A5100611054- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Spectroscopy and Chemometric Analyses
- Spectroscopy Techniques in Biomedical and Chemical Research
- Viral Infectious Diseases and Gene Expression in Insects
- Gut microbiota and health
- Radiomics and Machine Learning in Medical Imaging
- Computational Drug Discovery Methods
- Glioma Diagnosis and Treatment
- Gene Regulatory Network Analysis
- Ferroptosis and cancer prognosis
- Retinal Imaging and Analysis
- Metabolomics and Mass Spectrometry Studies
- MicroRNA in disease regulation
- Retinal and Optic Conditions
- Machine Learning in Bioinformatics
- Remote-Sensing Image Classification
- Identification and Quantification in Food
- Advanced Chemical Sensor Technologies
- Pharmaceutical Quality and Counterfeiting
- Genomics and Phylogenetic Studies
- Molecular Biology Techniques and Applications
- Retinal Diseases and Treatments
- Water Quality Monitoring and Analysis
- Coral and Marine Ecosystems Studies
Universidade Nova de Lisboa
2016-2025
University of Lisbon
2008-2025
Association for Innovation and Biomedical Research on Light and Image
2016-2024
Instituto de Telecomunicações
2010-2020
Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento
2019
Instituto Politécnico de Lisboa
2015-2018
Universidade Católica Portuguesa
2012-2016
Instituto Superior Técnico
2009-2015
Zero to Three
2014
Universidade de São Paulo
2013
The human microbiome has emerged as a central research topic in biology and biomedicine. Current studies generate high-throughput omics data across different body sites, populations, life stages. Many of the challenges are similar to other studies, quantitative analyses need address heterogeneity data, specific statistical properties, remarkable variation composition individuals sites. This led broad spectrum machine learning that range from study design, processing, standardization...
A combination of laser-induced breakdown spectroscopy (LIBS) and artificial neural networks (ANNs) has been used for the identification polymer materials, including polypropylene (PP), polyvinyl chloride (PVC), polytetrafluoroethylene (PTFE), polyoxymethylene (POM), polyethylene (PE), polyamide or nylon (PA), polycarbonate (PC) poly(methyl methacrylate) (PMMA). After optimization experimental setup spectrum acquisition protocol, successful rates between 81 100% were achieved using spectral...
A rapid detection of the nonauthenticity suspect tablets is a key first step in fight against pharmaceutical counterfeiting. The chemical characterization these logical next to evaluate their impact on patient health and help authorities tracking source. Hyperspectral unmixing near-infrared (NIR) image data an emerging effective technology infer number compounds, spectral signatures, mixing fractions given tablet, with resolution few tens micrometers. In linear scenario, hyperspectral...
The rapid development of machine learning (ML) techniques has opened up the data-dense field microbiome research for novel therapeutic, diagnostic, and prognostic applications targeting a wide range disorders, which could substantially improve healthcare practices in era precision medicine. However, several challenges must be addressed to exploit benefits ML this fully. In particular, there is need establish “gold standard” protocols conducting analysis experiments interactions between...
Gliomas are highly heterogeneous tumors with generally poor prognoses. Leveraging multi-omics data and network analysis holds great promise in uncovering crucial signatures molecular relationships that elucidate glioma heterogeneity. However, the complexity of problem high dimensionality increase challenges integrating information across various biological levels. This study develops a comprehensive framework aimed at identifying potential glioma-type-specific biomarkers through innovative...
High-dimensional omics data often contain more variables than observations, which negatively impacts the performance of classical analysis methods. Dimensionality reduction is typically addressed through variable selection strategies that incorporate a penalty term into model. While effective for selecting task-specific variables, this approach may not be optimal when goal to preserve dataset structure and overall biological information multiple downstream analyses. In such cases, priori...
The diets and the trophic niche overlap between seven flatfish species were studied in a coastal nursery adjoining to Tagus estuary (Portugal). Fish sampled monthly, from March November 1999, using beach seine. Arnoglossus imperialis (Rafinesque, 1810), laterna (Walbaum, 1792) thori Kyle, 1913, fed mainly on crustaceans. of Buglossidium luteum (Risso, 1810) Dicologoglossa cuneata (Moreau, 1881) composed Bivalvia Polychaeta, while for Scophthalmus rhombus (Linnaeus, 1758) main food items...
The development of biopharmaceutical manufacturing processes presents critical constraints, with the major constraint being that living cells synthesize these molecules, presenting inherent behavior variability due to their high sensitivity small fluctuations in cultivation environment. To speed up process and control this step, it is relevant develop high-throughput situ monitoring techniques, respectively. Here, mid-infrared (MIR) spectral analysis dehydrated cell pellets near-infrared...
Abstract The understanding of glioma disease has been evolving drastically with dedicated research into the genetic and molecular profiling tumour tissue. Molecular biomarkers have gained progressive substantial importance in providing diagnostic information, leading to groundbreaking changes classification system, criteria taxonomy standardised by 2016 2021 editions World Health Organization Classification Tumours Central Nervous System’s guidelines (WHO-2016 WHO-2021, respectively). Some...
Colorectal cancer (CRC) is the third most common and second deathly worldwide. It a very heterogeneous disease that can develop via distinct pathways where metastasis primary cause of death. Therefore, it crucial to understand molecular mechanisms underlying metastasis. RNA-sequencing an essential tool used for studying transcriptional landscape. However, high-dimensionality gene expression data makes selecting novel metastatic biomarkers problematic. To distinguish early-stage CRC patients...
Abstract Bootstrap‐based methods have been applied for spectral variable selection in near (NIR) and mid‐infrared (MIR) spectroscopy applications. In this paper, an extension of those the intervals instead single variables is proposed. This approach, interval partial least square (PLS)‐Bootstrap ( i PLS‐Bootstrap), was compared against PLS‐Bootstrap method use whole region model development. These were tested on a NIR dataset obtained from at‐line monitoring industrial fermentation process,...
Learning accurate models from 'omics data is bringing many challenges due to their inherent high-dimensionality, e.g. the number of gene expression variables, and comparatively lower sample sizes, which leads ill-posed inverse problems. Furthermore, presence outliers, either experimental errors or interesting abnormal clinical cases, may severely hamper a correct classification patients identification reliable biomarkers for particular disease. We propose address this problem through an...
Understanding cellular and molecular heterogeneity in glioblastoma (GBM), the most common aggressive primary brain malignancy, is a crucial step towards development of effective therapies. Besides inter-patient variability, presence multiple cell populations within tumors calls for need to develop modeling strategies able extract signatures driving tumor evolution treatment failure. With advances single-cell RNA Sequencing (scRNA-Seq), can now be dissected at level, unveiling information...
Abstract BACKGROUND While the pharmaceutical industry keeps an eye on plasmid DNA production for new generation gene therapies, real‐time monitoring techniques bioproduction are as yet unavailable. This work shows possibility of in situ Escherichia coli cultures using a near infrared ( NIR ) fiber optic probe. RESULTS Partial least squares PLS regression models based spectra were developed predicting bioprocess critical variables such concentrations biomass, plasmid, carbon sources (glucose...