ReLiance: a machine learning and literature-based prioritization of receptor--ligand pairings.

MOTIVATION: The prediction of receptor-ligand pairings is an important area of research as intercellular communications are mediated by the successful interaction of these key proteins. As the exhaustive assaying of receptor-ligand pairs is impractical, a computational approach to predict pairings is necessary. We propose a workflow to carry out this interaction prediction task, using a text mining approach in conjunction with a state of the art prediction method, as well as a widely accessible and comprehensive dataset. Among several modern classifiers, random forests have been found to be the best at this prediction task. The training of this classifier was carried out using an experimentally validated dataset of Database of Ligand-Receptor Partners (DLRP) receptor-ligand pairs. New examples, co-cited with the training receptors and ligands, are then classified using the trained classifier. After applying our method, we find that we are able to successfully predict receptor-ligand pairs within the GPCR family with a balanced accuracy of 0.96. Upon further inspection, we find several supported interactions that were not present in the Database of Interacting Proteins (DIPdatabase). We have measured the balanced accuracy of our method resulting in high quality predictions stored in the available database ReLiance. AVAILABILITY: http://homes.esat.kuleuven.be/~bioiuser/ReLianceDB/index.php CONTACT: yves.moreau@esat.kuleuven.be; ernesto.iacucci@gmail.com SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Predicting receptor-ligand pairs through kernel learning.

BACKGROUND: Regulation of cellular events is, often, initiated via extracellular signaling. Extracellular signaling occurs when a circulating ligand interacts with one or more membrane-bound receptors. Identification of receptor-ligand pairs is thus an important and specific form of PPI prediction. RESULTS: Given a set of disparate data sources (expression data, domain content, and phylogenetic profile) we seek to predict new receptor-ligand pairs. We create a combined kernel classifier and assess its performance with respect to the Database of Ligand-Receptor Partners (DLRP) 'golden standard' as well as the method proposed by Gertz et al. Among our findings, we discover that our predictions for the tgfß family accurately reconstruct over 76% of the supported edges (0.76 recall and 0.67 precision) of the receptor-ligand bipartite graph defined by the DLRP "golden standard". In addition, for the tgfß family, the combined kernel classifier is able to relatively improve upon the Gertz et al. work by a factor of approximately 1.5 when considering that our method has an F-measure of 0.71 while that of Gertz et al. has a value of 0.48. CONCLUSIONS: The prediction of receptor-ligand pairings is a difficult and complex task. We have demonstrated that using kernel learning on multiple data sources provides a stronger alternative to the existing method in solving this task.

Bempegaldesleukin (NKTR-214) plus Nivolumab in Patients with Advanced Solid Tumors: Phase I Dose-Escalation Study of Safety, Efficacy, and Immune Activation (PIVOT-02).

This single-arm, phase I dose-escalation trial (NCT02983045) evaluated bempegaldesleukin (NKTR-214/BEMPEG), a CD122-preferential IL2 pathway agonist, plus nivolumab in 38 patients with selected immunotherapy-naïve advanced solid tumors (melanoma, renal cell carcinoma, and non-small cell lung cancer). Three dose-limiting toxicities were reported in 2 of 17 patients during dose escalation [hypotension (n = 1), hyperglycemia (n = 1), metabolic acidosis (n = 1)]. The most common treatment-related adverse events (TRAE) were flu-like symptoms (86.8%), rash (78.9%), fatigue (73.7%), and pruritus (52.6%). Eight patients (21.1%) experienced grade 3/4 TRAEs; there were no treatment-related deaths. Total objective response rate across tumor types and dose cohorts was 59.5% (22/37), with 7 complete responses (18.9%). Cellular and gene expression analysis of longitudinal tumor biopsies revealed increased infiltration, activation, and cytotoxicity of CD8+ T cells, without regulatory T-cell enhancement. At the recommended phase II dose, BEMPEG 0.006 mg/kg plus nivolumab 360 mg every 3 weeks, the combination was well tolerated and demonstrated encouraging clinical activity irrespective of baseline PD-L1 status. SIGNIFICANCE: These data show that BEMPEG can be successfully combined with a checkpoint inhibitor as dual immunotherapy for a range of advanced solid tumors. Efficacy was observed regardless of baseline PD-L1 status and baseline levels of tumor-infiltrating lymphocytes, suggesting therapeutic potential for patients with poor prognostic risk factors for response to PD-1/PD-L1 blockade.See related commentary by Rouanne et al., p. 1097.This article is highlighted in the In This Issue feature, p. 1079.

Unraveling genomic variation from next generation sequencing data.

Elucidating the content of a DNA sequence is critical to deeper understand and decode the genetic information for any biological system. As next generation sequencing (NGS) techniques have become cheaper and more advanced in throughput over time, great innovations and breakthrough conclusions have been generated in various biological areas. Few of these areas, which get shaped by the new technological advances, involve evolution of species, microbial mapping, population genetics, genome-wide association studies (GWAs), comparative genomics, variant analysis, gene expression, gene regulation, epigenetics and personalized medicine. While NGS techniques stand as key players in modern biological research, the analysis and the interpretation of the vast amount of data that gets produced is a not an easy or a trivial task and still remains a great challenge in the field of bioinformatics. Therefore, efficient tools to cope with information overload, tackle the high complexity and provide meaningful visualizations to make the knowledge extraction easier are essential. In this article, we briefly refer to the sequencing methodologies and the available equipment to serve these analyses and we describe the data formats of the files which get produced by them. We conclude with a thorough review of tools developed to efficiently store, analyze and visualize such data with emphasis in structural variation analysis and comparative genomics. We finally comment on their functionality, strengths and weaknesses and we discuss how future applications could further develop in this field.

Methods for Determining the Statistical Significance of Enrichment or Depletion of Gene Ontology Classifications under Weighted Membership.

High-throughput molecular biology studies, such as microarray assays of gene expression, two-hybrid experiments for detecting protein interactions, or ChIP-Seq experiments for transcription factor binding, often result in an "interesting" set of genes - say, genes that are co-expressed or bound by the same factor. One way of understanding the biological meaning of such a set is to consider what processes or functions, as defined in an ontology, are over-represented (enriched) or under-represented (depleted) among genes in the set. Usually, the significance of enrichment or depletion scores is based on simple statistical models and on the membership of genes in different classifications. We consider the more general problem of computing p-values for arbitrary integer additive statistics, or weighted membership functions. Such membership functions can be used to represent, for example, prior knowledge on the role of certain genes or classifications, differential importance of different classifications or genes to the experimenter, hierarchical relationships between classifications, or different degrees of interestingness or evidence for specific genes. We describe a generic dynamic programming algorithm that can compute exact p-values for arbitrary integer additive statistics. We also describe several optimizations for important special cases, which can provide orders-of-magnitude speed up in the computations. We apply our methods to datasets describing oxidative phosphorylation and parturition and compare p-values based on computations of several different statistics for measuring enrichment. We find major differences between p-values resulting from these statistics, and that some statistics recover "gold standard" annotations of the data better than others. Our work establishes a theoretical and algorithmic basis for far richer notions of enrichment or depletion of gene sets with respect to gene ontologies than has previously been available.

Which clustering algorithm is better for predicting protein complexes?

BACKGROUND: Protein-Protein interactions (PPI) play a key role in determining the outcome of most cellular processes. The correct identification and characterization of protein interactions and the networks, which they comprise, is critical for understanding the molecular mechanisms within the cell. Large-scale techniques such as pull down assays and tandem affinity purification are used in order to detect protein interactions in an organism. Today, relatively new high-throughput methods like yeast two hybrid, mass spectrometry, microarrays, and phage display are also used to reveal protein interaction networks. RESULTS: In this paper we evaluated four different clustering algorithms using six different interaction datasets. We parameterized the MCL, Spectral, RNSC and Affinity Propagation algorithms and applied them to six PPI datasets produced experimentally by Yeast 2 Hybrid (Y2H) and Tandem Affinity Purification (TAP) methods. The predicted clusters, so called protein complexes, were then compared and benchmarked with already known complexes stored in published databases. CONCLUSIONS: While results may differ upon parameterization, the MCL and RNSC algorithms seem to be more promising and more accurate at predicting PPI complexes. Moreover, they predict more complexes than other reviewed algorithms in absolute numbers. On the other hand the spectral clustering algorithm achieves the highest valid prediction rate in our experiments. However, it is nearly always outperformed by both RNSC and MCL in terms of the geometrical accuracy while it generates the fewest valid clusters than any other reviewed algorithm. This article demonstrates various metrics to evaluate the accuracy of such predictions as they are presented in the text below. Supplementary material can be found at: http://www.bioacademy.gr/bioinformatics/projects/ppireview.htm.