Translational Challenges of Biomedical Machine Learning Solutions in Clinical and Laboratory Settings

in Bioinformatics and Biomedical Engineering (2022)

The ever increasing use of artificial intelligence (AI) methods in biomedical sciences calls for closer inter-disciplinary collaborations that transfer the domain knowledge from life scientists to ... [more ▼]

The ever increasing use of artificial intelligence (AI) methods in biomedical sciences calls for closer inter-disciplinary collaborations that transfer the domain knowledge from life scientists to computer science researchers and vice-versa. We highlight two general areas where the use of AI-based solutions designed for clinical and laboratory settings has proven problematic. These are used to demonstrate common sources of translational challenges that often stem from the differences in data interpretation between the clinical and research view, and the unmatched expectations and requirements on the result quality metrics. We outline how explicit interpretable inference reporting might be used as a guide to overcome such translational challenges. We conclude with several recommendations for safer translation of machine learning solutions into real-world settings. [less ▲]

COBREXA.jl: constraint-based reconstruction and exascale analysis

in Bioinformatics (2021)

COBREXA.jl is a Julia package for scalable, high-performance constraint-based reconstruction and analysis of very large-scale biological models. Its primary purpose is to facilitate the integration of ... [more ▼]

COBREXA.jl is a Julia package for scalable, high-performance constraint-based reconstruction and analysis of very large-scale biological models. Its primary purpose is to facilitate the integration of modern high performance computing environments with the processing and analysis of large-scale metabolic models of challenging complexity. We report the architecture of the package, and demonstrate how the design promotes analysis scalability on several use-cases with multi-organism community models.https://doi.org/10.17881/ZKCR-BT30.Supplementary data are available at Bioinformatics online. [less ▲]

PredictProtein - Predicting Protein Structure and Function for 29 Years

in Nucleic Acids Research (2021)

Since 1992 PredictProtein (https://predictprotein.org) is a one-stop online resource for protein sequence analysis with its main site hosted at the Luxembourg Centre for Systems Biomedicine (LCSB) and ... [more ▼]

Since 1992 PredictProtein (https://predictprotein.org) is a one-stop online resource for protein sequence analysis with its main site hosted at the Luxembourg Centre for Systems Biomedicine (LCSB) and queried monthly by over 3,000 users in 2020. PredictProtein was the first Internet server for protein predictions. It pioneered combining evolutionary information and machine learning. Given a protein sequence as input, the server outputs multiple sequence alignments, predictions of protein structure in 1D and 2D (secondary structure, solvent accessibility, transmembrane segments, disordered regions, protein flexibility, and disulfide bridges) and predictions of protein function (functional effects of sequence variation or point mutations, Gene Ontology (GO) terms, subcellular localization, and protein-, RNA-, and DNA binding). PredictProtein's infrastructure has moved to the LCSB increasing throughput; the use of MMseqs2 sequence search reduced runtime five-fold (apparently without lowering performance of prediction methods); user interface elements improved usability, and new prediction methods were added. PredictProtein recently included predictions from deep learning embeddings (GO and secondary structure) and a method for the prediction of proteins and residues binding DNA, RNA, or other proteins. PredictProtein.org aspires to provide reliable predictions to computational and experimental biologists alike. All scripts and methods are freely available for offline execution in high-throughput settings. [less ▲]

Supporting findability of COVID-19 research with large-scale text mining of scientific publications

Poster (2020, November 27)

When the COVID-19 pandemic hit in early 2020, a lot of research efforts were quickly redirected towards studies on SARS-CoV2 and COVID-19 disease, from the sequencing and assembly of viral genomes to the ... [more ▼]

When the COVID-19 pandemic hit in early 2020, a lot of research efforts were quickly redirected towards studies on SARS-CoV2 and COVID-19 disease, from the sequencing and assembly of viral genomes to the elaboration of robust testing methodologies and the development of treatment and vaccination strategies. At the same time, a flurry of scientific publications around SARS-CoV-2 and COVID-19 began to appear, making it increasingly difficult for researchers to stay up-to-date with latest trends and developments in this rapidly evolving field. The BioKB platform is a pipeline which, by exploiting text mining and semantic technologies, helps researchers easily access semantic content of thousands of abstracts and full text articles. The content of the articles is analysed and concepts from a range of contexts, including proteins, species, chemicals, diseases and biological processes are tagged based on existing dictionaries of controlled terms. Co-occurring concepts are classified based on their asserted relationship and the resulting subject-relation-object triples are stored in a publicly accessible human- and machine-readable knowledge base. All concepts in the BioKB dictionaries are linked to stable, persistent identifiers, either a resource accession such as an Ensembl, Uniprot or PubChem ID for genes, proteins and chemicals, or an ontology term ID for diseases, phenotypes and other ontology terms. In order to improve COVID-19 related text mining, we extended the underlying dictionaries to include many additional viral species (via NCBI Taxonomy identifiers), phenotypes from the Human Phenotype Ontology (HPO), COVID-related concepts including clinical and laboratory tests from the COVID-19 ontology, as well as additional diseases (DO) and biological processes (GO). We also added all viral proteins found in UniProt and gene entries from EntrezGene to increase the sensitivity of the text mining pipeline to viral data. To date, BioKB has indexed over 270’000 sentences from 21’935 publications relating to coronavirus infections, with publications dating from 1963 to 2021, 3’863 of which were published this year. We are currently working to further refine the text mining pipeline by training it on the extraction of increasingly complex relations such as protein-phenotype relationships. We are also regularly adding new terms to our dictionaries for areas where coverage is currently low, such as clinical and laboratory tests and procedures and novel drug treatments. [less ▲]

BioKC: a platform for quality controlled curation and annotation of systems biology models

Scientific Conference (2020, September 04)

Standardisation of biomedical knowledge into systems biology models is essential for the study of the biological function. However, biomedical knowledge curation is a laborious manual process aggravated ... [more ▼]

Standardisation of biomedical knowledge into systems biology models is essential for the study of the biological function. However, biomedical knowledge curation is a laborious manual process aggravated by the ever increasing growth of biomedical literature. High quality curation currently relies on pathway databases where outsider participation is minimal. The increasing demand of systems biology knowledge presents new challenges regarding curation, calling for new collaborative functionalities to improve quality control of the review process. These features are missing in the current systems biology environment, whose tools are not well suited for an open community-based model curation workflow. On one hand, diagram editors such as CellDesigner or Newt provide limited annotation features. On the other hand, most popular text annotations tools are not aimed for biomedical text annotation or model curation. Detaching the model curation and annotation tasks from diagram editing improves model iteration and centralizes the annotation of such models with supporting evidence. In this vain, we present BioKC, a web-based platform for systematic quality-controlled collaborative curation and annotation of biomedical knowledge following the standard data model from Systems Biology Markup Language (SBML). [less ▲]

BioKC: a collaborative platform for systems biology model curation and annotation

in bioRxiv (2020)

Curation of biomedical knowledge into standardised and inter-operable systems biology models is essential for studying complex biological processes. However, systems-level curation is a laborious manual ... [more ▼]

Curation of biomedical knowledge into standardised and inter-operable systems biology models is essential for studying complex biological processes. However, systems-level curation is a laborious manual process, especially when facing ever increasing growth of domain literature. Currently, these systems-level curation efforts concentrate around dedicated pathway databases, with a limited input from the research community. The demand for systems biology knowledge increases with new findings demonstrating elaborate relationships between multiple molecules, pathways and cells. This new challenge calls for novel collaborative tools and platforms allowing to improve the quality and the output of the curation process. In particular, in the current systems biology environment, curation tools lack reviewing features and are not well suited for an open, community-based curation workflows. An important concern is the complexity of the curation process and the limitations of the tools supporting it. Currently, systems-level curation combines model-building with diagram layout design. However, diagram editing tools offer limited annotation features. On the other hand, text-oriented tools have insufficient capabilities representing and annotating relationships between biological entities. Separating model curation and annotation from diagram editing enables iterative and distributed building of annotated models. Here, we present BioKC (Biological Knowledge Curation), a web-based collaborative platform for the curation and annotation of biomedical knowledge following the standard data model from Systems Biology Markup Language (SBML).Competing Interest StatementThe authors have declared no competing interest. [less ▲]

DAISY: A Data Information System for accountability under the General Data Protection Regulation

in GigaScience (2019), 8(12),

The new European legislation on data protection, namely, the General Data Protection Regulation (GDPR), has introduced comprehensive requirements for the documentation about the processing of personal ... [more ▼]

The new European legislation on data protection, namely, the General Data Protection Regulation (GDPR), has introduced comprehensive requirements for the documentation about the processing of personal data as well as informing the data subjects of its use. GDPR’s accountability principle requires institutions, projects, and data hubs to document their data processings and demonstrate compliance with the GDPR. In response to this requirement, we see the emergence of commercial data-mapping tools, and institutions creating GDPR data register with such tools. One shortcoming of this approach is the genericity of tools, and their process-based model not capturing the project-based, collaborative nature of data processing in biomedical research.We have developed a software tool to allow research institutions to comply with the GDPR accountability requirement and map the sometimes very complex data flows in biomedical research. By analysing the transparency and record-keeping obligations of each GDPR principle, we observe that our tool effectively meets the accountability requirement.The GDPR is bringing data protection to center stage in research data management, necessitating dedicated tools, personnel, and processes. Our tool, DAISY, is tailored specifically for biomedical research and can help institutions in tackling the documentation challenge brought about by the GDPR. DAISY is made available as a free and open source tool on Github. DAISY is actively being used at the Luxembourg Centre for Systems Biomedicine and the ELIXIR-Luxembourg data hub. [less ▲]

Multicenter Alzheimer's and Parkinson's disease immune biomarker verification study

in Alzheimer's and Dementia: the Journal of the Alzheimer's Association (2019)

Multiple immunity biomarkers have been suggested as tracers of neuroinflammation in neurodegeneration. This study aimed to verify findings in cerebrospinal fluid (CSF) samples of Alzheimer's disease (AD ... [more ▼]

Multiple immunity biomarkers have been suggested as tracers of neuroinflammation in neurodegeneration. This study aimed to verify findings in cerebrospinal fluid (CSF) samples of Alzheimer's disease (AD) and Parkinson's disease (PD) subjects from the network of the European, Innovative Medicines Initiative–funded project AETIONOMY. [less ▲]

Closing the gap between formats for storing layout information in systems biology.

in Briefings in bioinformatics (2019)

The understanding of complex biological networks often relies on both a dedicated layout and a topology. Currently, there are three major competing layout-aware systems biology formats, but there are no ... [more ▼]

The understanding of complex biological networks often relies on both a dedicated layout and a topology. Currently, there are three major competing layout-aware systems biology formats, but there are no software tools or software libraries supporting all of them. This complicates the management of molecular network layouts and hinders their reuse and extension. In this paper, we present a high-level overview of the layout formats in systems biology, focusing on their commonalities and differences, review their support in existing software tools, libraries and repositories and finally introduce a new conversion module within the MINERVA platform. The module is available via a REST API and offers, besides the ability to convert between layout-aware systems biology formats, the possibility to export layouts into several graphical formats. The module enables conversion of very large networks with thousands of elements, such as disease maps or metabolic reconstructions, rendering it widely applicable in systems biology. [less ▲]

Data and knowledge management in translational research: implementation of the eTRIKS platform for the IMI OncoTrack consortium

in BMC Bioinformatics (2019), 20(1), 164

For large international research consortia, such as those funded by the European Union’s Horizon 2020 programme or the Innovative Medicines Initiative, good data coordination practices and tools are ... [more ▼]

For large international research consortia, such as those funded by the European Union’s Horizon 2020 programme or the Innovative Medicines Initiative, good data coordination practices and tools are essential for the successful collection, organization and analysis of the resulting data. Research consortia are attempting ever more ambitious science to better understand disease, by leveraging technologies such as whole genome sequencing, proteomics, patient-derived biological models and computer-based systems biology simulations. [less ▲]