Linkage Graph Research Articles

Multi-Layer Stochastic Block Interaction driven by Logistic Regression (MLSBI-LR) for Efficient Link Recommendation in Intra-Layer Linkage Graphs

Link Recommendation (LR) in complex networks has attracted huge interest in the social and computer science communities. Numerous networks, such as recommendation systems and social networks (which facilitate user contact), are probabilistic rather than deterministic due to the uncertainty surrounding the presence of links. Evaluating the various characteristics of such networks has frequently been tricky as the Intra-layer linkage graph requires at least two nodes to be in the same layer. Moreover, many existing LR methods mainly operate well on Single-Layer Graphs (SLGs) compared to Multi-Layer Graphs (MLGs) when nodes traverse multi-layers in a network of Intra-layer linkages. Considering this drawback, this paper proposes a Multi-Layer Stochastic Block Interaction method driven by Logistic Regression (MLSBI-LR) to exploit the bi-directional resources associated with Intra-layer linkages. Its inherent dependence on knowledge-based systems uses multi-criteria recommender systems to accommodate additional criteria and can modify neighborhood-based approaches. A multi-criteria network with relations over the same set of nodes is used since the modified neighbor-based method can exhibit rich dependence between entities and have available experimental data sets in MLGs to recommend links that would efficiently enrich users' experience. The accuracy and robustness of the proposed MLSBI-LR method compared to existing LR methods were extensively investigated using three distinct benchmark data sets and four evaluation metrics. Based on our experimental results across the databases and metrics, the proposed MLSBI-LR method performed significantly better (recording up to 17% increment in accuracy), recommending potential links in MLGs. Consequently, the proposed method may revolutionize link recommendation tasks in social networks by improving users' overall experience.

GCP-HOLO: Generating High-Order Linkage Graphs for Path Synthesis

Abstract One degrees-of-freedom (1DOF) linkages are persistent in mechanical systems. However, designing linkages to follow a desired path, known as path synthesis, is challenging due to non-linearities, combinatorial nature, and strict geometric constraints. Current state-of-the-art algorithms cannot scale well to linkages with higher-order linkage graphs, which are required to satisfy more complicated paths for new mechanical systems, such as hopping and flying robots. One reason for this is that state-of-the-art algorithms spend the majority of the time exploring constraint-violating designs. This work uses an Assur group 0DOF linkage as a graph grammar rule to modify both linkage graph and spatial parameters, ensuring all designs are valid 1DOF linkages. Using this graph grammar, this paper formulates linkage path synthesis as a tree search and uses a deep reinforcement learning (DRL) agent to search the space of kinematically feasible planar 1DOF linkages. This paper introduces a method using a graph convolution policy for high-order linkage graph optimization (GCP-HOLO). An anytime algorithm, GCP-HOLO outputs linkages with 1–8 loops (4–16 bars) efficiently. When comparing the GCP-HOLO formulation to a recent state-of-the-art paper that solves a mixed integer conic program, GCP-HOLO generates sets of solutions of varying linkage complexities to eight test trajectories in a quarter of the time. Extending GCP-HOLO with a global node optimization, such as covariance matrix adaptation evolutionary strategy, the results quickly converge to finding better solutions for 4/8 tests, with the whole pipeline capable of a 13X speed increase.

Data Lake Organization

We consider the problem of building an organizational directory of data lakes to support effective user navigation. The organization directory is defined as an acyclic graph that contains nodes representing sets of attributes and edges indicating subset relationships between nodes. A probabilistic model is constructed to model user navigational behaviour. The model also predicts the likelihood of users finding relevant tables in a data lake given an organization. We formulate the data lake organization problem as an optimization over the organizational structure in order to maximize the expected likelihood of discovering tables by navigating. An approximation algorithm is proposed with an analysis of its error bound. The effectiveness and efficiency of the algorithm are evaluated on both synthetic and real data lakes. Our experiments show that our algorithm constructs organizations that outperform many existing organizations including an existing hand-curated taxonomy, a linkage graph, and a common baseline organization. We have also conducted a formal user study which shows that navigation can help users discover relevant tables that are not easily accessible by keyword search queries. This suggests that keyword search and navigation using an organization are complementary modalities for data discovery in data lakes.

Automatic CAD Assemblies Generation by Linkage Graph Overlay for Machine Learning Applications

Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, CAD data mining, CAD and the internet, CAD education, genetic algorithms and CAD engines. The journal is aimed at all developers and users of CAD technology to ptovide CAD solutions for various stages of design and manufacturing. The journal publishes all about Computer-Aided Design and Computer-Aided technologies.

Efficient point cloud segmentation approach using energy optimization with geometric features for 3D scene understanding.

Efficient and quick extraction of unknown objects in cluttered 3D scenes plays a significant role in robotics tasks such as object search, grasping, and manipulation. This paper describes a geometric-based unsupervised approach for the segmentation of cluttered scenes into objects. The proposed method first over-segments the raw point clouds into supervoxels to provide a more natural representation of 3D point clouds and reduce the computational cost with a minimal loss of geometric information. Then the fully connected local area linkage graph is used to distinguish between planar and nonplanar adjacent patches. Then the initial segmentation is completed utilizing the geometric features and local surface convexities. After the initial segmentation, many subgraphs are generated, each of which represents an individual object or part of it. Finally, we use the plane extracted from the scene to refine the initial segmentation result under the framework of global energy optimization. Experiments on the Object Cluttered Indoor Dataset dataset indicate that the proposed method can outperform the representative segmentation algorithms in terms of weighted overlap and accuracy, while our method has good robustness and real-time performance.

Fifty years of semi-dwarf spring wheat breeding at CIMMYT: Grain yield progress in optimum, drought and heat stress environments

Grain yield progress over 50 years of spring wheat breeding at the International Maize and Wheat Improvement Center (CIMMYT) was determined in field trials conducted during five crop seasons (2013–2017) at Norman E. Borlaug research station near Ciudad Obregon, Mexico. The trials included 30 varieties (24 bread wheat and 6 durum wheat) released between 1965–2014 and were sown under managed optimum, drought, and heat stress conditions. The optimum irrigated environment had 3 management systems, flat sowing with weekly drip irrigation (FDI), bed sowing with flood irrigation (BFI), and flat sowing with flood irrigation (FFI). The drought environment had 2 management systems, flat sowing with reduced irrigation (FRI) and flat sowing under severe drought stress (FSD). The heat stress environment was sown in beds (HFI) three months later than the normally sown irrigated and drought environments. The rate of grain yield progress was estimated relative to Sonalika released in 1965 and Mexicali C75 released in 1975 for bread and durum wheat, respectively. Grain yield progress per year for bread wheat was, 31.2 kg ha−1, 35.3 kg ha−1, and 24.7 kg ha−1 in irrigated environments FDI, BFI, and FFI, respectively. In the stress environments, bread wheat grain yield progress was estimated as 25.6 kg ha−1, 17.7 kg ha−1, and 18.1 kg ha−1 per year in FRI, FSD, and HFI, respectively. For durum wheat, the grain yield progress was estimated as 29.6 kg ha−1, 48.1 kg ha−1, 18.8 kg ha−1, and 29.8 kg ha−1, per year in FDI, BFI, FFI, and HFI, respectively. Trait linkage graph analysis using LASSO regularized graphical model estimated that biomass, harvest index, and grains per meter square (GNM) were linked to grain yield progress in all environments. Thousand kernel weight was associated with grain yield progress under optimum and heat stress conditions, whereas grain weight per tiller (GWT) associated with progress under drought. Results also show that the highest yielding varieties in each environment however, had different trait attributes, with some varieties having higher GNM and tillers per meter square compensating for low GWT, while others had high GWT to compensate for reduced GNM. In conclusion, CIMMYT’s wheat breeding program has continued to show progress in grain yield in different environments/management systems, and while certain traits have consistently improved over the years, the varieties developed have employed different trait strategies to achieve final grain yield.

LGH: A Fast and Accurate Algorithm for Single Individual Haplotyping Based on a Two-Locus Linkage Graph.

Phased haplotype information is crucial in our complete understanding of differences between individuals at the genetic level. Given a collection of DNA fragments sequenced from a homologous pair of chromosomes, the problem of single individual haplotyping (SIH) aims to reconstruct a pair of haplotypes using a computer algorithm. In this paper, we encode the information of aligned DNA fragments into a two-locus linkage graph and approach the SIH problem by vertex labeling of the graph. In order to find a vertex labeling with the minimum sum of weights of incompatible edges, we develop a fast and accurate heuristic algorithm. It starts with detecting error-tolerant components by an adapted breadth-first search. A proper labeling of vertices is then identified for each component, with which sequencing errors are further corrected and edge weights are adjusted accordingly. After contracting each error-tolerant component into a single vertex, the above procedure is iterated on the resulting condensed linkage graph until error-tolerant components are no longer detected. The algorithm finally outputs a haplotype pair based on the vertex labeling. Extensive experiments on simulated and real data show that our algorithm is more accurate and faster than five existing algorithms for single individual haplotyping.

Identification of retinoblastoma related genes with shortest path in a protein–protein interaction network

This paper presents a new method for identifying retinoblastoma related genes by integrating gene expression profile and shortest path in a functional linkage graph. With the existing protein-protein interaction data from STRING, a weighted functional linkage graph is constructed. 119 consistently differentially expressed genes between retinoblastoma and normal retina were obtained from the overlap of two gene expression studies of retinoblastoma. Then the shortest paths between each pair of these 119 genes were determined with Dijkstra's algorithm. Finally, all the genes present on the shortest paths were extracted and ranked according to their betweenness and the 119 shortest genes with a betweenness greater than 100 and with a p-value less than 0.05 were selected for further analysis. We also identified 53 retinoblastoma related miRNAs from published miRNA array data and most of the 238 (119 consistently differentially expressed genes and 119 shortest path genes) retinoblastoma genes were shown to be target genes of these 53 miRNAs. Interestingly, the genes we identified from both the gene expression profiles and the functional protein association network included more cancer genes than did the genes identified from the gene expression profiles alone. In addition, these genes also had greater functional similarity to the reported cancer genes than did the genes identified from the gene expression profiles alone. This study shows promising results and proves the efficiency of the proposed methods.

The Modeling Analysis and Dynamics Simulation of Load-Sensing Hydraulic Systems

This paper analyzes the mathematical model of load-sensing hydraulic system based on power linkage graph method and builds the simulation model AMESim of the system. The load sensitive hydraulic system is applied in the working device of loader, and the simulation model AMESim with ADAMS is built by combining the dynamics analysis system with ADAMS,. The study of simulation on the dynamics is completed under different working conditions and the results of simulation analysis are given.

Linkage graph analysis: A linkage-group-based QTL synthesis analysis approach

Consensus quantitative trait loci (QTL) in meta-analysis of multiple independent QTL mapping experiments provides a strong foundation for marker-assisted selection and gene cloning. However, meta-analysis suffers from the lack of available genomic information and the results vary when different reference linkage maps are used. Here, to overcome these limitations, we propose a linkage-group-based QTL synthesis analysis approach that we have named linkage graph analysis. First, a graph model is constructed from derived linkage groups. Next, an unsupervised classification approach is used to obtain marker intervals with co-segregating patterns among multiple genomes. Finally, a frequent itemset mining technique is used to identify the markers (or intervals) closely linked to the QTL. The proposed method was validated by one Monte Carlo simulation study and by real data analysis of cotton genomes. Two major advantages of the new method are: (i) A reference linkage group is not required; (ii) the effect of the initial QTL is reduced because false QTLs can be detected and excluded from the dataset. The ability to reliably identify the markers associated with a true QTL is valuable in crop breeding.

Predicting malaria interactome classifications from time-course transcriptomic data along the intraerythrocytic developmental cycle

Even though a vaccine for malaria infections has been under intense study for many years, it has resisted several different lines of attack attempted by biologists. More than half of Plasmodium proteins still remain uncharacterized and therefore cannot be used in clinical trials. The task is further complicated by the metamorphic life-cycle of the parasite, which allows for rapid evolutionary changes and diversity among related strains, thus making precise targeting of the appropriate proteins for vaccination a technical challenge. We propose an automated method for predicting functions for the malaria parasite, which capitalizes on the importance of the intraerythrocytic developmental cycle data and expression changes during its five phases, as determined computationally by our segmentation algorithm. Our method combines temporal gene expression profiles with protein-protein interaction data, sequence similarity scores, and metabolic pathway information to produce a set of predicted protein functions that can be used as targets for vaccine development. We use a Bayesian approach, which assigns a probability of having (or not having) a particular function to each protein, given the various sources of evidence. In our method, each data source is represented by either a functional linkage graph or a categorical feature vector. The methods are tested on Plasmodium falciparum, the species responsible for the deadliest malaria infections. The algorithm was able to assign meaningful functions to 628 out of 1439 previously unannotated proteins, which are first-choice candidates for experimental vaccine research. We conclude that analyzing time-course gene expression profiles in separate phases leads to much higher prediction accuracy when compared with Pearson correlation coefficients computed across the time course as a whole. Additionally, we demonstrate that temporal expression profiles alone are able to improve the predictive power of the integrated data.

Lower and Upper Bounds for Linkage Discovery

For a real-valued function <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</i> defined on {0,1} <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> , the linkage graph of <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</i> is a hypergraph that represents the interactions among the input variables with respect to <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</i> . In this paper, lower and upper bounds for the number of function evaluations required to discover the linkage graph are rigorously analyzed in the black box scenario. First, a lower bound for discovering linkage graph is presented. To the best of our knowledge, this is the first result on the lower bound for linkage discovery. The investigation on the lower bound is based on Yao's minimax principle. For the upper bounds, a simple randomized algorithm for linkage discovery is analyzed. Based on the Kruskal-Katona theorem, we present an upper bound for discovering the linkage graph. As a corollary, we rigorously prove that <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> log <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> ) function evaluations are enough for bounded functions when the number of hyperedges is <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ( <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> ), which was suggested but not proven in previous works. To see the typical behavior of the algorithm for linkage discovery, three random models of fitness functions are considered. Using probabilistic methods, we prove that the number of function evaluations on the random models is generally smaller than the bound for the arbitrary case. Finally, from the relation between the linkage graph and the Walsh coefficients, it is shown that, for bounded functions, the proposed bounds are eventually the bounds for finding the Walsh coefficients.

Protein function prediction with the shortest path in functional linkage graph and boosting

Annotating proteins with biological functions is one of the main goals in post genomic era. Various high-throughout technologies, e.g., yeast two-hybrid systems and microarray, have provided an alternative way to protein function prediction. Despite the success obtained by high-throughout data, the errors in the data have not been handled well. In this work, a new technique for protein function prediction is presented, where a weighted functional linkage graph is generated by exploiting the existing protein-protein interaction data, complex data and gene expression data. By finding the shortest path in the functional linkage graph, the functional links among proteins can be captured. With the functional links available, the functions of unknown proteins can be predicted utilising support vector machines and the functions of those proteins that have functional links to the unknown proteins. In addition, the boosting algorithm is employed to further improve the prediction accuracy. The experiments on yeast genes show promising results and prove the efficiency of the proposed methods.

Data Linkage Graph: computation, querying and knowledge discovery of life science database networks

Summary To support the interpretation of measured molecular facts, like gene expression experiments or EST sequencing, the functional or the system biological context has to be considered. Doing so, the relationship to existing biological knowledge has to be discovered. In general, biological knowledge is worldwide represented in a network of databases. In this paper we present a method for knowledge extraction in life science databases, which prevents the scientists from screen scraping and web clicking approaches.We developed a method for extraction of knowledge networks from distributed, heterogeneous life science databases. To meet the requirement of the very large data volume, the method used is based on the concept of data linkage graphs (DLG).We present an efficient software which enables the joining of millions of data points over hundreds of databases. In order to motivate possible applications, we computed networks of protein knowledge, which interconnect metabolic, disease, enzyme and gene function data.The computed networks enabled a holistic relationship among measured experimental facts and the combined biological knowledge. This was successfully applied for a high throughput functional classification of barley EST and gene expression experiments with the perspective of an automated pipeline for the provisioning of controlled annotation of plant gene arrays and chips.Availability: The data linkage graphs (XML or TGF format), the schema integrated database schema (GML or GRAPH-ML) and the graph computation software may be downloaded from the following URL: http://pgrc.ipk-gatersleben.de/dlg/

Probabilistic Protein Function Prediction from Heterogeneous Genome-Wide Data

Dramatic improvements in high throughput sequencing technologies have led to a staggering growth in the number of predicted genes. However, a large fraction of these newly discovered genes do not have a functional assignment. Fortunately, a variety of novel high-throughput genome-wide functional screening technologies provide important clues that shed light on gene function. The integration of heterogeneous data to predict protein function has been shown to improve the accuracy of automated gene annotation systems. In this paper, we propose and evaluate a probabilistic approach for protein function prediction that integrates protein-protein interaction (PPI) data, gene expression data, protein motif information, mutant phenotype data, and protein localization data. First, functional linkage graphs are constructed from PPI data and gene expression data, in which an edge between nodes (proteins) represents evidence for functional similarity. The assumption here is that graph neighbors are more likely to share protein function, compared to proteins that are not neighbors. The functional linkage graph model is then used in concert with protein domain, mutant phenotype and protein localization data to produce a functional prediction. Our method is applied to the functional prediction of Saccharomyces cerevisiae genes, using Gene Ontology (GO) terms as the basis of our annotation. In a cross validation study we show that the integrated model increases recall by 18%, compared to using PPI data alone at the 50% precision. We also show that the integrated predictor is significantly better than each individual predictor. However, the observed improvement vs. PPI depends on both the new source of data and the functional category to be predicted. Surprisingly, in some contexts integration hurts overall prediction accuracy. Lastly, we provide a comprehensive assignment of putative GO terms to 463 proteins that currently have no assigned function.

A graph-based clustering method for a large set of sequences using a graph partitioning algorithm.

A graph-based clustering method is proposed to cluster protein sequences into families, which automatically improves clusters of the conventional single linkage clustering method. Our approach formulates sequence clustering problem as a kind of graph partitioning problem in a weighted linkage graph, which vertices correspond to sequences, edges correspond to higher similarities than given threshold and are weighted by their similarities. The effectiveness of our method is shown in comparison with InterPro families in all mouse proteins in SWISS-PROT. The result clusters match to InterPro families much better than the single linkage clustering method. 77% of proteins in InterPro families are classified into appropriate clusters.

Classifying molecular sequences using a linkage graph with their pairwise similarities

This paper presents a method for classifying a large and mixed set of uncharacterized sequences provided by genome projects. As the measure of sequence similarity, we use similarity score computed by a method based on the dynamic programming (DP), such as the Smith-Waterman local alignment algorithm. Although comparison by DP based method is very sensitive, when given sequences include a family of sequences that are much diverged in evolutionary process, similarity among some of them may be hidden behind spurious similarity of some unrelated sequences. Also the distance derived from the similarity score may not be metric (i.e., triangle inequality may not hold) when some sequences have multi-domain structure. To cope with these problems, we introduce a new graph structure called p-quasi complete graph for describing a family of sequences with a confidence measure. We prove that a restricted version of the p-quasi complete graph problem (given a positive integer k, whether a graph contains a 0.5-quasi complete subgraph of which size ⩾ k or not) is NP-complete. Thus we present an approximation algorithm for classifying a set of sequences using p-quasi complete subgraphs. The effectiveness of our method is demonstrated by the result of classifying over 4000 protein sequences on the Escherichia coli genome that was completely determined recently.