Abstract We reevaluate the pairwise learning to rank approach based on neural nets, called RankNet, and present a theoretical analysis of its architecture. We show mathematically that the model can, under certain conditions, learn reflexive, antisymmetric, and transitive relations, enabling simplified training and improved performance. Experimental results on the LETOR MSLR-WEB10K, MQ2007 and MQ2008 datasets show that the model outperforms numerous state-of-the-art methods (including a listwise approach), while being inherently simpler in structure and using a pairwise approach only.

OBJECTIVE: Risk prediction models are widely used to inform evidence-based clinical decision making. However, few models developed from single cohorts can perform consistently well at population level where diverse prognoses exist (such as the SARS-CoV-2 [severe acute respiratory syndrome coronavirus 2] pandemic). This study aims at tackling this challenge by synergizing prediction models from the literature using ensemble learning. MATERIALS AND METHODS: In this study, we selected and reimplemented 7 prediction models for COVID-19 (coronavirus disease 2019) that were derived from diverse cohorts and used different implementation techniques. A novel ensemble learning framework was proposed to synergize them for realizing personalized predictions for individual patients. Four diverse international cohorts (2 from the United Kingdom and 2 from China; N = 5394) were used to validate all 8 models on discrimination, calibration, and clinical usefulness. RESULTS: Results showed that individual prediction models could perform well on some cohorts while poorly on others. Conversely, the ensemble model achieved the best performances consistently on all metrics quantifying discrimination, calibration, and clinical usefulness. Performance disparities were observed in cohorts from the 2 countries: all models achieved better performances on the China cohorts. DISCUSSION: When individual models were learned from complementary cohorts, the synergized model had the potential to achieve better performances than any individual model. Results indicate that blood parameters and physiological measurements might have better predictive powers when collected early, which remains to be confirmed by further studies. CONCLUSIONS: Combining a diverse set of individual prediction models, the ensemble method can synergize a robust and well-performing model by choosing the most competent ones for individual patients.

Discovering changes in the data distribution of streams and discovering recurrent data distributions are challenging problems in data mining and machine learning. Both have received a lot of attention in the context of classification. With the ever increasing growth of data, however, there is a high demand of compact and universal representations of data streams that enable the user to analyze current as well as historic data without having access to the raw data. To make a first step towards this direction, we propose a condensed representation that captures the various - possibly recurrent - data distributions of the stream by extending the notion of possible worlds. The representation enables queries concerning the whole stream and can, hence, serve as a tool for supporting decision-making processes or serve as a basis for implementing data mining and machine learning algorithms on top of it. We evaluate this condensed representation on synthetic and real-world data.

Data mining and machine learning algorithms usually operate directly on the data. However, if the data is not available at once or consists of billions of instances, these algorithms easily become infeasible with respect to memory and run-time concerns. As a solution to this problem, we propose a framework, called MiDEO (Mining Density Estimates inferred Online), in which algorithms are designed to operate on a condensed representation of the data. In particular, we propose to use density estimates, which are able to represent billions of instances in a compact form and can be updated when new instances arrive. As an example for an algorithm that operates on density estimates, we consider the task of mining association rules, which we consider as a form of simple statements about the data. The algorithm, called POEt (Pattern mining on Online density esTimates), is evaluated on synthetic and real-world data and is compared to state-of-the-art algorithms.

We address the problem of estimating a discrete joint density online, that is, the algorithm is only provided the current example and its current estimate. The proposed online estimator of discrete densities, EDDO (Estimation of Discrete Densities Online), uses classifier chains to model dependencies among features. Each classifier in the chain estimates the probability of one particular feature. Because a single chain may not provide a reliable estimate, we also consider ensembles of classifier chains and ensembles of weighted classifier chains. For all density estimators, we provide consistency proofs and propose algorithms to perform certain inference tasks. The empirical evaluation of the estimators is conducted in several experiments and on data sets of up to several million instances: We compare them to density estimates computed from Bayesian structure learners, evaluate them under the influence of noise, measure their ability to deal with concept drift, and measure the run-time performance. Our experiments demonstrate that, even though designed to work online, EDDO delivers estimators of competitive accuracy compared to batch Bayesian structure learners and batch variants of EDDO.

In recent years, graph kernels have received considerable interest within the machine learning and data mining community. Here, we introduce a novel approach enabling kernel methods to utilize additional information hidden in the structural neighborhood of the graphs under consideration. Our novel structural cluster kernel (SCK) incorporates similarities induced by a structural clustering algorithm to improve state-of-the-art graph kernels. The approach taken is based on the idea that graph similarity can not only be described by the similarity between the graphs themselves, but also by the similarity they possess with respect to their structural neighborhood. We applied our novel kernel in a supervised and a semi-supervised setting to regression and classification problems on a number of real-world datasets of molecular graphs.

We present a novel approach to incrementally determine the trajectory of a person in 3-D based on its motions and activities in real time. In our algorithm, we estimate the motions and activities of the user given the data that are obtained from a motion capture suit equipped with several inertial measurement units. These activities include walking up and down staircases, as well as opening and closing doors. We interpret the first two types of activities as motion constraints and door-handling events as landmark detections in a graph-based simultaneous localization and mapping (SLAM) framework. Since we cannot distinguish between individual doors, we employ a multihypothesis tracking approach on top of the SLAM procedure to deal with the high data-association uncertainty. As a result, we are able to accurately and robustly recover the trajectory of the person. Additionally, we present an algorithm to build approximate geometrical and topological maps based on the estimated trajectory and detected activities. We evaluate our approach in practical experiments that are carried out with different subjects and in various environments.

We present a novel approach to build approximate maps of structured environments utilizing human motion and activity. Our approach uses data recorded with a data suit which is equipped with several IMUs to detect movements of a person and door opening and closing events. In our approach we interpret the movements as motion constraints and door handling events as landmark detections in a graph-based SLAM framework. As we cannot distinguish between individual doors, we employ a multi-hypothesis approach on top of the SLAM system to deal with the high data-association uncertainty. As a result, our approach is able to accurately and robustly recover the trajectory of the person. We additionally take advantage of the fact that people traverse free space and that doors separate rooms to recover the geometric structure of the environment after the graph optimization. We evaluate our approach in several experiments carried out with different users and in environments of different types.

Scheme-specific attribute selection with the wrapper and variants of forward selection is a popular attribute selection technique for classification that yields good results. However, it can run the risk of overfitting because of the extent of the search and the extensive use of internal cross-validation. Moreover, although wrapper evaluators tend to achieve superior accuracy compared to filters, they face a high computational cost. The problems of overfitting and high runtime occur in particular on high-dimensional datasets, like microarray data. We investigate Linear Forward Selection, a technique to reduce the number of attributes expansions in each forward selection step. Our experiments demonstrate that this approach is faster, finds smaller subsets and can even increase the accuracy compared to standard forward selection. We also investigate a variant that applies explicit subset size determination in forward selection to combat overfitting, where the search is forced to stop at a precomputed “optimal” subset size. We show that this technique reduces subset size while maintaining comparable accuracy.

The task of aligning sequences arises in many applications. Classical dynamic programming approaches require the explicit state enumeration in the reward model. This is often impractical: the number of states grows very quickly with the number of domain objects and relations among these objects. Relational sequence alignment aims at exploiting symbolic structure to avoid the full enumeration. This comes at the expense of a more complex reward model selection problem: virtually infinitely many abstraction levels have to be explored. In this paper, we apply gradient-based boosting to leverage this problem. Specifically, we show how to reduce the learning problem to a series of relational regressions problems. The main benefit of this is that interactions between states variables are introduced only as needed, so that the potentially infinite search space is not explicitly considered. As our experimental results show, this boosting approach can significantly improve upon established results in challenging applications.

MOTIVATION: The genome of Arabidopsis thaliana, which has the best understood plant genome, still has approximately one-third of its genes with no functional annotation at all from either MIPS or TAIR. We have applied our Data Mining Prediction (DMP) method to the problem of predicting the functional classes of these protein sequences. This method is based on using a hybrid machine-learning/data-mining method to identify patterns in the bioinformatic data about sequences that are predictive of function. We use data about sequence, predicted secondary structure, predicted structural domain, InterPro patterns, sequence similarity profile and expressions data. RESULTS: We predicted the functional class of a high percentage of the Arabidopsis genes with currently unknown function. These predictions are interpretable and have good test accuracies. We describe in detail seven of the rules produced.

The authors would like to apologise for an error in citing H. Ougham's affiliated institution. It should be IGER, Plas Gogerddan, Aberystwyth, Ceredigion SY23 3EB, UK.

BACKGROUND: The inference of homology between proteins is a key problem in molecular biology The current best approaches only identify approximately 50% of homologies (with a false positive rate set at 1/1000). RESULTS: We present Homology Induction (HI), a new approach to inferring homology. HI uses machine learning to bootstrap from standard sequence similarity search methods. First a standard method is run, then HI learns rules which are true for sequences of high similarity to the target (assumed homologues) and not true for general sequences, these rules are then used to discriminate sequences in the twilight zone. To learn the rules HI describes the sequences in a novel way based on a bioinformatic knowledge base, and the machine learning method of inductive logic programming. To evaluate HI we used the PDB40D benchmark which lists sequences of known homology but low sequence similarity. We compared the HI methodology with PSI-BLAST alone and found HI performed significantly better. In addition, Receiver Operating Characteristic (ROC) curve analysis showed that these improvements were robust for all reasonable error costs. The predictive homology rules learnt by HI by can be interpreted biologically to provide insight into conserved features of homologous protein families. CONCLUSIONS: HI is a new technique for the detection of remote protein homology--a central bioinformatic problem. HI with PSI-BLAST is shown to outperform PSI-BLAST for all error costs. It is expect that similar improvements would be obtained using HI with any sequence similarity method.

Abstract Motivation: Data Mining Prediction (DMP) is a novel approach to predicting protein functional class from sequence. DMP works even in the absence of a homologous protein of known function. We investigate the utility of different ways of representing protein sequence in DMP (residue frequencies, phylogeny, predicted structure) using the Escherichia coli genome as a model. Results: Using the different representations DMP learnt prediction rules that were more accurate than default at every level of function using every type of representation. The most effective way to represent sequence was using phylogeny (75% accuracy and 13% coverage of unassigned ORFs at the most general level of function: 69% accuracy and 7% coverage at the most detailed). We tested different methods for combining predictions from the different types of representation. These improved both the accuracy and coverage of predictions, e.g. 40% of all unassigned ORFs could be predicted at an estimated accuracy of 60% and 5% of unassigned ORFs could be predicted at an estimated accuracy of 86%. Availability: The rules and data are freely available. Warmr is free to academics. Contact: [email protected] Supplementary information: http://www.aber.ac.uk/~dcswww/Research/bio/ProteinFunction * To whom correspondence should be addressed.

The ability to predict protein function from amino acid sequence is a central research goal of molecular biology.Such a capability would greatly aid the biological interpretation of the genomic data and accelerate its medical exploitation.For the existing sequenced genomes function can be assigned to typically only between 40-60% of the genes [4,8,12,7].The new science of functional genomics is dedicated to discovering the function of these genes, and to further detailing gene function [10,27,17,6].Here we present a novel data-mining [24,18] approach to predicting protein functional class from sequence.We demonstrate the effectiveness of this approach on the Mycobacterium tuberculosis [8] genome.Biologically interpretable rules are identified that can predict protein function even in the absence of identifiable sequence homology.These rules predict 65% of the genes with no previous assigned function in Mycobacterium tuberculosis (the bacteria which causes TB) with an estimated accuracy of 60-80% (depending on the level of functional assignment).The rules give insight into the evolutionary history of the organism.