Jérôme Azé

Bio: Jérôme Azé is an academic researcher from University of Montpellier. The author has contributed to research in topics: Social media & Terminology extraction. The author has an hindex of 18, co-authored 97 publications receiving 1108 citations. Previous affiliations of Jérôme Azé include Centre national de la recherche scientifique & University of Paris-Sud.

Detection of suicide-related posts in Twitter data streams

Abstract: Suicidal ideation detection in online social networks is an emerging research area with major challenges. Recent research has shown that the publicly available information, spread across social media platforms, holds valuable indicators for effectively detecting individuals with suicidal intentions. The key challenge of suicide prevention is understanding and detecting the complex risk factors and warning signs that may precipitate the event. In this paper, we present a new approach that uses the social media platform Twitter to quantify suicide warning signs for individuals and to detect posts containing suicide-related content. The main originality of this approach is the automatic identification of sudden changes in a user's online behavior. To detect such changes, we combine natural language processing techniques to aggregate behavioral and textual features and pass these features through a martingale framework, which is widely used for change detection in data streams. Experiments show that our text-scoring approach effectively captures warning signs in text compared to traditional machine learning classifiers. Additionally, the application of the martingale framework highlights changes in online behavior and shows promise for detecting behavioral changes in at-risk individuals.

FEEL: a French Expanded Emotion Lexicon

Abstract: 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 94 % of the pre-validated entries (those found by a majority of translators) and less than 18 % 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.

Mining Twitter for Suicide Prevention

Abstract: Automatically detect suicidal people in social networks is a real social issue. In France, suicide attempt is an economic burden with strong socio-economic consequences. In this paper, we describe a complete process to automatically collect suspect tweets according to a vocabulary of topics suicidal persons are used to talk. We automatically capture tweets indicating suicidal risky behaviour based on simple classification methods. An interface for psychiatrists has been implemented to enable them to consult suspect tweets and profiles associated with these tweets. The method has been validated on real datasets. The early feedback of psychiatrists is encouraging and allow to consider a personalised response according to the estimated level of risk.

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

Abstract: Motivation: Protein--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. Results: To address the second step, we developed a scoring function based on a Voronoi tessellation of the protein three-dimensional structure. We showed that the Voronoi 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. Availability: http://genomics.eu.org/spip/-Bioinformatics-tools-

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Interactome networks and human disease

Abstract: Complex biological systems and cellular networks may underlie most genotype to phenotype relationships. Here, we review basic concepts in network biology, discussing different types of interactome networks and the insights that can come from analyzing them. We elaborate on why interactome networks are important to consider in biology, how they can be mapped and integrated with each other, what global properties are starting to emerge from interactome network models, and how these properties may relate to human disease.

PIPER: An FFT‐based protein docking program with pairwise potentials

Abstract: The Fast Fourier Transform (FFT) correlation approach to protein-protein docking can evaluate the energies of billions of docked conformations on a grid if the energy is described in the form of a correlation function. Here, this restriction is removed, and the approach is efficiently used with pairwise interaction potentials that substantially improve the docking results. The basic idea is approximating the interaction matrix by its eigenvectors corresponding to the few dominant eigenvalues, resulting in an energy expression written as the sum of a few correlation functions, and solving the problem by repeated FFT calculations. In addition to describing how the method is implemented, we present a novel class of structure-based pairwise intermolecular potentials. The DARS (Decoys As the Reference State) potentials are extracted from structures of protein-protein complexes and use large sets of docked conformations as decoys to derive atom pair distributions in the reference state. The current version of the DARS potential works well for enzyme-inhibitor complexes. With the new FFT-based program, DARS provides much better docking results than the earlier approaches, in many cases generating 50% more near-native docked conformations. Although the potential is far from optimal for antibody-antigen pairs, the results are still slightly better than those given by an earlier FFT method. The docking program PIPER is freely available for noncommercial applications.