arXiv subjects

Mikel Hernaez

Publications and source records attributed to Mikel Hernaez.

6 recordsLinked to original sources

arXiv2026

A quantum generative model for in silico clinical trials using scarce training datasets

In silico methods have emerged as a strategy to complement clinical trials. These are particularly relevant for rare or heterogeneous diseases for which traditional methods are costly or difficult to apply. While classical generative models have shown an extremely good ability to generate high fidelity data when trained using extensive databases, they often struggle when the available samples for training are scarce. In this work, we leverage the potential of quantum computers to represent complex probability distributions to generate high fidelity in silico patients. We propose a pipeline able to combine asymmetric databases into a quantum circuit that serves as a quantum generative model. We evaluate the efficacy of our proposal using a database of Myelodysplastic Syndrome (MDS) patients with 7 clinical variables as a proof-of-concept. We executed our quantum generative model in the IBM Heron r2 ``ibm\_basquecountry'' superconducting quantum computer and compare our method with well known classical baselines. Our results show that the quantum generative model surpasses the classical generative models in generalization and expressivity metrics, indicating its potential validity to generate high fidelity in silico patients for clinical trials.

quant-ph↗

arXiv2025

Interpretable Causal Representation Learning for Biological Data in the Pathway Space

Predicting the impact of genomic and drug perturbations in cellular function is crucial for understanding gene functions and drug effects, ultimately leading to improved therapies. To this end, Causal Representation Learning (CRL) constitutes one of the most promising approaches, as it aims to identify the latent factors that causally govern biological systems, thus facilitating the prediction of the effect of unseen perturbations. Yet, current CRL methods fail in reconciling their principled latent representations with known biological processes, leading to models that are not interpretable. To address this major issue, we present SENA-discrepancy-VAE, a model based on the recently proposed CRL method discrepancy-VAE, that produces representations where each latent factor can be interpreted as the (linear) combination of the activity of a (learned) set of biological processes. To this extent, we present an encoder, SENA-δ, that efficiently compute and map biological processes' activity levels to the latent causal factors. We show that SENA-discrepancy-VAE achieves predictive performances on unseen combinations of interventions that are comparable with its original, non-interpretable counterpart, while inferring causal latent factors that are biologically meaningful.

cs.LG↗

arXiv2024

Sweetwater: An interpretable and adaptive autoencoder for efficient tissue deconvolution

Single-cell RNA-sequencing (scRNA-seq) stands as a powerful tool for deciphering cellular heterogeneity and exploring gene expression profiles at high resolution. However, its high cost renders it impractical for extensive sample cohorts within routine clinical care, hindering its broader applicability. Hence, many methodologies have recently arised to estimate cell type proportions from bulk RNA-seq samples (known as deconvolution methods). However, they have several limitations: Many depend on selecting a robust scRNA-seq reference dataset, which is often challenging. Secondly, building reliable pseudobulk samples requires determining the optimal number of genes or cells involved in the simulated data generation process, which has not been studied in depth. Moreover, pseudobulk and bulk RNA-seq samples often exhibit distribution shifts. Finally, most modern deconvolution approaches behave as a black box, and the underlying mechanisms of the deconvolution task are still unknown, which can compromise the reliability of the results. In this work, we present Sweetwater, an adaptive and interpretable autoencoder able to efficiently deconvolve bulk RNA-seq and microarray samples leveraging multiple classes of reference data, such as scRNA-seq and single-nuclei RNA-seq. Moreover, it can be trained on a mixture of FACS-sorted FASTQ files, which we newly propose to use as this reduces platform-specific biases and may potentially outperform single-cell-based references. Also, we demonstrate that Sweetwater effectively uncovers biologically meaningful patterns during the training process, increasing the reliability of the results. Sweetwater is available at https://github.com/ubioinformat/Sweetwater, and we anticipate will facilitate and expedite the accurate examination of high-throughput clinical data across diverse applications.

q-bio.GN↗

arXiv2023

Towards a more inductive world for drug repurposing approaches

Drug-target interaction (DTI) prediction is a challenging, albeit essential task in drug repurposing. Learning on graph models have drawn special attention as they can significantly reduce drug repurposing costs and time commitment. However, many current approaches require high-demanding additional information besides DTIs that complicates their evaluation process and usability. Additionally, structural differences in the learning architecture of current models hinder their fair benchmarking. In this work, we first perform an in-depth evaluation of current DTI datasets and prediction models through a robust benchmarking process, and show that DTI prediction methods based on transductive models lack generalization and lead to inflated performance when evaluated as previously done in the literature, hence not being suited for drug repurposing approaches. We then propose a novel biologically-driven strategy for negative edge subsampling and show through in vitro validation that newly discovered interactions are indeed true. We envision this work as the underpinning for future fair benchmarking and robust model design. All generated resources and tools are publicly available as a python package.

cs.LG↗

arXiv2012

A Flexible Channel Coding Approach for Short-Length Codewords

This letter introduces a novel channel coding design framework for short-length codewords that permits balancing the tradeoff between the bit error rate floor and waterfall region by modifying a single real-valued parameter. The proposed approach is based on combining convolutional coding with a $q$-ary linear combination and unequal energy allocation, the latter being controlled by the aforementioned parameter. EXIT charts are used to shed light on the convergence characteristics of the associated iterative decoder, which is described in terms of factor graphs. Simulation results show that the proposed scheme is able to adjust its end-to-end error rate performance efficiently and easily, on the contrary to previous approaches that require a full code redesign when the error rate requirements of the application change. Simulations also show that, at mid-range bit-error rates, there is a small performance penalty with respect to the previous approaches. However, the EXIT chart analysis and the simulation results suggest that for very low bit-error rates the proposed system will exhibit lower error floors than previous approaches.

cs.IT↗

arXiv2012

On the Design of a Novel Joint Network-Channel Coding Scheme for the Multiple Access Relay Channel

This paper proposes a novel joint non-binary network-channel code for the Time-Division Decode-and-Forward Multiple Access Relay Channel (TD-DF-MARC), where the relay linearly combines -- over a non-binary finite field -- the coded sequences from the source nodes. A method based on an EXIT chart analysis is derived for selecting the best coefficients of the linear combination. Moreover, it is shown that for different setups of the system, different coefficients should be chosen in order to improve the performance. This conclusion contrasts with previous works where a random selection was considered. Monte Carlo simulations show that the proposed scheme outperforms, in terms of its gap to the outage probabilities, the previously published joint network-channel coding approaches. Besides, this gain is achieved by using very short-length codewords, which makes the scheme particularly attractive for low-latency applications.

cs.IT↗