Biology subjects

Freitas, A. A.

Publications and source records attributed to Freitas, A. A..

4 recordsLinked to original sources

bioRxiv2024

Predicting Mouse Lifespan-Extending Chemical Compounds with Machine Learning

Pharmacological interventions targeting the biological processes of ageing hold significant potential to extend healthspan and promote longevity. This, to our knowledge, is the first study that uses Machine Learning models trained specifically on mouse lifespan data (from DrugAge) to predict lifespan-extending compounds. The use of mammalian data significantly elevates translational relevance compared to previously available models trained predominately on C. elegans data. Our most successful Random Forest classifiers were trained on direct drug-target annotations, including Gene Ontology, UniProt Keywords, pathways (KEGG, Reactome, Wiki) and protein domains (InterPro), whereas models trained on gene expression (LINCS) and chemical substructures (PubChem) underperformed. Models trained on male datasets performed better than those trained on mixed-sex and female datasets, with the latter suffering from severe class imbalance due to much fewer positive-class instances. Notably, features related to G-protein coupled receptors, especially receptors for neurotransmitters, metabolic hormones and sex hormones, were identified as strong predictors of lifespan extension. We used ensemble classifiers comprised of top models to screen compounds from DrugBank, highlighting novel candidates for longevity studies. Major clusters of compounds with the highest predicted longevity-promoting effects target IGF1 and insulin receptors, beta adrenergic receptors, carbonic anhydrases, dopamine and serotonin receptors, voltage-gated potassium and calcium channels, sodium-dependent dopamine, serotonin and noradrenalin transporters, muscarinic acetylcholine receptors and adenosine receptors. We tested 22 predicted compounds in C. elegans and found that 6 of them significantly extended median lifespan: dihydroergotamine, mianserin, bromocriptine, voxtalisib, bms-754807 and solifenacine. We have also created a public web server with our top performing classifier ensembles: https://www.cs.kent.ac.uk/projects/lodprime/ Our study not only provides an important contribution to the longevity pharmacology field but also informs research on the fundamental mechanisms of ageing.

bioinformatics↗

bioRxiv2022

Predicting lifespan-extending chemical compounds with machine learning and biologically interpretable features

Recently, there has been a growing interest in the development of pharmacological interventions targeting ageing, as well as on the use of machine learning for analysing ageing-related data. In this work we use machine learning methods to analyse data from DrugAge, a database of chemical compounds (including drugs) modulating lifespan in model organisms. To this end, we created four datasets for predicting whether or not a compound extends the lifespan of C. elegans (the most frequent model organism in DrugAge), using four different types of predictive biological features, based on compound-protein interactions, interactions between compounds and proteins encoded by ageing-related genes, and two types of terms annotated for proteins targeted by the compounds, namely Gene Ontology (GO) terms and physiology terms from the WormBases Phenotype Ontology. To analyse these datasets we used a combination of feature selection methods in a data pre-processing phase and the well-established random forest algorithm for learning predictive models from the selected features. The two best models were learned using GO terms and protein interactors as features, with predictive accuracies of about 82% and 80%, respectively. In addition, we interpreted the most important features in those two best models in light of the biology of ageing, and we also predicted the most promising novel compounds for extending lifespan from a list of previously unlabelled compounds.

bioinformatics↗

bioRxiv2019

Ageing Transcriptome Meta-Analysis Reveals Similarities Between Key Mammalian Tissues

1Understanding the expression changes that come with age is an important step in understanding the ageing process as a whole. By combining such transcriptomic data with other sources of information, for instance protein-protein interaction (PPI) data, it is possible to make inferences about the functional changes that occur with age. To address this, we conducted a meta-analysis on 127 publicly available microarray and RNA-Seq datasets from mice, rats and humans, to identify genes that are commonly differentially expressed with age in mammals. We also conducted analyses on subsets of these datasets, to produce transcriptomic signatures for brain, heart and muscle tissues, all of which are important tissues in the pathophysiology of ageing. This approach identified the transcriptomic signatures of the ageing system, as well as brain, heart and muscle tissues. We then applied enrichment analysis and machine learning to functionally describe those signatures. This revealed a typical ageing signature including the overexpression of immune and stress response genes and the underexpression of metabolic and developmental genes. Further analysis of the ageing expression signatures revealed that genes differentially expressed with age tend to be broadly expressed across tissues, rather than be tissue-specific, and that the ageing expression signatures (particularly the overexpressed signatures) of the whole system, brain and muscle tend to include genes that are central in PPI networks. We also show that genes underexpressed in the brain are highly central in a co-expression map, suggesting that underexpression of these genes may play a part in cognitive ageing. In sum, we show numerous functional similarities between the ageing transcriptomes of these important tissues, a broad non-specific expression pattern in genes differentially expressed with age, along with altered network properties of these genes in both a PPI and co-expression network.

bioinformatics↗

bioRxiv2019

PICKER-HG: a web server using random forests for classifying human genes into categories

MotivationOne of the main challenges faced by biologists is how to extract valuable knowledge from the data produced by high-throughput genomic experiments. Although machine learning can be used for this, in general, machine learning tools on the web were not designed for biologist users. They require users to create suitable biological datasets and often produce results that are hard to interpret.\n\nObjectiveOur aim is to develop a freely available web server, named PerformIng Classification and Knowledge Extraction via Rules using random forests on Human Genes (PICKER-HG), aimed at biologists looking for a straightforward application of a powerful machine learning technique (random forests) to their data.\n\nResultsWe have developed the first web server that, as far as we know, dynamically constructs a classification dataset, given a list of human genes with annotations entered by the user, and outputs classification rules extracted of a Random Forest model. The web server can also classify a list of genes whose class labels are unknown, potentially assisting biologists investigating the association between class labels of interest and human genes.\n\nAvailabilityhttp://machine-learning-genomics.com/

bioinformatics↗