Protein remote homology detection and structural alignment using deep learning.

Exploiting sequence-structure-function relationships in biotechnology requires improved methods for aligning proteins that have low sequence similarity to previously annotated proteins. We develop two deep learning methods to address this gap, TM-Vec and DeepBLAST. TM-Vec allows searching for structure-structure similarities in large sequence databases. It is trained to accurately predict TM-scores as a metric of structural similarity directly from sequence pairs without the need for intermediate computation or solution of structures. Once structurally similar proteins have been identified, DeepBLAST can structurally align proteins using only sequence information by identifying structurally homologous regions between proteins. It outperforms traditional sequence alignment methods and performs similarly to structure-based alignment methods. We show the merits of TM-Vec and DeepBLAST on a variety of datasets, including better identification of remotely homologous proteins compared with state-of-the-art sequence alignment and structure prediction methods.

Comprehensive Functional Annotation of Metagenomes and Microbial Genomes Using a Deep Learning-Based Method.

Comprehensive protein function annotation is essential for understanding microbiome-related disease mechanisms in the host organisms. However, a large portion of human gut microbial proteins lack functional annotation. Here, we have developed a new metagenome analysis workflow integrating de novo genome reconstruction, taxonomic profiling, and deep learning-based functional annotations from DeepFRI. This is the first approach to apply deep learning-based functional annotations in metagenomics. We validate DeepFRI functional annotations by comparing them to orthology-based annotations from eggNOG on a set of 1,070 infant metagenomes from the DIABIMMUNE cohort. Using this workflow, we generated a sequence catalogue of 1.9 million nonredundant microbial genes. The functional annotations revealed 70% concordance between Gene Ontology annotations predicted by DeepFRI and eggNOG. DeepFRI improved the annotation coverage, with 99% of the gene catalogue obtaining Gene Ontology molecular function annotations, although they are less specific than those from eggNOG. Additionally, we constructed pangenomes in a reference-free manner using high-quality metagenome-assembled genomes (MAGs) and analyzed the associated annotations. eggNOG annotated more genes on well-studied organisms, such as Escherichia coli, while DeepFRI was less sensitive to taxa. Further, we show that DeepFRI provides additional annotations in comparison to the previous DIABIMMUNE studies. This workflow will contribute to novel understanding of the functional signature of the human gut microbiome in health and disease as well as guiding future metagenomics studies. IMPORTANCE The past decade has seen advancement in high-throughput sequencing technologies resulting in rapid accumulation of genomic data from microbial communities. While this growth in sequence data and gene discovery is impressive, the majority of microbial gene functions remain uncharacterized. The coverage of functional information coming from either experimental sources or inferences is low. To solve these challenges, we have developed a new workflow to computationally assemble microbial genomes and annotate the genes using a deep learning-based model DeepFRI. This improved microbial gene annotation coverage to 1.9 million metagenome-assembled genes, representing 99% of the assembled genes, which is a significant improvement compared to 12% Gene Ontology term annotation coverage by commonly used orthology-based approaches. Importantly, the workflow supports pangenome reconstruction in a reference-free manner, allowing us to analyze the functional potential of individual bacterial species. We therefore propose this alternative approach combining deep-learning functional predictions with the commonly used orthology-based annotations as one that could help us uncover novel functions observed in metagenomic microbiome studies.

Sequence-structure-function relationships in the microbial protein universe.

For the past half-century, structural biologists relied on the notion that similar protein sequences give rise to similar structures and functions. While this assumption has driven research to explore certain parts of the protein universe, it disregards spaces that don't rely on this assumption. Here we explore areas of the protein universe where similar protein functions can be achieved by different sequences and different structures. We predict ~200,000 structures for diverse protein sequences from 1,003 representative genomes across the microbial tree of life and annotate them functionally on a per-residue basis. Structure prediction is accomplished using the World Community Grid, a large-scale citizen science initiative. The resulting database of structural models is complementary to the AlphaFold database, with regards to domains of life as well as sequence diversity and sequence length. We identify 148 novel folds and describe examples where we map specific functions to structural motifs. We also show that the structural space is continuous and largely saturated, highlighting the need for a shift in focus across all branches of biology, from obtaining structures to putting them into context and from sequence-based to sequence-structure-function based meta-omics analyses.

TCRconv: predicting recognition between T cell receptors and epitopes using contextualized motifs.

MOTIVATION: T cells use T cell receptors (TCRs) to recognize small parts of antigens, called epitopes, presented by major histocompatibility complexes. Once an epitope is recognized, an immune response is initiated and T cell activation and proliferation by clonal expansion begin. Clonal populations of T cells with identical TCRs can remain in the body for years, thus forming immunological memory and potentially mappable immunological signatures, which could have implications in clinical applications including infectious diseases, autoimmunity and tumor immunology. RESULTS: We introduce TCRconv, a deep learning model for predicting recognition between TCRs and epitopes. TCRconv uses a deep protein language model and convolutions to extract contextualized motifs and provides state-of-the-art TCR-epitope prediction accuracy. Using TCR repertoires from COVID-19 patients, we demonstrate that TCRconv can provide insight into T cell dynamics and phenotypes during the disease. AVAILABILITY AND IMPLEMENTATION: TCRconv is available at https://github.com/emmijokinen/tcrconv. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Structure-based protein function prediction using graph convolutional networks.

The rapid increase in the number of proteins in sequence databases and the diversity of their functions challenge computational approaches for automated function prediction. Here, we introduce DeepFRI, a Graph Convolutional Network for predicting protein functions by leveraging sequence features extracted from a protein language model and protein structures. It outperforms current leading methods and sequence-based Convolutional Neural Networks and scales to the size of current sequence repositories. Augmenting the training set of experimental structures with homology models allows us to significantly expand the number of predictable functions. DeepFRI has significant de-noising capability, with only a minor drop in performance when experimental structures are replaced by protein models. Class activation mapping allows function predictions at an unprecedented resolution, allowing site-specific annotations at the residue-level in an automated manner. We show the utility and high performance of our method by annotating structures from the PDB and SWISS-MODEL, making several new confident function predictions. DeepFRI is available as a webserver at https://beta.deepfri.flatironinstitute.org/ .

NetQuilt: deep multispecies network-based protein function prediction using homology-informed network similarity.

MOTIVATION: Transferring knowledge between species is challenging: different species contain distinct proteomes and cellular architectures, which cause their proteins to carry out different functions via different interaction networks. Many approaches to protein functional annotation use sequence similarity to transfer knowledge between species. These approaches cannot produce accurate predictions for proteins without homologues of known function, as many functions require cellular context for meaningful prediction. To supply this context, network-based methods use protein-protein interaction (PPI) networks as a source of information for inferring protein function and have demonstrated promising results in function prediction. However, most of these methods are tied to a network for a single species, and many species lack biological networks. RESULTS: In this work, we integrate sequence and network information across multiple species by computing IsoRank similarity scores to create a meta-network profile of the proteins of multiple species. We use this integrated multispecies meta-network as input to train a maxout neural network with Gene Ontology terms as target labels. Our multispecies approach takes advantage of more training examples, and consequently leads to significant improvements in function prediction performance compared to two network-based methods, a deep learning sequence-based method and the BLAST annotation method used in the Critial Assessment of Functional Annotation. We are able to demonstrate that our approach performs well even in cases where a species has no network information available: when an organism's PPI network is left out we can use our multi-species method to make predictions for the left-out organism with good performance. AVAILABILITY AND IMPLEMENTATION: The code is freely available at https://github.com/nowittynamesleft/NetQuilt. The data, including sequences, PPI networks and GO annotations are available at https://string-db.org/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Non-Negative Matrix Factorizations for Multiplex Network Analysis.

Networks have been a general tool for representing, analyzing, and modeling relational data arising in several domains. One of the most important aspect of network analysis is community detection or network clustering. Until recently, the major focus have been on discovering community structure in single (i.e., monoplex) networks. However, with the advent of relational data with multiple modalities, multiplex networks, i.e., networks composed of multiple layers representing different aspects of relations, have emerged. Consequently, community detection in multiplex network, i.e., detecting clusters of nodes shared by all layers, has become a new challenge. In this paper, we propose Network Fusion for Composite Community Extraction (NF-CCE), a new class of algorithms, based on four different non-negative matrix factorization models, capable of extracting composite communities in multiplex networks. Each algorithm works in two steps: first, it finds a non-negative, low-dimensional feature representation of each network layer; then, it fuses the feature representation of layers into a common non-negative, low-dimensional feature representation via collective factorization. The composite clusters are extracted from the common feature representation. We demonstrate the superior performance of our algorithms over the state-of-the-art methods on various types of multiplex networks, including biological, social, economic, citation, phone communication, and brain multiplex networks.

deepNF: deep network fusion for protein function prediction.

Motivation: The prevalence of high-throughput experimental methods has resulted in an abundance of large-scale molecular and functional interaction networks. The connectivity of these networks provides a rich source of information for inferring functional annotations for genes and proteins. An important challenge has been to develop methods for combining these heterogeneous networks to extract useful protein feature representations for function prediction. Most of the existing approaches for network integration use shallow models that encounter difficulty in capturing complex and highly non-linear network structures. Thus, we propose deepNF, a network fusion method based on Multimodal Deep Autoencoders to extract high-level features of proteins from multiple heterogeneous interaction networks. Results: We apply this method to combine STRING networks to construct a common low-dimensional representation containing high-level protein features. We use separate layers for different network types in the early stages of the multimodal autoencoder, later connecting all the layers into a single bottleneck layer from which we extract features to predict protein function. We compare the cross-validation and temporal holdout predictive performance of our method with state-of-the-art methods, including the recently proposed method Mashup. Our results show that our method outperforms previous methods for both human and yeast STRING networks. We also show substantial improvement in the performance of our method in predicting gene ontology terms of varying type and specificity. Availability and implementation: deepNF is freely available at: https://github.com/VGligorijevic/deepNF. Supplementary information: Supplementary data are available at Bioinformatics online.

PATIENT-SPECIFIC DATA FUSION FOR CANCER STRATIFICATION AND PERSONALISED TREATMENT.

According to Cancer Research UK, cancer is a leading cause of death accounting for more than one in four of all deaths in 2011. The recent advances in experimental technologies in cancer research have resulted in the accumulation of large amounts of patient-specific datasets, which provide complementary information on the same cancer type. We introduce a versatile data fusion (integration) framework that can effectively integrate somatic mutation data, molecular interactions and drug chemical data to address three key challenges in cancer research: stratification of patients into groups having different clinical outcomes, prediction of driver genes whose mutations trigger the onset and development of cancers, and repurposing of drugs treating particular cancer patient groups. Our new framework is based on graph-regularised non-negative matrix tri-factorization, a machine learning technique for co-clustering heterogeneous datasets. We apply our framework on ovarian cancer data to simultaneously cluster patients, genes and drugs by utilising all datasets.We demonstrate superior performance of our method over the state-of-the-art method, Network-based Stratification, in identifying three patient subgroups that have significant differences in survival outcomes and that are in good agreement with other clinical data. Also, we identify potential new driver genes that we obtain by analysing the gene clusters enriched in known drivers of ovarian cancer progression. We validated the top scoring genes identified as new drivers through database search and biomedical literature curation. Finally, we identify potential candidate drugs for repurposing that could be used in treatment of the identified patient subgroups by targeting their mutated gene products. We validated a large percentage of our drug-target predictions by using other databases and through literature curation.

Integrative methods for analyzing big data in precision medicine.

We provide an overview of recent developments in big data analyses in the context of precision medicine and health informatics. With the advance in technologies capturing molecular and medical data, we entered the area of "Big Data" in biology and medicine. These data offer many opportunities to advance precision medicine. We outline key challenges in precision medicine and present recent advances in data integration-based methods to uncover personalized information from big data produced by various omics studies. We survey recent integrative methods for disease subtyping, biomarkers discovery, and drug repurposing, and list the tools that are available to domain scientists. Given the ever-growing nature of these big data, we highlight key issues that big data integration methods will face.

Fuse: multiple network alignment via data fusion.

MOTIVATION: Discovering patterns in networks of protein-protein interactions (PPIs) is a central problem in systems biology. Alignments between these networks aid functional understanding as they uncover important information, such as evolutionary conserved pathways, protein complexes and functional orthologs. However, the complexity of the multiple network alignment problem grows exponentially with the number of networks being aligned and designing a multiple network aligner that is both scalable and that produces biologically relevant alignments is a challenging task that has not been fully addressed. The objective of multiple network alignment is to create clusters of nodes that are evolutionarily and functionally conserved across all networks. Unfortunately, the alignment methods proposed thus far do not meet this objective as they are guided by pairwise scores that do not utilize the entire functional and evolutionary information across all networks. RESULTS: To overcome this weakness, we propose Fuse, a new multiple network alignment algorithm that works in two steps. First, it computes our novel protein functional similarity scores by fusing information from wiring patterns of all aligned PPI networks and sequence similarities between their proteins. This is in contrast with the previous tools that are all based on protein similarities in pairs of networks being aligned. Our comprehensive new protein similarity scores are computed by Non-negative Matrix Tri-Factorization (NMTF) method that predicts associations between proteins whose homology (from sequences) and functioning similarity (from wiring patterns) are supported by all networks. Using the five largest and most complete PPI networks from BioGRID, we show that NMTF predicts a large number protein pairs that are biologically consistent. Second, to identify clusters of aligned proteins over all networks, Fuse uses our novel maximum weight k-partite matching approximation algorithm. We compare Fuse with the state of the art multiple network aligners and show that (i) by using only sequence alignment scores, Fuse already outperforms other aligners and produces a larger number of biologically consistent clusters that cover all aligned PPI networks and (ii) using both sequence alignments and topological NMTF-predicted scores leads to the best multiple network alignments thus far. AVAILABILITY AND IMPLEMENTATION: Our dataset and software are freely available from the web site: http://bio-nets.doc.ic.ac.uk/Fuse/ CONTACT: natasha@imperial.ac.uk SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Methods for biological data integration: perspectives and challenges.

Rapid technological advances have led to the production of different types of biological data and enabled construction of complex networks with various types of interactions between diverse biological entities. Standard network data analysis methods were shown to be limited in dealing with such heterogeneous networked data and consequently, new methods for integrative data analyses have been proposed. The integrative methods can collectively mine multiple types of biological data and produce more holistic, systems-level biological insights. We survey recent methods for collective mining (integration) of various types of networked biological data. We compare different state-of-the-art methods for data integration and highlight their advantages and disadvantages in addressing important biological problems. We identify the important computational challenges of these methods and provide a general guideline for which methods are suited for specific biological problems, or specific data types. Moreover, we propose that recent non-negative matrix factorization-based approaches may become the integration methodology of choice, as they are well suited and accurate in dealing with heterogeneous data and have many opportunities for further development.

Integration of molecular network data reconstructs Gene Ontology.

MOTIVATION: Recently, a shift was made from using Gene Ontology (GO) to evaluate molecular network data to using these data to construct and evaluate GO. Dutkowski et al. provide the first evidence that a large part of GO can be reconstructed solely from topologies of molecular networks. Motivated by this work, we develop a novel data integration framework that integrates multiple types of molecular network data to reconstruct and update GO. We ask how much of GO can be recovered by integrating various molecular interaction data. RESULTS: We introduce a computational framework for integration of various biological networks using penalized non-negative matrix tri-factorization (PNMTF). It takes all network data in a matrix form and performs simultaneous clustering of genes and GO terms, inducing new relations between genes and GO terms (annotations) and between GO terms themselves. To improve the accuracy of our predicted relations, we extend the integration methodology to include additional topological information represented as the similarity in wiring around non-interacting genes. Surprisingly, by integrating topologies of bakers' yeasts protein-protein interaction, genetic interaction (GI) and co-expression networks, our method reports as related 96% of GO terms that are directly related in GO. The inclusion of the wiring similarity of non-interacting genes contributes 6% to this large GO term association capture. Furthermore, we use our method to infer new relationships between GO terms solely from the topologies of these networks and validate 44% of our predictions in the literature. In addition, our integration method reproduces 48% of cellular component, 41% of molecular function and 41% of biological process GO terms, outperforming the previous method in the former two domains of GO. Finally, we predict new GO annotations of yeast genes and validate our predictions through GIs profiling. AVAILABILITY AND IMPLEMENTATION: Supplementary Tables of new GO term associations and predicted gene annotations are available at http://bio-nets.doc.ic.ac.uk/GO-Reconstruction/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Network wiring of pleiotropic kinases yields insight into protective role of diabetes on aneurysm.

Recent studies suggest a protective role of diabetes in the development of aneurysm, but the biological mechanisms behind this are still unknown. This type of association is not present in the case of diabetes and atherosclerosis despite similar risk factors for aneurysm and atherosclerosis. We postulate the existence of genes that disrupt the pathways needed for the onset of aneurysm in the presence of diabetes. Motivated by the significance of genetic interactions in understanding disease-disease associations, we tackle this problem by integrating protein-protein interaction and genetic interaction data, i.e., we examine the biological pathways related to the three diseases that contain genes involved in the following genetic interactions: one gene in a genetic interaction is part of a diabetes pathway, the other gene is part of an aneurysm, or an atherosclerosis pathway. We create a protein-protein interaction sub-network that contains disease pathways described above. We then use a "brokerage" measure - a topological measure that identifies proteins in this sub-network whose removal severely affects the interconnectedness of their neighbourhood, enabling such proteins to disrupt the pathway they are in. We identify a set of proteins with high brokerage values and find this set to be enriched in biological functions, including cell-matrix adhesion, which facilitates mechanisms that have already been suggested as possible causes of diabetes-aneurysm association. We further narrow down our set to 16 proteins that are involved in an aneurysm or an atherosclerosis pathway and are encoded by genes participating in genetic interactions with a gene in a diabetes pathway. This set is enriched in kinases and phosphorylation processes, with two pleiotropic kinases that are involved in both aneurysm and atherosclerosis pathways. Kinases can turn on or off proteins, explaining how functional changes of such proteins could result in the disruption of pathways. So if in an aneurysm-related pathway a gene is turned off, the onset of the disease could be prevented. However, mutations of pleiotropic genes could have effects only on one of the traits, which explains why pleiotropic kinases that are involved in both aneurysm and atherosclerosis pathways could disrupt aneurysm pathways explaining the reduced risk of aneurysm in diabetes patients, but not affect the atherosclerosis pathways.

Autoimmune polyglandular syndrome type 2, alopecia universalis and Crohn's disease.

Autoimmune polyglandular syndromes are defined as a spectrum of association between 2 or more organ specific endocrinopaties and non-endocrine autoimmune diseases. Autoimmune polyglandular syndromes type 2 is characterized by the coexistence of adrenal failure with autoimmune thyroid disease and diabetes mellitus type 1. Inflammatory bowel diseases are rarely associated with these autoimmune disorders. Here, we report about a case of 33 years old male with known history of Crohn's colitis diagnosed in childhood. In 2003 the patient experienced sudden loss of hair, eyebrows, eyelashes, beard and body hair - alopecia universalis was diagnosed. At the age of 28, the patient was hospitalized with severe dehydration and clinical signs of ketoacidosis. Increased blood glucose (40 mmol/L), ketonuria and metabolic acidosis indicated diabetes mellitus type 1. In 2005, he had severe relapse of Crohn's disease and was treated with systemic corticosteroid. Although patient responded well to the induction therapy, fatigue, hypotension, bradycardia called for further investigations: free thyroxine - 6.99 pmol/L, thyroid-stimulating hormone >75 U/ml, anti-thyroid peroxidase antibodies >1000 U/mL, so diagnosis of Haschimoto thyroiditis was confirmed. Persistent hypotension and fatigue, recurrent hypoglycemic crises indicated a possible presence of hypo-function of adrenal glands. After complete withdrawal of corticosteroid therapy, low cortisol levels (69.4 nmol/L) and positive tetracosactide stimulation test proved adrenal cortex failure. Regardless of the intensive treatment for diabetes, hypothyroidism, adrenal insufficiency and Crohn's disease, it was extremely difficult to achieve and maintain control of all four diseases.

How the online social networks are used: dialogues-based structure of MySpace.

Quantitative study of collective dynamics in online social networks is a new challenge based on the abundance of empirical data. Conclusions, however, may depend on factors such as user's psychology profiles and their reasons to use the online contacts. In this study, we have compiled and analysed two datasets from MySpace. The data contain networked dialogues occurring within a specified time depth, high temporal resolution and texts of messages, in which the emotion valence is assessed by using the SentiStrength classifier. Performing a comprehensive analysis, we obtain three groups of results: dynamic topology of the dialogues-based networks have a characteristic structure with Zipf's distribution of communities, low link reciprocity and disassortative correlations. Overlaps supporting 'weak-ties' hypothesis are found to follow the laws recently conjectured for online games. Long-range temporal correlations and persistent fluctuations occur in the time series of messages carrying positive (negative) emotion; patterns of user communications have dominant positive emotion (attractiveness) and strong impact of circadian cycles and interactivity times longer than 1 day. Taken together, these results give a new insight into the functioning of online social networks and unveil the importance of the amount of information and emotion that is communicated along the social links. All data used in this study are fully anonymized.