Replacing non-biomedical concepts improves embedding of biomedical concepts.
Ontology highlight
ABSTRACT: Objectives
Concept embeddings are low-dimensional vector representations of concepts such as MeSH:D009203 (Myocardial Infarction), whose similarity in the embedded vector space reflects their semantic similarity. Here, we test the hypothesis that non-biomedical concept synonym replacement can improve the quality of biomedical concepts embeddings.Materials and methods
We developed an approach that leverages WordNet to replace sets of synonyms with the most common representative of the synonym set.Results
We tested our approach on 1055 concept sets and found that, on average, the mean intra-cluster distance was reduced by 8% in the vector-space. Assuming that homophily of related concepts in the vector space is desirable, our approach tends to improve the quality of embeddings.Discussion and conclusion
This pilot study shows that non-biomedical synonym replacement tends to improve the quality of embeddings of biomedical concepts using the Word2Vec algorithm. We have implemented our approach in a freely available Python package available at https://github.com/TheJacksonLaboratory/wn2vec.
SUBMITTER: Niyonkuru E
PROVIDER: S-EPMC11244985 | biostudies-literature | 2024 Jul
REPOSITORIES: biostudies-literature
Publications
Replacing non-biomedical concepts improves embedding of biomedical concepts.
Niyonkuru Enock E Gomez Mauricio Soto MS Casiraghi Elena E Antogiovanni Stephan S Blau Hannah H Reese Justin T JT Valentini Giorgio G Robinson Peter N PN
bioRxiv : the preprint server for biology 20240704
<h4>Objectives</h4>Concept embeddings are low-dimensional vector representations of concepts such as MeSH:D009203 (Myocardial Infarction), whose similarity in the embedded vector space reflects their semantic similarity. Here, we test the hypothesis that non-biomedical concept synonym replacement can improve the quality of biomedical concepts embeddings.<h4>Materials and methods</h4>We developed an approach that leverages WordNet to replace sets of synonyms with the most common representative of ...[more]
Similar Datasets
Project description:ObjectivesElectronic health record data is often considered sensitive medical information. Therefore, the EHR data from different medical centers often cannot be shared, making it difficult to create prediction models using multicenter EHR data, which is essential for such models' robustness and generalizability. Federated learning (FL) is an algorithmic approach that allows learning a shared model using data in multiple locations without the need to store all data in a single central place. Our study aims to evaluate an FL approach using the BEHRT model for predictive tasks on EHR data, focusing on next visit prediction.Materials and methodsWe propose an FL approach for learning medical concepts embedding. This pretrained model can be used for fine-tuning for specific downstream tasks. Our approach is based on an embedding model like BEHRT, a deep neural sequence transduction model for EHR. We train using FL, both the masked language modeling (MLM) and the next visit downstream model.ResultsWe demonstrate our approach on the MIMIC-IV dataset. We compare the performance of a model trained with FL to one trained on centralized data, observing a difference in average precision ranging from 0% to 3% (absolute), depending on the length of the patients' visit history. Moreover, our approach improves average precision by 4%-10% (absolute) compared to local models. In addition, we show the importance of the usage of pretrained MLM for the next visit diagnoses prediction task.Discussion and conclusionWe find that our FL approach reaches very close to the performance of a centralized model, and it outperforms local models in terms of average precision. We also show that pretrained MLM improves the model's average precision performance in the next visit diagnoses prediction task, compared to an MLM without pretraining.
| S-EPMC11498200 | biostudies-literature
Project description:ObjectiveHospital readmission costs a lot of money every year. Many hospital readmissions are avoidable, and excessive hospital readmissions could also be harmful to the patients. Accurate prediction of hospital readmission can effectively help reduce the readmission risk. However, the complex relationship between readmission and potential risk factors makes readmission prediction a difficult task. The main goal of this paper is to explore deep learning models to distill such complex relationships and make accurate predictions.Materials and methodsWe propose CONTENT, a deep model that predicts hospital readmissions via learning interpretable patient representations by capturing both local and global contexts from patient Electronic Health Records (EHR) through a hybrid Topic Recurrent Neural Network (TopicRNN) model. The experiment was conducted using the EHR of a real world Congestive Heart Failure (CHF) cohort of 5,393 patients.ResultsThe proposed model outperforms state-of-the-art methods in readmission prediction (e.g. 0.6103 ± 0.0130 vs. second best 0.5998 ± 0.0124 in terms of ROC-AUC). The derived patient representations were further utilized for patient phenotyping. The learned phenotypes provide more precise understanding of readmission risks.DiscussionEmbedding both local and global context in patient representation not only improves prediction performance, but also brings interpretable insights of understanding readmission risks for heterogeneous chronic clinical conditions.ConclusionThis is the first of its kind model that integrates the power of both conventional deep neural network and the probabilistic generative models for highly interpretable deep patient representation learning. Experimental results and case studies demonstrate the improved performance and interpretability of the model.
| S-EPMC5890980 | biostudies-literature
Project description:Motivation: Graph embedding learning that aims to automatically learn low-dimensional node representations, has drawn increasing attention in recent years. To date, most recent graph embedding methods are evaluated on social and information networks and are not comprehensively studied on biomedical networks under systematic experiments and analyses. On the other hand, for a variety of biomedical network analysis tasks, traditional techniques such as matrix factorization (which can be seen as a type of graph embedding methods) have shown promising results, and hence there is a need to systematically evaluate the more recent graph embedding methods (e.g. random walk-based and neural network-based) in terms of their usability and potential to further the state-of-the-art.Results: We select 11 representative graph embedding methods and conduct a systematic comparison on 3 important biomedical link prediction tasks: drug-disease association (DDA) prediction, drug-drug interaction (DDI) prediction, protein-protein interaction (PPI) prediction; and 2 node classification tasks: medical term semantic type classification, protein function prediction. Our experimental results demonstrate that the recent graph embedding methods achieve promising results and deserve more attention in the future biomedical graph analysis. Compared with three state-of-the-art methods for DDAs, DDIs and protein function predictions, the recent graph embedding methods achieve competitive performance without using any biological features and the learned embeddings can be treated as complementary representations for the biological features. By summarizing the experimental results, we provide general guidelines for properly selecting graph embedding methods and setting their hyper-parameters for different biomedical tasks.Availability and implementation: As part of our contributions in the paper, we develop an easy-to-use Python package with detailed instructions, BioNEV, available at: https://github.com/xiangyue9607/BioNEV, including all source code and datasets, to facilitate studying various graph embedding methods on biomedical tasks.Supplementary information: Supplementary data are available at Bioinformatics online.
| S-EPMC7703771 | biostudies-literature
Project description:UnlabelledFACTA is a text search engine for MEDLINE abstracts, which is designed particularly to help users browse biomedical concepts (e.g. genes/proteins, diseases, enzymes and chemical compounds) appearing in the documents retrieved by the query. The concepts are presented to the user in a tabular format and ranked based on the co-occurrence statistics. Unlike existing systems that provide similar functionality, FACTA pre-indexes not only the words but also the concepts mentioned in the documents, which enables the user to issue a flexible query (e.g. free keywords or Boolean combinations of keywords/concepts) and receive the results immediately even when the number of the documents that match the query is very large. The user can also view snippets from MEDLINE to get textual evidence of associations between the query terms and the concepts. The concept IDs and their names/synonyms for building the indexes were collected from several biomedical databases and thesauri, such as UniProt, BioThesaurus, UMLS, KEGG and DrugBank.AvailabilityThe system is available at http://www.nactem.ac.uk/software/facta/
| S-EPMC2572701 | biostudies-literature
Project description:Advances in machine learning and deep learning methods, together with the increasing availability of large-scale pharmacological, genomic, and chemical datasets, have created opportunities for identifying potentially useful relationships within biochemical networks. Knowledge embedding models have been found to have value in detecting knowledge-based correlations among entities, but little effort has been made to apply them to networks of biochemical entities. This is because such networks tend to be unbalanced and sparse, and knowledge embedding models do not work well on them. However, to some extent, the shortcomings of knowledge embedding models can be compensated for if they are used in association with graph embedding. In this paper, we combine knowledge embedding and graph embedding to represent biochemical entities and their relations as dense and low-dimensional vectors. We build a cascade learning framework which incorporates semantic features from the knowledge embedding model, and graph features from the graph embedding model, to score the probability of linking. The proposed method performs noticeably better than the models with which it is compared. It predicted links and entities with an accuracy of 93%, and its average hits@10 score has an average of 8.6% absolute improvement compared with original knowledge embedding model, 1.1% to 9.7% absolute improvement compared with other knowledge and graph embedding algorithm. In addition, we designed a meta-path algorithm to detect path relations in the biomedical network. Case studies further verify the value of the proposed model in finding potential relationships between diseases, drugs, genes, treatments, etc. Amongst the findings of the proposed model are the suggestion that VDR (vitamin D receptor) may be linked to prostate cancer. This is backed by evidence from medical databases and published research, supporting the suggestion that our proposed model could be of value to biomedical researchers.
| S-EPMC6565371 | biostudies-literature
Project description:Peer-facilitated workshops enhanced interactivity in our introductory biology course, which led to increased student engagement and learning. A majority of students preferred attending two lectures and a workshop each week over attending three weekly lectures. In the workshops, students worked in small cooperative groups as they solved challenging problems, evaluated case studies, and participated in activities designed to improve their general learning skills. Students in the workshop version of the course scored higher on exam questions recycled from preworkshop semesters. Grades were higher over three workshop semesters in comparison with the seven preworkshop semesters. Although males and females benefited from workshops, there was a larger improvement of grades and increased retention by female students; although underrepresented minority (URM) and non-URM students benefited from workshops, there was a larger improvement of grades by URM students. As well as improving student performance and retention, the addition of interactive workshops also improved the quality of student learning: Student scores on exam questions that required higher-level thinking increased from preworkshop to workshop semesters.
| S-EPMC2736022 | biostudies-literature
Project description:UnlabelledSearch engines running on MEDLINE abstracts have been widely used by biologists to find publications that are related to their research. The existing search engines such as PubMed, however, have limitations when applied for the task of seeking textual evidence of relations between given concepts. The limitations are mainly due to the problem that the search engines do not effectively deal with multi-term queries which may imply semantic relations between the terms. To address this problem, we present MedEvi, a novel search engine that imposes positional restriction on occurrences matching multi-term queries, based on the observation that terms with semantic relations which are explicitly stated in text are not found too far from each other. MedEvi further identifies additional keywords of biological and statistical significance from local context of matching occurrences in order to help users reformulate their queries for better results.Availabilityhttp://www.ebi.ac.uk/tc-test/textmining/medevi/
| S-EPMC2387223 | biostudies-literature
Project description:Introduction: Scientific communication, particularly the dissemination of research findings to both the scientific community and the general public, are skills required of graduates embarking on post-graduate studies and employment within the biomedical sciences sector. The aims of this action research project were to i) co-design an online scientific communication and digital capabilities resource, constructively aligned to the learning objectives of a final year undergraduate investigative research project; ii) ensure resource flexibility for future adaptation by others iii) embed authentic scientific communication learning assessments, namely, the preparation of a lay summary and visual abstract and iv) promote students' awareness of developed digital capabilities and transferable skills through written reflection. Materials and Methods: Student engagement, self-efficacy, experiences and performance and staff perceptions (n = 15) were evaluated by a mixed methods approach. Qualitative data was gathered from focus sessions, free text responses within questionnaires and content analysis of students' written reflections (n = 104). Quantitative data from 5-point Likert responses within student questionnaires (n = 31) and analysis of student scientific and lay writing (n = 146) using the readability parameters Flesch-Kincaid Grade Level and Flesch Reading Ease were analysed using non-parametric statistical methods. Results: A learning resource was co-designed with students, staff, local, national and international contributors and valued by both students and staff, enabling students to prepare scientific communication outputs of a professional standard by application of digital, analytical and scientific communication skills. Students prepared lay summaries which were statistically (p < 0.0001) more readable than their paired scientific abstracts. Significant correlations between easier readability of lay summaries and awarded marks for the written elements of the module were noted. Students reported their digital and communication capabilities increased significantly (p < 0.0001) throughout, from limited to good/excellent and reflected on the numerous transferable skills developed during preparation of assessments, with 75% reflecting on their digital capabilities. Discussion: Undergraduate students developed, appreciated and used varied scientific communication and digital skills to articulate research findings. The embedding of such activities throughout all levels of higher education will enable students to develop their digital and scientific skills and reflect on the development of such transferable skills for application in their future careers.
| S-EPMC10154515 | biostudies-literature
Project description:BackgroundNeural network based embedding models are receiving significant attention in the field of natural language processing due to their capability to effectively capture semantic information representing words, sentences or even larger text elements in low-dimensional vector space. While current state-of-the-art models for assessing the semantic similarity of textual statements from biomedical publications depend on the availability of laboriously curated ontologies, unsupervised neural embedding models only require large text corpora as input and do not need manual curation. In this study, we investigated the efficacy of current state-of-the-art neural sentence embedding models for semantic similarity estimation of sentences from biomedical literature. We trained different neural embedding models on 1.7 million articles from the PubMed Open Access dataset, and evaluated them based on a biomedical benchmark set containing 100 sentence pairs annotated by human experts and a smaller contradiction subset derived from the original benchmark set.ResultsExperimental results showed that, with a Pearson correlation of 0.819, our best unsupervised model based on the Paragraph Vector Distributed Memory algorithm outperforms previous state-of-the-art results achieved on the BIOSSES biomedical benchmark set. Moreover, our proposed supervised model that combines different string-based similarity metrics with a neural embedding model surpasses previous ontology-dependent supervised state-of-the-art approaches in terms of Pearson's r (r = 0.871) on the biomedical benchmark set. In contrast to the promising results for the original benchmark, we found our best models' performance on the smaller contradiction subset to be poor.ConclusionsIn this study, we have highlighted the value of neural network-based models for semantic similarity estimation in the biomedical domain by showing that they can keep up with and even surpass previous state-of-the-art approaches for semantic similarity estimation that depend on the availability of laboriously curated ontologies, when evaluated on a biomedical benchmark set. Capturing contradictions and negations in biomedical sentences, however, emerged as an essential area for further work.
| S-EPMC6460644 | biostudies-literature
Project description:MotivationCapabilities in the field of metabolomics have grown tremendously in recent years. Many existing resources contain the chemical properties and classifications of commonly identified metabolites. However, the annotation of small molecules (both endogenous and synthetic) to meaningful biological pathways and concepts still lags behind the analytical capabilities and the chemistry-based annotations. Furthermore, no tools are available to visually explore relationships and networks among functionally related groups of metabolites (biomedical concepts). Such a tool would provide the ability to establish testable hypotheses regarding links among metabolic pathways, cellular processes, phenotypes and diseases.ResultsHere we present ConceptMetab, an interactive web-based tool for mapping and exploring the relationships among 16 069 biologically defined metabolite sets developed from Gene Ontology, KEGG and Medical Subject Headings, using both KEGG and PubChem compound identifiers, and based on statistical tests for association. We demonstrate the utility of ConceptMetab with multiple scenarios, showing it can be used to identify known and potentially novel relationships among metabolic pathways, cellular processes, phenotypes and diseases, and provides an intuitive interface for linking compounds to their molecular functions and higher level biological effects.Availability and implementationhttp://conceptmetab.med.umich.eduContactsakarnovsky@umich.edu or sartorma@umich.eduSupplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC5860403 | biostudies-literature