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
Publications

Publications by Nuno Fonseca

2016

Parallel Algorithms for Multirelational Data Mining: Application to Life Science Problems

Authors
Camacho, R; Barbosa, JG; Sampaio, AM; Ladeiras, J; Fonseca, NA; Costa, VS;

Publication
Resource Management for Big Data Platforms - Algorithms, Modelling, and High-Performance Computing Techniques

Abstract

2013

Boosting the Detection of Transposable Elements Using Machine Learning

Authors
Loureiro, T; Camacho, R; Vieira, J; Fonseca, NA;

Publication
Advances in Intelligent Systems and Computing

Abstract
Transposable Elements (TE) are sequences of DNA that move and transpose within a genome. TEs, as mutation agents, are quite important for their role in both genome alteration diseases and on species evolution. Several tools have been developed to discover and annotate TEs but no single one achieves good results on all different types of TEs. In this paper we evaluate the performance of several TEs detection and annotation tools and investigate if Machine Learning techniques can be used to improve their overall detection accuracy. The results of an in silico evaluation of TEs detection and annotation tools indicate that their performance can be improved by using machine learning classifiers. © Springer International Publishing Switzerland 2013.

2014

High-resolution mapping of transcriptional dynamics across tissue development reveals a stable mRNA-tRNA interface

Authors
Schmitt, BM; Rudolph, KLM; Karagianni, P; Fonseca, NA; White, RJ; Talianidis, L; Odom, DT; Marioni, JC; Kutter, C;

Publication
GENOME RESEARCH

Abstract
The genetic code is an abstraction of how mRNA codons and tRNA anticodons molecularly interact during protein synthesis; the stability and regulation of this interaction remains largely unexplored. Here, we characterized the expression of mRNA and tRNA genes quantitatively at multiple time points in two developing mouse tissues. We discovered that mRNA codon pools are highly stable over development and simply reflect the genomic background; in contrast, precise regulation of tRNA gene families is required to create the corresponding tRNA transcriptomes. The dynamic regulation of tRNA genes during development is controlled in order to generate an anticodon pool that closely corresponds to messenger RNAs. Thus, across development, the pools of mRNA codons and tRNA anticodons are invariant and highly correlated, revealing a stable molecular interaction interlocking transcription and translation.

2013

Improving the performance of Transposable Elements detection tools

Authors
Loureiro, T; Camacho, R; Vieira, J; Fonseca, NA;

Publication
J. Integrative Bioinformatics

Abstract
Transposable Elements (TE) are sequences of DNA that move and transpose within a genome. TEs, as mutation agents, are quite important for their role in both genome alteration diseases and on species evolution. Several tools have been developed to discover and annotate TEs but no single tool achieves good results on all different types of TEs. In this paper we evaluate the performance of several TEs detection and annotation tools and investigate if Machine Learning techniques can be used to improve their overall detection accuracy. The results of an in silico evaluation of TEs detection and annotation tools indicate that their performance can be improved by using machine learning constructed classifiers.

2015

Predicting malignancy from mammography findings and image-guided core biopsies

Authors
Ferreira, P; Fonseca, NA; Dutra, I; Woods, R; Burnside, E;

Publication
INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS

Abstract
The main goal of this work is to produce machine learning models that predict the outcome of a mammography from a reduced set of annotated mammography findings. In the study we used a dataset consisting of 348 consecutive breast masses that underwent image guided core biopsy performed between October 2005 and December 2007 on 328 female subjects. We applied various algorithms with parameter variation to learn from the data. The tasks were to predict mass density and to predict malignancy. The best classifier that predicts mass density is based on a support vector machine and has accuracy of 81.3%. The expert correctly annotated 70% of the mass densities. The best classifier that predicts malignancy is also based on a support vector machine and has accuracy of 85.6%, with a positive predictive value of 85%. One important contribution of this work is that our model can predict malignancy in the absence of the mass density attribute, since we can fill up this attribute using our mass density predictor.

2013

Drosophila americana as a Model Species for Comparative Studies on the Molecular Basis of Phenotypic Variation

Authors
Fonseca, NA; Morales Hojas, R; Reis, M; Rocha, H; Vieira, CP; Nolte, V; Schloetterer, C; Vieira, J;

Publication
GENOME BIOLOGY AND EVOLUTION

Abstract
Understanding the molecular basis of within and between species phenotypic variation is one of the main goals of Biology. In Drosophila, most of the work regarding this issue has been performed in D. melanogaster, but other distantly related species must also be studied to verify the generality of the findings obtained for this species. Here, we make the case for D. americana, a species of the virilis group of Drosophila that has been diverging from the model species, D. melanogaster, for approximately 40 Myr. To determine the suitability of this species for such studies, polymorphism and recombination estimates are presented for D. americana based on the largest nucleotide sequence polymorphism data set so far analyzed (more than 100 data sets) for this species. The polymorphism estimates are also compared with those obtained from the comparison of the genome assembly of two D. americana strains (H5 and W11) here reported. As an example of the general utility of these resources, we perform a preliminary study on the molecular basis of lifespan differences in D. americana. First, we show that there are lifespan differences between D. americana populations from different regions of the distribution range. Then, we perform five F2 association experiments using markers for 21 candidate genes previously identified in D. melanogaster. Significant associations are found between polymorphism at two genes (hep and Lim3) and lifespan. For the F2 association study involving the two sequenced strains (H5 and W11), we identify amino acid differences at Lim3 and Hep that could be responsible for the observed changes in lifespan. For both genes, no large gene expression differences were observed between the two strains.

  • 1
  • 20