Cost-sensitive and parametrized Hopfield Networks for gene function prediction

In gene function prediction problems functional classes are unbalanced, since usually only a small subset of the genes are annotated for a specific GO term or FunCat category. In this context both supervised and semi-supervised algorithms usually fail to detect genes "positive" for a given class.

To deal with this problem we developed COSNet (COst Sensitive neural Network), a novel cost-sensitive family of parametrized Hopfield networks, whose characteristics can be summarized as follows (Frasca et al. 2013, Bertoni et al. 2011):

1. Class labels and neuron states are conceptually separated. In this way a class of Hopfield networks is introduced, having as parameters the values of neuron states and the neuron thresholds.

2.The parameters of the network are learned from the data through an efficient supervised algorithm, in order to take into account the unbalance between positive and negative node labels.

3. The dynamics of the network is restricted to its unlabeled part, preserving the minimization of the overall objective function and the a priori information and significantly reducing the time complexity of the learning algorithm.

A regularized version has also been proposed to deal with extremely unbalanced functional classes (Frasca et al. 2012) and we are currently working on SINTNET, a COSNet-inspired unbalance-aware method for integrating multiple sources of bio-molecular data (Frasca et al. 2013).

Variants of COSNet exploit gene multi-functionality to improve gene function predictions (Frasca 2015), and a new multi-parametric Hopfield network (Hopfield multi-category -- HoMCat), designed to take into account a priori-known "categories" of neurons within networks, has been successfully applied to the multi-species protein function prediction problem (Frasca et al. 2015).

In the same context of protein function prediction,

unbalance-aware network integration, coupled with unbalance-aware parametrized Hopfield networks, showed improved performances with respect to state-of-the-art algorithms, and introduced a valuable way to evaluate the informativeness of different sources of information for the prediction of specific GO terms (UNIPred method, Frasca et al. in press).


M. Frasca, A. Bertoni, G. Valentini UNIPred: Unbalance-aware Network Integration and Prediction of protein functions, Journal of Computational Biology, Supplementary Information (in press)

M. Frasca, S.Bassis, G. Valentini Learning node labels with multi-category Hopfield networks, Neural Computing and Applications, , 2015

M. Frasca. Automated Gene Function Prediction through Gene Multifunctionality in Biological Networks. Neurocomputing, vol. 162, pp. 48-56, 2015.

M.Frasca, A. Bertoni, G. Valentini An unbalance-aware network integration method for gene function prediction, MLSB 2013 - Machine Learning for Systems Biology - Berlin, 2013

M. Frasca, A. Bertoni, M. Re, and G. Valentini, A neural network algorithm for semi-supervised node label learning from unbalanced data, Neural Networks 43, pp.84-98, July 2013 Science Direct link

M. Frasca, A. Bertoni, A. Sion. A neural procedure for Gene Function Prediction, Neural Nets and Surroundings, Smart Innovation, Systems and Technologies. Volume 19, 2013, pp 179-188.

M. Frasca, A. Bertoni, G. Valentini, RegularizedNetwork-Based Algorithm for Predicting Gene Functions with High-Imbalanced Data, EMBnet.journal, vol 18, Supplement A, pp.41,42, 2012.

A. Bertoni, M. Frasca, G. Valentini COSNet: a Cost Sensitive Neural Network for Semi-supervised Learning in Graphs., In: "Machine Learning and Knowledge Discovery in Databases". European Conference, ECML PKDD 2011, Athens, Greece, Proceedings, Part I, Lecture Notes in Artificial Intelligence, vol. 6911, pp.219-234, Springer, 2011.

M. Frasca, A. Bertoni, G. Valentini A cost-sensitive neural algorithm to predict gene functions using large biological networks., Network Biology SIG: On the Analysis and Visualization of Networks in Biology, ISMB 2011, Wien

A. Bertoni, M. Frasca, G. Grossi, G. Valentini, Learningfunctional linkage networks with a cost-sensitive approach Neural Networks - WIRN 2010, IOS Press, pp. 52-61, 2010