Proteins perform much of the work in living organisms, and consequently the development of efficient computational methods for protein representation is essential for advancing large-scale biological research. Most current approaches struggle to efficiently integrate the wealth of information contained in the protein sequence and structure. In this paper, we propose a novel framework for embedding protein graphs in geometric vector spaces, by learning an encoder function that preserves the structural distance between protein graphs. Utilizing Graph Neural Networks (GNNs) and Large Language Models (LLMs), the proposed framework generates structure- and sequence- aware protein representations. We demonstrate that our embeddings are successful in the task of comparing protein structures, while providing a significant speed-up compared to traditional approaches based on structural alignment. Our framework achieves remarkable results in the task of protein structure classification; in particular, when compared to other work, the proposed method shows an average F1-Score improvement of 26% on out-of-distribution (OOD) samples and of 32% when tested on samples coming from the same distribution as the training data. Our approach finds applications in areas such as drug prioritization, drug re-purposing, disease sub-type analysis and elsewhere.

Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) involves acquiring a sequence of MRIs during the administration of a contrast agent. Radiologists then aim to discern the contrast uptake differences between malignant and benign lesions for tumor classification. Regrettably, existing literature underutilizes the temporal structure inherent to DCEMRI time series, leading to tumor classifications based on individual instants rather than entire sequences. This research introduces two Graph Neural Network (GNN)-based methods designed to aggregate information from multiple instants within the DCE-MRI sequence. Each lesion undergoes manual segmentation, and radiomic features are individually extracted from each time instant of the DCE-MRI sequence. Two graph construction methodologies are proposed: (i) a fully connected graph topology, aiming to represent each temporal instant as a node in a graph; (ii) a multiplex network, named MUGI-MRI (MUltiplex Graph neural network for Integration of MRI), where each layer identifies an instant of the DCE-MRI sequence. MUGI-MRI achieves an AUROC of 0.8017 ± 0.1146, showcasing promising performance in lesion classification. In addition to improving upon current state-of-the-art, the integration capability of MUGIMRI addresses the problem of imbalance between sensitivity and specificity, which affects numerous studies in the realm of DCE-MRI. Our findings strongly indicate that the aggregation of information across all time instants is pivotal for enhancing the diagnostic process, and vastly superior to a simplistic instant-wise analysis. While applied to MRI sequences, our approach can be extended to general problems of multimodal data integration.

Graph Neural Networks (GNNs) have demonstrated remarkable success in learning from graph-structured data. However, they face significant limitations in expressive power, struggling with long-range interactions and lacking a principled approach to modeling higher-order structures and group interactions. Cellular Isomorphism Networks (CINs) recently addressed most of these challenges with a message passing scheme based on cell complexes. Despite their advantages, CINs make use only of boundary and upper messages which do not consider a direct interaction between the rings present in the underlying complex. Accounting for these interactions might be crucial for learning representations of many real-world complex phenomena such as the dynamics of supramolecular assemblies, neural activity within the brain, and gene regulation processes. In this work, we propose CIN++, an enhancement of the topological message passing scheme introduced in CINs. Our message passing scheme accounts for the aforementioned limitations by letting the cells receive also lower messages within each layer. By providing a more comprehensive representation of higher-order and long-range interactions, our enhanced topological message passing scheme achieves state-of-the-art results on large-scale and long-range chemistry benchmarks.

MOTIVATION: The cost of drug development has dramatically increased in the last decades, with the number new drugs approved per billion US dollars spent on R&D halving every year or less. The selection and prioritization of targets is one the most influential decisions in drug discovery. Here we present a Gaussian Process model for the prioritization of drug targets cast as a problem of learning with only positive and unlabeled examples. RESULTS: Since the absence of negative samples does not allow standard methods for automatic selection of hyperparameters, we propose a novel approach for hyperparameter selection of the kernel in One Class Gaussian Processes. We compare our methods with state-of-the-art approaches on benchmark datasets and then show its application to druggability prediction of oncology drugs. Our score reaches an AUC 0.90 on a set of clinical trial targets starting from a small training set of 102 validated oncology targets. Our score recovers the majority of known drug targets and can be used to identify novel set of proteins as drug target candidates. AVAILABILITY AND IMPLEMENTATION: The matrix of features for each protein is available at: https://bit.ly/3iLgZTa. Source code implemented in Python is freely available for download at https://github.com/AntonioDeFalco/Adaptive-OCGP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Multiple databases provide valuable information about curated pathways and other resources that can be used to build and analyze networks. OmniPath combines 61 (and continuously growing) network resources into a comprehensive collection, with over 120 000 interactions. We present here the OmniPath App, a Cytoscape plugin to flexibly import data from OmniPath via a simple and intuitive interface. Thus, it makes possible to directly access the large body of high-quality knowledge provided by OmniPath within Cytoscape for inspection and further use with other tools. AVAILABILITY AND IMPLEMENTATION: The OmniPath App has been developed for Cytoscape 3 in the Java programing language. The latest source code and the plugin can be found at: https://github.com/saezlab/Omnipath_Cytoscape and http://apps.cytoscape.org/apps/omnipath, respectively. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Small non-coding RNAs (ncRNAs) are short non-coding sequences involved in gene regulation in many biological processes and diseases. The lack of a complete comprehension of their biological functionality, especially in a genome-wide scenario, has demanded new computational approaches to annotate their roles. It is widely known that secondary structure is determinant to know RNA function and machine learning based approaches have been successfully proven to predict RNA function from secondary structure information. Here we show that RNA function can be predicted with good accuracy from a lightweight representation of sequence information without the necessity of computing secondary structure features which is computationally expensive. This finding appears to go against the dogma of secondary structure being a key determinant of function in RNA. Compared to recent secondary structure based methods, the proposed solution is more robust to sequence boundary noise and reduces drastically the computational cost allowing for large data volume annotations. Scripts and datasets to reproduce the results of experiments proposed in this study are available at: https://github.com/bioinformatics-sannio/ncrna-deep.