Ensemble methods are a very diverse family of algorithms with a wide range of applications. One of the most commonly used is boosting, with the prominent Adaboost. Adaboost relies on greedily learning base classifiers that rectify the error from previous iterations. Then, it combines them through a weighted majority vote, based on their quality on the entire learning set. In this paper, we propose a supervised binary classification framework that propagates the local knowledge acquired during the boosting iterations to the prediction function. Based on this general framework, we introduce SamBA, an interpretable greedy ensemble method designed for fat datasets, with a large number of dimensions and a small number of samples. SamBA learns local classifiers and combines them, using a similarity function, to optimize its efficiency in data extraction. We provide a theoretical analysis of SamBA, yielding convergence and generalization guarantees. In addition, we highlight SamBA’s empirical behavior in an extensive experimental analysis on both real biological and generated datasets, comparing it to state-of-the-art ensemble methods and similarity-based approaches.

scikit-multimodallearn is a Python library for multimodal supervised learning, licensed under Free BSD, and compatible with the well-known scikit-learn toolbox (Fabian Pedregosa, 2011). This paper details the content of the library, including a specific multimodal data formatting and classification and regression algorithms. Use cases and examples are also provided.

We consider the kernel completion problem with the presence of multiple views in the data. In this context the data samples can be fully missing in some views, creating missing columns and rows to the kernel matrices that are calculated individually for each view. We propose to solve the problem of completing the kernel matrices with Cross-View Kernel Transfer (CVKT) procedure, in which the features of the other views are transformed to represent the view under consideration. The transformations are learned with kernel alignment to the known part of the kernel matrix, allowing for finding generalizable structures in the kernel matrix under completion. Its missing values can then be predicted with the data available in other views. We illustrate the benefits of our approach with simulated data, multivariate digits dataset and multi-view dataset on gesture classification, as well as with real biological datasets from studies of pattern formation in early Drosophila melanogaster embryogenesis.

BACKGROUND: Accurate identification of Transcriptional Regulator binding locations is essential for analysis of genomic regions, including Cis Regulatory Elements. The customary NGS approaches, predominantly ChIP-Seq, can be obscured by data anomalies and biases which are difficult to detect without supervision. RESULTS: Here, we develop a method to leverage the usual combinations between many experimental series to mark such atypical peaks. We use deep learning to perform a lossy compression of the genomic regions' representations with multiview convolutions. Using artificial data, we show that our method correctly identifies groups of correlating series and evaluates CRE according to group completeness. It is then applied to the ReMap database's large volume of curated ChIP-seq data. We show that peaks lacking known biological correlators are singled out and less confirmed in real data. We propose normalization approaches useful in interpreting black-box models. CONCLUSION: Our approach detects peaks that are less corroborated than average. It can be extended to other similar problems, and can be interpreted to identify correlation groups. It is implemented in an open-source tool called atyPeak.

MOTIVATION: Various bioinformatics analyses provide sets of genomic coordinates of interest. Whether two such sets possess a functional relation is a frequent question. This is often determined by interpreting the statistical significance of their overlaps. However, only few existing methods consider the lengths of the overlap, and they do not provide a resolutive p-value. RESULTS: Here, we introduce OLOGRAM, which performs overlap statistics between sets of genomic regions described in BEDs or GTF. It uses Monte Carlo simulation, taking into account both the distributions of region and inter-region lengths, to fit a negative binomial model of the total overlap length. Exclusion of user-defined genomic areas during the shuffling is supported. AVAILABILITY: This tool is available through the command line interface of the pygtftk toolkit. It has been tested on Linux and OSX and is available on Bioconda and from https://github.com/dputhier/pygtftk under the GNU GPL license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Abstract The $$\mathcal {C}$$ C -bound is a tight bound on the true risk of a majority vote classifier that relies on the individual quality and pairwise disagreement of the voters and provides PAC-Bayesian generalization guarantees. Based on this bound, MinCq is a classification algorithm that returns a dense distribution on a finite set of voters by minimizing it. Introduced later and inspired by boosting, CqBoost uses a column generation approach to build a sparse $$\mathcal {C}$$ C -bound optimal distribution on a possibly infinite set of voters. However, both approaches have a high computational learning time because they minimize the $$\mathcal {C}$$ C -bound by solving a quadratic program. Yet, one advantage of CqBoost is its experimental ability to provide sparse solutions. In this work, we address the problem of accelerating the $$\mathcal {C}$$ C -bound minimization process while keeping the sparsity of the solution and without losing accuracy. We present CB-Boost, a computationally efficient classification algorithm relying on a greedy–boosting-based– $$\mathcal {C}$$ C -bound optimization. An in-depth analysis proves the optimality of the greedy minimization process and quantifies the decrease of the $$\mathcal {C}$$ C -bound operated by the algorithm. Generalization guarantees are then drawn based on already existing PAC-Bayesian theorems. In addition, we experimentally evaluate the relevance of CB-Boost in terms of the three main properties we expect about it: accuracy, sparsity, and computational efficiency compared to MinCq, CqBoost, Adaboost and other ensemble methods. As observed in these experiments, CB-Boost not only achieves results comparable to the state of the art, but also provides $$\mathcal {C}$$ C -bound sub-optimal weights with very few computational demand while keeping the sparsity property of CqBoost.

We consider the problem of metric learning for multi-view data and present a novel method for learning within-view as well as between-view metrics in vector-valued kernel spaces, as a way to capture multi-modal structure of the data. We formulate two convex optimization problems to jointly learn the metric and the classifier or regressor in kernel feature spaces. An iterative three-step multi-view metric learning algorithm is derived from the optimization problems. In order to scale the computation to large training sets, a block-wise Nyström approximation of the multi-view kernel matrix is introduced. We justify our approach theoretically and experimentally, and show its performance on real-world datasets against relevant state-of-the-art methods.

We study the problem of learning from multiple views using kernel methods in a supervised setting. We approach this problem from a multi-task learning point of view and illustrate how to capture the interesting multimodal structure of the data using multi-task kernels. Our analysis shows that the multi-task perspective offers the flexibility to design more efficient multiple-source learning algorithms, and hence the ability to exploit multiple descriptions of the data. In particular, we formulate the multimodal learning framework using vector-valued reproducing kernel Hilbert spaces, and we derive specific multi-task kernels that can operate over multiple modalities. Finally, we analyze the vector-valued regularized least squares algorithm in this context, and demonstrate its potential in a series of experiments with a real-world multimodal data set.

In imbalanced multi-class classification problems, the misclassification rate as an error measure may not be a relevant choice. Several methods have been developed where the performance measure retained richer information than the mere misclassification rate: misclassification costs, ROC-based information, etc. Following this idea of dealing with alternate measures of performance, we propose to address imbalanced classification problems by using a new measure to be optimized: the norm of the confusion matrix. Indeed, recent results show that using the norm of the confusion matrix as an error measure can be quite interesting due to the fine-grain informations contained in the matrix, especially in the case of imbalanced classes. Our first contribution then consists in showing that optimizing criterion based on the confusion matrix gives rise to a common background for cost-sensitive methods aimed at dealing with imbalanced classes learning problems. As our second contribution, we propose an extension of a recent multi-class boosting method — namely AdaBoost.MM — to the imbalanced class problem, by greedily minimizing the empirical norm of the confusion matrix. A theoretical analysis of the properties of the proposed method is presented, while experimental results illustrate the behavior of the algorithm and show the relevancy of the approach compared to other methods.

The tridimensional structure of a protein is constrained or stabilized by some local interactions between distant residues of the protein, such as disulfide bonds, electrostatic interactions or hydrogen links. The in silico prediction of the disulfide connectivity has been widely studied: most results were based on few amino-acids around bonded cysteines, which we call local environments of cysteines. In order to evaluate the impact of such local information onto residue pairing, we propose a machine learning based protocol, independent from the type of contact, to detect affinities between local environments which would contribute to residues pairing. Finally, we experiment our protocol on proteins that feature disulfide or salt bridges. The results show that local environments contribute to the formation of salt bridges. However, results on disulfide bridges are not significantly positive with the class of linear functions used by the perceptron-type algorithm we propose.

MOTIVATION: Complex biological functions emerge from interactions between proteins in stable supra-molecular assemblies and/or through transitory contacts. Most of the time protein partners of the assemblies are composed of one or several domains which exhibit different biochemical functions. Thus the study of cellular process requires the identification of different functional units and their integration in an interaction network; such complexes are referred to as integrated systems. In order to exploit with optimum efficiency the increased release of data, automated bioinformatics strategies are needed to identify, reconstruct and model such systems. For that purpose, we have developed a knowledge warehouse dedicated to the representation and acquisition of bacterial integrated systems involved in the exchange of the bacterial cell with its environment. RESULTS: ISYMOD is a knowledge warehouse that consistently integrates in the same environment the data and the methods used for their acquisition. This is achieved through the construction of (1) a domain knowledge base (DKB) devoted to the storage of the knowledge about the systems, their functional specificities, their partners and how they are related and (2) a methodological knowledge base (MKB) which depicts the task layout used to identify and reconstruct functional integrated systems. Instantiation of the DKB is obtained by solving the tasks of the MKB, whereas some tasks need instances of the DKB to be solved. AROM, an object-based knowledge representation system, has been used to design the DKB, and its task manager, AROMTasks, for developing the MKB. In this study two integrated systems, ABC transporters and two component systems, both involved in adaptation processes of a bacterial cell to its biotope, have been used to evaluate the feasibility of the approach.