Learning node labels with multi-category Hopfield networks

Frasca, Marco; Bassis, Simone; Valentini, Giorgio

doi:10.1007/s00521-015-1965-1

Cited by 7 publications

(10 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…previous results obtained with inductive methods (Cesa-Bianchi et al, 2012), but the hierarchical correction of the predictions (Mostafavi and Morris, 2009;Cesa-Bianchi et al, 2012;Cozzetto et al, 2013;Robinson et al, 2015), and the multi-species setting of the classification problem (Wong et al, 2012;Mesiti et al, 2014) could further improve the performances of the proposed method, as shown by our recent results obtained with multi-category Hopfield networks, a variant of COSNet well-suited to multi-species protein function prediction problems (Frasca et al, 2015).…”

Section: Discussionmentioning

confidence: 55%

UNIPred: Unbalance-Aware Network Integration and Prediction of Protein Functions

Frasca

Bertoni

Valentini

2015

Journal of Computational Biology

Self Cite

View full text Add to dashboard Cite

The proper integration of multiple sources of data and the unbalance between annotated and unannotated proteins represent two of the main issues of the automated function prediction (AFP) problem. Most of supervised and semisupervised learning algorithms for AFP proposed in literature do not jointly consider these items, with a negative impact on both sensitivity and precision performances, due to the unbalance between annotated and unannotated proteins that characterize the majority of functional classes and to the specific and complementary information content embedded in each available source of data. We propose UNIPred (unbalance-aware network integration and prediction of protein functions), an algorithm that properly combines different biomolecular networks and predicts protein functions using parametric semisupervised neural models. The algorithm explicitly takes into account the unbalance between unannotated and annotated proteins both to construct the integrated network and to predict protein annotations for each functional class. Full-genome and ontology-wide experiments with three eukaryotic model organisms show that the proposed method compares favorably with state-of-the-art learning algorithms for AFP.

show abstract

Section: Discussionmentioning

confidence: 55%

UNIPred: Unbalance-Aware Network Integration and Prediction of Protein Functions

Frasca

Bertoni

Valentini

2015

Journal of Computational Biology

Self Cite

View full text Add to dashboard Cite

show abstract

“…That is, before applying any algorithm to learn negative examples, it is of paramount importance studying which ‘protein representation’ is more informative for the problem itself. In this context, most information sources about the relationships between proteins are naturally represented through protein networks, where each node represents a protein and an edge the relationship between two proteins [13]; additionally, most approaches proposed for AFP are network-based [14–20]. Thus, the purpose here is twofold: extracting meaningful protein features from protein networks, and assessing their ability to improve the identification of good negative examples.…”

Section: Introductionmentioning

confidence: 99%

Evaluating the impact of topological protein features on the negative examples selection

2018

Self Cite

View full text Add to dashboard Cite

BackgroundSupervised machine learning methods when applied to the problem of automated protein-function prediction (AFP) require the availability of both positive examples (i.e., proteins which are known to possess a given protein function) and negative examples (corresponding to proteins not associated with that function). Unfortunately, publicly available proteome and genome data sources such as the Gene Ontology rarely store the functions not possessed by a protein. Thus the negative selection, consisting in identifying informative negative examples, is currently a central and challenging problem in AFP. Several heuristics have been proposed through the years to solve this problem; nevertheless, despite their effectiveness, to the best of our knowledge no previous existing work studied which protein features are more relevant to this task, that is, which protein features help more in discriminating reliable and unreliable negatives.ResultsThe present work analyses the impact of several features on the selection of negative proteins for the Gene Ontology (GO) terms. The analysis is network-based: it exploits the fact that proteins can be naturally structured in a network, considering the pairwise relationships coming from several sources of data, such as protein-protein and genetic interactions. Overall, the proposed protein features, including local and global graph centrality measures and protein multifunctionality, can be term-aware (i.e., depending on the GO term) and term-unaware (i.e., invariant across the GO terms). We validated the informativeness of each feature utilizing a temporal holdout in three different experiments on yeast, mouse and human proteomes: (i) feature selection to detect which protein features are more helpful for the negative selection; (ii) protein function prediction to verify whether the features considered are also useful to predict GO terms; (iii) negative selection by applying two different negative selection algorithms on proteins represented through the proposed features.ConclusionsTerm-aware features (with some exceptions) resulted more informative for problem (i), together with node betweenness, which is the most relevant among term-unaware features. The node positive neighborhood instead is the most predictive feature for the AFP problem, while experiment (iii) showed that the proposed features allow negative selection algorithms to select effectively negative instances in the temporal holdout setting, with better results when nonlinear combinations of features are also exploited.Electronic supplementary materialThe online version of this article (10.1186/s12859-018-2385-x) contains supplementary material, which is available to authorized users.

show abstract

“…for every task c k . Following the approach proposed in [16], a set of membership functions can be defined, extending the crisp memberships introduced above:…”

Section: Multitask Hopfield Networkmentioning

confidence: 99%

Multitask Hopfield Networks

Frasca¹,

Grossi²,

Valentini³

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Multitask algorithms typically use task similarity information as a bias to speed up and improve the performance of learning processes. Tasks are learned jointly, sharing information across them, in order to construct models more accurate than those learned separately over single tasks. In this contribution, we present the first multitask model, to our knowledge, based on Hopfield Networks (HNs), named HoMTask. We show that by appropriately building a unique HN embedding all tasks, a more robust and effective classification model can be learned. HoMTask is a transductive semi-supervised parametric HN, that minimizes an energy function extended to all nodes and to all tasks under study. We provide theoretical evidence that the optimal parameters automatically estimated by HoMTask make coherent the model itself with the prior knowledge (connection weights and node labels). The convergence properties of HNs are preserved, and the fixed point reached by the network dynamics gives rise to the prediction of unlabeled nodes. The proposed model improves the classification abilities of singletask HNs on a preliminary benchmark comparison, and achieves competitive performance with state-of-the-art semi-supervised graph-based algorithms.

show abstract

Learning node labels with multi-category Hopfield networks

Cited by 7 publications

References 63 publications

UNIPred: Unbalance-Aware Network Integration and Prediction of Protein Functions

UNIPred: Unbalance-Aware Network Integration and Prediction of Protein Functions

Evaluating the impact of topological protein features on the negative examples selection

Multitask Hopfield Networks

Contact Info

Product

Resources

About