins are instrumental in regulating RNA stability and translation. AGO2, the major mammalian Argonaute protein, is known to primarily associate with microRNAs, a family of small RNA 'guide' sequences, and identifies its targets primarily via a 'seed' mediated partial complementarity process. Despite numerous studies, a definitive experimental dataset of AGO2 'guide'-'target' interactions remains elusive. Our study employs two experimental methods-AGO2 CLASH and AGO2 eCLIP, to generate thousands of AGO2 target sites verified by chimeric reads. These chimeric reads contain both the AGO2 loaded small RNA 'guide' and the target sequence, providing a robust resource for modeling AGO2 binding preferences. Our novel analysis pipeline reveals thousands of AGO2 target sites driven by microRNAs and a significant number of AGO2 'guides' derived from fragments of other small RNAs such as tRNAs, YRNAs, snoRNAs, rRNAs, and more. We utilize convolutional neural networks to train machine learning models that accurately predict the binding potential for each 'guide' class and experimentally validate several interactions. In conclusion, our comprehensive analysis of the AGO2 targetome broadens our understanding of its 'guide' repertoire and potential function in development and disease. Moreover, we offer practical bioinformatic tools for future experiments and the prediction of AGO2 targets. All data and code from this study are freely available at https://github.com/ML-Bioinfo-CEITEC/HybriDetector/ .

Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics.

Quantification of the dynamics of RNA metabolism is essential for understanding gene regulation in health and disease. Existing methods rely on metabolic labeling of nascent RNAs and physical separation or inference of labeling through PCR-generated mutations, followed by short-read sequencing. However, these methods are limited in their ability to identify transient decay intermediates or co-analyze RNA decay with cis-regulatory elements of RNA stability such as poly(A) tail length and modification status, at single molecule resolution. Here we use 5-ethynyl uridine (5EU) to label nascent RNA followed by direct RNA sequencing with nanopores. We developed RNAkinet, a deep convolutional and recurrent neural network that processes the electrical signal produced by nanopore sequencing to identify 5EU-labeled nascent RNA molecules. RNAkinet demonstrates generalizability to distinct cell types and organisms and reproducibly quantifies RNA kinetic parameters allowing the combined interrogation of RNA metabolism and cis-acting RNA regulatory elements.

Transfer Learning Allows Accurate RBP Target Site Prediction with Limited Sample Sizes.

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.

The SAP domain of Ku facilitates its efficient loading onto DNA ends.

The evolutionarily conserved DNA repair complex Ku serves as the primary sensor of free DNA ends in eukaryotic cells. Its rapid association with DNA ends is crucial for several cellular processes, including non-homologous end joining (NHEJ) DNA repair and telomere protection. In this study, we conducted a transient kinetic analysis to investigate the impact of the SAP domain on individual phases of the Ku-DNA interaction. Specifically, we examined the initial binding, the subsequent docking of Ku onto DNA, and sliding of Ku along DNA. Our findings revealed that the C-terminal SAP domain of Ku70 facilitates the initial phases of the Ku-DNA interaction but does not affect the sliding process. This suggests that the SAP domain may either establish the first interactions with DNA, or stabilize these initial interactions during loading. To assess the biological role of the SAP domain, we generated Arabidopsis plants expressing Ku lacking the SAP domain. Intriguingly, despite the decreased efficiency of the ΔSAP Ku complex in loading onto DNA, the mutant plants exhibited full proficiency in classical NHEJ and telomere maintenance. This indicates that the speed with which Ku loads onto telomeres or DNA double-strand breaks is not the decisive factor in stabilizing these DNA structures.

Genomic benchmarks: a collection of datasets for genomic sequence classification.

BACKGROUND: Recently, deep neural networks have been successfully applied in many biological fields. In 2020, a deep learning model AlphaFold won the protein folding competition with predicted structures within the error tolerance of experimental methods. However, this solution to the most prominent bioinformatic challenge of the past 50 years has been possible only thanks to a carefully curated benchmark of experimentally predicted protein structures. In Genomics, we have similar challenges (annotation of genomes and identification of functional elements) but currently, we lack benchmarks similar to protein folding competition. RESULTS: Here we present a collection of curated and easily accessible sequence classification datasets in the field of genomics. The proposed collection is based on a combination of novel datasets constructed from the mining of publicly available databases and existing datasets obtained from published articles. The collection currently contains nine datasets that focus on regulatory elements (promoters, enhancers, open chromatin region) from three model organisms: human, mouse, and roundworm. A simple convolution neural network is also included in a repository and can be used as a baseline model. Benchmarks and the baseline model are distributed as the Python package 'genomic-benchmarks', and the code is available at https://github.com/ML-Bioinfo-CEITEC/genomic_benchmarks . CONCLUSIONS: Deep learning techniques revolutionized many biological fields but mainly thanks to the carefully curated benchmarks. For the field of Genomics, we propose a collection of benchmark datasets for the classification of genomic sequences with an interface for the most commonly used deep learning libraries, implementation of the simple neural network and a training framework that can be used as a starting point for future research. The main aim of this effort is to create a repository for shared datasets that will make machine learning for genomics more comparable and reproducible while reducing the overhead of researchers who want to enter the field, leading to healthy competition and new discoveries.

The MOV10 RNA helicase is a dosage-dependent host restriction factor for LINE1 retrotransposition in mice.

Transposable elements constitute nearly half of the mammalian genome and play important roles in genome evolution. While a multitude of both transcriptional and post-transcriptional mechanisms exist to silence transposable elements, control of transposition in vivo remains poorly understood. MOV10, an RNA helicase, is an inhibitor of mobilization of retrotransposons and retroviruses in cell culture assays. Here we report that MOV10 restricts LINE1 retrotransposition in mice. Although MOV10 is broadly expressed, its loss causes only incomplete penetrance of embryonic lethality, and the surviving MOV10-deficient mice are healthy and fertile. Biochemically, MOV10 forms a complex with UPF1, a key component of the nonsense-mediated mRNA decay pathway, and primarily binds to the 3' UTR of somatically expressed transcripts in testis. Consequently, loss of MOV10 results in an altered transcriptome in testis. Analyses using a LINE1 reporter transgene reveal that loss of MOV10 leads to increased LINE1 retrotransposition in somatic and reproductive tissues from both embryos and adult mice. Moreover, the degree of LINE1 retrotransposition inhibition is dependent on the Mov10 gene dosage. Furthermore, MOV10 deficiency reduces reproductive fitness over successive generations. Our findings demonstrate that MOV10 attenuates LINE1 retrotransposition in a dosage-dependent manner in mice.

Hormone-regulated expansins: Expression, localization, and cell wall biomechanics in Arabidopsis root growth.

Expansins facilitate cell expansion by mediating pH-dependent cell wall (CW) loosening. However, the role of expansins in controlling CW biomechanical properties in specific tissues and organs remains elusive. We monitored hormonal responsiveness and spatial specificity of expression and localization of expansins predicted to be the direct targets of cytokinin signaling in Arabidopsis (Arabidopsis thaliana). We found EXPANSIN1 (EXPA1) homogenously distributed throughout the CW of columella/lateral root cap, while EXPA10 and EXPA14 localized predominantly at 3-cell boundaries in the epidermis/cortex in various root zones. EXPA15 revealed cell-type-specific combination of homogenous vs. 3-cell boundaries localization. By comparing Brillouin frequency shift and AFM-measured Young's modulus, we demonstrated Brillouin light scattering (BLS) as a tool suitable for non-invasive in vivo quantitative assessment of CW viscoelasticity. Using both BLS and AFM, we showed that EXPA1 overexpression upregulated CW stiffness in the root transition zone (TZ). The dexamethasone-controlled EXPA1 overexpression induced fast changes in the transcription of numerous CW-associated genes, including several EXPAs and XYLOGLUCAN:XYLOGLUCOSYL TRANSFERASEs (XTHs), and associated with rapid pectin methylesterification determined by in situ Fourier-transform infrared spectroscopy in the root TZ. The EXPA1-induced CW remodeling is associated with the shortening of the root apical meristem, leading to root growth arrest. Based on our results, we propose that expansins control root growth by a delicate orchestration of CW biomechanical properties, possibly regulating both CW loosening and CW remodeling.

Using Attribution Sequence Alignment to Interpret Deep Learning Models for miRNA Binding Site Prediction.

MicroRNAs (miRNAs) are small non-coding RNAs that play a central role in the post-transcriptional regulation of biological processes. miRNAs regulate transcripts through direct binding involving the Argonaute protein family. The exact rules of binding are not known, and several in silico miRNA target prediction methods have been developed to date. Deep learning has recently revolutionized miRNA target prediction. However, the higher predictive power comes with a decreased ability to interpret increasingly complex models. Here, we present a novel interpretation technique, called attribution sequence alignment, for miRNA target site prediction models that can interpret such deep learning models on a two-dimensional representation of miRNA and putative target sequence. Our method produces a human readable visual representation of miRNA:target interactions and can be used as a proxy for the further interpretation of biological concepts learned by the neural network. We demonstrate applications of this method in the clustering of experimental data into binding classes, as well as using the method to narrow down predicted miRNA binding sites on long transcript sequences. Importantly, the presented method works with any neural network model trained on a two-dimensional representation of interactions and can be easily extended to further domains such as protein-protein interactions.

Catsnap: a user-friendly algorithm for determining the conservation of protein variants reveals extensive parallelisms in the evolution of alternative splicing.

Understanding the evolutionary conservation of complex eukaryotic transcriptomes significantly illuminates the physiological relevance of alternative splicing (AS). Examining the evolutionary depth of a given AS event with ordinary homology searches is generally challenging and time-consuming. Here, we present Catsnap, an algorithmic pipeline for assessing the conservation of putative protein isoforms generated by AS. It employs a machine learning approach following a database search with the provided pair of protein sequences. We used the Catsnap algorithm for analyzing the conservation of emerging experimentally characterized alternative proteins from plants and animals. Indeed, most of them are conserved among other species. Catsnap can detect the conserved functional protein isoforms regardless of the AS type by which they are generated. Notably, we found that while the primary amino acid sequence is maintained, the type of AS determining the inclusion or exclusion of protein regions varies throughout plant phylogenetic lineages in these proteins. We also document that this phenomenon is less seen among animals. In sum, our algorithm highlights the presence of unexpectedly frequent hotspots where protein isoforms recurrently arise to carry physiologically relevant functions. The user web interface is available at https://catsnap.cesnet.cz/.

Small RNA Targets: Advances in Prediction Tools and High-Throughput Profiling.

MicroRNAs (miRNAs) are an abundant class of small non-coding RNAs that regulate gene expression at the post-transcriptional level. They are suggested to be involved in most biological processes of the cell primarily by targeting messenger RNAs (mRNAs) for cleavage or translational repression. Their binding to their target sites is mediated by the Argonaute (AGO) family of proteins. Thus, miRNA target prediction is pivotal for research and clinical applications. Moreover, transfer-RNA-derived fragments (tRFs) and other types of small RNAs have been found to be potent regulators of Ago-mediated gene expression. Their role in mRNA regulation is still to be fully elucidated, and advancements in the computational prediction of their targets are in their infancy. To shed light on these complex RNA-RNA interactions, the availability of good quality high-throughput data and reliable computational methods is of utmost importance. Even though the arsenal of computational approaches in the field has been enriched in the last decade, there is still a degree of discrepancy between the results they yield. This review offers an overview of the relevant advancements in the field of bioinformatics and machine learning and summarizes the key strategies utilized for small RNA target prediction. Furthermore, we report the recent development of high-throughput sequencing technologies, and explore the role of non-miRNA AGO driver sequences.

miRBind: A Deep Learning Method for miRNA Binding Classification.

The binding of microRNAs (miRNAs) to their target sites is a complex process, mediated by the Argonaute (Ago) family of proteins. The prediction of miRNA:target site binding is an important first step for any miRNA target prediction algorithm. To date, the potential for miRNA:target site binding is evaluated using either co-folding free energy measures or heuristic approaches, based on the identification of binding 'seeds', i.e., continuous stretches of binding corresponding to specific parts of the miRNA. The limitations of both these families of methods have produced generations of miRNA target prediction algorithms that are primarily focused on 'canonical' seed targets, even though unbiased experimental methods have shown that only approximately half of in vivo miRNA targets are 'canonical'. Herein, we present miRBind, a deep learning method and web server that can be used to accurately predict the potential of miRNA:target site binding. We trained our method using seed-agnostic experimental data and show that our method outperforms both seed-based approaches and co-fold free energy approaches. The full code for the development of miRBind and a freely accessible web server are freely available.

Economic crisis in Greece: The invisible enemy of blood donation or not?

INTRODUCTION: Volunteering presupposes having free time and refers to the provision of services without the motivation of material reward, for the benefit of society. In this study, we aimed to provide insight into the impact of economic crisis on blood donors and their motivation to donate blood during that period. STUDY DESIGN AND METHODS: We asked blood donors about their blood donation activity and motivation to donate using a standardized, anonymous questionnaire (n = 3000). Descriptive analysis was performed for the consideration of donor turnout during this economic period. The results were analyzed using the χ2 test and Spearman's correlation coefficient. RESULTS: Regarding gender, 68.2% were males, while 31.8% were females. Most blood donors donated voluntarily (75.8%) and only 24.2% were replacement or family blood donors. The economic crisis has affected the inhabitants of Athens more than the inhabitants of the province (χ2 = 9.910,p = 0.007). The influence of economic crisis on the regular blood donors' quality of life was greater than the non-regular donors (χ2 = 16.227,p < 0.001). According to our results, the economic crisis reduced the quality of life, but it did not affect the frequency of blood donations in a percentage of 87,3%. Not any significant difference was found between employment status, economic crisis and blood donation. CONCLUSION: Although the economic crisis has affected the lives of blood donors, it does not seem to affect the frequency of blood donation. We suggest that blood collection services should consider specialist campaigns that focus on the altruistic motivation of donors during an economic crisis.

ENNGene: an Easy Neural Network model building tool for Genomics.

BACKGROUND: The recent big data revolution in Genomics, coupled with the emergence of Deep Learning as a set of powerful machine learning methods, has shifted the standard practices of machine learning for Genomics. Even though Deep Learning methods such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are becoming widespread in Genomics, developing and training such models is outside the ability of most researchers in the field. RESULTS: Here we present ENNGene-Easy Neural Network model building tool for Genomics. This tool simplifies training of custom CNN or hybrid CNN-RNN models on genomic data via an easy-to-use Graphical User Interface. ENNGene allows multiple input branches, including sequence, evolutionary conservation, and secondary structure, and performs all the necessary preprocessing steps, allowing simple input such as genomic coordinates. The network architecture is selected and fully customized by the user, from the number and types of the layers to each layer's precise set-up. ENNGene then deals with all steps of training and evaluation of the model, exporting valuable metrics such as multi-class ROC and precision-recall curve plots or TensorBoard log files. To facilitate interpretation of the predicted results, we deploy Integrated Gradients, providing the user with a graphical representation of an attribution level of each input position. To showcase the usage of ENNGene, we train multiple models on the RBP24 dataset, quickly reaching the state of the art while improving the performance on more than half of the proteins by including the evolutionary conservation score and tuning the network per protein. CONCLUSIONS: As the role of DL in big data analysis in the near future is indisputable, it is important to make it available for a broader range of researchers. We believe that an easy-to-use tool such as ENNGene can allow Genomics researchers without a background in Computational Sciences to harness the power of DL to gain better insights into and extract important information from the large amounts of data available in the field.

Bioinformatics and Machine Learning Approaches to Understand the Regulation of Mobile Genetic Elements.

Transposable elements (TEs, or mobile genetic elements, MGEs) are ubiquitous genetic elements that make up a substantial proportion of the genome of many species. The recent growing interest in understanding the evolution and function of TEs has revealed that TEs play a dual role in genome evolution, development, disease, and drug resistance. Cells regulate TE expression against uncontrolled activity that can lead to developmental defects and disease, using multiple strategies, such as DNA chemical modification, small RNA (sRNA) silencing, chromatin modification, as well as sequence-specific repressors. Advancements in bioinformatics and machine learning approaches are increasingly contributing to the analysis of the regulation mechanisms. A plethora of tools and machine learning approaches have been developed for prediction, annotation, and expression profiling of sRNAs, for methylation analysis of TEs, as well as for genome-wide methylation analysis through bisulfite sequencing data. In this review, we provide a guided overview of the bioinformatic and machine learning state of the art of fields closely associated with TE regulation and function.

Modulation of Aub-TDRD interactions elucidates piRNA amplification and germplasm formation.

Aub guided by piRNAs ensures genome integrity by cleaving retrotransposons, and genome propagation by trapping mRNAs to form the germplasm that instructs germ cell formation. Arginines at the N-terminus of Aub (Aub-NTRs) interact with Tudor and other Tudor domain-containing proteins (TDRDs). Aub-TDRD interactions suppress active retrotransposons via piRNA amplification and form germplasm via generation of Aub-Tudor ribonucleoproteins. Here, we show that Aub-NTRs are dispensable for primary piRNA biogenesis but essential for piRNA amplification and that their symmetric dimethylation is required for germplasm formation and germ cell specification but largely redundant for piRNA amplification.

DIANA-miRGen v4: indexing promoters and regulators for more than 1500 microRNAs.

Deregulation of microRNA (miRNA) expression plays a critical role in the transition from a physiological to a pathological state. The accurate miRNA promoter identification in multiple cell types is a fundamental endeavor towards understanding and characterizing the underlying mechanisms of both physiological as well as pathological conditions. DIANA-miRGen v4 (www.microrna.gr/mirgenv4) provides cell type specific miRNA transcription start sites (TSSs) for over 1500 miRNAs retrieved from the analysis of >1000 cap analysis of gene expression (CAGE) samples corresponding to 133 tissues, cell lines and primary cells available in FANTOM repository. MiRNA TSS locations were associated with transcription factor binding site (TFBSs) annotation, for >280 TFs, derived from analyzing the majority of ENCODE ChIP-Seq datasets. For the first time, clusters of cell types having common miRNA TSSs are characterized and provided through a user friendly interface with multiple layers of customization. DIANA-miRGen v4 significantly improves our understanding of miRNA biogenesis regulation at the transcriptional level by providing a unique integration of high-quality annotations for hundreds of cell specific miRNA promoters with experimentally derived TFBSs.

PENGUINN: Precise Exploration of Nuclear G-Quadruplexes Using Interpretable Neural Networks.

G-quadruplexes (G4s) are a class of stable structural nucleic acid secondary structures that are known to play a role in a wide spectrum of genomic functions, such as DNA replication and transcription. The classical understanding of G4 structure points to four variable length guanine strands joined by variable length nucleotide stretches. Experiments using G4 immunoprecipitation and sequencing experiments have produced a high number of highly probable G4 forming genomic sequences. The expense and technical difficulty of experimental techniques highlights the need for computational approaches of G4 identification. Here, we present PENGUINN, a machine learning method based on Convolutional neural networks, that learns the characteristics of G4 sequences and accurately predicts G4s outperforming state-of-the-art methods. We provide both a standalone implementation of the trained model, and a web application that can be used to evaluate sequences for their G4 potential.

CDK9 activity is critical for maintaining MDM4 overexpression in tumor cells.

The identification of the essential role of cyclin-dependent kinases (CDKs) in the control of cell division has prompted the development of small-molecule CDK inhibitors as anticancer drugs. For many of these compounds, the precise mechanism of action in individual tumor types remains unclear as they simultaneously target different classes of CDKs - enzymes controlling the cell cycle progression as well as CDKs involved in the regulation of transcription. CDK inhibitors are also capable of activating p53 tumor suppressor in tumor cells retaining wild-type p53 gene by modulating MDM2 levels and activity. In the current study, we link, for the first time, CDK activity to the overexpression of the MDM4 (MDMX) oncogene in cancer cells. Small-molecule drugs targeting the CDK9 kinase, dinaciclib, flavopiridol, roscovitine, AT-7519, SNS-032, and DRB, diminished MDM4 levels and activated p53 in A375 melanoma and MCF7 breast carcinoma cells with only a limited effect on MDM2. These results suggest that MDM4, rather than MDM2, could be the primary transcriptional target of pharmacological CDK inhibitors in the p53 pathway. CDK9 inhibitor atuveciclib downregulated MDM4 and enhanced p53 activity induced by nutlin-3a, an inhibitor of p53-MDM2 interaction, and synergized with nutlin-3a in killing A375 melanoma cells. Furthermore, we found that human pluripotent stem cell lines express significant levels of MDM4, which are also maintained by CDK9 activity. In summary, we show that CDK9 activity is essential for the maintenance of high levels of MDM4 in human cells, and drugs targeting CDK9 might restore p53 tumor suppressor function in malignancies overexpressing MDM4.

Multi-branch Convolutional Neural Network for Identification of Small Non-coding RNA genomic loci.

Genomic regions that encode small RNA genes exhibit characteristic patterns in their sequence, secondary structure, and evolutionary conservation. Convolutional Neural Networks are a family of algorithms that can classify data based on learned patterns. Here we present MuStARD an application of Convolutional Neural Networks that can learn patterns associated with user-defined sets of genomic regions, and scan large genomic areas for novel regions exhibiting similar characteristics. We demonstrate that MuStARD is a generic method that can be trained on different classes of human small RNA genomic loci, without need for domain specific knowledge, due to the automated feature and background selection processes built into the model. We also demonstrate the ability of MuStARD for inter-species identification of functional elements by predicting mouse small RNAs (pre-miRNAs and snoRNAs) using models trained on the human genome. MuStARD can be used to filter small RNA-Seq datasets for identification of novel small RNA loci, intra- and inter- species, as demonstrated in three use cases of human, mouse, and fly pre-miRNA prediction. MuStARD is easy to deploy and extend to a variety of genomic classification questions. Code and trained models are freely available at gitlab.com/RBP_Bioinformatics/mustard.

Ribothrypsis, a novel process of canonical mRNA decay, mediates ribosome-phased mRNA endonucleolysis.

mRNAs transmit the genetic information that dictates protein production and are a nexus for numerous pathways that regulate gene expression. The prevailing view of canonical mRNA decay is that it is mediated by deadenylation and decapping followed by exonucleolysis from the 3' and 5' ends. By developing Akron-seq, a novel approach that captures the native 3' and 5' ends of capped and polyadenylated RNAs, respectively, we show that canonical human mRNAs are subject to repeated cotranslational and ribosome-phased endonucleolytic cuts at the exit site of the mRNA ribosome channel, in a process that we term ribothrypsis. We uncovered RNA G quadruplexes among likely ribothrypsis triggers and show that ribothrypsis is a conserved process. Strikingly, we found that mRNA fragments are abundant in living cells and thus have important implications for the interpretation of experiments, such as RNA-seq, that rely on the assumption that mRNAs exist largely as full-length molecules in vivo.