Biology subjects

Couto, F. M.

Publications and source records attributed to Couto, F. M..

6 recordsLinked to original sources

bioRxiv2024

Predicting non-coding RNA function using Artificial Intelligence

Non-coding RNAs (ncRNAs) represent the majority of human gene products, and are involved in various important biological processes, being considered relevant disease biomarkers and therapeutic agents. However, information about these biomolecules remains sparsely distributed, mostly in the form of scientific research articles. It is then of pivotal importance to aggregate and summarize the existing information. Natural Language Processing (NLP) methods applied to text mining can be used to generate collections of annotated sentences expressing relations between entities, called relational corpora. In this work we developed a text mining pipeline to generate a ncRNA-phenotype relational corpus (ncoRP) using Distant Supervision Relation Extraction (DSRE), comprising 21,608 annotated articles, 2,835 unique ncRNAs, 1,118 unique phenotypes and 35,295 unique relations, with a precision of 0.761 and F1-score of 0.593, calculated through human validation. DSRE methods require a set of pre-documented relations to function, as such, a high-fidelity ncRNA-phenotype relation dataset, consisting of 214,300 unique relations, was created by the aggregation of five comprehensive ncRNA-disease functional annotation databases. Then, both ncoRP and the relation dataset represent important contributions towards solving the problem with the sparseness of information about ncRNAs. Large Language Models (LLMs) are an emergent type of language model, showing great capabilities in general task-solving through text generation, without the requirement of fine-tuning with large datasets. In this work, a LLM RE methodology is proposed and evaluated, achieving an F1-score of 0.978 by combining the RE task with a preceding sentence filtering task and applying prompting principles such as in-context learning and Chain-of-Thought self-explanation.

bioinformatics↗

bioRxiv2021

Named Entity Recognition and Linking: a Portuguese and Spanish Oncological Parallel Corpus

Biomedical literature is the main mean of communication for researchers to share their findings. Since biomedical literature is composed of a large collection of text expressed in natural language, the usage of text mining tools to extract information from those texts automatically is of utmost importance. The problem is that the majority of the state-of-the-art tools were not developed to deal with other languages besides English, which in biomedical literature is even more critical since a significant part of health-related texts is written in the authors native language. To address this issue, this work presents a deep learning NERL (Named Entity Recognition and Linking) system and a parallel corpus for the Spanish and Portuguese languages focused on the oncological domain. Both the system and the corpus are available at https://github.com/lasigeBioTM/ICERL_system-ICR_Corpus.

bioinformatics↗

bioRxiv2020

Information Retrieval using Machine Learning for Biomarker Curation in the Exposome-Explorer

In 2016, the International Agency for Research on Cancer, part of the World Health Organization, released the Exposome-Explorer, the first database dedicated to biomarkers of exposure for environmental risk factors for diseases. The database contents resulted from a manual literature search that yielded over 8500 citations, but only a small fraction of these publications were used in the final database. Manually curating a database is time-consuming and requires domain expertise to gather relevant data scattered throughout millions of articles. This work proposes a supervised machine learning approach to assist the previous manual literature retrieval process. The manually retrieved corpus of scientific publications used in the Exposome-Explorer was used as training and testing sets for the machine learning models (classifiers). Several parameters and algorithms were evaluated to predict an articles relevance based on different datasets made of titles, abstracts and metadata. The top performance classifier was built with the Logistic Regression algorithm using the title and abstract set, achieving an F2-score of 70.1%. Furthermore, from 705 articles classified as relevant, we extracted 545 biomarkers, including 460 new candidate entries to the Exposome-Explorer database. Our methodology reduced the number of articles to be manually screened by the database curators by nearly 90%, while only misclassifying 22.1% of the relevant articles. We expect that this methodology can also be applied to similar biomarkers datasets or be adapted to assist the manual curation process of similar chemical or disease databases.

bioinformatics↗

bioRxiv2018

Identifying disease genes using machine learning and gene functional similarities, assessed through Gene Ontology

Identifying disease genes from a vast amount of genetic data is one of the most challenging tasks in the post-genomic era. Also, complex diseases present highly heterogeneous genotype, which difficult biological marker identification. Machine learning methods are widely used to identify these markers, but their performance is highly dependent upon the size and quality of available data.\n\nIn this study, we demonstrated that machine learning classifiers trained on gene functional similarities, using Gene Ontology (GO), can improve the identification of genes involved in complex diseases. For this purpose, we developed a supervised machine learning methodology to predict complex disease genes. The proposed pipeline was assessed using Autism Spectrum Disorder (ASD) candidate genes. A quantitative measure of gene functional similarities was obtained by employing different semantic similarity measures. To infer the hidden functional similarities between ASD genes, various types of machine learning classifiers were built on quantitative semantic similarity matrices of ASD and non-ASD genes. The classifiers trained and tested on ASD and non-ASD gene functional similarities outperformed previously reported ASD classifiers. For example, a Random Forest (RF) classifier achieved an AUC of 0. 80 for predicting new ASD genes, which was higher than the reported classifier (0.73). Additionally, this classifier was able to predict 73 novel ASD candidate genes that were were enriched for core ASD phenotypes, such as autism and obsessive-compulsive behavior. In addition, predicted genes were also enriched for ASD co-occurring conditions, including Attention Deficit Hyperactivity Disorder (ADHD).\n\nWe also developed a KNIME workflow with the proposed methodology which allows users to configure and execute it without requiring machine learning and programming skills. Machine learning is an effective and reliable technique to decipher ASD mechanism by identifying novel disease genes, but this study further demonstrated that their performance can be improved by incorporating a quantitative measure of gene functional similarities. Source code and the workflow of the proposed methodology are available at https://github.com/Muh-Asif/ASD-genes-prediction.

bioinformatics↗

bioRxiv2018

An integrative systems medicine approach to delineate complex genotype-phenotype associations in Autism Spectrum Disorder

The complex genetic architecture of Autism Spectrum Disorder (ASD) and its heterogeneous phenotype make molecular diagnosis and patient prognosis challenging tasks. To establish more precise genotype-phenotype correlations in ASD, we developed a novel machine learning integrative approach, which seeks to delineate associations between patients clinical profiles and disrupted biological processes inferred from their Copy Number Variants (CNVs) that span brain genes. Clustering analysis of relevant clinical measures from 2446 ASD cases in the Autism Genome Project identified two distinct phenotypic subgroups. Patients in these clusters differed significantly in ADOS-defined severity, adaptive behaviour profiles, intellectual ability and verbal status, the latter contributing the most for cluster stability and cohesion. Functional enrichment analysis of brain genes disrupted by CNVs in these ASD cases identified 15 statistically significant biological processes, including cell adhesion, neural development, cognition and polyubiquitination, in line with previous ASD findings. A Naive Bayes classifier, generated to predict the ASD phenotypic clusters from disrupted biological processes, achieved predictions with a high Precision (0.82) but low recall (0.39), for a subset of patients with higher biological Information Content scores. This study shows that milder and more severe clinical presentations can have distinct underlying biological mechanisms. It further highlights how machine learning approaches can reduce clinical heterogeneity using multidimensional clinical measures, and establish genotype-phenotype correlations in ASD. However, predictions are strongly dependent on patients information content. Findings are therefore a first step towards the translation of genetic information into clinically useful applications, but emphasize the need for larger datasets with very complete clinical and biological information.

systems biology↗

bioRxiv2018

BO-LSTM: Classifying relations via long short-term memory networks along biomedical ontologies

Recent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks. However, these techniques rarely take advantage of existing domain-specific resources, such as ontologies. In Life and Health Sciences there is a vast and valuable set of such resources publicly available, which are continuously being updated. Biomedical ontologies are nowadays a mainstream approach to formalize existing knowledge about entities, such as genes, chemicals, phenotypes, and disorders. These resources contain supplementary information that may not be yet encoded in training data, particularly in domains with limited labeled data.\n\nWe propose a new model, BO-LSTM, that takes advantage of domain-specific ontologies, by representing each entity as the sequence of its ancestors in the ontology. We implemented BO-LSTM as a recurrent neural network with long short-term memory units and using an open biomedical ontology, which in our case-study was Chemical Entities of Biological Interest (ChEBI). We assessed the performance of BO-LSTM on detecting and classifying drug-drug interactions in a publicly available corpus from an international challenge, composed of 792 drug descriptions and 233 scientific abstracts. By using the domain-specific ontology in addition to word embeddings and WordNet, BO-LSTM improved both the F1-score of the detection and classification of drug-drug interactions, particularly in a document set with a limited number of annotations. Our findings demonstrate that besides the high performance of current deep learning techniques, domain-specific ontologies can still be useful to mitigate the lack of labeled data.\n\nAuthor summaryA high quantity of biomedical information is only available in documents such as scientific articles and patents. Due to the rate at which new documents are produced, we need automatic methods to extract useful information from them. Text mining is a subfield of information retrieval which aims at extracting relevant information from text. Scientific literature is a challenge to text mining because of the complexity and specificity of the topics approached. In recent years, deep learning has obtained promising results in various text mining tasks by exploring large datasets. On the other hand, ontologies provide a detailed and sound representation of a domain and have been developed to diverse biomedical domains. We propose a model that combines deep learning algorithms with biomedical ontologies to identify relations between concepts in text. We demonstrate the potential of this model to extract drug-drug interactions from abstracts and drug descriptions. This model can be applied to other biomedical domains using an annotated corpus of documents and an ontology related to that domain to train a new classifier.

bioinformatics↗