Jérôme Azé

A new protein--protein docking scoring function based on interface residue properties

MOTIVATIONnProtein-protein complexes are known to play key roles in many cellular processes. However, they are often not accessible to experimental study because of their low stability and difficulty to produce the proteins and assemble them in native conformation. Thus, docking algorithms have been developed to provide an in silico approach of the problem. A protein-protein docking procedure traditionally consists of two successive tasks: a search algorithm generates a large number of candidate solutions, and then a scoring function is used to rank them.nnnRESULTSnTo address the second step, we developed a scoring function based on a Voronoï tessellation of the protein three-dimensional structure. We showed that the Voronoï representation may be used to describe in a simplified but useful manner, the geometric and physico-chemical complementarities of two molecular surfaces. We measured a set of parameters on native protein-protein complexes and on decoys, and used them as attributes in several statistical learning procedures: a logistic function, Support Vector Machines (SVM), and a genetic algorithm. For the later, we used ROGER, a genetic algorithm designed to optimize the area under the receiver operating characteristics curve. To further test the scores derived with ROGER, we ranked models generated by two different docking algorithms on targets of a blind prediction experiment, improving in almost all cases the rank of native-like solutions.nnnAVAILABILITYnhttp://genomics.eu.org/spip/-Bioinformatics-tools-

Unraveling the molecular architecture of a G protein-coupled receptor/ β -arrestin/Erk module complex

β-arrestins serve as signaling scaffolds downstream of G protein-coupled receptors, and thus play a crucial role in a plethora of cellular processes. Although it is largely accepted that the ability of β-arrestins to interact simultaneously with many protein partners is key in G protein-independent signaling of GPCRs, only the precise knowledge of these multimeric arrangements will allow a full understanding of the dynamics of these interactions and their functional consequences. However, current experimental procedures for the determination of the three-dimensional structures of protein-protein complexes are not well adapted to analyze these short-lived, multi-component assemblies. We propose a model of the receptor/β-arrestin/Erk1 signaling module, which is consistent with most of the available experimental data. Moreover, for the β-arrestin/Raf1 and the β-arrestin/ERK interactions, we have used the model to design interfering peptides and shown that they compete with both partners, hereby demonstrating the validity of the predicted interaction regions.

Genomics and Machine Learning for Taxonomy Consensus: The Mycobacterium tuberculosis Complex Paradigm

Infra-species taxonomy is a prerequisite to compare features such as virulence in different pathogen lineages. Mycobacterium tuberculosis complex taxonomy has rapidly evolved in the last 20 years through intensive clinical isolation, advances in sequencing and in the description of fast-evolving loci (CRISPR and MIRU-VNTR). On-line tools to describe new isolates have been set up based on known diversity either on CRISPRs (also known as spoligotypes) or on MIRU-VNTR profiles. The underlying taxonomies are largely concordant but use different names and offer different depths. The objectives of this study were 1) to explicit the consensus that exists between the alternative taxonomies, and 2) to provide an on-line tool to ease classification of new isolates. Genotyping (24-VNTR, 43-spacers spoligotypes, IS6110-RFLP) was undertaken for 3,454 clinical isolates from the Netherlands (2004-2008). The resulting database was enlarged with African isolates to include most human tuberculosis diversity. Assignations were obtained using TB-Lineage, MIRU-VNTRPlus, SITVITWEB and an algorithm from Borile et al. By identifying the recurrent concordances between the alternative taxonomies, we proposed a consensus including 22 sublineages. Original and consensus assignations of the all isolates from the database were subsequently implemented into an ensemble learning approach based on Machine Learning tool Weka to derive a classification scheme. All assignations were reproduced with very good sensibilities and specificities. When applied to independent datasets, it was able to suggest new sublineages such as pseudo-Beijing. This Lineage Prediction tool, efficient on 15-MIRU, 24-VNTR and spoligotype data is available on the web interface “TBminer.” Another section of this website helps summarizing key molecular epidemiological data, easing tuberculosis surveillance. Altogether, we successfully used Machine Learning on a large dataset to set up and make available the first consensual taxonomy for human Mycobacterium tuberculosis complex. Additional developments using SNPs will help stabilizing it.

Towards a semi-automatic functional annotation tool based on decision-tree techniques

BackgroundDue to the continuous improvements of high throughput technologies and experimental procedures, the number of sequenced genomes is increasing exponentially. Ultimately, the task of annotating these data relies on the expertise of biologists. The necessity for annotation to be supervised by human experts is the rate limiting step of the data analysis. To face the deluge of new genomic data, the need for automating, as much as possible, the annotation process becomes critical.ResultsWe consider annotation of a protein with terms of the functional hierarchy that has been used to annotate Bacillus subtilis and propose a set of rules that predict classes in terms of elements of the functional hierarchy, i.e., a class is a node or a leaf of the hierarchy tree. The rules are obtained through two decision-trees techniques: first-order decision-trees and multilabel attribute-value decision-trees, by using as training data the proteins from two lactic bacteria: Lactobacillus sakei and Lactobacillus bulgaricus. We tested the two methods, first independently, then in a combined approach, and evaluated the obtained results using hierarchical evaluation measures. Results obtained for the two approaches on both genomes are comparable and show a good precision together with a high prediction rate. Using combined approaches increases the recall and the prediction rate.ConclusionThe combination of the two approaches is very encouraging and we will further refine these combinations in order to get rules even more useful for the annotators. This first study is a crucial step towards designing a semi-automatic functional annotation tool.

A knowledge discovery process for spatiotemporal data: Application to river water quality monitoring

Rapid population growth and human activity (such as agriculture, industry, transports,...) development have increased vulnerability risk for water resources. Due to the complexity of natural processes and the numerous interactions between hydro-systems and human pressures, water quality is difficult to be quantified. In this context, we present a knowledge discovery process applied to hydrological data. To achieve this objective, we combine successive methods to extract knowledge on data collected at stations located along several rivers. Firstly, data is pre-processed in order to obtain different spatial proximities. Later, we apply a standard algorithm to extract sequential patterns. Finally we propose a combination of two techniques (1) to filter patterns based on interest measure, and; (2) to group and present them graphically, to help the experts. Such elements can be used to assess spatialized indicators to assist the interpretation of ecological and river monitoring pressure data.

Efficient Prediction of Co-Complexed Proteins Based on Coevolution

The prediction of the network of protein-protein interactions (PPI) of an organism is crucial for the understanding of biological processes and for the development of new drugs. Machine learning methods have been successfully applied to the prediction of PPI in yeast by the integration of multiple direct and indirect biological data sources. However, experimental data are not available for most organisms. We propose here an ensemble machine learning approach for the prediction of PPI that depends solely on features independent from experimental data. We developed new estimators of the coevolution between proteins and combined them in an ensemble learning procedure. We applied this method to a dataset of known co-complexed proteins in Escherichia coli and compared it to previously published methods. We show that our method allows prediction of PPI with an unprecedented precision of 95.5% for the first 200 sorted pairs of proteins compared to 28.5% on the same dataset with the previous best method. A close inspection of the best predicted pairs allowed us to detect new or recently discovered interactions between chemotactic components, the flagellar apparatus and RNA polymerase complexes in E. coli.

Comparing Voronoi and Laguerre Tessellations in the Protein-Protein Docking Context

Most proteins fulfill their functions through the interaction with other proteins. Because most of these interactions are transitory, they are difficult to detect experimentally, and obtaining the structure of the complex is generally not possible. Consequently, prediction of the existence of these interactions and of the structure of the resulting complex has received a lot of attention in the last decade. However, proteins are very complex objects, and classical computing methods have lead to computer-time consuming methods, whose accuracy is not sufficient for large-scale exploration of the so-called “interactome”, the ensemble of protein-protein complexes in the cell. In order to design an accurate and high-throughput prediction method for protein-protein docking, the first step was to model a protein structure using a formalism allowing fast computation, without losing the intrinsic properties of the object. In our work, we have tested two different, but related, formalisms: the Voronoi and Laguerre tessellations. We present here a comparison of these two models in the context of protein-protein docking.

Collaborative Content-Based Method for Estimating User Reputation in Online Forums

Collaborative ratings of forum posts have been successfully applied in order to infer the reputations of forum users. Famous websites such as Slashdot or Stack Exchange allow their users to score messages in order to evaluate their content. These scores can be aggregated for each user in order to compute a reputation value in the forum. However, explicit rating functionalities are rarely used in many online communities such as health forums. At the same time, the textual content of the messages can reveal a lot of information regarding the trust that users have in the posted information. In this work, we propose to use these hidden expressions of trust in order to estimate user reputation in online forums.

Predicting Medical Roles in Online Health Fora

Online health fora are increasingly visited by patients to get help and information related to their health. However, these fora are not limited to patients: a significant number of health professionals actively participate in many discussions. As experts their posted information are very important since, they are able to well explain the problems, the symptoms, correct false affirmations and give useful advices, etc. For someone interested in trusty medical information, obtaining only these kinds of posts can be very useful and informative. Unfortunately, extracting such knowledge needs to navigate over the fora in order to evaluate the information. Navigation and selection are time consuming, tedious, difficult and error-prone activities when done manually. It is thus important to propose a new method for automatically categorize information proposed both by non-experts as well as by professionals in online health fora. In this paper, we propose to use a supervised approach to evaluate what are the most representative components of a post considering vocabularies, uncertainty markers, emotions, misspellings and interrogative forms to perform efficiently this categorization. Experiments have been conducted on two real fora and shown that our approach is efficient for extracting posts done by professionals.

FEEL: a French Expanded Emotion Lexicon

Sentiment analysis allows the semantic evaluation of pieces of text according to the expressed sentiments and opinions. While considerable attention has been given to the polarity (positive, negative) of English words, only few studies were interested in the conveyed emotions (joy, anger, surprise, sadness, etc.) especially in other languages. In this paper, we present the elaboration and the evaluation of a new French lexicon considering both polarity and emotion. The elaboration method is based on the semi-automatic translation and expansion to synonyms of the English NRC Word Emotion Association Lexicon (NRC-EmoLex). First, online translators have been automatically queried in order to create a first version of our new French Expanded Emotion Lexicon (FEEL). Then, a human professional translator manually validated the automatically obtained entries and the associated emotions. She agreed with more than 94xa0% of the pre-validated entries (those found by a majority of translators) and less than 18xa0% of the remaining entries (those found by very few translators). This result highlights that online tools can be used to get high quality resources with low cost. Annotating a subset of terms by three different annotators shows that the associated sentiments and emotions are consistent. Finally, extensive experiments have been conducted to compare the final version of FEEL with other existing French lexicons. Various French benchmarks for polarity and emotion classifications have been used in these evaluations. Experiments have shown that FEEL obtains competitive results for polarity, and significantly better results for basic emotions.