NLIMED: Natural Language Interface for Model Entity Discovery in Biosimulation Model Repositories

Munarko, Yuda; Sarwar, Dewan M.; Rampadarath, Anand; Atalag, Koray; Gennari, John H.; Neal, Maxwell Lewis; Nickerson, David

doi:10.3389/fphys.2022.820683

Cited by 4 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e c is the average of ontology class feature embeddings; for example, FMA:54537 has a preferred label feature of ‘Astrocyte’ and a synonym feature of ‘Astrocytus’. There are other features, such as parent labels and definitions, but using the selected two features only can give a higher performance ( Munarko et al, 2022 ). For e p calculation, predicate terms in camelCase format are normalised to phrases in lowercase before converting to embeddings.…”

Section: Methodsmentioning

confidence: 99%

“…Working well with structured and unstructured text-based queries, Natural Language Interface for Model Entity Discovery (NLIMED) provides an interface to retrieve entities annotated compositely ( Munarko et al, 2022 ). It identifies phrases in the query associated with the physiological domain and links them to possible ontology classes and predicates.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CASBERT: BERT-based retrieval for compositely annotated biosimulation model entities

Munarko

Rampadarath²,

Nickerson³

2023

Front. Bioinform.

Self Cite

View full text Add to dashboard Cite

Maximising FAIRness of biosimulation models requires a comprehensive description of model entities such as reactions, variables, and components. The COmputational Modeling in BIology NEtwork (COMBINE) community encourages the use of Resource Description Framework with composite annotations that semantically involve ontologies to ensure completeness and accuracy. These annotations facilitate scientists to find models or detailed information to inform further reuse, such as model composition, reproduction, and curation. SPARQL has been recommended as a key standard to access semantic annotation with RDF, which helps get entities precisely. However, SPARQL is unsuitable for most repository users who explore biosimulation models freely without adequate knowledge of ontologies, RDF structure, and SPARQL syntax. We propose here a text-based information retrieval approach, CASBERT, that is easy to use and can present candidates of relevant entities from models across a repository’s contents. CASBERT adapts Bidirectional Encoder Representations from Transformers (BERT), where each composite annotation about an entity is converted into an entity embedding for subsequent storage in a list of entity embeddings. For entity lookup, a query is transformed to a query embedding and compared to the entity embeddings, and then the entities are displayed in order based on their similarity. The list structure makes it possible to implement CASBERT as an efficient search engine product, with inexpensive addition, modification, and insertion of entity embedding. To demonstrate and test CASBERT, we created a dataset for testing from the Physiome Model Repository and a static export of the BioModels database consisting of query-entities pairs. Measured using Mean Average Precision and Mean Reciprocal Rank, we found that our approach can perform better than the traditional bag-of-words method.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CASBERT: BERT-based retrieval for compositely annotated biosimulation model entities

Munarko

Rampadarath²,

Nickerson³

2023

Front. Bioinform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We provide an interface to automatically convert user queries in natural language form to SPARQL. All sections have been published in Frontiers of Physiology [69].…”

Section: Repositoriesmentioning

confidence: 99%

“…e c is the average of ontology class feature embeddings, including preferred label embedding and synonym embedding (see Equation (4.1)). We do not use other features such as parent label and definition because using the preferred label and synonym alone can give a higher performance [69]. We apply w p between 0 to 1 in Equation 4.2 as a multiplier to limit the role of e p to the path embedding, so it does not exceed the ontology class embedding.…”

Section: Entity Embeddingmentioning

confidence: 99%

Smart Searching for the Physiome Project

Munarko

2024

Preprint

Self Cite

View full text Add to dashboard Cite

The Physiome Project's standards for biosimulation models in the Physiome Model Repository (PMR) aim to create a virtual physiological human. Despite an increase in models, users need help finding relevant ones. This thesis proposes approaches to aid search using semantic annotations and Natural Language Processing (NLP). The first approach is NLIMED, which converts free-text queries to SPARQL, while the second one is CASBERT, which encodes model entities for exploratory searches. Integrated into a web-based tool, CASBERT enables comprehensive searches, facilitating model discovery and maximizing FAIRness. These methods can be extended to other standards like SBML, promising multi-scale, multi-repository searches in the future. We further investigate CASBERT to identify unannotated entities by leveraging the hierarchical structure of the model. This exploration led to the development of a functional search tool called BMSE.

show abstract

“…However, creating SPARQL is difficult as it requires good knowledge of annotation structure, syntax, and ontology terms. Tools to help generating SPARQL from natural languages, such as NLIMED, 11 are helpful. Still, it is more suitable for experts who already know the target entity, not for those doing exploratory searches like using commercial search engines.…”

Section: Introductionmentioning

confidence: 99%

Building a search tool for compositely annotated entities using Transformer-based approach: Case study in Biosimulation Model Search Engine (BMSE)

Munarko

Rampadarath²,

Nickerson³

2023

F1000Res

Self Cite

View full text Add to dashboard Cite

The Transformer-based approaches to solving natural language processing (NLP) tasks such as BERT and GPT are gaining popularity due to their ability to achieve high performance. These approaches benefit from using enormous data sizes to create pre-trained models and the ability to understand the context of words in a sentence. Their use in the information retrieval domain is thought to increase effectiveness and efficiency. This paper demonstrates a BERT-based method (CASBERT) implementation to build a search tool over data annotated compositely using ontologies. The data was a collection of biosimulation models written using the CellML standard in the Physiome Model Repository (PMR). A biosimulation model structurally consists of basic entities of constants and variables that construct higher-level entities such as components, reactions, and the model. Finding these entities specific to their level is beneficial for various purposes regarding variable reuse, experiment setup, and model audit. Initially, we created embeddings representing compositely-annotated entities for constant and variable search (lowest level entity). Then, these low-level entity embeddings were vertically and efficiently combined to create higher-level entity embeddings to search components, models, images, and simulation setups. Our approach was general, so it can be used to create search tools with other data semantically annotated with ontologies - biosimulation models encoded in the SBML format, for example. Our tool is named Biosimulation Model Search Engine (BMSE).

show abstract

NLIMED: Natural Language Interface for Model Entity Discovery in Biosimulation Model Repositories

Cited by 4 publications

References 40 publications

CASBERT: BERT-based retrieval for compositely annotated biosimulation model entities

CASBERT: BERT-based retrieval for compositely annotated biosimulation model entities

Smart Searching for the Physiome Project

Building a search tool for compositely annotated entities using Transformer-based approach: Case study in Biosimulation Model Search Engine (BMSE)

Contact Info

Product

Resources

About