A scalable re-ranking method for content-based image retrieval

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Unsupervised manifold learning using Reciprocal kNN Graphs in image re-ranking and rank aggregation tasks

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Image Re-Ranking Acceleration on GPUs

Huge image collections are becoming available lately. In this scenario, the use of Content-Based Image Retrieval (CBIR) systems has emerged as a promising approach to support image searches. The objective of CBIR systems is to retrieve the most similar images in a collection, given a query image, by taking into account image visual properties such as texture, color, and shape. In these systems, the effectiveness of the retrieval process depends heavily on the accuracy of ranking approaches. Recently, re-ranking approaches have been proposed to improve the effectiveness of CBIR systems by taking into account the relationships among images. The re-ranking approaches consider the relationships among all images in a given dataset. These approaches typically demands a huge amount of computational power, which hampers its use in practical situations. On the other hand, these methods can be massively parallelized. In this paper, we propose to speedup the computation of the RL-Sim algorithm, a recently proposed image re-ranking approach, by using the computational power of Graphics Processing Units (GPU). GPUs are emerging as relatively inexpensive parallel processors that are becoming available on a wide range of computer systems. We address the image re-ranking performance challenges by proposing a parallel solution designed to fit the computational model of GPUs. We conducted an experimental evaluation considering different implementations and devices. Experimental results demonstrate that significant performance gains can be obtained. Our approach achieves speedups of 7x from serial implementation considering the overall algorithm and up to 36x on its core steps.

Document re-ranking by generality in bio-medical information retrieval

Document ranking is an important process in information retrieval (IR). It presents retrieved documents in an order of their estimated degrees of relevance to query. Traditional document ranking methods are mostly based on the similarity computations between documents and query. In this paper we argue that the similarity-based document ranking is insufficient in some cases. There are two reasons. Firstly it is about the increased information variety. There are far too many different types documents available now for user to search. The second is about the users variety. In many cases user may want to retrieve documents that are not only similar but also general or broad regarding a certain topic. This is particularly the case in some domains such as bio-medical IR. In this paper we propose a novel approach to re-rank the retrieved documents by incorporating the similarity with their generality. By an ontology-based analysis on the semantic cohesion of text, document generality can be quantified. The retrieved documents are then re-ranked by their combined scores of similarity and the closeness of documents’ generality to the query’s. Our experiments have shown an encouraging performance on a large bio-medical document collection, OHSUMED, containing 348,566 medical journal references and 101 test queries.

Collaborative personal profiling for web service ranking and recommendation

Web service is one of the most fundamental technologies in implementing service oriented architecture (SOA) based applications. One essential challenge related to web service is to find suitable candidates with regard to web service consumer’s requests, which is normally called web service discovery. During a web service discovery protocol, it is expected that the consumer will find it hard to distinguish which ones are more suitable in the retrieval set, thereby making selection of web services a critical task. In this paper, inspired by the idea that the service composition pattern is significant hint for service selection, a personal profiling mechanism is proposed to improve ranking and recommendation performance. Since service selection is highly dependent on the composition process, personal knowledge is accumulated from previous service composition process and shared via collaborative filtering where a set of users with similar interest will be firstly identified. Afterwards a web service re-ranking mechanism is employed for personalised recommendation. Experimental studies are conduced and analysed to demonstrate the promising potential of this research.

Cheminformatic studies of molecular properties and their influence on bioactivity in the context of drug discovery

Molecular shape has long been known to be an important property for the process of molecular recognition. Previous studies postulated the existence of a drug-like shape space that could be used to artificially bias the composition of screening libraries, with the aim to increase the chance of success in Hit Identification. In this work, it was analysed to which extend this assumption holds true. Normalized Principal Moments of Inertia Ratios (NPRs) have been used to describe the molecular shape of small molecules. It was investigated, whether active molecules of diverse targets are located in preferred subspaces of the NPR shape space. Results illustrated a significantly stronger clustering than could be expected by chance, with parts of the space unlikely to be occupied by active compounds. Furthermore, a strong enrichment of elongated, rather flat shapes could be observed, while globular compounds were highly underrepresented. This was confirmed for a wide range of small molecule datasets from different origins. Active compounds exhibited a high overlap in their shape distributions across different targets, making a purely shape­ based discrimination very difficult. An additional perspective was provided by comparing the shapes of protein binding pockets with those of their respective ligands. Although more globular than their ligands, it was observed that binding sites shapes exhibited a similarly skewed distribution in shape space: spherical shapes were highly underrepresented. This was different for unoccupied binding pockets of smaller size. These were on the contrary identified to possess a more globular shape. The relation between shape complementarity and exhibited bioactivity was analysed; a moderate correlation between bioactivity and parameters including pocket coverage, distance in shape space, and others could be identified, which reflects the importance of shape complementarity. However, this also suggests that other aspects are of relevance for molecular recognition. A subsequent analysis assessed if and how shape and volume information retrieved from pocket or respective reference ligands could be used as a pre-filter in a virtual screening approach. ln Lead Optimization compounds need to get optimized with respect to a variety of pararneters. Here, the availability of past success stories is very valuable, as they can guide medicinal chemists during their analogue synthesis plans. However, although of tremendous interest for the public domain, so far only large corporations had the ability to mine historical knowledge in their proprietary databases. With the aim to provide such information, the SwissBioisostere database was developed and released during this thesis. This database contains information on 21,293,355 performed substructural exchanges, corresponding to 5,586,462 unique replacements that have been measured in 35,039 assays against 1,948 molecular targets representing 30 target classes, and on their impact on bioactivity . A user-friendly interface was developed that provides facile access to these data and is accessible at http//www.swissbioisostere.ch. The ChEMBL database was used as primary data source of bioactivity information. Matched molecular pairs have been identified in the extracted and cleaned data. Success-based scores were developed and integrated into the database to allow re-ranking of proposed replacements by their past outcomes. It was analysed to which degree these scores correlate with chemical similarity of the underlying fragments. An unexpectedly weak relationship was detected and further investigated. Use cases of this database were envisioned, and functionalities implemented accordingly: replacement outcomes are aggregatable at the assay level, and it was shawn that an aggregation at the target or target class level could also be performed, but should be accompanied by a careful case-by-case assessment. It was furthermore observed that replacement success depends on the activity of the starting compound A within a matched molecular pair A-B. With increasing potency the probability to lose bioactivity through any substructural exchange was significantly higher than in low affine binders. A potential existence of a publication bias could be refuted. Furthermore, often performed medicinal chemistry strategies for structure-activity-relationship exploration were analysed using the acquired data. Finally, data originating from pharmaceutical companies were compared with those reported in the literature. It could be seen that industrial medicinal chemistry can access replacement information not available in the public domain. In contrast, a large amount of often-performed replacements within companies could also be identified in literature data. Preferences for particular replacements differed between these two sources. The value of combining different endpoints in an evaluation of molecular replacements was investigated. The performed studies highlighted furthermore that there seem to exist no universal substructural replacement that always retains bioactivity irrespective of the biological environment. A generalization of bioisosteric replacements seems therefore not possible. - La forme tridimensionnelle des molécules a depuis longtemps été reconnue comme une propriété importante pour le processus de reconnaissance moléculaire. Des études antérieures ont postulé que les médicaments occupent préférentiellement un sous-ensemble de l'espace des formes des molécules. Ce sous-ensemble pourrait être utilisé pour biaiser la composition de chimiothèques à cribler, dans le but d'augmenter les chances d'identifier des Hits. L'analyse et la validation de cette assertion fait l'objet de cette première partie. Les Ratios de Moments Principaux d'Inertie Normalisés (RPN) ont été utilisés pour décrire la forme tridimensionnelle de petites molécules de type médicament. Il a été étudié si les molécules actives sur des cibles différentes se co-localisaient dans des sous-espaces privilégiés de l'espace des formes. Les résultats montrent des regroupements de molécules incompatibles avec une répartition aléatoire, avec certaines parties de l'espace peu susceptibles d'être occupées par des composés actifs. Par ailleurs, un fort enrichissement en formes allongées et plutôt plates a pu être observé, tandis que les composés globulaires étaient fortement sous-représentés. Cela a été confirmé pour un large ensemble de compilations de molécules d'origines différentes. Les distributions de forme des molécules actives sur des cibles différentes se recoupent largement, rendant une discrimination fondée uniquement sur la forme très difficile. Une perspective supplémentaire a été ajoutée par la comparaison des formes des ligands avec celles de leurs sites de liaison (poches) dans leurs protéines respectives. Bien que plus globulaires que leurs ligands, il a été observé que les formes des poches présentent une distribution dans l'espace des formes avec le même type d'asymétrie que celle observée pour les ligands: les formes sphériques sont fortement sous­ représentées. Un résultat différent a été obtenu pour les poches de plus petite taille et cristallisées sans ligand: elles possédaient une forme plus globulaire. La relation entre complémentarité de forme et bioactivité a été également analysée; une corrélation modérée entre bioactivité et des paramètres tels que remplissage de poche, distance dans l'espace des formes, ainsi que d'autres, a pu être identifiée. Ceci reflète l'importance de la complémentarité des formes, mais aussi l'implication d'autres facteurs. Une analyse ultérieure a évalué si et comment la forme et le volume d'une poche ou de ses ligands de référence pouvaient être utilisés comme un pré-filtre dans une approche de criblage virtuel. Durant l'optimisation d'un Lead, de nombreux paramètres doivent être optimisés simultanément. Dans ce contexte, la disponibilité d'exemples d'optimisations réussies est précieuse, car ils peuvent orienter les chimistes médicinaux dans leurs plans de synthèse par analogie. Cependant, bien que d'un extrême intérêt pour les chercheurs dans le domaine public, seules les grandes sociétés pharmaceutiques avaient jusqu'à présent la capacité d'exploiter de telles connaissances au sein de leurs bases de données internes. Dans le but de remédier à cette limitation, la base de données SwissBioisostere a été élaborée et publiée dans le domaine public au cours de cette thèse. Cette base de données contient des informations sur 21 293 355 échanges sous-structuraux observés, correspondant à 5 586 462 remplacements uniques mesurés dans 35 039 tests contre 1948 cibles représentant 30 familles, ainsi que sur leur impact sur la bioactivité. Une interface a été développée pour permettre un accès facile à ces données, accessible à http:/ /www.swissbioisostere.ch. La base de données ChEMBL a été utilisée comme source de données de bioactivité. Une version modifiée de l'algorithme de Hussain et Rea a été implémentée pour identifier les Matched Molecular Pairs (MMP) dans les données préparées au préalable. Des scores de succès ont été développés et intégrés dans la base de données pour permettre un reclassement des remplacements proposés selon leurs résultats précédemment observés. La corrélation entre ces scores et la similarité chimique des fragments correspondants a été étudiée. Une corrélation plus faible qu'attendue a été détectée et analysée. Différents cas d'utilisation de cette base de données ont été envisagés, et les fonctionnalités correspondantes implémentées: l'agrégation des résultats de remplacement est effectuée au niveau de chaque test, et il a été montré qu'elle pourrait également être effectuée au niveau de la cible ou de la classe de cible, sous réserve d'une analyse au cas par cas. Il a en outre été constaté que le succès d'un remplacement dépend de l'activité du composé A au sein d'une paire A-B. Il a été montré que la probabilité de perdre la bioactivité à la suite d'un remplacement moléculaire quelconque est plus importante au sein des molécules les plus actives que chez les molécules de plus faible activité. L'existence potentielle d'un biais lié au processus de publication par articles a pu être réfutée. En outre, les stratégies fréquentes de chimie médicinale pour l'exploration des relations structure-activité ont été analysées à l'aide des données acquises. Enfin, les données provenant des compagnies pharmaceutiques ont été comparées à celles reportées dans la littérature. Il a pu être constaté que les chimistes médicinaux dans l'industrie peuvent accéder à des remplacements qui ne sont pas disponibles dans le domaine public. Par contre, un grand nombre de remplacements fréquemment observés dans les données de l'industrie ont également pu être identifiés dans les données de la littérature. Les préférences pour certains remplacements particuliers diffèrent entre ces deux sources. L'intérêt d'évaluer les remplacements moléculaires simultanément selon plusieurs paramètres (bioactivité et stabilité métabolique par ex.) a aussi été étudié. Les études réalisées ont souligné qu'il semble n'exister aucun remplacement sous-structural universel qui conserve toujours la bioactivité quel que soit le contexte biologique. Une généralisation des remplacements bioisostériques ne semble donc pas possible.

Question Waves: A multicast query routing algorithm for social search

This paper describes Question Waves, an algorithm that can be applied to social search protocols, such as Asknext or Sixearch. In this model, the queries are propagated through the social network, with faster propagation through more trustable acquaintances. Question Waves uses local information to make decisions and obtain an answer ranking. With Question Waves, the answers that arrive first are the most likely to be relevant, and we computed the correlation of answer relevance with the order of arrival to demonstrate this result. We obtained correlations equivalent to the heuristics that use global knowledge, such as profile similarity among users or the expertise value of an agent. Because Question Waves is compatible with the social search protocol Asknext, it is possible to stop a search when enough relevant answers have been found; additionally, stopping the search early only introduces a minimal risk of not obtaining the best possible answer. Furthermore, Question Waves does not require a re-ranking algorithm because the results arrive sorted

Benchmarking consensus model quality assessment for protein fold recognition

Background: Selecting the highest quality 3D model of a protein structure from a number of alternatives remains an important challenge in the field of structural bioinformatics. Many Model Quality Assessment Programs (MQAPs) have been developed which adopt various strategies in order to tackle this problem, ranging from the so called "true" MQAPs capable of producing a single energy score based on a single model, to methods which rely on structural comparisons of multiple models or additional information from meta-servers. However, it is clear that no current method can separate the highest accuracy models from the lowest consistently. In this paper, a number of the top performing MQAP methods are benchmarked in the context of the potential value that they add to protein fold recognition. Two novel methods are also described: ModSSEA, which based on the alignment of predicted secondary structure elements and ModFOLD which combines several true MQAP methods using an artificial neural network. Results: The ModSSEA method is found to be an effective model quality assessment program for ranking multiple models from many servers, however further accuracy can be gained by using the consensus approach of ModFOLD. The ModFOLD method is shown to significantly outperform the true MQAPs tested and is competitive with methods which make use of clustering or additional information from multiple servers. Several of the true MQAPs are also shown to add value to most individual fold recognition servers by improving model selection, when applied as a post filter in order to re-rank models. Conclusion: MQAPs should be benchmarked appropriately for the practical context in which they are intended to be used. Clustering based methods are the top performing MQAPs where many models are available from many servers; however, they often do not add value to individual fold recognition servers when limited models are available. Conversely, the true MQAP methods tested can often be used as effective post filters for re-ranking few models from individual fold recognition servers and further improvements can be achieved using a consensus of these methods.

Improvement of 3D protein models using multiple templates guided by single-template model quality assessment

Motivation: Modelling the 3D structures of proteins can often be enhanced if more than one fold template is used during the modelling process. However, in many cases, this may also result in poorer model quality for a given target or alignment method. There is a need for modelling protocols that can both consistently and significantly improve 3D models and provide an indication of when models might not benefit from the use of multiple target-template alignments. Here, we investigate the use of both global and local model quality prediction scores produced by ModFOLDclust2, to improve the selection of target-template alignments for the construction of multiple-template models. Additionally, we evaluate clustering the resulting population of multi- and single-template models for the improvement of our IntFOLD-TS tertiary structure prediction method. Results: We find that using accurate local model quality scores to guide alignment selection is the most consistent way to significantly improve models for each of the sequence to structure alignment methods tested. In addition, using accurate global model quality for re-ranking alignments, prior to selection, further improves the majority of multi-template modelling methods tested. Furthermore, subsequent clustering of the resulting population of multiple-template models significantly improves the quality of selected models compared with the previous version of our tertiary structure prediction method, IntFOLD-TS.

A comparison of statistical methods for genomic selection in a mice population

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Phenotypic plasticity of composite beef cattle performance using reaction norms model with unknown covariate

The objective of the present study was to determine the presence of genotype by environment interaction (G × E) and to characterize the phenotypic plasticity of birth weight (BW), weaning weight (WW), postweaning weight gain (PWG) and yearling scrotal circumference (SC) in composite beef cattle using the reaction norms model with unknown covariate. The animals were born between 1995 and 2008 on 33 farms located throughout all Brazilian biomes between latitude -7 and -31, longitude -40 and -63. The contemporary group was chosen as the environmental descriptor, that is, the environmental covariate of the reaction norms. In general, higher estimates of direct heritability were observed in extreme favorable environments. The mean of direct heritability across the environmental gradient ranged from 0.05 to 0.51, 0.09 to 0.43, 0.01 to 0.43 and from 0.12 to 0.26 for BW, WW, PWG and SC, respectively. The variation in direct heritability observed indicates a different response to selection according to the environment in which the animals of the population are evaluated. The correlation between the level and slope of the reaction norm for BW and PWG was high, indicating that animals with higher average breeding values responded better to improvement in environmental conditions, a fact characterizing a scale of G × E. Low correlation between the intercept and slope was obtained for WW and SC, implying re-ranking of animals in different environments. Genetic variation exists in the sensitivity of animals to the environment, a fact that permits the selection of more plastic or robust genotypes in the population studied. Thus, the G × E is an important factor that should be considered in the genetic evaluation of the present population of composite beef cattle. © The Animal Consortium 2012.

Optimality theory and historical phonology: an example from nasal harmony in Mundurukú

Este trabalho pretende mostrar que a Teoria da Otimidade proporciona novas formas para explicar mudanças de som que não a re-ordenação no ranqueamento deconstraints. Ele examina os aspectos diacrônicos de harmonia nasal na família Mundurukú, tronco Tupi. A comparação entre os sistemas modernos de Mundurukú e Kuruaya salienta que o sistema original, Proto-Mundurukú, tem propriedades semelhantes às atualmente observadas em Kuruaya. Em especial, os alvos do espalhamento de nasalidadeincluiamoclusivas sonoras e soantes, enquanto que as obstruintes surdas eram transparentes. Esse sistema evoluiu para outro em Pré-Munduruku, quando novos contrastes foram introduzidos na língua, transformando obstruintes em segmentos opacos e, portanto, bloqueando a nasalização. A análise, formalizada dentro da Teoria da Otimidade, demonstra que não houve uma re-ordenação dos constraints harmônicos; eles apenas se tornaram mais restritos, como mostra a cronologia relativa que deu origem ao sistema moderno de Mundurukú. Além disso, o estudo discute também as consequências dessa mudança para a gramática sincrônica, e como isso explica as irregularidades do processo.

Multiple Hashing Integration for Real-Time Large Scale Part-to-Part Video Matching

A real-time large scale part-to-part video matching algorithm, based on the cross correlation of the intensity of motion curves, is proposed with a view to originality recognition, video database cleansing, copyright enforcement, video tagging or video result re-ranking. Moreover, it is suggested how the most representative hashes and distance functions - strada, discrete cosine transformation, Marr-Hildreth and radial - should be integrated in order for the matching algorithm to be invariant against blur, compression and rotation distortions: (R; _) 2 [1; 20]_[1; 8], from 512_512 to 32_32pixels2 and from 10 to 180_. The DCT hash is invariant against blur and compression up to 64x64 pixels2. Nevertheless, although its performance against rotation is the best, with a success up to 70%, it should be combined with the Marr-Hildreth distance function. With the latter, the image selected by the DCT hash should be at a distance lower than 1.15 times the Marr-Hildreth minimum distance.

Concept-based document readability in domain specific information retrieval

Domain specific information retrieval has become in demand. Not only domain experts, but also average non-expert users are interested in searching domain specific (e.g., medical and health) information from online resources. However, a typical problem to average users is that the search results are always a mixture of documents with different levels of readability. Non-expert users may want to see documents with higher readability on the top of the list. Consequently the search results need to be re-ranked in a descending order of readability. It is often not practical for domain experts to manually label the readability of documents for large databases. Computational models of readability needs to be investigated. However, traditional readability formulas are designed for general purpose text and insufficient to deal with technical materials for domain specific information retrieval. More advanced algorithms such as textual coherence model are computationally expensive for re-ranking a large number of retrieved documents. In this paper, we propose an effective and computationally tractable concept-based model of text readability. In addition to textual genres of a document, our model also takes into account domain specific knowledge, i.e., how the domain-specific concepts contained in the document affect the document’s readability. Three major readability formulas are proposed and applied to health and medical information retrieval. Experimental results show that our proposed readability formulas lead to remarkable improvements in terms of correlation with users’ readability ratings over four traditional readability measures.