Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Interest
Topics
Details

Details

  • Name

    Rui Camacho
  • Cluster

    Computer Science
  • Role

    Senior Researcher
  • Since

    01st January 2011
004
Publications

2020

Using autoencoders as a weight initialization method on deep neural networks for disease detection

Authors
Ferreira, MF; Camacho, R; Teixeira, LF;

Publication
BMC Medical Informatics and Decision Making

Abstract

2020

Gastric Microbiome Diversities in Gastric Cancer Patients from Europe and Asia Mimic the Human Population Structure and Are Partly Driven by Microbiome Quantitative Trait Loci

Authors
Cavadas, B; Camacho, R; Ferreira, JC; Ferreira, RM; Figueiredo, C; Brazma, A; Fonseca, NA; Pereira, L;

Publication
MICROORGANISMS

Abstract
The human gastrointestinal tract harbors approximately 100 trillion microorganisms with different microbial compositions across geographic locations. In this work, we used RNASeq data from stomach samples of non-disease (164 individuals from European ancestry) and gastric cancer patients (137 from Europe and Asia) from public databases. Although these data were intended to characterize the human expression profiles, they allowed for a reliable inference of the microbiome composition, as confirmed from measures such as the genus coverage, richness and evenness. The microbiome diversity (weighted UniFrac distances) in gastric cancer mimics host diversity across the world, with European gastric microbiome profiles clustering together, distinct from Asian ones. Despite the confirmed loss of microbiome diversity from a healthy status to a cancer status, the structured profile was still recognized in the disease condition. In concordance with the parallel host-bacteria population structure, we found 16 human loci (non-synonymous variants) in the European-descendent cohorts that were significantly associated with specific genera abundance. These microbiome quantitative trait loci display heterogeneity between population groups, being mainly linked to the immune system or cellular features that may play a role in enabling microbe colonization and inflammation.

2019

EvoPPI: A Web Application to Compare Protein-Protein Interactions (PPIs) from Different Databases and Species

Authors
Vazquez, N; Rocha, S; Lopez Fernandez, H; Torres, A; Camacho, R; Fdez Riverola, F; Vieira, J; Vieira, CP; Reboiro Jato, M;

Publication
Practical Applications of Computational Biology and Bioinformatics, 12th International Conference, PACBB 2018, Toledo, Spain, 20-22 May, 2018.

Abstract
Biological processes are mediated by protein-protein interactions (PPI) that have been studied using different methodologies, and organized as centralized repositories - PPI databases. The data stored in the different PPI databases only overlaps partially. Moreover, some of the repositories are dedicated to a species or subset of species, not all have the same functionalities, or store data in the same format, making comparisons between different databases difficult to perform. Therefore, here we present EvoPPI (http://evoppi.i3s.up.pt), an open source web application tool that allows users to compare the protein interactions reported in two different interactomes. When interactomes belong to different species, a versatile BLAST search approach is used to identify orthologous/paralogous genes, which to our knowledge is a unique feature of EvoPPI. © Springer Nature Switzerland AG 2019.

2019

EvoPPI 1.0: a Web Platform for Within- and Between-Species Multiple Interactome Comparisons and Application to Nine PolyQ Proteins Determining Neurodegenerative Diseases

Authors
Vazquez, N; Rocha, S; Lopez Fernandez, H; Torres, A; Camacho, R; Fdez Riverola, F; Vieira, J; Vieira, CP; Reboiro Jato, M;

Publication
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES

Abstract
Protein-protein interaction (PPI) data is essential to elucidate the complex molecular relationships in living systems, and thus understand the biological functions at cellular and systems levels. The complete map of PPIs that can occur in a living organism is called the interactome. For animals, PPI data is stored in multiple databases (e.g., BioGRID, CCSB, DroID, FlyBase, HIPPIE, HitPredict, HomoMINT, INstruct, Interactome3D, mentha, MINT, and PINA2) with different formats. This makes PPI comparisons difficult to perform, especially between species, since orthologous proteins may have different names. Moreover, there is only a partial overlap between databases, even when considering a single species. The EvoPPI (http://evoppi.i3s.up.pt) web application presented in this paper allows comparison of data from the different databases at the species level, or between species using a BLAST approach. We show its usefulness by performing a comparative study of the interactome of the nine polyglutamine (polyQ) disease proteins, namely androgen receptor (AR), atrophin-1 (ATN1), ataxin 1 (ATXN1), ataxin 2 (ATXN2), ataxin 3 (ATXN3), ataxin 7 (ATXN7), calcium voltage-gated channel subunit alpha1 A (CACNA1A), Huntingtin (HTT), and TATA-binding protein (TBP). Here we show that none of the human interactors of these proteins is common to all nine interactomes. Only 15 proteins are common to at least 4 of these polyQ disease proteins, and 40% of these are involved in ubiquitin protein ligase-binding function. The results obtained in this study suggest that polyQ disease proteins are involved in different functional networks. Comparisons with Mus musculus PPIs are also made for AR and TBP, using EvoPPI BLAST search approach (a unique feature of EvoPPI), with the goal of understanding why there is a significant excess of common interactors for these proteins in humans.

2019

Empowering Distributed Analysis Across Federated Cohort Data Repositories Adhering to FAIR Principles

Authors
Rocha, A; Ornelas, JP; Lopes, JC; Camacho, R;

Publication
ERCIM News

Abstract

Supervised
thesis

2019

A Toolbox for Genomic Studies

Author
Carlos Miguel da Silva Pereira

Institution
UP-FEUP

2019

Framework for genomic based cancer studies using Machine Learning algorithms

Author
João Alexandre Gonçalinho Loureiro

Institution
UP-FEUP

2019

Deep Learning for identification and quantification of oncocytic cells in microscopic images

Author
Luís Telmo Soares Costa

Institution
UP-FEUP

2019

Hybrid coding taxonomy for clinical search harmonization in Safe Havens

Author
Michael André Pinto Domingues

Institution
UP-FEUP

2019

sistema de apoio à escolha de algoritmos para problemas de optimização

Author
Pedro Manuel Correia de Abreu

Institution
UP-FEUP