Leandro E. Di Persia

L. I. Zablocki, L. A. Bugnon, M. Gerard et al.

Inspired by the success of large language models (LLM) for DNA and proteins, several LLM for RNA have been developed recently. RNA-LLM uses large datasets of RNA sequences to learn, in a self-supervised way, how to represent each RNA base with a semantically rich numerical vector. This is done under the hypothesis that obtaining high-quality RNA representations can enhance data-costly downstream tasks. Among them, predicting the secondary structure is a fundamental task for uncovering RNA functional mechanisms. In this work we present a comprehensive experimental analysis of several pre-trained RNA-LLM, comparing them for the RNA secondary structure prediction task in an unified deep learning framework. The RNA-LLM were assessed with increasing generalization difficulty on benchmark datasets. Results showed that two LLM clearly outperform the other models, and revealed significant challenges for generalization in low-homology scenarios.

Eugenio Borzone, Leandro Di Persia, Matias Gerard

This paper presents a novel graph-based deep learning model for tasks involving relations between two nodes (edge-centric tasks), where the focus lies on predicting relationships and interactions between pairs of nodes rather than node properties themselves. This model combines supervised and self-supervised learning, taking into account for the loss function the embeddings learned and patterns with and without ground truth. Additionally it incorporates an attention mechanism that leverages both node and edge features. The architecture, trained end-to-end, comprises two primary components: embedding generation and prediction. First, a graph neural network (GNN) transform raw node features into dense, low-dimensional embeddings, incorporating edge attributes. Then, a feedforward neural model processes the node embeddings to produce the final output. Experiments demonstrate that our model matches or exceeds existing methods for protein-protein interactions prediction and Gene Ontology (GO) terms prediction. The model also performs effectively with one-hot encoding for node features, providing a solution for the previously unsolved problem of predicting similarity between compounds with unknown structures.

Ramiro Casal, Leandro E. Di Persia, Gastón Schlotthauer

Sleep disorders are very widespread in the world population and suffer from a generalized underdiagnosis, given the complexity of their diagnostic methods. Therefore, there is an increasing interest in developing simpler screening methods. A pulse oximeter is an ideal device for sleep disorder screenings since it is a portable, low-cost and accessible technology. This device can provide an estimation of the heart rate (HR), which can be useful to obtain information regarding the sleep stage. In this work, we developed a network architecture with the aim of classifying the sleep stage in awake or asleep using only HR signals from a pulse oximeter. The proposed architecture has two fundamental parts. The first part has the objective of obtaining a representation of the HR by using temporal convolutional networks. Then, the obtained representation is used to feed the second part, which is based on transformers, a model built solely with attention mechanisms. Transformers are able to model the sequence, learning the transition rules between sleep stages. The performance of the proposed method was evaluated on Sleep Heart Health Study dataset, composed of 5000 healthy and pathological subjects. The dataset was split into three subsets: 2500 for training, $1250$ for validating, and 1250 for testing. The overall accuracy, specificity, sensibility, and Cohen's Kappa coefficient were 90.0%, 94.9%, 78.1%, and 0.73.

Ramiro Casal, Leandro E. Di Persia, Gastón Schlotthauer

The regulation of the autonomic nervous system changes with the sleep stages causing variations in the physiological variables. We exploit these changes with the aim of classifying the sleep stages in awake or asleep using pulse oximeter signals. We applied a recurrent neural network to heart rate and peripheral oxygen saturation signals to classify the sleep stage every 30 seconds. The network architecture consists of two stacked layers of bidirectional gated recurrent units (GRUs) and a softmax layer to classify the output. In this paper, we used 5000 patients from the Sleep Heart Health Study dataset. 2500 patients were used to train the network, and two subsets of 1250 were used to validate and test the trained models. In the test stage, the best result obtained was 90.13% accuracy, 94.13% sensitivity, 80.26% specificity, 92.05% precision, and 84.68% negative predictive value. Further, the Cohen's Kappa coefficient was 0.74 and the average absolute error percentage to the actual sleep time was 8.9%. The performance of the proposed network is comparable with the state-of-the-art algorithms when they use much more informative signals (except those with EEG).

R. E. Rolón, L. E. Di Persia, R. D. Spies et al.

In the last decade, traditional dictionary learning methods have been successfully applied to various pattern classification tasks. Although these methods produce sparse representations of signals which are robust against distortions and missing data, such representations quite often turn out to be unsuitable if the final objective is signal classification. In order to overcome or at least to attenuate such a weakness, several new methods which incorporate discriminative information into sparse-inducing models have emerged in recent years. In particular, methods for discriminative dictionary learning have shown to be more accurate (in terms of signal classification) than the traditional ones, which are only focused on minimizing the total representation error. In this work, we present both a novel multi-class discriminative measure and an innovative dictionary learning method. For a given dictionary, this new measure, which takes into account not only when a particular atom is used for representing signals coming from a certain class and the magnitude of its corresponding representation coefficient, but also the effect that such an atom has in the total representation error, is capable of efficiently quantifying the degree of discriminability of each one of the atoms. On the other hand, the new dictionary construction method yields dictionaries which are highly suitable for multi-class classification tasks. Our method was tested with a widely used database for handwritten digit recognition and compared with three state-of-the-art classification methods. The results show that our method significantly outperforms the other three achieving good recognition rates and additionally, reducing the computational cost of the classifier.

Francisco Ibarrola, Leandro Di Persia, Ruben Spies

When recorded in an enclosed room, a sound signal will most certainly get affected by reverberation. This not only undermines audio quality, but also poses a problem for many human-machine interaction technologies that use speech as their input. In this work, a new blind, two-stage dereverberation approach based in a generalized β-divergence as a fidelity term over a non-negative representation is proposed. The first stage consists of learning the spectral structure of the signal solely from the observed spectrogram, while the second stage is devoted to model reverberation. Both steps are taken by minimizing a cost function in which the aim is put either in constructing a dictionary or a good representation by changing the divergence involved. In addition, an approach for finding an optimal fidelity parameter for dictionary learning is proposed. An algorithm for implementing the proposed method is described and tested against state-of-the-art methods. Results show improvements for both artificial reverberation and real recordings.

Francisco J. Ibarrola, Leandro E. Di Persia, Ruben D. Spies

When a signal is recorded in an enclosed room, it typically gets affected by reverberation. This degradation represents a problem when dealing with audio signals, particularly in the field of speech signal processing, such as automatic speech recognition. Although there are some approaches to deal with this issue that are quite satisfactory under certain conditions, constructing a method that works well in a general context still poses a significant challenge. In this article, we propose a method based on convolutive nonnegative matrix factorization that mixes two penalizers in order to impose certain characteristics over the time-frequency components of the restored signal and the reverberant components. An algorithm for implementing the method is described and tested. Comparisons of the results against those obtained with state of the art methods are presented, showing significant improvement.