Biology subjects

Amorim, E.

Publications and source records attributed to Amorim, E..

3 recordsLinked to original sources

bioRxiv2024

AI-readiness for Biomedical Data: Bridge2AI Recommendations

Biomedical research is rapidly adopting artificial intelligence (AI). Yet the inherent complexity of biomedical data preparation requires implementing actionable, robust criteria for ethical and explainable AI (XAI) at the "pre-model" stage, encompassing data acquisition, detailed transformations, and ethical governance. Simple conformance to FAIR (Findable, Accessible, Interoperable, Reusable) Principles is insufficient. Here, we define criteria and practices for reliable AI-readiness of biomedical data, developed by the NIH Bridge to Artificial Intelligence (Bridge2AI) Standards Working Group across seven core dimensions of dataset AI-readiness: FAIRness, Provenance, Characterization, Ethics, Pre-model Explainability, Sustainability, and Computability. Conformance to these criteria provides a basis for pre-model scientific rigor and ethical integrity, mitigating downstream risks of bias and error prior to AI modeling. We apply and evaluate these standards across all four Bridge2AI flagship datasets, spanning functional genomics to clinical medicine, and encode them in machine-actionable metadata bound to the datasets. This framework sets a benchmark for preparing ethical, reusable datasets in biomedical AI and provides standardized methods for reliable pre-model data evaluation.

bioinformatics↗

bioRxiv2021

Expert-integrated automated machine learning uncovers hemodynamic predictors in spinal cord injury

Automated machine learning (AutoML) is positioned to democratize artificial intelligence (AI) by reducing the amount of human input and ML expertise needed to create prediction models. However, successful translation of ML in biomedicine requires moving beyond optimizing only for prediction accuracy and towards discovering reproducible clinical and biological inferences. Here, we present a model-agnostic framework to reinforce AutoML using strategies and tools of explainable and reproducible AI, including novel metrics for performance precision and feature instability. The framework enables clinicians to interpret AutoML-generated models for clinical and biological verifiability and consequently integrate domain expertise during model development. We applied the framework towards spinal cord injury prognostication and identified a detrimental relationship between intraoperative hypertension and patient outcome. Furthermore, our analysis captured evolving clinical practices such as faster time-to-surgery and blood pressure management that affected clinical model validation. Altogether, we illustrate how augmenting AutoML for inferential reproducibility empowers biomedical discovery and builds trust in AI processes towards effective clinical integration.

bioinformatics↗

bioRxiv2019

The Euler Characteristic and Topological Phase Transitions in Complex Systems

In this work, we use methods and concepts of applied algebraic topology to comprehensively explore the recent idea of topological phase transitions (TPT) in complex systems. TPTs are characterized by the emergence of nontrivial homology groups as a function of a threshold parameter. Under certain conditions, one can identify TPTs via the zeros of the Euler characteristic or by singularities of the Euler entropy. Recent works provide strong evidence that TPTs can be interpreted as a complex networks intrinsic fingerprint. This work illustrates this possibility by investigating some classic network and empirical protein interaction networks under a topological perspective. We first investigate TPT in protein-protein interaction networks (PPIN) using methods of topological data analysis for two variants of the Duplication-Divergence model, namely, the totally asymmetric model and the heterodimerization model. We compare our theoretical and computational results to experimental data freely available for gene co-expression networks (GCN) of Saccharomyces cerevisiae, also known as bakers yeast, as well as of the nematode Caenorhabditis elegans. Supporting our theoretical expectations, we can detect topological phase transitions in both networks obtained according to different similarity measures. Later, we perform numerical simulations of TPTs in four classical network models: the Erd[o]s-Renyi model, the Watts-Strogatz model, the Random Geometric model, and the Barabasi-Albert. Finally, we discuss some perspectives and insights on the topic. Given the universality and wide use of those models across disciplines, our work indicates that TPT permeates a wide range of theoretical and empirical networks.

biophysics↗