Biology subjects

Dumontier, M.

Publications and source records attributed to Dumontier, M..

7 recordsLinked to original sources

bioRxiv2024

Bridging Auditory Perception and Natural Language Processing with Semantically informed Deep Neural Networks

Sound recognition is effortless for humans but poses a significant chal-lenge for artificial hearing systems. Deep neural networks (DNNs), especially convolutional neural networks (CNNs), have recently sur-passed traditional machine learning in sound classification. However, current DNNs map sounds to labels using binary categorical variables, neglecting the semantic relations between labels. Cognitive neuroscience research suggests that human listeners exploit such semantic informa-tion besides acoustic cues. Hence, our hypothesis is that incorporating semantic information improves DNNs sound recognition performance, emulating human behavior. In our approach, sound recognition is framed as a regression problem, with CNNs trained to map spec-trograms to continuous semantic representations from NLP models (Word2Vec, BERT, and CLAP text encoder). Two DNN types were trained: semDNN with continuous embeddings and catDNN with cat-egorical labels, both with a dataset extracted from a collection of 388,211 sounds enriched with semantic descriptions. Evaluations across four external datasets, confirmed the superiority of semantic labeling from semDNN compared to catDNN, preserving higher-level relations. Importantly, an analysis of human similarity ratings for natural sounds, showed that semDNN approximated human listener behavior better than catDNN, other DNNs, and NLP models. Our work contributes to understanding the role of semantics in sound recognition, bridging the gap between artificial systems and human auditory perception.

neuroscience↗

bioRxiv2019

Evaluating FAIR Maturity Through a Scalable, Automated, Community-Governed Framework

Transparent evaluations of FAIRness are increasingly required by a wide range of stakeholders, from scientists to publishers, funding agencies and policy makers. We propose a scalable, automatable framework to evaluate digital resources that encompasses measurable indicators, open source tools, and participation guidelines, which come together to accommodate domain relevant community-defined FAIR assessments. The components of the framework are: (1) Maturity Indicators - community-authored specifications that delimit a specific automatically-measurable FAIR behavior; (2) Compliance Tests - small Web apps that test digital resources against individual Maturity Indicators; and (3) the Evaluator, a Web application that registers, assembles, and applies community-relevant sets of Compliance Tests against a digital resource, and provides a detailed report about what a machine \"sees\" when it visits that resource. We discuss the technical and social considerations of FAIR assessments, and how this translates to our community-driven infrastructure. We then illustrate how the output of the Evaluator tool can serve as a roadmap to assist data stewards to incrementally and realistically improve the FAIRness of their resources.

bioinformatics↗

bioRxiv2019

A Novel Ensemble-Based Machine Learning Algorithm To Predict The Conversion From Mild Cognitive Impairment To Alzheimer's Disease Using Socio-demographic Characteristics, Clinical Information And Neuropsychological Measures

BackgroundDespite the increasing availability in brain health related data, clinically translatable methods to predict the conversion from Mild Cognitive Impairment (MCI) to Alzheimers disease (AD) are still lacking. Although MCI typically precedes AD, only a fraction of 20-40% of MCI individuals will progress to dementia within 3 years following the initial diagnosis. As currently available and emerging therapies likely have the greatest impact when provided at the earliest disease stage, the prompt identification of subjects at high risk for conversion to full AD is of great importance in the fight against this disease. In this work, we propose a highly predictive machine learning algorithm, based only on non-invasively and easily in-the-clinic collectable predictors, to identify MCI subjects at risk for conversion to full AD. MethodsThe algorithm was developed using the open dataset from the Alzheimers Disease Neuroimaging Initiative (ADNI), employing a sample of 550 MCI subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. A restricted set of information regarding sociodemographic and clinical characteristics, neuropsychological test scores was used as predictors and several different supervised machine learning algorithms were developed and ensembled in final algorithm. A site-independent stratified train/test split protocol was used to provide an estimate of the generalized performance of the algorithm. ResultsThe final algorithm demonstrated an AUROC of 0.88, sensitivity of 77.7%, and a specificity of 79.9% on excluded test data. The specificity of the algorithm was 40.2% for 100% sensitivity. DiscussionThe algorithm we developed achieved sound and high prognostic performance to predict AD conversion using easily clinically derived information that makes the algorithm easy to be translated into practice. This indicates beneficial application to improve recruitment in clinical trials and to more selectively prescribe new and newly emerging early interventions to high AD risk patients.

neuroscience↗

bioRxiv2018

Vec2SPARQL: integrating SPARQL queries and knowledge graph embeddings

Recent developments in machine learning have lead to a rise of large number of methods for extracting features from structured data. The features are represented as a vectors and may encode for some semantic aspects of data. They can be used in a machine learning models for different tasks or to compute similarities between the entities of the data. SPARQL is a query language for structured data originally developed for querying Resource Description Framework (RDF) data. It has been in use for over a decade as a standardized NoSQL query language. Many different tools have been developed to enable data sharing with SPARQL. For example, SPARQL endpoints make your data interoperable and available to the world. SPARQL queries can be executed across multiple endpoints. We have developed a Vec2SPARQL, which is a general framework for integrating structured data and their vector space representations. Vec2SPARQL allows jointly querying vector functions such as computing similarities (cosine, correlations) or classifications with machine learning models within a single SPARQL query. We demonstrate applications of our approach for biomedical and clinical use cases. Our source code is freely available at https://github.com/bio-ontology-research-group/vec2sparql and we make a Vec2SPARQL endpoint available at http://sparql.bio2vec.net/.

bioinformatics↗

bioRxiv2018

Evaluating FAIR-Compliance Through an Objective, Automated, Community-Governed Framework

With the increased adoption of the FAIR Principles, a wide range of stakeholders, from scientists to publishers, funding agencies and policy makers, are seeking ways to transparently evaluate resource FAIRness. We describe the FAIR Evaluator, a software infrastructure to register and execute tests of compliance with the recently published FAIR Metrics. The Evaluator enables digital resources to be assessed objectively and transparently. We illustrate its application to three widely used generalist repositories - Dataverse, Dryad, and Zenodo - and report their feedback. Evaluations allow communities to select relevant Metric subsets to deliver FAIRness measurements in diverse and specialized applications. Evaluations are executed in a semi-automated manner through Web Forms filled-in by a user, or through a JSON-based API. A comparison of manual vs automated evaluation reveals that automated evaluations are generally stricter, resulting in lower, though more accurate, FAIRness scores. Finally, we highlight the need for enhanced infrastructure such as standards registries, like FAIRsharing, as well as additional community involvement in domain-specific data infrastructure creation.

scientific communication and education↗

bioRxiv2017

A design framework and exemplar metrics for FAIRness

\"FAIRness\" - the degree to which a digital resource is Findable, Accessible, Interoperable, and Reusable - is aspirational, yet the means of reaching it may be defined by increased adherence to measurable indicators. We report on the production of a core set of semi-quantitative metrics having universal applicability for the evaluation of FAIRness, and a rubric within which additional metrics can be generated by the community. This effort is the output from a stakeholder-representative group, founded by a core of FAIR principles co-authors and drivers. We now seek input from the community to more broadly discuss their merit.

scientific communication and education↗

bioRxiv2017

Identifiers for the 21st century:How to design, provision, and reuse persistent identifiers to maximize utility and impact of life science data

In many disciplines, data is highly decentralized across thousands of online databases (repositories, registries, and knowledgebases). Wringing value from such databases depends on the discipline of data science and on the humble bricks and mortar that make integration possible; identifiers are a core component of this integration infrastructure. Drawing on our experience and on work by other groups, we outline ten lessons we have learned about the identifier qualities and best practices that facilitate large-scale data integration. Specifically, we propose actions that identifier practitioners (database providers) should take in the design, provision and reuse of identifiers; we also outline important considerations for those referencing identifiers in various circumstances, including by authors and data generators. While the importance and relevance of each lesson will vary by context, there is a need for increased awareness about how to avoid and manage common identifier problems, especially those related to persistence and web-accessibility/resolvability. We focus strongly on web-based identifiers in the life sciences; however, the principles are broadly relevant to other disciplines.

bioinformatics↗