Drug repurposing and prediction of multiple interaction types via graph embedding.

BACKGROUND: Finding drugs that can interact with a specific target to induce a desired therapeutic outcome is key deliverable in drug discovery for targeted treatment. Therefore, both identifying new drug-target links, as well as delineating the type of drug interaction, are important in drug repurposing studies. RESULTS: A computational drug repurposing approach was proposed to predict novel drug-target interactions (DTIs), as well as to predict the type of interaction induced. The methodology is based on mining a heterogeneous graph that integrates drug-drug and protein-protein similarity networks, together with verified drug-disease and protein-disease associations. In order to extract appropriate features, the three-layer heterogeneous graph was mapped to low dimensional vectors using node embedding principles. The DTI prediction problem was formulated as a multi-label, multi-class classification task, aiming to determine drug modes of action. DTIs were defined by concatenating pairs of drug and target vectors extracted from graph embedding, which were used as input to classification via gradient boosted trees, where a model is trained to predict the type of interaction. After validating the prediction ability of DT2Vec+, a comprehensive analysis of all unknown DTIs was conducted to predict the degree and type of interaction. Finally, the model was applied to propose potential approved drugs to target cancer-specific biomarkers. CONCLUSION: DT2Vec+ showed promising results in predicting type of DTI, which was achieved via integrating and mapping triplet drug-target-disease association graphs into low-dimensional dense vectors. To our knowledge, this is the first approach that addresses prediction between drugs and targets across six interaction types.

Novel drug-target interactions via link prediction and network embedding.

BACKGROUND: As many interactions between the chemical and genomic space remain undiscovered, computational methods able to identify potential drug-target interactions (DTIs) are employed to accelerate drug discovery and reduce the required cost. Predicting new DTIs can leverage drug repurposing by identifying new targets for approved drugs. However, developing an accurate computational framework that can efficiently incorporate chemical and genomic spaces remains extremely demanding. A key issue is that most DTI predictions suffer from the lack of experimentally validated negative interactions or limited availability of target 3D structures. RESULTS: We report DT2Vec, a pipeline for DTI prediction based on graph embedding and gradient boosted tree classification. It maps drug-drug and protein-protein similarity networks to low-dimensional features and the DTI prediction is formulated as binary classification based on a strategy of concatenating the drug and target embedding vectors as input features. DT2Vec was compared with three top-performing graph similarity-based algorithms on a standard benchmark dataset and achieved competitive results. In order to explore credible novel DTIs, the model was applied to data from the ChEMBL repository that contain experimentally validated positive and negative interactions which yield a strong predictive model. Then, the developed model was applied to all possible unknown DTIs to predict new interactions. The applicability of DT2Vec as an effective method for drug repurposing is discussed through case studies and evaluation of some novel DTI predictions is undertaken using molecular docking. CONCLUSIONS: The proposed method was able to integrate and map chemical and genomic space into low-dimensional dense vectors and showed promising results in predicting novel DTIs.

Cancer Grade Model: a multi-gene machine learning-based risk classification for improving prognosis in breast cancer.

BACKGROUND: Prognostic stratification of breast cancers remains a challenge to improve clinical decision making. We employ machine learning on breast cancer transcriptomics from multiple studies to link the expression of specific genes to histological grade and classify tumours into a more or less aggressive prognostic type. MATERIALS AND METHODS: Microarray data of 5031 untreated breast tumours spanning 33 published datasets and corresponding clinical data were integrated. A machine learning model based on gradient boosted trees was trained on histological grade-1 and grade-3 samples. The resulting predictive model (Cancer Grade Model, CGM) was applied on samples of grade-2 and unknown-grade (3029) for prognostic risk classification. RESULTS: A 70-gene signature for assessing clinical risk was identified and was shown to be 90% accurate when tested on known histological-grade samples. The predictive framework was validated through survival analysis and showed robust prognostic performance. CGM was cross-referenced with existing genomic tests and demonstrated the competitive predictive power of tumour risk. CONCLUSIONS: CGM is able to classify tumours into better-defined prognostic categories without employing information on tumour size, stage, or subgroups. The model offers means to improve prognosis and support the clinical decision and precision treatments, thereby potentially contributing to preventing underdiagnosis of high-risk tumours and minimising over-treatment of low-risk disease.

An immunologically relevant rodent model demonstrates safety of therapy using a tumour-specific IgE.

BACKGROUND: Designing biologically informative models for assessing the safety of novel agents, especially for cancer immunotherapy, carries substantial challenges. The choice of an in vivo system for studies on IgE antibodies represents a major impediment to their clinical translation, especially with respect to class-specific immunological functions and safety. Fcε receptor expression and structure are different in humans and mice, so that the murine system is not informative when studying human IgE biology. By contrast, FcεRI expression and cellular distribution in rats mirror that of humans. METHODS: We are developing MOv18 IgE, a human chimeric antibody recognizing the tumour-associated antigen folate receptor alpha. We created an immunologically congruent surrogate rat model likely to recapitulate human IgE-FcεR interactions and engineered a surrogate rat IgE equivalent to MOv18. Employing this model, we examined in vivo safety and efficacy of antitumour IgE antibodies. RESULTS: In immunocompetent rats, rodent IgE restricted growth of syngeneic tumours in the absence of clinical, histopathological or metabolic signs associated with obvious toxicity. No physiological or immunological evidence of a "cytokine storm" or allergic response was seen, even at 50 mg/kg weekly doses. IgE treatment was associated with elevated serum concentrations of TNFα, a mediator previously linked with IgE-mediated antitumour and antiparasitic functions, alongside evidence of substantially elevated tumoural immune cell infiltration and immunological pathway activation in tumour-bearing lungs. CONCLUSION: Our findings indicate safety of MOv18 IgE, in conjunction with efficacy and immune activation, supporting the translation of this therapeutic approach to the clinical arena.

Recent developments and future directions in computational genomics.

Computational genomics is a subfield of computational biology that deals with the analysis of entire genome sequences. Transcending the boundaries of classical sequence analysis, computational genomics exploits the inherent properties of entire genomes by modelling them as systems. We review recent developments in the field, discuss in some detail a number of novel approaches that take into account the genomic context and argue that progress will be made by novel knowledge representation and simulation technologies.

Selection of chromatographic protein purification operations based on physicochemical properties.

The charge characteristics of four proteins (conalbumin, ovalbumin, apotransferrin, and soybean trypsin inhibitor) were determined over a range of pH using an electrophoretic technique (titration curve). HPLC anion-exchange chromatography for each of the proteins was performed to investigate whether electrophoretic and chromatographic results could be correlated. It was found that charge density, estimated from the electrophoretic titration curves (as net charge divided by the protein molecular weight) in most cases correlates extremely well the retention of the protein in terms of time needed for the protein to be eluted from the column. This correlation was far better than that of net charge or that of surface charge (net charge/surface area). The performance of anion-exchange chromatography, hydrophobic interaction chromatography, and gel filtration using preparative columns on an FPLC were compared. The ability of each method to separate the components of the mixture of the four proteins was assessed by calculating the resolution of the chromatographic results obtained for each pair of proteins. Using the concept of the deviation factor (DF) between individual properties of pairs of proteins (charge density, molecular weight, hydrophobicity), the separation efficiency factor (eta s) could be calculated. Resolution results showed that anion exchange was the best technique for separating the proteins followed by hydrophobic interaction chromatography and gel filtration. Calculations for efficiency, eta s, confirmed the superiority of anion-exchange chromatography as a separation method over gel filtration. For hydrophobic interaction chromatography, it was not possible to find a suitable parameter to express DF and, consequently, eta s. An appropriate way to express the hydrophobicity of a protein, as a physicochemical property, that can be used in the expression of DF should be investigated.

Rapid monitoring of virus-like particles using an optical biosensor: a feasibility study.

Virus-like particles (VLPs) are multimeric proteins expressed by Saccharomyces cerevisiae. The particles are approximately 80 nm in diameter and they are used as a framework for a range of biological products; for example as carriers of viral antigens. Rapid monitoring of purified VLPs was investigated using an optical biosensor. The aim was to develop an assay which may be employed for real-time bioprocess monitoring of VLPs. Problems of mass transfer of analyte were overcome through selection of a planar biosensor surface, in preference to the traditional polymer-coated surface. To prolong the surface activity for interaction analysis, a sandwich assay was developed which involved the use of a secondary capture species. It was shown that VLP concentration in pure solution could be determined within 10 min.

Selective flocculation and precipitation for the improvement of virus-like particle recovery from yeast homogenate.

The purification of an intracellular product from a complex mixture of contaminants after cell disruption is a common problem in processes downstream of fermentation systems. This is particularly challenging for the recovery of particulate (80 nm in diameter) multimeric protein products, named virus-like particles (VLPs), from cell debris and other intracellular components. Selective flocculation for debris removal followed by selective precipitation of the target protein can be used as a preclarification step to aid purification. In this paper, selective borax flocculation of cell debris in yeast homogenate, followed by selective poly(ethylene glycol) precipitation of VLPs are defined with a view to demonstrating their potential in aiding the initial clarification stages of the purification sequence. The translation from laboratory scale to pilot scale operation is addressed, demonstrating the challenge of scale-up of solid-liquid separation stages for biological particle processing.

Virus-like particle analysis in yeast homogenate using a laser light-scattering assay.

Virus-like particles (VLPs) expressed intracellularly by the yeast S. cerevisiae have helped set the framework of a wide range of biologicals, particularly as carriers for viral antigens. This article investigates the use of dynamic light scattering (DLS) for the rapid evaluation of the concentration and purity of VLPs to aid the complex purification strategy. Development of the assay was performed in a high background process stream (yeast homogenate) and involved a change in the signal proportional to the VLP concentration by addition of antibodies that bind on the VLP surface and detection of that size change by DLS. Overall, the assay was found to provide a significant improvement of rapid monitoring alternatives for VLPs, exhibiting good sensitivity and speed of measurement. Data are given for the use of the DLS-based assay for optimization of VLP release during a yeast cell disruption treatment.

Functional versatility and molecular diversity of the metabolic map of Escherichia coli.

We have analyzed the known metabolic enzymes of Escherichia coli in relation to their biochemical reaction properties and their involvement in biochemical pathways. All enzymes involved in small-molecule metabolism and their corresponding protein sequences have been extracted from the EcoCyc database. These 548 metabolic enzymes are clustered into 405 protein families according to sequence similarity. In this study, we examine the functional versatility within enzyme families in terms of their reaction capabilities and pathway participation. In addition, we examine the molecular diversity of reactions and pathways according to their presence across enzyme families. These complex, many-to-many relationships between protein sequence and biochemical function reveal a significant degree of correlation between enzyme families and reactions. Pathways, however, appear to require more than one enzyme type to perform their complex biochemical transformations. Finally, the distribution of enzyme family members across different pathways provides support for the "recruitment" hypothesis of biochemical pathway evolution.

CAST: an iterative algorithm for the complexity analysis of sequence tracts. Complexity analysis of sequence tracts.

MOTIVATION: Sensitive detection and masking of low-complexity regions in protein sequences. Filtered sequences can be used in sequence comparison without the risk of matching compositionally biased regions. The main advantage of the method over similar approaches is the selective masking of single residue types without affecting other, possibly important, regions. RESULTS: A novel algorithm for low-complexity region detection and selective masking. The algorithm is based on multiple-pass Smith-Waterman comparison of the query sequence against twenty homopolymers with infinite gap penalties. The output of the algorithm is both the masked query sequence for further analysis, e.g. database searches, as well as the regions of low complexity. The detection of low-complexity regions is highly specific for single residue types. It is shown that this approach is sufficient for masking database query sequences without generating false positives. The algorithm is benchmarked against widely available algorithms using the 210 genes of Plasmodium falciparum chromosome 2, a dataset known to contain a large number of low-complexity regions. AVAILABILITY: CAST (version 1.0) executable binaries are available to academic users free of charge under license. Web site entry point, server and additional material: http://www.ebi.ac.uk/research/cgg/services/cast/

Genome sequences and great expectations.

To assess how automatic function assignment will contribute to genome annotation in the next five years, we have performed an analysis of 31 available genome sequences. An emerging pattern is that function can be predicted for almost two-thirds of the 73,500 genes that were analyzed. Despite progress in computational biology, there will always be a great need for large-scale experimental determination of protein function.