Predicting protein-protein interactions through sequence-based deep learning.

Motivation: High-throughput experimental techniques have produced a large amount of protein-protein interaction (PPI) data, but their coverage is still low and the PPI data is also very noisy. Computational prediction of PPIs can be used to discover new PPIs and identify errors in the experimental PPI data. Results: We present a novel deep learning framework, DPPI, to model and predict PPIs from sequence information alone. Our model efficiently applies a deep, Siamese-like convolutional neural network combined with random projection and data augmentation to predict PPIs, leveraging existing high-quality experimental PPI data and evolutionary information of a protein pair under prediction. Our experimental results show that DPPI outperforms the state-of-the-art methods on several benchmarks in terms of area under precision-recall curve (auPR), and computationally is more efficient. We also show that DPPI is able to predict homodimeric interactions where other methods fail to work accurately, and the effectiveness of DPPI in specific applications such as predicting cytokine-receptor binding affinities. Availability and implementation: Predicting protein-protein interactions through sequence-based deep learning): https://github.com/hashemifar/DPPI/. Supplementary information: Supplementary data are available at Bioinformatics online.

Lynx: a knowledge base and an analytical workbench for integrative medicine.

Lynx (http://lynx.ci.uchicago.edu) is a web-based database and a knowledge extraction engine. It supports annotation and analysis of high-throughput experimental data and generation of weighted hypotheses regarding genes and molecular mechanisms contributing to human phenotypes or conditions of interest. Since the last release, the Lynx knowledge base (LynxKB) has been periodically updated with the latest versions of the existing databases and supplemented with additional information from public databases. These additions have enriched the data annotations provided by Lynx and improved the performance of Lynx analytical tools. Moreover, the Lynx analytical workbench has been supplemented with new tools for reconstruction of co-expression networks and feature-and-network-based prioritization of genetic factors and molecular mechanisms. These developments facilitate the extraction of meaningful knowledge from experimental data and LynxKB. The Service Oriented Architecture provides public access to LynxKB and its analytical tools via user-friendly web services and interfaces.

ModuleAlign: module-based global alignment of protein-protein interaction networks.

MOTIVATION: As an increasing amount of protein-protein interaction (PPI) data becomes available, their computational interpretation has become an important problem in bioinformatics. The alignment of PPI networks from different species provides valuable information about conserved subnetworks, evolutionary pathways and functional orthologs. Although several methods have been proposed for global network alignment, there is a pressing need for methods that produce more accurate alignments in terms of both topological and functional consistency. RESULTS: In this work, we present a novel global network alignment algorithm, named ModuleAlign, which makes use of local topology information to define a module-based homology score. Based on a hierarchical clustering of functionally coherent proteins involved in the same module, ModuleAlign employs a novel iterative scheme to find the alignment between two networks. Evaluated on a diverse set of benchmarks, ModuleAlign outperforms state-of-the-art methods in producing functionally consistent alignments. By aligning Pathogen-Human PPI networks, ModuleAlign also detects a novel set of conserved human genes that pathogens preferentially target to cause pathogenesis. AVAILABILITY: http://ttic.uchicago.edu/∼hashemifar/ModuleAlign.html CONTACT: canzar@ttic.edu or j3xu.ttic.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

HubAlign: an accurate and efficient method for global alignment of protein-protein interaction networks.

MOTIVATION: High-throughput experimental techniques have produced a large amount of protein-protein interaction (PPI) data. The study of PPI networks, such as comparative analysis, shall benefit the understanding of life process and diseases at the molecular level. One way of comparative analysis is to align PPI networks to identify conserved or species-specific subnetwork motifs. A few methods have been developed for global PPI network alignment, but it still remains challenging in terms of both accuracy and efficiency. RESULTS: This paper presents a novel global network alignment algorithm, denoted as HubAlign, that makes use of both network topology and sequence homology information, based upon the observation that topologically important proteins in a PPI network usually are much more conserved and thus, more likely to be aligned. HubAlign uses a minimum-degree heuristic algorithm to estimate the topological and functional importance of a protein from the global network topology information. Then HubAlign aligns topologically important proteins first and gradually extends the alignment to the whole network. Extensive tests indicate that HubAlign greatly outperforms several popular methods in terms of both accuracy and efficiency, especially in detecting functionally similar proteins. AVAILABILITY: HubAlign is available freely for non-commercial purposes at http://ttic.uchicago.edu/∼hashemifar/software/HubAlign.zip. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

NETAL: a new graph-based method for global alignment of protein-protein interaction networks.

MOTIVATION: The interactions among proteins and the resulting networks of such interactions have a central role in cell biology. Aligning these networks gives us important information, such as conserved complexes and evolutionary relationships. Although there have been several publications on the global alignment of protein networks; however, none of proposed methods are able to produce a highly conserved and meaningful alignment. Moreover, time complexity of current algorithms makes them impossible to use for multiple alignment of several large networks together. RESULTS: We present a novel algorithm for the global alignment of protein-protein interaction networks. It uses a greedy method, based on the alignment scoring matrix, which is derived from both biological and topological information of input networks to find the best global network alignment. NETAL outperforms other global alignment methods in terms of several measurements, such as Edge Correctness, Largest Common Connected Subgraphs and the number of common Gene Ontology terms between aligned proteins. As the running time of NETAL is much less than other available methods, NETAL can be easily expanded to multiple alignment algorithm. Furthermore, NETAL overpowers all other existing algorithms in term of performance so that the short running time of NETAL allowed us to implement it as the first server for global alignment of protein-protein interaction networks. AVAILABILITY: Binaries supported on linux are freely available for download at http://www.bioinf.cs.ipm.ir/software/netal. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Automated detection of progressive speech changes in early Alzheimer's disease.

Speech and language changes occur in Alzheimer's disease (AD), but few studies have characterized their longitudinal course. We analyzed open-ended speech samples from a prodromal-to-mild AD cohort to develop a novel composite score to characterize progressive speech changes. Participant speech from the Clinical Dementia Rating (CDR) interview was analyzed to compute metrics reflecting speech and language characteristics. We determined the aspects of speech and language that exhibited significant longitudinal change over 18 months. Nine acoustic and linguistic measures were combined to create a novel composite score. The speech composite exhibited significant correlations with primary and secondary clinical endpoints and a similar effect size for detecting longitudinal change. Our results demonstrate the feasibility of using automated speech processing to characterize longitudinal change in early AD. Speech-based composite scores could be used to monitor change and detect response to treatment in future research. HIGHLIGHTS: Longitudinal speech samples were analyzed to characterize speech changes in early AD.Acoustic and linguistic measures showed significant change over 18 months.A novel speech composite score was computed to characterize longitudinal change.The speech composite correlated with primary and secondary trial endpoints.Automated speech analysis could facilitate remote, high frequency monitoring in AD.

Novel candidate genes in esophageal atresia/tracheoesophageal fistula identified by exome sequencing.

The various malformations of the aerodigestive tract collectively known as esophageal atresia/tracheoesophageal fistula (EA/TEF) constitute a rare group of birth defects of largely unknown etiology. Previous studies have identified a small number of rare genetic variants causing syndromes associated with EA/TEF. We performed a pilot exome sequencing study of 45 unrelated simplex trios (probands and parents) with EA/TEF. Thirteen had isolated and 32 had nonisolated EA/TEF; none had a family history of EA/TEF. We identified de novo variants in protein-coding regions, including 19 missense variants predicted to be deleterious (D-mis) and 3 likely gene-disrupting (LGD) variants. Consistent with previous studies of structural birth defects, there is a trend of increased burden of de novo D-mis in cases (1.57-fold increase over the background mutation rate), and the burden is greater in constrained genes (2.55-fold, p = 0.003). There is a frameshift de novo variant in EFTUD2, a known EA/TEF risk gene involved in mRNA splicing. Strikingly, 15 out of 19 de novo D-mis variants are located in genes that are putative target genes of EFTUD2 or SOX2 (another known EA/TEF gene), much greater than expected by chance (3.34-fold, p value = 7.20e-5). We estimated that 33% of patients can be attributed to de novo deleterious variants in known and novel genes. We identified APC2, AMER3, PCDH1, GTF3C1, POLR2B, RAB3GAP2, and ITSN1 as plausible candidate genes in the etiology of EA/TEF. We conclude that further genomic analysis to identify de novo variants will likely identify previously undescribed genetic causes of EA/TEF.

Chemokine expression in the early response to injury in human airway epithelial cells.

Basal airway epithelial cells (AEC) constitute stem/progenitor cells within the central airways and respond to mucosal injury in an ordered sequence of spreading, migration, proliferation, and differentiation to needed cell types. However, dynamic gene transcription in the early events after mucosal injury has not been studied in AEC. We examined gene expression using microarrays following mechanical injury (MI) in primary human AEC grown in submersion culture to generate basal cells and in the air-liquid interface to generate differentiated AEC (dAEC) that include goblet and ciliated cells. A select group of ~150 genes was in differential expression (DE) within 2-24 hr after MI, and enrichment analysis of these genes showed over-representation of functional categories related to inflammatory cytokines and chemokines. Network-based gene prioritization and network reconstruction using the PINTA heat kernel diffusion algorithm demonstrated highly connected networks that were richer in differentiated AEC compared to basal cells. Similar experiments done in basal AEC collected from asthmatic donor lungs demonstrated substantial changes in DE genes and functional categories related to inflammation compared to basal AEC from normal donors. In dAEC, similar but more modest differences were observed. We demonstrate that the AEC transcription signature after MI identifies genes and pathways that are important to the initiation and perpetuation of airway mucosal inflammation. Gene expression occurs quickly after injury and is more profound in differentiated AEC, and is altered in AEC from asthmatic airways. Our data suggest that the early response to injury is substantially different in asthmatic airways, particularly in basal airway epithelial cells.

Differential cell-intrinsic regulations of germinal center B and T cells by miR-146a and miR-146b.

Reciprocal interactions between B and follicular T helper (Tfh) cells orchestrate the germinal center (GC) reaction, a hallmark of humoral immunity. Abnormal GC responses could lead to the production of pathogenic autoantibodies and the development of autoimmunity. Here we show that miR-146a controls GC responses by targeting multiple CD40 signaling pathway components in B cells; by contrast, loss of miR-146a in T cells does not alter humoral responses. However, specific deletion of both miR-146a and its paralog, miR-146b, in T cells increases Tfh cell numbers and enhanced GC reactions. Thus, our data reveal differential cell-intrinsic regulations of GC B and Tfh cells by miR-146a and miR-146b. Together, members of the miR-146 family serve as crucial molecular brakes to coordinately control GC reactions to generate protective humoral responses without eliciting unwanted autoimmunity.

Excessive expression of miR-27 impairs Treg-mediated immunological tolerance.

MicroRNAs (miRs) are tightly regulated in the immune system, and aberrant expression of miRs often results in hematopoietic malignancies and autoimmune diseases. Previously, it was suggested that elevated levels of miR-27 in T cells isolated from patients with multiple sclerosis facilitate disease progression by inhibiting Th2 immunity and promoting pathogenic Th1 responses. Here we have demonstrated that, although mice with T cell-specific overexpression of miR-27 harbor dysregulated Th1 responses and develop autoimmune pathology, these disease phenotypes are not driven by miR-27 in effector T cells in a cell-autonomous manner. Rather, dysregulation of Th1 responses and autoimmunity resulted from a perturbed Treg compartment. Excessive miR-27 expression in murine T cells severely impaired Treg differentiation. Moreover, Tregs with exaggerated miR-27-mediated gene regulation exhibited diminished homeostasis and suppressor function in vivo. Mechanistically, we determined that miR-27 represses several known as well as previously uncharacterized targets that play critical roles in controlling multiple aspects of Treg biology. Collectively, our data show that miR-27 functions as a key regulator in Treg development and function and suggest that proper regulation of miR-27 is pivotal to safeguarding Treg-mediated immunological tolerance.

Strategic Integration of Multiple Bioinformatics Resources for System Level Analysis of Biological Networks.

Recent technological advances in genomics allow the production of biological data at unprecedented tera- and petabyte scales. Efficient mining of these vast and complex datasets for the needs of biomedical research critically depends on a seamless integration of the clinical, genomic, and experimental information with prior knowledge about genotype-phenotype relationships. Such experimental data accumulated in publicly available databases should be accessible to a variety of algorithms and analytical pipelines that drive computational analysis and data mining.We present an integrated computational platform Lynx (Sulakhe et al., Nucleic Acids Res 44:D882-D887, 2016) ( http://lynx.cri.uchicago.edu ), a web-based database and knowledge extraction engine. It provides advanced search capabilities and a variety of algorithms for enrichment analysis and network-based gene prioritization. It gives public access to the Lynx integrated knowledge base (LynxKB) and its analytical tools via user-friendly web services and interfaces. The Lynx service-oriented architecture supports annotation and analysis of high-throughput experimental data. Lynx tools assist the user in extracting meaningful knowledge from LynxKB and experimental data, and in the generation of weighted hypotheses regarding the genes and molecular mechanisms contributing to human phenotypes or conditions of interest. The goal of this integrated platform is to support the end-to-end analytical needs of various translational projects.

Joint Alignment of Multiple Protein-Protein Interaction Networks via Convex Optimization.

High-throughput experimental techniques have been producing more and more protein-protein interaction (PPI) data. The PPI network alignment greatly benefits the understanding of evolutionary relationship among species, helps identify conserved subnetworks, and provides extra information for functional annotations. Although a few methods have been developed for multiple PPI network alignment, the alignment quality is still far from perfect, and thus, new network alignment methods are needed. In this article, we present a novel method, denoted as ConvexAlign, for joint alignment of multiple PPI networks by convex optimization of a scoring function composed of sequence similarity, topological score, and interaction conservation score. In contrast to existing methods that generate multiple alignments in a greedy or progressive manner, our convex method optimizes alignments globally and enforces consistency among all pairwise alignments, resulting in much better alignment quality. Tested on both synthetic and real data, our experimental results show that ConvexAlign outperforms several popular methods in producing functionally coherent alignments. ConvexAlign even has a larger advantage over the others in aligning real PPI networks. ConvexAlign also finds a few conserved complexes, which cannot be detected by the other methods.