#############################################################################################
# 2000- 3 publications [sum =  3 publications]
#############################################################################################

@article{deBrevern2000,
   Author = {de Brevern, A. G. and Etchebest, C. and Hazout, S.},
   Title = {{Bayesian probabilistic approach for predicting backbone structures in terms of protein blocks}},
   Journal = {Proteins},
   Volume = {41},
   Number = {3},
   Pages = {271-87},
      Keywords = {Artificial Intelligence
*Bayes Theorem
Cluster Analysis
*Computer Simulation
Databases, Factual
Forecasting
Ligases
*Models, Molecular
Neural Networks (Computer)
Peptide Fragments/*chemistry/classification
*Protein Conformation
Protein Structure, Secondary
Ubiquitins/metabolism},
   Abstract = {By using an unsupervised cluster analyzer, we have identified a local structural alphabet composed of 16 folding patterns of five consecutive C(alpha) ("protein blocks"). The dependence that exists between successive blocks is explicitly taken into account. A Bayesian approach based on the relation protein block-amino acid propensity is used for prediction and leads to a success rate close to 35%. Sharing sequence windows associated with certain blocks into "sequence families" improves the prediction accuracy by 6%. This prediction accuracy exceeds 75% when keeping the first four predicted protein blocks at each site of the protein. In addition, two different strategies are proposed: the first one defines the number of protein blocks in each site needed for respecting a user-fixed prediction accuracy, and alternatively, the second one defines the different protein sites to be predicted with a user-fixed number of blocks and a chosen accuracy. This last strategy applied to the ubiquitin conjugating enzyme (alpha/beta protein) shows that 91% of the sites may be predicted with a prediction accuracy larger than 77% considering only three blocks per site. The prediction strategies proposed improve our knowledge about sequence-structure dependence and should be very useful in ab initio protein modelling.},
   Note = {0887-3585 (Print)
Journal Article},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=11025540 },
   EndNoteRefType = {Journal Article},
   Year = {2000} }

@inproceedings{deBrevern2000b,
   Author = {de Brevern, Alexandre G. and Hazout, Serge},
   Title = {{"Hybrid Protein Model (HPM)" : une nouvelle approche pour caractériser les relations séquence-structure dans les protéines}},
   Booktitle = {Premières Journées Ouvertes de Biologie, Informatique et Mathématiques (JOBIM) pour la génomique},
   Address = {Montpellier},
   Pages = {105-112},
   pdf = {internal-pdf://hpm_fr[1]-1507957760/hpm_fr[1].pdf},
   Abstract = {Le passage de la séquence protéique codante à la structure tridimensionnelle est une des difficultés majeures de la biologie structurale. La recherche d'un alphabet structural permettant de coder la structure locale du squelette protéique a été précédemment réalisée au moyen d’un classifieur non supervisé (de Brevern et al., 2000). L’alphabet obtenu en 16 Blocs Protéiques (BPs) assure une bonne approximation des structures protéiques. La prédiction locale de ces BPs montre que l'information de la séquence induit fortement le type de repliement local, mais reste imparfaite (taux de prédiction correcte = 40,7%). La méthode " Hybrid Protein Model " présentée dans cette étude vise à apprendre à la fois la séquence et la structure des protéines, et donc permet d’étudier la répartition de l'information structure + séquence. L’analyse de la répartition le long de la protéine hybride en relation avec la nature du bloc structural a permis d’affiner le rôle de certains acides aminés dans les structures secondaires et des régions flanquantes. L’étude aboutit à un concept de " modèle flou " entre la séquence et la structure. },
   EndNoteRefType = {Conference Proceedings},
   Year = {2000} }

@article{deBrevern2000c,
   Author = {de Brevern, Alexandre G. and Hazout, Serge},
   Title = {{Hybrid Protein Model (HPM): a method to compact protein 3D-structures information and physicochemical properties}},
   Journal = {IEEE - Computer Society },
   Volume = {S1},
   Number = {1},
   Pages = {49-54},
   pdf = {internal-pdf://de_Brevern_IEEE_Comp_Soc_2000[1]-0819931648/de_Brevern_IEEE_Comp_Soc_2000[1].pdf},
   Abstract = {The transformation of protein 1D-sequence to protein 3D-structure is one of the main difficulties of the structural biology. A structural alphabet had been previously defined from dihedral angles describing the protein backbone as structural information by using an unsupervised classifier. The 16 Protein Blocks (PBs), basis element of the structural alphabet, allows a correct 3D structure approximation. Local prediction had been estimated by a Bayesian approach and shown that sequence information induces strongly the local fold, but stays coarse (prediction rate of 40.7 % with one PB, 75.8 % with the four most probable PBs). The Hybrid Protein Model presented in this study learns both sequence and structure of the proteins. The analysis made along the hybrid protein has permitted to appreciate more precisely the spatial location of some types of amino acid residues in the secondary structures and their flanking regions. This study leads to a fuzzy model of dependence between sequence and structure.},
   URL = {http://csdl.computer.org/comp/proceedings/spire/2000/0746/00/07460049abs.htm },
   EndNoteRefType = {Journal Article},
   Year = {2000} }

#############################################################################################
# 2001- 4 publications [sum =  7 publications]
#############################################################################################

@phdthesis{deBrevern2001a,
   Author = {de Brevern, Alexandre G.},
   Title = {{Nouvelles stratégies d'analyses et de prédiction des structures tridimensionnelles des protéines}},
   Address = {Paris},
   Pages = {208},
   School = {University Paris 7},
   School = {Biology (Analyses de Génomes et Modélisation Moléculaire)},
   Type = {Bioinformatics},
   pdf = {internal-pdf://de_Brevern_PhD_2001[1]-1944323584/de_Brevern_PhD_2001[1].pdf},
   Abstract = {Résumé :Caractériser la structure tridimensionnelle des protéines avec les structures secondaires classiques est assez pauvre structurellement. Nous avons donc développé une nouvelle méthodologie pour concevoir des séries de petits prototypes moyens nommés Blocs Protéiques (BPs) qui permettent une bonne approximation des structures protéiques. L'analyse de la spécificité des blocs protéiques a montré leur stabilité et leur spécificité sur le plan structural. Le choix final du nombre de BPs est associé a une prédiction locale correcte.
Cette prédiction se base avec une méthode bayésienne qui permet de comprendre l'importance des acides aminés de manière simple. Pour améliorer cette prédiction, nous nous sommes bases sur deux concepts : (i) 1 repliement local -> n séquences et (ii) 1 séquence -> n repliements. Le premier concept signifie que plusieurs types de séquences peuvent être associes a la même structure et le second qu'une séquence peut-être associée a plusieurs type de repliements. Ces deux aspects sont développés en se basant sur la recherche d'un indice de fiabilité lie a la prédiction locale, pour trouver des zones de fortes probabilités. Certains mots, i.e. successions de blocs protéiques apparaissent plus fréquemment que d'autres. Nous avons donc défini au mieux quelle est l'architecture de ces successions, les liens existants entre ces différents mots.
Du fait de cette redondance qui peut apparaître dans la structure protéique, une méthode de compactage qui permet d'associer des structures structurellement proches sur le plan local a été mise au point. Cette approche appelée "protéine hybride" de conception simple permet de catégoriser en classes "structurellement dépendantes" l'ensemble des structures de la base de données protéiques. Cette approche, en plus du compactage, peut être utilisée dans une optique différente, celle de la recherche d'homologie structurale et de la caractérisation des dépendances entre structures et séquences.

Abstract :The secondary structures approximate badly the 3D protein structures. A new method have been developped to create a more complex and precise structural alphabet (called Protein Blocks) which could be used in a local prediction method. The analysis of the specificity and stability of this alphabet has been performed. This alphabet is composed of 16 prototypes of 5 Calpha length. The local prediction of PBs from the sequence gives correct results.
The prediction is based on Bayesian statistics which is efficient to understand the meaning and influences of every amino acids. To improve this prediction, we have used two concepts : (i) 1 local fold is associated with a set of sequences and (ii) 1 sequence could give different folds. The first point is associated with the splitting of occurrence matrices associated with the most common PBs. The second point is based upon a confidence index and allow the location of well-predicted residues. Some succession of Protein Blocks are over-represented. So, we have define a network describing most of the protein topology.
Finally, we propose a method called Hybrid Protein Model which allow the compaction of succession of Protein Blocks in a fuzzy manner and create structurally dependant cluster. This approach has been extended to the research of structural homology. 
},
   URL = {http://althese.free.fr/THESE/pub/index.html },
   EndNoteRefType = {Thesis},
   Year = {2001} }

@incollection{deBrevern2001b,
   Author = {de Brevern, Alexandre G. and Camproux, Anne-Claude and Hazout, Serge and Etchebest, Catherine and Tuffery, Pierre},
   Title = {{Protein structural alphabets: beyond the secondary structure description}},
   Editor = {Sangadai, SG },
   Booktitle = {Recent Research Developments in  Protein Engineering},
   Address = {Trivandrum },
   Publisher = {Research Signpost},
   Volume = {1},
   Volume = {1},
   Pages = {319-331},
   ISBN = {81-7736-052-3},
   pdf = {internal-pdf://Review_2001[1]-3487908864/Review_2001[1].PDF},
   Abstract = {The considerable increase of the protein structural database allows to cross the line from the classical secondary structure description of proteins. While still confronted with numerous problems, defining structural alphabets is an emerging concept in the field of protein structure analysis. It is an attempt to objectively classify the whole set of conformations occurring in protein structures described by small overlapping fragments. It is expected to lead to a better understanding of protein architecture and to open new opportunities for protein structure prediction.},
   URL = {http://alexandre.debrevern.free.fr/PUB/05_Review/Review_2001.pdf},
   EndNoteRefType = {Book Section},
   Year = {2001} }

@article{deBrevern2001c,
   Author = {de Brevern, Alexandre G. and Hazout, Serge},
   Title = {{Compacting local protein folds with a "hybrid protein model"}},
   Journal = {Theo Chem Acc},
   Volume = {106},
   Number = {1 - 2},
   Pages = {36-47},
   URL = {http://springerlink.metapress.com/index/10.1007/s002140000227  },
   EndNoteRefType = {Journal Article},
   Year = {2001} }

@inproceedings{deBrevern2001d,
   Author = {de Brevern, Alexandre G. and Hazout, Serge},
   Title = {{Compactage d'une base de données protéiques recodées dans un alphabet structural}},
   Booktitle = {Secondes Journées Ouvertes de Biologie, Informatique et Mathématiques (JOBIM) pour la génomique },
   Address = {Toulouse},
   Pages = {85-92},
   EndNoteRefType = {Conference Proceedings},
   Year = {2001} }

#############################################################################################
# 2002- 4 publications [sum = 11 publications]
#############################################################################################

@inproceedings{Benros2002,
   Author = {Benros, Cristina and Hazout, Serge and de Brevern, Alexandre G.},
   Title = {{Extension of a local backbone description using a structural alphabet. "Hybrid Protein Model": a new clustering approach for 3D local structures}},
   Booktitle = {International Workshop on Bioinformatics ISMIS},
   Address = {Lyon, France},
   Pages = {36-45},
   pdf = {http://www.ebgm.jussieu.fr/~debrevern/CONGRES/15_ISMIS_2002/hpm_ismis.pdf},
   Abstract = {The "Hybrid Protein Model" (HPM) is a fuzzy model for compacting biological data series such as 3D structures into a limited number of overlapping cluster. The 3D structures of a non-redundant structural databank is encoded in a previously defined structural alphabet composed of 16 protein blocks (PBs) [1]. The hybrid protein is composed of a series of distributions of the probability of observing the PBs. The training is an iterative unsupervised process that for every fold to be learn consists of looking for the most similar pattern present in the hybrid protein and modifying it slightly. Finally each position of the hybrid protein corresponds to a set of similar local structures. Compared with conventional clustering and the definition of a partition into independent subsets, the hybrid protein characterizes a series of structurally dependent subsets: that is, it maintains the sequentiality of the local structures. In a second step, to define the optimal length of the hybrid protein, we have defined an new approach based on the deletion of the redundant parts of the hybrid protein. },
   URL = {http://www.ebgm.jussieu.fr/~debrevern/CONGRES/15_ISMIS_2002/hpm_ismis.pdf},
   EndNoteRefType = {Conference Proceedings},
   Year = {2002} }

@article{deBrevern2002a,
   Author = {de Brevern, Alexandre G.},
   Title = {{Compartimentation chromosomique}},
   Journal = {Biofutur},
   Volume = {225},
   Pages = {20-22},
   Abstract = {Du fait du nombre important de génomes complets actuellement disponibles, il devient possible de les comparer directement. La méthode de chromosome hybride (HXM) permet, en découpant ces génomes en longues zones similaires, cette comparaison. },
   URL = {http://www.ebgm.jussieu.fr/~debrevern/PUB/09_Biofutur/},
   EndNoteRefType = {Journal Article},
   Year = {2002} }

@article{deBrevern2002b,
   Author = {de Brevern, A. G. and Loirat, F. and Badel-Chagnon, A. and Andre, C. and Vincens, P. and Hazout, S.},
   Title = {{Genome compartimentation by a hybrid chromosome model (HXM). Application to Saccharomyces cerevisae subtelomeres}},
   Journal = {Comput Chem},
   Volume = {26},
   Number = {5},
   Pages = {437-45},
   Keywords = {Base Sequence
Chromosomes, Fungal/ genetics
Databases, Nucleic Acid
Genome, Fungal
Physical Chromosome Mapping/ methods
Research Support, Non-U.S. Gov't
Saccharomyces cerevisiae/ genetics
Sequence Alignment/methods
Telomere/ genetics},
   Abstract = {The aim of this paper is to present a new approach, called 'Hybrid Chromosome Model' (HXM), which allows both the extraction of regions of similarity between two sequences, and the compartimentation of a set of DNA sequences. The principle of the method consists in compacting a set of sequences (split into fragments of fixed length) into a 'hybrid chromosome', which results from the stacking of the whole sequence fragments. We have illustrated our approach on the 32 subtelomeres of Saccharomyces cerevisae. The compartimentation of these chromosome extremities into common regions of similarity has been carried out. The approach HXM is a fast and efficient tool for mapping entire genomes and for extracting ancient duplications within or between genomes.},
   Note = {Journal Article},
   URL = {http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6TFV-451DM0W-1&_user=674833&_coverDate=07%2F31%2F2002&_rdoc=5&_fmt=summary&_orig=browse&_srch=%23toc%235236%232002%23999739994%23321480!&_cdi=5236&_sort=d&_docanchor=&_acct=C000036558&_version=1&_urlVersion=0&_userid=674833&md5=d4a1b474b68d6b7b48b19f97f902d9ed},
   EndNoteRefType = {Journal Article},
   Year = {2002} }

@article{deBrevern2002c,
   Author = {de Brevern, A. G. and Valadie, H. and Hazout, S. and Etchebest, C.},
   Title = {{Extension of a local backbone description using a structural alphabet: a new approach to the sequence-structure relationship}},
   Journal = {Protein Sci},
   Volume = {11},
   Number = {12},
   Pages = {2871-86},
   Keywords = {Amino Acid Sequence
Bayes Theorem
Computational Biology/*methods
Computer Simulation
Databases, Protein
Methionine-tRNA Ligase/chemistry
*Models, Molecular
Molecular Sequence Data
Peptide Fragments/*chemistry
Protein Conformation
Thermodynamics
Thermus thermophilus/enzymology},
   Abstract = {Protein Blocks (PBs) comprise a structural alphabet of 16 protein fragments, each 5 Calpha long. They make it possible to approximate and correctly predict local protein three-dimensional (3D) structures. We have selected the 72 most frequent sequences of five PBs, which we call Structural Words (SWs). Analysis of four different protein data banks shows that SWs cover 92% of the amino acids in them and provide a good structural approximation for residues (i.e., sequences) 9 Calpha long. We present most of them in a simple network that describes 90% of the overall residues and, interestingly, includes more than 80% of the amino acids present in coils. Analysis of the network shows the specificity and quality of the 3D descriptions as well as a new type of relation between local folds and amino acid distribution. The results show that the 3D structure of these protein data banks can be easily described by a combination of subgraphs included in the network. Finally, a Bayesian probabilistic approach improved the prediction rate by 4%.},
   Note = {0961-8368 (Print)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=12441385 },
   EndNoteRefType = {Journal Article},
   Year = {2002} }

#############################################################################################
# 2003- 2 publications [sum = 13 publications]
#############################################################################################

@inproceedings{Benros2003,
   Author = {Benros, Cristina and de Brevern, Alexandre G. and Hazout, Serge},
   Title = {{Hybrid Protein Model (HPM) : A Method For Building A Library Of Overlapping Local Structural Prototypes. Sensitivity Study And Improvements Of The Training}},
   Booktitle = {IEEE Workshop on Neural Networks for Signal Processing },
   Pages = {53-72},
   Abstract = {Predicting protein structure from amino acid sequence is one of the main challenges of Genomics. Various computational methods have been developed during the last decade to reach this goal. However, the problem of structure prediction remains difficult. Before facing this complex problem, our goal is to focus on the accurate analysis of protein structures at a local level. In our study, we present an approach called "Hybrid Protein Model" (HPM) which uses a training procedure similar to the one of the Self-Organizing Maps. It allows the compression of a non-redundant protein structure databank into a library of overlapping 3D structural fragments. The "Hybrid Protein Model" carries out a multiple alignment of structural fragments. We present in this study an improvement of this strategy by introducing gaps in the local structures, and a sensitivity study of the training according to the control parameters. The library obtained is composed of a finite number of structural classes, each class including fragments sharing similar local structures. These classes are representative of the structural motifs found in the protein structures from the databank. Thus, this library constitutes an efficient tool for determining structural similarities between proteins and especially for predicting the local protein structure from the amino acid sequence. },
   EndNoteRefType = {Conference Proceedings},
   Year = {2003} }

@article{deBrevern2003,
   Author = {de Brevern, A. G. and Hazout, S.},
   Title = {{'Hybrid protein model' for optimally defining 3D protein structure fragments}},
   Journal = {Bioinformatics},
   Volume = {19},
   Number = {3},
   Pages = {345-53},
   Keywords = {*Algorithms
Amino Acid Sequence
Artificial Intelligence
*Databases, Protein
*Models, Molecular
Molecular Sequence Data
Peptide Fragments/chemistry
Protein Conformation
Protein Folding
Proteins/*chemistry
Quality Control},
   Abstract = {MOTIVATION: Our aim is to develop a process that automatically defines a repertory of contiguous 3D protein structure fragments and can be used in homology modeling. We present here improvements to the method we introduced previously: the 'hybrid protein model' (de Brevern and Hazout, THEOR: Chem. Acc., 106, 36-47, (2001)) The hybrid protein learns a non-redundant databank encoded in a structural alphabet composed of 16 Protein Blocks (PBs; de Brevern et al., Proteins, 41, 271-287, (2000)). Every local fold is learned by looking for the most similar pattern present in the hybrid protein and modifying it slightly. Finally each position corresponds to a cluster of similar 3D local folds. RESULTS: In this paper, we describe improvements to our method for building an optimal hybrid protein: (i) 'baby training,' which is defined as the introduction of large structure fragments and the progressive reduction in the size of training fragments; and (ii) the deletion of the redundant parts of the hybrid protein. This repertory of contiguous 3D protein structure fragments should be a useful tool for molecular modeling.},
   Note = {1367-4803 (Print)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=12584119 },
   EndNoteRefType = {Journal Article},
   Year = {2003} }

#############################################################################################
# 2004-  3 publications [sum = 16 publications]
#############################################################################################

@article{deBrevern2004a,
   Author = {de Brevern, A. G. and Benros, C. and Gautier, R. and Valadie, H. and Hazout, S. and Etchebest, C.},
   Title = {{Local backbone structure prediction of proteins}},
   Journal = {In Silico Biol},
   Volume = {4},
   Number = {3},
   Pages = {381-6},
   Keywords = {Amino Acid Sequence
Models, Molecular
Molecular Sequence Data
Protein Conformation
Proteins/*chemistry},
   Abstract = {A statistical analysis of the PDB structures has led us to define a new set of small 3D structural prototypes called Protein Blocks (PBs). This structural alphabet includes 16 PBs, each one is defined by the (phi, psi) dihedral angles of 5 consecutive residues. The amino acid distributions observed in sequence windows encompassing these PBs are used to predict by a Bayesian approach the local 3D structure of proteins from the sole knowledge of their sequences. LocPred is a software which allows the users to submit a protein sequence and performs a prediction in terms of PBs. The prediction results are given both textually and graphically.},
   Note = {1386-6338 (Print)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=15724288 },
   EndNoteRefType = {Journal Article},
   Year = {2004} }

@article{deBrevern2004b,
   Author = {de Brevern, A. G. and Hazout, S. and Malpertuy, A.},
   Title = {{Influence of microarrays experiments missing values on the stability of gene groups by hierarchical clustering}},
   Journal = {BMC Bioinformatics},
   Volume = {5},
   Number = {1},
   Pages = {114},
   pdf = {http://www.biomedcentral.com/content/pdf/1471-2105-5-114.pdf},
   Keywords = {Cluster Analysis
Computational Biology/statistics & numerical data
Databases, Genetic
Gene Expression Profiling/methods/ statistics & numerical data
Gene Expression Regulation, Fungal/ genetics
Genes, Structural, Fungal/ genetics
Oligonucleotide Array Sequence Analysis/methods/ statistics & numerical
data
Reference Values
Research Design/statistics & numerical data
Research Support, Non-U.S. Gov't
Saccharomyces cerevisiae/genetics},
   Abstract = {BACKGROUND: Microarray technologies produced large amount of data. The hierarchical clustering is commonly used to identify clusters of co-expressed genes. However, microarray datasets often contain missing values (MVs) representing a major drawback for the use of the clustering methods. Usually the MVs are not treated, or replaced by zero or estimated by the k-Nearest Neighbor (kNN) approach. The topic of the paper is to study the stability of gene clusters, defined by various hierarchical clustering algorithms, of microarrays experiments including or not MVs. RESULTS: In this study, we show that the MVs have important effects on the stability of the gene clusters. Moreover, the magnitude of the gene misallocations is depending on the aggregation algorithm. The most appropriate aggregation methods (e.g. complete-linkage and Ward) are highly sensitive to MVs, and surprisingly, for a very tiny proportion of MVs (e.g. 1%). In most of the case, the MVs must be replaced by expected values. The MVs replacement by the kNN approach clearly improves the identification of co-expressed gene clusters. Nevertheless, we observe that kNN approach is less suitable for the extreme values of gene expression. CONCLUSION: The presence of MVs (even at a low rate) is a major factor of gene cluster instability. In addition, the impact depends on the hierarchical clustering algorithm used. Some methods should be used carefully. Nevertheless, the kNN approach constitutes one efficient method for restoring the missing expression gene values, with a low error level. Our study highlights the need of statistical treatments in microarray data to avoid misinterpretation.},
   Note = {Journal Article},
   URL = {http://www.biomedcentral.com/1471-2105/5/114/abstract},
   EndNoteRefType = {Journal Article},
   Year = {2004} }

@article{{Fourrier2004,
   Author = {Fourrier, L. and Benros, C. and de Brevern, A. G.},
   Title = {{Use of a structural alphabet for analysis of short loops connecting repetitive structures}},
   Journal = {BMC Bioinformatics},
   Volume = {5},
   Number = {1},
   Pages = {58},
   pdf = {http://www.biomedcentral.com/content/pdf/1471-2105-5-58.pdf},
   Keywords = {Computational Biology/methods
Molecular Sequence Data
Peptides/chemistry
Predictive Value of Tests
Protein Conformation
Protein Structure, Secondary
Protein Structure, Tertiary
Proteins/chemistry
Repetitive Sequences, Amino Acid
Research Support, Non-U.S. Gov't
Software},
   Abstract = {BACKGROUND: Because loops connect regular secondary structures, analysis of the former depends directly on the definition of the latter. The numerous assignment methods, however, can offer different definitions. In a previous study, we defined a structural alphabet composed of 16 average protein fragments, which we called Protein Blocks (PBs). They allow an accurate description of every region of 3D protein backbones and have been used in local structure prediction. In the present study, we use this structural alphabet to analyze and predict the loops connecting two repetitive structures. RESULTS: We first analyzed the secondary structure assignments. Use of five different assignment methods (DSSP, DEFINE, PCURVE, STRIDE and PSEA) showed the absence of consensus: 20% of the residues were assigned to different states. The discrepancies were particularly important at the extremities of the repetitive structures. We used PBs to describe and predict the short loops because they can help analyze and in part explain these discrepancies. An analysis of the PB distribution in these regions showed some specificities in the sequence-structure relationship. Of the amino acid over- or under-representations observed in the short loop databank, 20% did not appear in the entire databank. Finally, predicting 3D structure in terms of PBs with a Bayesian approach yielded an accuracy rate of 36.0% for all loops and 41.2% for the short loops. Specific learning in the short loops increased the latter by 1%. CONCLUSION: This work highlights the difficulties of assigning repetitive structures and the advantages of using more precise descriptions, that is, PBs. We observed some new amino acid distributions in the short loops and used this information to enhance local prediction. Instead of describing entire loops, our approach predicts each position in the loops locally. It can thus be used to propose many different structures for the loops and to probe and sample their flexibility. It can be a useful tool in ab initio loop prediction.},
   Note = {Journal Article},
   URL = {http://www.biomedcentral.com/1471-2105/5/58/abstract},
   EndNoteRefType = {Journal Article},
   Year = {2004} }

#############################################################################################
# 2005- 5 publications [sum = 21 publications]
#############################################################################################

@article{deBrevern2005a,
   Author = {de Brevern, A. G.},
   Title = {{New assessment of a structural alphabet}},
   Journal = {In Silico Biol},
   Volume = {5},
   Number = {3},
   Pages = {283-9},
   Keywords = {*Databases, Protein
*Protein Structure, Secondary
Proteins/*chemistry},
   Abstract = {A statistical analysis of the Protein Databank (PDB) structures had led us to define a set of small 3D structural prototypes called Protein Blocks (PBs). This structural alphabet includes 16 PBs, each one defined by the (phi, psi) dihedral angles of 5 consecutive residues. Here, we analyze the effect of the enlargement of the PDB on the PBs' definition. The results highlight the quality of the 3D approximation ensured by the PBs. These last could be of great interest in ab initio modeling.},
   Note = {1386-6338 (Print)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=15996119 },
   EndNoteRefType = {Journal Article},
   Year = {2005} }

@incollection{deBrevern2005b,
   Author = {de Brevern, Alexandre G. and Benros, Cristina and Hazout, Serge},
   Title = {{Structural Alphabet: From a Local Point of View to a Global Description of Protein 3D Structures}},
   Editor = {Yan, Peter V},
   Booktitle = {Bioinformatics: New Research },
   Publisher = {Nova Publishers},
   Pages = {127-169},
   pdf = {http://www.ebgm.jussieu.fr/~debrevern/PUB/13-NovaBook/preprint_structural_alphabet.pdf},
   Abstract = {The study of protein structures' local conformations has a long history principally based on the analysis of the classical repetitive structures (i.e. alpha-helix and beta-sheet), and also on the characterization of some particular structures in the coil state (e.g. turns). The secondary structures are interesting for describing the global protein fold but miss all the orientations of the connecting regions and so neglect many particularities of the coil state.
In order to take these structural features into account, we have identified a local structural alphabet composed of 16 folding patterns of five consecutive residues, called Protein Blocks (PBs). Conversely to the secondary structures, the PBs are able to approximate every part of the protein structures. These PBs have been used both to describe precisely the 3D protein backbones with an average rmsd of 0.42 Å, and to perform a local structure prediction with a rate of correct prediction of 48.7%. 
In this chapter, we present the interest of the Protein Blocks by comparing the secondary structure assignment with the assignment in terms of PBs. We highlight the discrepancies between different secondary structure assignment methods and show some interesting correspondence between particular local folds and the Protein Blocks. Then, we use the Protein Block prediction to classify proteins into the classical structural classes, namely all , all and mixed. The prediction rate of theses different classes is good, i.e. 71.5%, with no confusion between all and all classes. Finally, we present a new approach named TopKAPi that stands for "Triangular Kohonen Map for Analyzing Proteins". It enables to classify and analyze proteins according to their Protein Block frequencies using for this purpose a novel unsupervised clustering method: a triangular self-organizing Kohonen map. This method enables to determine new relationships between local structures and amino acid distributions. This new methodology could be of great interest in proteomics and sequence alignment. },
   URL = {http://novapublishers.com/catalog/product_info.php?products_id=146},
   EndNoteRefType = {Book Section},
   Year = {2005} }

@article{deBrevern2005c,
   Author = {de Brevern, A. G. and Wong, H. and Tournamille, C. and Colin, Y. and Le Van Kim, C. and Etchebest, C.},
   Title = {{A structural model of a seven-transmembrane helix receptor: the Duffy antigen/receptor for chemokine (DARC)}},
   Journal = {Biochim Biophys Acta},
   Volume = {1724},
   Number = {3},
   Pages = {288-306},
   doi = {S0304-4165(05)00159-5 [pii]
10.1016/j.bbagen.2005.05.016},
   Keywords = {Amino Acid Sequence
Animals
Chemokines, CC/*blood/chemistry
Computational Biology/methods
Computer Simulation
Duffy Blood-Group System/blood/*chemistry/genetics
Electrostatics
Erythrocyte Membrane/chemistry/metabolism
Erythrocytes/*chemistry/metabolism
Glycoproteins/chemistry
Haplorhini
Humans
*Models, Molecular
Molecular Sequence Data
Plasmodium knowlesi
Plasmodium vivax
Receptors, Cell Surface/blood/*chemistry/genetics
Structural Homology, Protein},
   Abstract = {The Duffy antigen/receptor for chemokine (DARC) is an erythrocyte receptor for malaria parasites (Plasmodium vivax and Plasmodium knowlesi) and for chemokines. In contrast to other chemokine receptors, DARC is a promiscuous receptor that binds chemokines of both CC and CXC classes. The four extracellular domains (ECDs) of DARC are essential for its interaction with chemokines, whilst the first (ECD1) is sufficient for the interaction with malaria erythrocyte-binding protein. In this study, we elaborate and analyze structural models of the DARC. The construction of the 3D models is based on a comparative modeling process and on the use of many procedures to predict transmembrane segments and to detect far homologous proteins with known structures. Threading, ab initio, secondary structure and Protein Blocks approaches are used to build a very large number of models. The conformational exploration of the ECDs is performed with simulated annealing. The second and fourth ECDs are strongly constrained. On the contrary, the ECD1 is highly flexible, but seems composed of three consecutive regions: a small beta-sheet, a linker region and a structured loop. The chosen structural models encompass most of the biochemical features and reflect the known experimental data. They may be used to analyze functional interaction properties.},
   Note = {de Brevern, A G
Wong, H
Tournamille, C
Colin, Y
Le Van Kim, C
Etchebest, C
Research Support, Non-U.S. Gov't
Netherlands
Biochimica et biophysica acta
Biochim Biophys Acta. 2005 Aug 5;1724(3):288-306.},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=16046070},
   EndNoteRefType = {Journal Article},
   Year = {2005} }

@article{{Etchebest2005,
   Author = {Etchebest, C. and Benros, C. and Hazout, S. and de Brevern, A. G.},
   Title = {{A structural alphabet for local protein structures: improved prediction methods}},
   Journal = {Proteins},
   Volume = {59},
   Number = {4},
   Pages = {810-27},
   Keywords = {Amino Acid Sequence
Bayes Theorem
Databases, Protein
Peptide Fragments/*chemistry
Probability
Protein Conformation
*Protein Structure, Secondary
Proteins/*chemistry
Reproducibility of Results},
   Abstract = {Three-dimensional protein structures can be described with a library of 3D fragments that define a structural alphabet. We have previously proposed such an alphabet, composed of 16 patterns of five consecutive amino acids, called Protein Blocks (PBs). These PBs have been used to describe protein backbones and to predict local structures from protein sequences. The Q16 prediction rate reaches 40.7% with an optimization procedure. This article examines two aspects of PBs. First, we determine the effect of the enlargement of databanks on their definition. The results show that the geometrical features of the different PBs are preserved (local RMSD value equal to 0.41 A on average) and sequence-structure specificities reinforced when databanks are enlarged. Second, we improve the methods for optimizing PB predictions from sequences, revisiting the optimization procedure and exploring different local prediction strategies. Use of a statistical optimization procedure for the sequence-local structure relation improves prediction accuracy by 8% (Q16 = 48.7%). Better recognition of repetitive structures occurs without losing the prediction efficiency of the other local folds. Adding secondary structure prediction improved the accuracy of Q16 by only 1%. An entropy index (Neq), strongly related to the RMSD value of the difference between predicted PBs and true local structures, is proposed to estimate prediction quality. The Neq is linearly correlated with the Q16 prediction rate distributions, computed for a large set of proteins. An "expected" prediction rate QE16 is deduced with a mean error of 5%.},
   Note = {1097-0134 (Electronic)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=15822101 },
   EndNoteRefType = {Journal Article},
   Year = {2005} }

@article{Martin2005,
   Author = {Martin, J. and Letellier, G. and Marin, A. and Taly, J. F. and de Brevern, A. G. and Gibrat, J. F.},
   Title = {{Protein secondary structure assignment revisited: a detailed analysis of different assignment methods}},
   Journal = {BMC Struct Biol},
   Volume = {5},
   Pages = {17},
   doi = {1472-6807-5-17 [pii]
10.1186/1472-6807-5-17},
   Keywords = {Algorithms
Amino Acid Sequence
Computational Biology/*methods
Databases, Protein
Hydrogen Bonding
Magnetic Resonance Spectroscopy
Models, Molecular
Models, Statistical
Models, Theoretical
Molecular Structure
Protein Conformation
Protein Structure, Secondary
Proteins/*chemistry
Proteomics/methods
Software},
   Abstract = {BACKGROUND: A number of methods are now available to perform automatic assignment of periodic secondary structures from atomic coordinates, based on different characteristics of the secondary structures. In general these methods exhibit a broad consensus as to the location of most helix and strand core segments in protein structures. However the termini of the segments are often ill-defined and it is difficult to decide unambiguously which residues at the edge of the segments have to be included. In addition, there is a "twilight zone" where secondary structure segments depart significantly from the idealized models of Pauling and Corey. For these segments, one has to decide whether the observed structural variations are merely distorsions or whether they constitute a break in the secondary structure. METHODS: To address these problems, we have developed a method for secondary structure assignment, called KAKSI. Assignments made by KAKSI are compared with assignments given by DSSP, STRIDE, XTLSSTR, PSEA and SECSTR, as well as secondary structures found in PDB files, on 4 datasets (X-ray structures with different resolution range, NMR structures). RESULTS: A detailed comparison of KAKSI assignments with those of STRIDE and PSEA reveals that KAKSI assigns slightly longer helices and strands than STRIDE in case of one-to-one correspondence between the segments. However, KAKSI tends also to favor the assignment of several short helices when STRIDE and PSEA assign longer, kinked, helices. Helices assigned by KAKSI have geometrical characteristics close to those described in the PDB. They are more linear than helices assigned by other methods. The same tendency to split long segments is observed for strands, although less systematically. We present a number of cases of secondary structure assignments that illustrate this behavior. CONCLUSION: Our method provides valuable assignments which favor the regularity of secondary structure segments.},
   Note = {Martin, Juliette
Letellier, Guillaume
Marin, Antoine
Taly, Jean-Francois
de Brevern, Alexandre G
Gibrat, Jean-Francois
Research Support, Non-U.S. Gov't
England
BMC structural biology
BMC Struct Biol. 2005 Sep 15;5:17.},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=16164759},
   EndNoteRefType = {Journal Article},
   Year = {2005} }


#############################################################################################
# 2006- 7 publications [sum = 28 publications]
#############################################################################################

@article{Benros2006,
   Author = {Benros, C. and de Brevern, A. G. and Etchebest, C. and Hazout, S.},
   Title = {{Assessing a novel approach for predicting local 3D protein structures from sequence}},
   Journal = {Proteins},
   Volume = {62},
   Number = {4},
   Pages = {865-80},
   Keywords = {Amino Acid Sequence
Models, Molecular
Models, Theoretical
Peptide Library
Protein Conformation
Protein Hybridization
Proteins/*chemistry
Software},
   Abstract = {We developed a novel approach for predicting local protein structure from sequence. It relies on the Hybrid Protein Model (HPM), an unsupervised clustering method we previously developed. This model learns three-dimensional protein fragments encoded into a structural alphabet of 16 protein blocks (PBs). Here, we focused on 11-residue fragments encoded as a series of seven PBs and used HPM to cluster them according to their local similarities. We thus built a library of 120 overlapping prototypes (mean fragments from each cluster), with good three-dimensional local approximation, i.e., a mean accuracy of 1.61 A Calpha root-mean-square distance. Our prediction method is intended to optimize the exploitation of the sequence-structure relations deduced from this library of long protein fragments. This was achieved by setting up a system of 120 experts, each defined by logistic regression to optimize the discrimination from sequence of a given prototype relative to the others. For a target sequence window, the experts computed probabilities of sequence-structure compatibility for the prototypes and ranked them, proposing the top scorers as structural candidates. Predictions were defined as successful when a prototype <2.5 A from the true local structure was found among those proposed. Our strategy yielded a prediction rate of 51.2% for an average of 4.2 candidates per sequence window. We also proposed a confidence index to estimate prediction quality. Our approach predicts from sequence alone and will thus provide valuable information for proteins without structural homologs. Candidates will also contribute to global structure prediction by fragment assembly.},
   Note = {1097-0134 (Electronic)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=16385557 },
   EndNoteRefType = {Journal Article},
   Year = {2006} }

@article{Bornot2006,
   Author = {Bornot, A. and de Brevern, A. G.},
   Title = {{Protein beta-turn assignments}},
   Journal = {Bioinformation},
   Volume = {1},
   Number = {5},
   Pages = {153-5},
   Abstract = {A classical way to analyze protein 3D structures or models is to investigate their secondary structures. Their predictions are also widely used as a help to build new 3D models. Thus, hundreds of prediction methods have been proposed. Nonetheless before predicting, secondary structure assignment is required even if not trivial. Therefore numerous but diverging assignment methods have been developed. Beta-turns constitute the third most important secondary structures. However, no analysis to compare the beta-turn distributions according to different secondary structure assignment methods has ever been done. We propose in this paper to analyze and evaluate the results of such a comparison. We highlight some important divergence that could have important consequence for the analysis and prediction of beta-turns.},
   Note = {0973-2063 (Electronic)
Journal Article},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=17597878 },
   EndNoteRefType = {Journal Article},
   Year = {2006} }

@phdthesis{deBrevern2006,
   Author = {de Brevern, Alexandre G.},
   Title = {Bioinformatique Structurale},
   School = {University Paris Diderot - Paris 7},
   Type = {Habilitations à Diriger les Recherches
},
      Year = {2006} }

@article{Gelly2006a,
   Author = {Gelly, J. C. and de Brevern, A. G. and Hazout, S.},
   Title = {{'Protein Peeling': an approach for splitting a 3D protein structure into compact fragments}},
   Journal = {Bioinformatics},
   Volume = {22},
   Number = {2},
   Pages = {129-33},
   Abstract = {MOTIVATION: The object of this study is to propose a new method to identify small compact units that compose protein three-dimensional structures. These fragments, called 'protein units (PU)', are a new level of description to well understand and analyze the organization of protein structures. The method only works from the contact probability matrix, i.e. the inter Calpha-distances translated into probabilities. It uses the principle of conventional hierarchical clustering, leading to a series of nested partitions of the 3D structure. Every step aims at dividing optimally a unit into 2 or 3 subunits according to a criterion called 'partition index' assessing the structural independence of the subunits newly defined. Moreover, an entropy-derived squared correlation R is used for assessing globally the protein structure dissection. The method is compared to other splitting algorithms and shows relevant performance. AVAILABILITY: An Internet server with dedicated tools is available at http://www.ebgm.jussieu.fr/~gelly/ CONTACT: debrevern@ebgm.jussieu.fr.},
   Note = {Journal Article},
   EndNoteRefType = {Journal Article},
   Year = {2006} }

@article{Gelly2006b,
   Author = {Gelly, J. C. and Etchebest, C. and Hazout, S. and de Brevern, A. G.},
   Title = {{Protein Peeling 2: a web server to convert protein structures into series of protein units}},
   Journal = {Nucleic Acids Res},
   Volume = {34},
   Number = {Web Server issue},
   Pages = {W75-8},
   Keywords = {Computer Graphics
Internet
*Protein Conformation
Protein Folding
Proteins/chemistry
Research Support, Non-U.S. Gov't
*Software
User-Computer Interface},
   Abstract = {Protein Peeling 2 (PP2) is a web server for the automatic identification of protein units (PUs) given the 3D coordinates of a protein. PUs are an intermediate level of protein structure description between protein domains and secondary structures. It is a new tool to better understand and analyze the organization of protein structures. PP2 uses only the matrices of protein contact probabilities and cuts the protein structures optimally using Matthews' coefficient correlation. An index assesses the compactness quality of each PU. Results are given both textually and graphically using JMol and PyMol softwares. The server can be accessed from http://www.ebgm.jussieu.fr/~gelly/index.html.},
   Note = {1362-4962 (Electronic)
Journal Article},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=16845113 },
   EndNoteRefType = {Journal Article},
   Year = {2006} }

@article{Tyagi2006a,
   Author = {Tyagi, M. and Gowri, V. S. and Srinivasan, N. and de Brevern, A. G. and Offmann, B.},
   Title = {{A substitution matrix for structural alphabet based on structural alignment of homologous proteins and its applications}},
   Journal = {Proteins},
   Volume = {65},
   Number = {1},
   Pages = {32-9},
   Keywords = {Databases, Protein
Protein Conformation
Protein Folding
Sequence Alignment/*methods
Sequence Analysis, Protein/*methods},
   Abstract = {Analysis of protein structures based on backbone structural patterns known as structural alphabets have been shown to be very useful. Among them, a set of 16 pentapeptide structural motifs known as protein blocks (PBs) has been identified and upon which backbone model of most protein structures can be built. PBs allows simplification of 3D space onto 1D space in the form of sequence of PBs. Here, for the first time, substitution probabilities of PBs in a large number of aligned homologous protein structures have been studied and are expressed as a simplified 16 x 16 substitution matrix. The matrix was validated by benchmarking how well it can align sequences of PBs rather like amino acid alignment to identify structurally equivalent regions in closely or distantly related proteins using dynamic programming approach. The alignment results obtained are very comparable to well established structure comparison methods like DALI and STAMP. Other interesting applications of the matrix have been investigated. We first show that, in variable regions between two superimposed homologous proteins, one can distinguish between local conformational differences and rigid-body displacement of a conserved motif by comparing the PBs and their substitution scores. Second, we demonstrate, with the example of aspartic proteinases, that PBs can be efficiently used to detect the lobe/domain flexibility in the multidomain proteins. Lastly, using protein kinase as an example, we identify regions of conformational variations and rigid body movements in the enzyme as it is changed to the active state from an inactive state.},
   Note = {1097-0134 (Electronic)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=16894618 },
   EndNoteRefType = {Journal Article},
   Year = {2006} }

@article{Tyagi2006b,
   Author = {Tyagi, M. and Sharma, P. and Swamy, C. S. and Cadet, F. and Srinivasan, N. and de Brevern, A. G. and Offmann, B.},
   Title = {{Protein Block Expert (PBE): a web-based protein structure analysis server using a structural alphabet}},
   Journal = {Nucleic Acids Res},
   Volume = {34},
   Number = {Web Server issue},
   Pages = {W119-23},
   Keywords = {*Amino Acid Motifs
Databases, Protein
Internet
*Protein Conformation
Protein Folding
Sequence Alignment/*methods
Sequence Analysis, Protein/*methods
*Software
User-Computer Interface},
   Abstract = {Encoding protein 3D structures into 1D string using short structural prototypes or structural alphabets opens a new front for structure comparison and analysis. Using the well-documented 16 motifs of Protein Blocks (PBs) as structural alphabet, we have developed a methodology to compare protein structures that are encoded as sequences of PBs by aligning them using dynamic programming which uses a substitution matrix for PBs. This methodology is implemented in the applications available in Protein Block Expert (PBE) server. PBE addresses common issues in the field of protein structure analysis such as comparison of proteins structures and identification of protein structures in structural databanks that resemble a given structure. PBE-T provides facility to transform any PDB file into sequences of PBs. PBE-ALIGNc performs comparison of two protein structures based on the alignment of their corresponding PB sequences. PBE-ALIGNm is a facility for mining SCOP database for similar structures based on the alignment of PBs. Besides, PBE provides an interface to a database (PBE-SAdb) of preprocessed PB sequences from SCOP culled at 95% and of all-against-all pairwise PB alignments at family and superfamily levels. PBE server is freely available at http://bioinformatics.univ-reunion.fr/PBE/.},
   Note = {1362-4962 (Electronic)
Journal Article
Research Support, Non-U.S. Gov't},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=16844973 },
   EndNoteRefType = {Journal Article},
   Year = {2006}
}



#############################################################################################
# 2007- 8 publications [sum = 36 publications] 
#############################################################################################


@article{Bornot2007,
   Author = {Bornot, Aurélie and Offmann, Bernard and de Brevern, Alexandre G.},
   Title = {{How flexible protein structures are ? New questions on the protein structure plasticity}},
   Journal = {Bioforum Europe},
   Volume = {11},
   Pages = {24-25},
   Year = {2007}
}


@incollection{Benros2007,
   Author = {Benros, Cristina and Martin, Juliette and Tyagi, Manoj and de Brevern, Alexandre G.},
   Title = {{Description of the local protein structure. I. Classical approaches}},
   Editor = {de Brevern, Alexandre G.},
   Booktitle = {Recent Research Developments in  Protein Engineering},
   Address = {Trivandrum },
   Publisher = {Research Signpost},
   Pages = {1-33},
   EndNoteRefType = {Book Section},
   Year = {2007} }


@article{deBrevern2007,
   Author = {de Brevern, A. G. and Etchebest, C. and Benros, C. and Hazout, S.},
   Title = {{"Pinning strategy": a novel approach for predicting the backbone structure in terms of protein blocks from sequence}},
   Journal = {J Biosci},
   Volume = {32},
   Number = {1},
   Pages = {51-70},
   Keywords = {Amino Acid Sequence
Bayes Theorem
Computational Biology/*methods
Databases, Protein
Escherichia coli Proteins/chemistry
Molecular Sequence Data
Peptide Library
*Protein Conformation
Proteins/*chemistry
*Sequence Analysis, Protein},
   Abstract = {The description of protein 3D structures can be performed through a library of 3D fragments, named a structural alphabet. Our structural alphabet is composed of 16 small protein fragments of 5 C alpha in length, called protein blocks (PBs). It allows an efficient approximation of the 3D protein structures and a correct prediction of the local structure. The 72 most frequent series of 5 consecutive PBs, called structural words (SWs)are able to cover more than 90% of the 3D structures. PBs are highly conditioned by the presence of a limited number of transitions between them. In this study, we propose a new method called "pinning strategy" that used this specific feature to predict long protein fragments. Its goal is to define highly probable successions of PBs. It starts from the most probable SW and is then extended with overlapping SWs. Starting from an initial prediction rate of 34.4%, the use of the SWs instead of the PBs allows a gain of 4.5%. The pinning strategy simply applied to the SWs increases the prediction accuracy to 39.9%. In a second step, the sequence-structure relationship is optimized, the prediction accuracy reaches 43.6%.},
   Note = {0250-5991 (Print)
Journal Article},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=17426380 },
   EndNoteRefType = {Journal Article},
   Year = {2007} }

@article{Doppelt2007,
   Author = {Doppelt, O. and Moriaud, F. and Bornot, A. and de Brevern, A. G.},
   Title = {{Functional annotation strategy for protein structures}},
   Journal = {Bioinformation},
   Volume = {1},
   Number = {9},
   Pages = {357-9},
   Abstract = {Whole-genome sequencing projects are a major source of unknown function proteins. However, as predicting protein function from sequence remains a difficult task, research groups recently started to use 3D protein structures and structural models to bypass it. MED-SuMo compares protein surfaces analyzing the composition and spatial distribution of specific chemical groups (hydrogen bond donor, acceptor, positive, negative, aromatic, hydrophobic, guanidinium, hydroxyl, acyl and glycine). It is able to recognize proteins that have similar binding sites and thus, may perform similar functions. We present here a fine example which points out the interest of MED-SuMo approach for functional structural annotation.},
   Note = {Doppelt, Olivia
Moriaud, Fabrice
Bornot, Aurelie
de Brevern, Alexandre G
Singapore
Bioinformation
Bioinformation. 2007 Mar 19;1(9):357-9.},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=17597920},
   EndNoteRefType = {Journal Article},
   Year = {2007} }


@article{{Etchebest2007,
   Author = {Etchebest, C. and Benros, C. and Bornot, A. and Camproux, A. C. and de Brevern, A. G.},
   Title = {{A reduced amino acid alphabet for understanding and designing protein adaptation to mutation}},
   Journal = {Eur Biophys J},
   Volume = {36},
   Number = {8},
   Pages = {1059-69},
   Abstract = {Protein sequence world is considerably larger than structure world. In consequence, numerous non-related sequences may adopt similar 3D folds and different kinds of amino acids may thus be found in similar 3D structures. By grouping together the 20 amino acids into a smaller number of representative residues with similar features, sequence world simplification may be achieved. This clustering hence defines a reduced amino acid alphabet (reduced AAA). Numerous works have shown that protein 3D structures are composed of a limited number of building blocks, defining a structural alphabet. We previously identified such an alphabet composed of 16 representative structural motifs (5-residues length) called Protein Blocks (PBs). This alphabet permits to translate the structure (3D) in sequence of PBs (1D). Based on these two concepts, reduced AAA and PBs, we analyzed the distributions of the different kinds of amino acids and their equivalences in the structural context. Different reduced sets were considered. Recurrent amino acid associations were found in all the local structures while other were specific of some local structures (PBs) (e.g Cysteine, Histidine, Threonine and Serine for the alpha-helix Ncap). Some similar associations are found in other reduced AAAs, e.g Ile with Val, or hydrophobic aromatic residues Trp with Phe and Tyr. We put into evidence interesting alternative associations. This highlights the dependence on the information considered (sequence or structure). This approach, equivalent to a substitution matrix, could be useful for designing protein sequence with different features (for instance adaptation to environment) while preserving mainly the 3D fold.},
Note = {0175-7571 (Print)
Journal Article},
URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=17565494 },
EndNoteRefType = {Journal Article},
Year = {2007}
}


@incollection{Fuchs2007,
   Author = {Fuchs, Patrick and Etchebest, Catherine and de Brevern, Alexandre G.},
   Title = {{Turns prediction}},
   Editor = {de Brevern, Alexandre G.},
   Booktitle = {Recent Adv. In Structural Bioinformatics},
   Address = {Trivandrum},
   Publisher = {Research signpost},
   Volume = {1},
   Volume = {1},
Pages = {37-56},
EndNoteRefType = {Book Section},
Year = {2007}
}

@article{Offmann2007,
Author = {Offmann, B. and Tyagi, M. and de Brevern, A. G.},
Title = {{Local Protein Structures}},
Journal = {Current Bioinformatics},
Volume = {3},
Pages = {165-202},
EndNoteRefType = {Journal Article},
Year = {2007}
}


@incollection{Tyagi2007,
   Author = {Tyagi, Manoj and Benros, Cristina and Martin, Juliette and de Brevern, Alexandre G.},
   Title = {{Description of the local protein structure. II. Novel approaches.}},
   Editor = {de Brevern, Alexandre G.},
   Booktitle = {Recent Research Developments in  Protein Engineering},
   Address = {Trivandrum },
   Publisher = {Research Signpost},
   Pages = {34-47},
   EndNoteRefType = {Book Section},
   Year = {2007} }


#############################################################################################
# 2008- 3 publications [sum = 39 publications]  
#############################################################################################

@article{Faure2008,
   Author = {Faure, G. and Bornot, A. and de Brevern, A. G.},
   Title = {{Protein contacts, inter-residue interactions and side-chain modelling}},
   Journal = {Biochimie},
   Volume = {90},
   Number = {4},
   Pages = {626-39},
   doi = {S0300-9084(07)00316-1 [pii]
10.1016/j.biochi.2007.11.007},
   Keywords = {Amino Acid Sequence
Amino Acids/*chemistry
Binding Sites
Databases, Protein
Models, Molecular
Molecular Sequence Data
Protein Binding
*Protein Conformation
*Protein Folding
Proteins/*chemistry/genetics},
   Abstract = {Three-dimensional structures of proteins are the support of their biological functions. Their folds are stabilized by contacts between residues. Inner protein contacts are generally described through direct atomic contacts, i.e. interactions between side-chain atoms, while contact prediction methods mainly used inter-Calpha distances. In this paper, we have analyzed the protein contacts on a recent high quality non-redundant databank using different criteria. First, we have studied the average number of contacts depending on the distance threshold to define a contact. Preferential contacts between types of amino acids have been highlighted. Detailed analyses have been done concerning the proximity of contacts in the sequence, the size of the proteins and fold classes. The strongest differences have been extracted, highlighting important residues. Then, we studied the influence of five different side-chain conformation prediction methods (SCWRL, IRECS, SCAP, SCATD and SCCOMP) on the distribution of contacts. The prediction rates of these different methods are quite similar. However, using a distance criterion between side chains, the results are quite different, e.g. SCAP predicts 50% more contacts than observed, unlike other methods that predict fewer contacts than observed. Contacts deduced are quite distinct from one method to another with at most 75% contacts in common. Moreover, distributions of amino acid preferential contacts present unexpected behaviours distinct from previously observed in the X-ray structures, especially at the surface of proteins. For instance, the interactions involving Tryptophan greatly decrease.},
   Note = {Faure, Guilhem
Bornot, Aurelie
de Brevern, Alexandre G
Research Support, Non-U.S. Gov't
France
Biochimie
Biochimie. 2008 Apr;90(4):626-39. Epub 2007 Nov 28.},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=18086572},
   EndNoteRefType = {Journal Article},
   Year = {2008} }

@article{Martin2008,
   Author = {Martin, J. and de Brevern, A. G. and Camproux, A. C.},
   Title = {{In silico local structure approach: a case study on outer membrane proteins}},
   Journal = {Proteins},
   Volume = {71},
   Number = {1},
   Pages = {92-109},
   doi = {10.1002/prot.21659},
   Keywords = {Bacterial Outer Membrane Proteins/*chemistry
*Computational Biology
Databases, Protein
Peptide Fragments/chemistry
Protein Conformation},
   Abstract = {The detection of Outer Membrane Proteins (OMP) in whole genomes is an actual question, their sequence characteristics have thus been intensively studied. This class of protein displays a common beta-barrel architecture, formed by adjacent antiparallel strands. However, due to the lack of available structures, few structural studies have been made on this class of proteins. Here we propose a novel OMP local structure investigation, based on a structural alphabet approach, i.e., the decomposition of 3D structures using a library of four-residue protein fragments. The optimal decomposition of structures using hidden Markov model results in a specific structural alphabet of 20 fragments, six of them dedicated to the decomposition of beta-strands. This optimal alphabet, called SA20-OMP, is analyzed in details, in terms of local structures and transitions between fragments. It highlights a particular and strong organization of beta-strands as series of regular canonical structural fragments. The comparison with alphabets learned on globular structures indicates that the internal organization of OMP structures is more constrained than in globular structures. The analysis of OMP structures using SA20-OMP reveals some recurrent structural patterns. The preferred location of fragments in the distinct regions of the membrane is investigated. The study of pairwise specificity of fragments reveals that some contacts between structural fragments in beta-sheets are clearly favored whereas others are avoided. This contact specificity is stronger in OMP than in globular structures. Moreover, SA20-OMP also captured sequential information. This can be integrated in a scoring function for structural model ranking with very promising results.},
   Note = {Martin, Juliette
de Brevern, Alexandre G
Camproux, Anne-Claude
Research Support, Non-U.S. Gov't
United States
Proteins
Proteins. 2008 Apr;71(1):92-109.},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=17932925},
   EndNoteRefType = {Journal Article},
   Year = {2008} }

@article{Tyagi2008,
   Author = {Tyagi, M. and de Brevern, A. G. and Srinivasan, N. and Offmann, B.},
   Title = {{Protein structure mining using a structural alphabet}},
   Journal = {Proteins},
   Volume = {71},
   Number = {2},
   Pages = {920-37},
   doi = {10.1002/prot.21776},
   Keywords = {Algorithms
Amino Acid Motifs
Amino Acid Sequence
Databases, Protein
Models, Molecular
Protein Folding
Proteins/*chemistry
Sensitivity and Specificity
Sequence Alignment/methods
Sequence Analysis, Protein/methods
Software
src Homology Domains},
   Abstract = {We present a comprehensive evaluation of a new structure mining method called PB-ALIGN. It is based on the encoding of protein structure as 1D sequence of a combination of 16 short structural motifs or protein blocks (PBs). PBs are short motifs capable of representing most of the local structural features of a protein backbone. Using derived PB substitution matrix and simple dynamic programming algorithm, PB sequences are aligned the same way amino acid sequences to yield structure alignment. PBs are short motifs capable of representing most of the local structural features of a protein backbone. Alignment of these local features as sequence of symbols enables fast detection of structural similarities between two proteins. Ability of the method to characterize and align regions beyond regular secondary structures, for example, N and C caps of helix and loops connecting regular structures, puts it a step ahead of existing methods, which strongly rely on secondary structure elements. PB-ALIGN achieved efficiency of 85% in extracting true fold from a large database of 7259 SCOP domains and was successful in 82% cases to identify true super-family members. On comparison to 13 existing structure comparison/mining methods, PB-ALIGN emerged as the best on general ability test dataset and was at par with methods like YAKUSA and CE on nontrivial test dataset. Furthermore, the proposed method performed well when compared to flexible structure alignment method like FATCAT and outperforms in processing speed (less than 45 s per database scan). This work also establishes a reliable cut-off value for the demarcation of similar folds. It finally shows that global alignment scores of unrelated structures using PBs follow an extreme value distribution. PB-ALIGN is freely available on web server called Protein Block Expert (PBE) at http://bioinformatics.univ-reunion.fr/PBE/.},
   Note = {Tyagi, M
de Brevern, A G
Srinivasan, N
Offmann, B
Comparative Study
Evaluation Studies
Research Support, Non-U.S. Gov't
United States
Proteins
Proteins. 2008 May 1;71(2):920-37.},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=18004784},
   EndNoteRefType = {Journal Article},
   Year = {2008}
}


#############################################################################################
# 2009- 4 publications [sum = 43 publications]   
#############################################################################################

@article{Benros2009,
   Author = {Benros, C. and de Brevern, A. G. and Hazout, S.},
   Title = {{Analyzing the sequence-structure relationship of a library of local structural prototypes}},
   Journal = {J Theor Biol},
   Volume = {256},
   Number = {2},
   Pages = {215-26},
   doi = {S0022-5193(08)00465-7 [pii]
10.1016/j.jtbi.2008.08.032},
   Abstract = {We present a thorough analysis of the relation between amino acid sequence and local three-dimensional structure in proteins. A library of overlapping local structural prototypes was built using an unsupervised clustering approach called "hybrid protein model" (HPM). The HPM carries out a multiple structural alignment of local folds from a non-redundant protein structure databank encoded into a structural alphabet composed of 16 protein blocks (PBs). Following previous research focusing on the HPM protocol, we have considered gaps in the local structure prototype. This methodology allows to have variable length fragments. Hence, 120 local structure prototypes were obtained. Twenty-five percent of the protein fragments learnt by HPM had gaps. An investigation of tight turns suggested that they are mainly derived from three PB series with precise locations in the HPM. The amino acid information content of the whole conformational classes was tackled by multivariate methods, e.g., canonical correlation analysis. It points out the presence of seven amino acid equivalence classes showing high propensities for preferential local structures. In the same way, definition of "contrast factors" based on sequence-structure properties underline the specificity of certain structural prototypes, e.g., the dependence of Gly or Asn-rich turns to a limited number of PBs, or, the opposition between Pro-rich coils to those enriched in Ser, Thr, Asn and Glu. These results are so useful to analyze the sequence-structure relationships, but could also be used to improve fragment-based method for protein structure prediction from sequence.},
   Note = {Benros, Cristina
de Brevern, Alexandre G
Hazout, Serge
Research Support, Non-U.S. Gov't
England
Journal of theoretical biology
J Theor Biol. 2009 Jan 21;256(2):215-26. Epub 2008 Oct 14.},
   URL = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&dopt=Citation&list_uids=18977232},
   EndNoteRefType = {Journal Article},
   pmid={18977232},
   Year = {2009} }

@article{Bornot2009,
   Author = {Bornot, Aurélie and Etchebest, Catherine and de Brevern, Alexandre G.},
   Title = {A new prediction strategy for long local protein structures using an original description},
   Journal = {Proteins},
   Number = {in press},
      Year = {2009} }


@article{Doppelt-Azeroual2009,
   Author = {Doppelt-Azeroual, Olivia and Moriaud, Fabrice and Delfaud, François and de Brevern, Alexandre G.},
   Title = {Analysis of HSP90 related folds with MED-SuMo classification approach},
   Journal = {Drug Design, Development and Therapy},
   Volume = {3},
   Pages = {59-72},
      Year = {2009} }

@article{Ghozlane2009,
Author = {Ghozlane, Amine  and Joseph, Agnel Praveen and Bornot, Aurélie and de Brevern, Alexandre G.},
Title = {Analysis of protein chameleon sequence characteristics},
Journal = {Bioinformation},
Number = {in press},
Year = {2009}
}

@article{DARC2009,
Author = {de Brevern, Alexandre G. and Autin, Ludovic and Colin, Yves and Bertrand, Olivier and Etchebest, Catherine},
Title = {in silico studies on DARC},
Journal = {Infectious Diseases - Drug Targets},
Number = {in press},
Year = {2009}
}

@incollection{AdB2009book,
   Author = {de Brevern, A.G.},
   Title = {3D-structural models of transmembrane proteins},
   Editor = {Lacapère, J.J.},
   Booktitle = {In Methods in Molecular Biology},
   Address = { },
   Publisher = {Humana Press Inc. Totowa, NJ, USA},
   Pages = {in press},
   Year = {2009}
}

@article{Faure2009,
   Author = {Faure, G. and Bornot, A. and de Brevern, A. G.},
   Title = {{Analysis of protein contacts into Protein Units}},
   Journal = {Biochimie},
   Volume = {},
   Number = {},
   Pages = {in press},
   Year = {2009}
}