Assistant Professor - Department of Computer Science, Faculty of Sciences University of Porto
2019 - presentParticipates in the 1st cycle (L:BIOINF L:IACD ), 2nd cycle (M:CC, M:IERSI and M:BBC) and 3rd cycle MAPi.
pgferreira@fc.up.pt
Phone
+351 220402959
Location
Porto, Portugal
About me
Education and professional summary.
About
Pedro Ferreira is an Assistant Professor with Habilitation and Tenure at the Department of Computer Science at FCUP and a Senior Researcher at the Artificial Intelligence and Decision Support Lab at INESCTEC. He is the Director of the BSc in Bioinformatics, Sub-Director of the BSc in Artificial Intelligence and Data Science, and Sub-Director of the MSc in Bioinformatics and Computational Biology. His research combines artificial intelligence, machine learning, and bioinformatics to advance genomic data science and precision medicine. He has contributed to major international consortia such as ENCODE, GTEx, and ICGC-CLL, and published in leading journals including Nature, Science, Nature Communications or Machine Learning.
- Name : Pedro G. Ferreira
- Email : pgferreira@fc.up.pt
- Nationality : Portugal
- Phone : +351220402959
- Position : Assistant Professor
- Affiliation : Department of Computer Science, Faculty of Sciences, University of Porto
- Work Address : FC6, Rua do Campo Alegre, 4169-007 Porto
- Researcher : INESCTEC
My Expericence
Senior Researcher - INESC-TEC
2020 - presentMember of Artificial Intelligence and Decision Support Laboratory.
Associate Researcher - Ipatimup/i3s
2015 - 2019Position funded by a FCT Investigator Starting Grant (overall success rate 15.1%).
Senior Bioinformatician - CBR Genomics
2014 - 2015Genomics-as-a-Service company for personalized medicine.
Training
Habilitation in Computer Science - Faculty of Sciences University of Porto
2022Advanced Computing Training - University of Texas at Austin
2018Visiting Researcher at Texas Advanced Computing Center & Dell Medical School. Fellowship from UTAustin|Portugal.
Post-doctoral Fellow - University of Geneva, School of Medicine
2012 - 2014Supervision: E. Dermitzakis.
Post-doctoral Fellow - Centre for Genomic Regulation
2018 - 2012Supervision: R. Guigó. Supported by a Postdoctoral fellowship from FCT Portugal (2008-2010).
PhD in Artificial Intelligence - University of Minho
2003 - 2007Thesis: Sequence Pattern Mining in Biochemical Data. Supervision: P. Azevedo. Supported by a PhD fellowship from FCT Portugal.
Bachelor Degree (5 Years) - University of Minho
1997 - 2002Systems and Informatics Engineering.
Publications
Some selected papers published in the last years and representative of my main research lines.
GenMed'25
The molecular impact of cigarette smoking resembles aging across tissues
Jose M. Ramirez*, Rogério Ribeiro*, Oleksandra Soldatkina, Athos Moraes, Raquel García-Pérez, Winona Oliveros, Pedro G Ferreira#, Marta Melé#
Genome Medicine
2025
We use data from the Genotype-Tissue Expression Project (GTEx) to perform a characterization of the effect of cigarette smoking across human tissues. We perform a multi-tissue analysis across 46 human tissues. Our multi-omics characterization includes analysis of gene expression, alternative splicing, DNA methylation, and histological alterations. We further analyze ex-smoker samples to assess the reversibility of these molecular alterations upon smoking cessation.
GYOSA'25
Exploiting Trusted Execution Environments and Distributed Computation for Genomic Association Tests
Cláudia V Brito, Pedro G Ferreira, João T Paulo
IEEE Journal of Biomedical and Health Informatics
2025
We introduce Gyosa, a secure and privacy-preserving distributed genomic analysis solution. By leveraging trusted execution environments (TEEs), Gyosa allows users to confidentially delegate their GWAS analysis to untrusted infrastructures. Gyosa implements a computation partitioning scheme that reduces the computation done inside the TEEs while safeguarding the users' genomic data privacy.
ML'24
Integration of multi-modal datasets to estimate human aging
Rogério Ribeiro, Athos Moraes, Marta Moreno, Pedro G Ferreira
Machine Learning
2024
Integration of multi-modal datasets is a powerful approach for the analysis of complex biological systems, with the potential to uncover novel aging biomarkers. In this study, we leveraged publicly available epigenomic, transcriptomic and telomere length data along with histological images from the Genotype-Tissue Expression project to build tissue-specific regression models for age prediction.
IE'23
Privacy-Preserving Machine Learning on Apache Spark
Cláudia V Brito, Pedro G Ferreira, Bernardo L Portela, Rui C Oliveira, João T Paulo
IEEE Access
2023
This paper explores security/performance trade-offs for the distributed Apache Spark framework and its ML library. Concretely, we build upon a key insight: in specific deployment settings, one can reveal carefully chosen non-sensitive operations (e.g. statistical calculations). This allows us to considerably improve the performance of privacy-preserving solutions without exposing the protocol to pervasive ML attacks.
BMC'22
Scalable transcriptomics analysis with Dask: applications in data science and machine learning
Moreno, M; Vilaça, R; Ferreira, PGC;
BMC Bioinformatics
2022
Background: Gene expression studies are an important tool in biological and bio- medical research. The signal carried in expression profiles helps derive signatures for the prediction, diagnosis and prognosis of different diseases. Data science and specifi- cally machine learning have many applications in gene expression analysis. However, as the dimensionality of genomics datasets grows, scalable solutions become necessary.
Methods: Inthispaperwereviewthemainstepsandbottlenecksinmachinelearning pipelines, as well as the main concepts behind scalable data science including those of concurrent and parallel programming. We discuss the benefits of the Dask framework and how it can be integrated with the Python scientific environment to perform data analysis in computational biology and bioinformatics.
Results: This review illustrates the role of Dask for boosting data science applications in different case studies. Detailed documentation and code on these procedures is made available at https://github.com/martaccmoreno/gexp-ml-dask.
Conclusion: By showing when and how Dask can be used in transcriptomics analysis, this review will serve as an entry point to help genomic data scientists develop more scalable data analysis procedures.
Keywords: Machine learning, Scalable data science, Gene expression, Transcriptomics, Data analysis
BI'20
Deep learning for drug response prediction in cancer
Baptista, D; Ferreira, PG; Rocha, M;
Briefings in Bioinformatics
2020
Predicting the sensitivity of tumors to specific anti-cancer treatments is a challenge of paramount importance for precision medicine. Machine learning(ML) algorithms can be trained on high-throughput screening data to develop models that are able to predict the response of cancer cell lines and patients to novel drugs or drug combinations. Deep learning (DL) refers to a distinct class of ML algorithms that have achieved top-level performance in a variety of fields, including drug discovery. These types of models have unique characteristics that may make them more suitable for the complex task of modeling drug response based on both biological and chemical data, but the application of DL to drug response prediction has been unexplored until very recently. The few studies that have been published have shown promising results, and the use of DL for drug response prediction is beginning to attract greater interest from researchers in the field. In this article, we critically review recently published studies that have employed DL methods to predict drug response in cancer cell lines. We also provide a brief description of DL and the main types of architectures that have been used in these studies. Additionally, we present a selection of publicly available drug screening data resources that can be used to develop drug response prediction models. Finally, we also address the limitations of these approaches and provide a discussion on possible paths for further improvement.
FG'20
Gender Differential Transcriptome in Gastric and Thyroid Cancers
A Sousa, M Ferreira, C OliveiraC, PG FerreiraC
Frontiers in Genetics 11, 808
2020
Cancer has an important and considerable gender differential susceptibility confirmed by several epidemiological studies. Gastric (GC) and thyroid cancer (TC) are examples of malignancies with a higher incidence in males and females, respectively. Beyond environmental predisposing factors, it is expected that gender-specific gene deregulation contributes to this differential incidence. We performed a detailed characterization of the transcriptomic differences between genders in normal and tumor tissues from stomach and thyroid using Genotype-Tissue Expression (GTEx) and The Cancer Genome Atlas (TCGA) data. We found hundreds of sex-biased genes (SBGs). Most of the SBGs shared by normal and tumor belong to sexual chromosomes, while the normal and tumor-specific tend to be found in the autosomes. Expression of several cancer-associated genes is also found to differ between sexes in both types of tissue. Thousands of differentially expressed genes (DEGs) between paired tumor-normal tissues were identified in GC and TC. For both cancers, in the most susceptible gender, the DEGs were mostly under-expressed in the tumor tissue, with an enrichment for tumor-suppressor genes (TSGs). Moreover, we found gene networks preferentially associated to males in GC and to females in TC and correlated with cancer histological subtypes. Our results shed light on the molecular differences and commonalities between genders and provide novel insights in the differential risk underlying these cancers.
NC'18
The effects of death and post-mortem cold ischemia on human tissue transcriptomes
PG FerreiraC, M Muñoz-Aguirre, F Reverter, CPS Godinho, A Sousa, ...
Nature communications 9 (1), 1-15
2018
Post-mortem tissues samples are a key resource for investigating patterns of gene expression. However, the processes triggered by death and the post-mortem interval (PMI) can significantly alter physiologically normal RNA levels. We investigate the impact of PMI on gene expression using data from multiple tissues of post-mortem donors obtained from the GTEx project. We find that many genes change expression over relatively short PMIs in a tissue-specific manner, but this potentially confounding effect in a biological analysis can be minimized by taking into account appropriate covariates. By comparing ante-and postmortem blood samples, we identify the cascade of transcriptional events triggered by death of the organism. These events do not appear to simply reflect stochastic variation resulting from mRNA degradation, but active and ongoing regulation of transcription. Finally, we develop a model to predict the time since death from the analysis of the transcriptome of a few readily accessible tissues.
SC'16
Sequence variation between 462 human individuals fine-tunes functional sites of RNA processing
PG Ferreira, M Oti, M Barann, T Wieland, S Ezquina, MR Friedländer, ...
Scientific Reports 6, 32406
2016
Recent advances in the cost-efficiency of sequencing technologies enabled the combined DNA- and RNA-sequencing of human individuals at the population-scale, making genome-wide investigations of the inter-individual genetic impact on gene expression viable. Employing mRNA-sequencing data from the Geuvadis Project and genome sequencing data from the 1000 Genomes Project we show that the computational analysis of DNA sequences around splice sites and poly-A signals is able to explain several observations in the phenotype data. In contrast to widespread assessments of statistically significant associations between DNA polymorphisms and quantitative traits, we developed a computational tool to pinpoint the molecular mechanisms by which genetic markers drive variation in RNA-processing, cataloguing and classifying alleles that change the affinity of core RNA elements to their recognizing factors. The in silico models we employ further suggest RNA editing can moonlight as a splicing-modulator, albeit less frequently than genomic sequence diversity. Beyond existing annotations, we demonstrate that the ultra-high resolution of RNA-Seq combined from 462 individuals also provides evidence for thousands of bona fide novel elements of RNA processing—alternative splice sites, introns and cleavage sites—which are often rare and lowly expressed but in other characteristics similar to their annotated counterparts.
SC'15'A
The human transcriptome across tissues and individuals
M Melé*, PG Ferreira*, F Reverter*, DS DeLuca, J Monlong, M Sammeth, ...
* equal contribution
Science 348 (6235), 660-665
2015
Transcriptional regulation and posttranscriptional processing underlie many cellular and organismal phenotypes. We used RNA sequence data generated by Genotype-Tissue Expression (GTEx) project to investigate the patterns of transcriptome variation across individuals and tissues. Tissues exhibit characteristic transcriptional signatures that show stability in postmortem samples. These signatures are dominated by a relatively small number of genes—which is most clearly seen in blood—though few are exclusive to a particular tissue and vary more across tissues than individuals. Genes exhibiting high interindividual expression variation include disease candidates associated with sex, ethnicity, and age. Primary transcription is the major driver of cellular specificity, with splicing playing mostly a complementary role; except for the brain, which exhibits a more divergent splicing program. Variation in splicing, despite its stochasticity, may play in contrast a comparatively greater role in defining individual phenotypes.
SC'15'B
The Genotype-Tissue Expression (GTEx) pilot analysis: Multitissue gene regulation in humans
GTEx Consortium (including PG Ferreira)
Science 348 (6235), 648-660
2015
Understanding the functional consequences of genetic variation, and how it affects complex human disease and quantitative traits, remains a critical challenge for biomedicine. We present an analysis of RNA sequencing data from 1641 samples across 43 tissues from 175 individuals, generated as part of the pilot phase of the Genotype-Tissue Expression (GTEx) project. We describe the landscape of gene expression across tissues, catalog thousands of tissue-specific and shared regulatory expression quantitative trait loci (eQTL) variants, describe complex network relationships, and identify signals from genome-wide association studies explained by eQTLs. These findings provide a systematic understanding of the cellular and biological consequences of human genetic variation and of the heterogeneity of such effects among a diverse set of human tissues.
SC'20
The GTEx Consortium atlas of genetic regulatory effects across human tissues
GTEx Consortium (including PG Ferreira)
Science 369 (6509), 1318-1330
2020
The Genotype-Tissue Expression (GTEx) project was established to characterize genetic effects on the transcriptome across human tissues and to link these regulatory mechanisms to trait and disease associations. Here, we present analyses of the version 8 data, examining 15,201 RNA-sequencing samples from 49 tissues of 838 postmortem donors. We comprehensively characterize genetic associations for gene expression and splicing in cis and trans, showing that regulatory associations are found for almost all genes, and describe the underlying molecular mechanisms and their contribution to allelic heterogeneity and pleiotropy of complex traits. Leveraging the large diversity of tissues, we provide insights into the tissue specificity of genetic effects and show that cell type composition is a key factor in understanding gene regulatory mechanisms in human tissues.
Teaching
In the last years I have been involved in teaching in the following courses either as chair or as a teacher for practical classes.
Supervisions
Concluded PhD supervisions.
Study of control of protein abundance using multi-omics data from cancer samples |
A framework for predicting drug sensitivity and synergy in cancer cells using deep learning. |
Transcriptomics-based prediction of human phenotypes using scalable and secure machine learning approaches |
Towards a Privacy-Preserving Distributed Machine Learning. |
Ongoing Supervisions
Ongoing PhD supervisions.
BioPredictor: a tool to predict the outcome of molecular alterations. |
Integration of multi-modal genomics datasets with expert data: a patient centered approach to improve diagnosis and prognosis. |
Deepening the understanding of Alzheimer’s disease risk and progression: a multimodal approach. |
Implementation of Human-Assistant Based an Artificial Intelligence for Critical Networks Infrastructures. |
Multimodal Deep Learning for Biomarker Discovery in Early-Onset Cancer: A Comprehensive Analysis Across Age Cohorts and Tissue Types. |
Teste Genético Pré-Implantação em Portugal - impacto, inovação e expansão no âmbito da Medicina Reprodutiva. |
My Blog
The Last posts about Data Analysis and Machine Learning.
July, 2025 #ML
Researchers demonstrate that tobacco mimics and accelerates ageing in human tissues.
A team of researchers from INESC TEC, the Faculty of Sciences of the University of Porto, and the Barcelona Supercomputing Centre analysed 46 types of tissues from over 700 individuals. The team concluded that smoking impacts tissue architecture and can cause molecular changes not only in organs directly associated with smoke inhalation, e.g., lungs, but also in tissues from other organs, including the pancreas, thyroid, oesophagus, and specific regions of the brain. In many cases, the effects of smoking significantly overlap with those of ageing. Check out the coverage of our recent paper in Genome Medicine in the jornal Público.
Público UPorto INESCTEC
June, 2025 #ML
Secure genetics: innovate data processing in cloud computing.
A team of researchers at INESC TEC has developed a new tool called Gyosa, capable of performing genomic studies securely in cloud computing environments without compromising data privacy. Check the coverage of one of our recent publications at the IEEE Journal of Biomedical and Health Informatics.
UPorto Coverage INESCTEC Coverage
June, 2025 #ML
Bioinformatics: at the interface of the ongoing revolutions in biology and computer science.
The University of Porto offers a pioneering course in Bioinformatics that I am proud to be the current director. Bioinformatics is a multidisciplinary field at the intersection of the ongoing revolutions in biology and computer science. Its goal is to analyze and understand biological and biomedical data, particularly at the cellular and molecular level. It involves the development and application of algorithms and computational tools, namely artificial intelligence and machine learning, to organize, analyze, and extract relevant information from large biological data sets, contributing to advances in areas such as genomics and other omics, genetics, systems biology, pathology, ecology, evolution, epidemiology, among others.
BSc in Bioinformatics
7 June, 2021 #ML
New Degree in Artificial Intelligence and Data Science at the University of Porto
Checkout the new Degree in Artificial Intelligence and Data Science at the University of Porto that will open this year with 55 places!
Read More
1 June, 2021 #ML
Check out the conference: Cutaneous Melanoma: from where to where?
I am honoured to be part of the scientific committee of the anual conference of the Portuguese League Against Cancer.
Read More
1 June, 2021 #ML
Dimensionality Reduction: PCA, MDS, t-SNE and UMAP
Dimensionality reduction with Matrix factorization and Neighbour graph based methods. An application case with R.
Read More
