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.

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.

Rapid identification of pathogens in blood serum via Raman tweezers in combination with advanced processing methods.

Pathogenic microbes contribute to several major global diseases that kill millions of people every year. Bloodstream infections caused by these microbes are associated with high morbidity and mortality rates, which are among the most common causes of hospitalizations. The search for the "Holy Grail" in clinical diagnostic microbiology, a reliable, accurate, low cost, real-time, and easy-to-use diagnostic method, is one of the essential issues in clinical practice. These very critical conditions can be met by Raman tweezers in combination with advanced analysis methods. Here, we present a proof-of-concept study based on Raman tweezers combined with spectral mixture analysis that allows for the identification of microbial strains directly from human blood serum without user intervention, thus eliminating the influence of a data analyst.

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.

Cost-effective straightforward method for captured whole mitogenome sequencing of ancient DNA.

Working with mitochondrial DNA from highly degraded samples is challenging. We present a whole mitogenome Illumina-based sequencing method suitable for highly degraded samples. The method makes use of double-stranded library preparation with hybridization-based target enrichment. The aim of the study was to implement a new user-friendly method for analysing many ancient DNA samples at low cost. The method combines the Swift 2S™ Turbo library preparation kit and xGen® panel for mitogenome enrichment. Swift allows to use low input of aDNA and own adapters and primers, handles inhibitors well, and has only two purification steps. xGen is straightforward to use and is able to leverage already pooled libraries. Given the ancient DNA is more challenging to work with, the protocol was developed with several improvements, especially multiplying DNA input in case of low concentration DNA extractions followed by AMPure® beads size selection and real-time pre-capture PCR monitoring in order to avoid cycle-optimization step. Nine out of eleven analysed samples successfully retrieved mitogenomes. Hence, our method provides an effective analysis of whole mtDNA, and has proven to be fast, cost-effective, straightforward, with utilisation in population-wide research of burial sites.