Chemical Identification and Indexing in PubMed articles

Actions

Order Studies

Overview
Related items

Current chemical concept recognition tools have demonstrated significantly lower performance for in full-text articles than in abstracts. Improving automated full-text chemical concept recognition can substantially accelerate manual indexing and curation and advance downstream NLP tasks such as relevant article retrieval. Participating in BioCreative Track NLM-Chem we focus identifying chemicals in full-text articles (i.e. named entity recognition and normalization).

SEEK ID: https://fairdomhub.org/investigations/484

Projects: BioCreative VII

Investigation position:

Help

Tree Split Graph

Export PNG

Click below to download a copy of the image

Download

Creators and Submitter

Creators

Olga Krebs
Ghadeer Mobasher
Lukrécia Mertová
Sucheta Ghosh
Bettina Heinlein
Wolfgang Müller

Submitter

Olga Krebs

Activity

Views: 256

Created: 12th Oct 2021 at 16:54

Last updated: 27th Sep 2023 at 14:21

Related items

People (6)
Programmes (1)
Projects (1)
Studies (1)
Assays (2)
Data files (1)
Models (1)
Publications (2)

Advanced People list for this Investigation with search and filtering

Sucheta Ghosh

Projects: COVID-19 Disease Map, BioCreative VII, SDBV/HITS

Institutions: Heidelberg Institute for Theoretical Studies (HITS gGmbH)

https://orcid.org/0000-0002-2896-4552

Research Associate, SDBV

Bettina Heinlein

Projects: BioCreative VII

Institutions: Heidelberg Institute for Theoretical Studies (HITS gGmbH)

Expertise: Physics, Mathematics

Tools: Python, Machine Learning, Data analysis

Olga Krebs

Projects: SysMO DB, FAIRDOM, ICYSB 2015 - International Practical Course in Systems Biology, ZucAt, SysMO-LAB, Kinetics on the move - Workshop 2016, Example use cases, FAIRDOM user meeting, ErasysApp Funders, EraCoBiotech 2 nd call proposal preparation, Service to URV Tarragona, Spain with respect to their Safety Assessment of Endocrine Disrupting Chemicals model (Active NOW), FAIRDOM & LiSyM & de.NBI Data Structuring Training, MESI-STRAT, INCOME, Multiscale modelling of state transitions in the host-microbiome-brain network, BESTER, TRALAMINOL, Sustainable co-production, INDIE - Biotechnological production of sustainable indole, Extremophiles metabolsim, PoLiMeR - Polymers in the Liver: Metabolism and Regulation, OLCIR: Optimization of Lung Cancer Therapy with Ionizing Radiation, NAD COMPARTMENTATION, HOTSOLUTE, Stress granules, FAIRDOM Community Workers, GMDS Project Group "FAIRe Dateninfrastrukturen für die Biomedizinische Informatik", Mechanism based modeling viral disease ( COVID-19 ) dynamics in human population, COVID-19 Disease Map, AquaHealth (ERA-BlueBio), LiSyM Core Infrastructure and Management (LiSyM-PD), Early Metabolic Injury (LiSyM-EMI - Pillar I), Regeneration and Repair in Acute-on-Chronic Liver Failure (LiSyM-ACLF - Pillar III), Chronic Liver Disease Progression (LiSyM-DP - Pillar II), Liver Function Diagnostics (LiSyM-LiFuDi - Pillar IV), The Hedgehog Signalling Pathway (LiSyM-JGMMS), Multi-Scale Models for Personalized Liver Function Tests (LiSyM-MM-PLF), Model Guided Pharmacotherapy In Chronic Liver Disease (LiSyM-MGP), Molecular Steatosis - Imaging & Modeling (LiSyM-MSIM), Modelling COVID-19 epidemics, SNAPPER: Synergistic Neurotoxicology APP for Environmental Regulation, SCyCode The Autotrophy-Heterotrophy Switch in Cyanobacteria: Coherent Decision-Making at Multiple Regulatory Layers, SASKit: Senescence-Associated Systems diagnostics Kit for cancer and stroke, CC-TOP, BioCreative VII, MESI-STRAT Review, SDBV/HITS, MESI-Review 2024

Institutions: Heidelberg Institute for Theoretical Studies (HITS gGmbH), FAIRDOM User meeting, Norwegian University of Science and Technology, University of Rostock, University of Innsbruck

https://orcid.org/0000-0003-3540-0402

Expertise: Genetics, Molecular Biology, Bioinformatics, Data Management, Transcriptomics, semantics, Curation, Ontology, Data Modelling

Tools: Cell and tissue culture, Databases, Chip-chip, BioMart, Protege, RightField, SEEK

I am a researcher at the Scientific Databases and Visualization Group at Heidelberg Institute for Theoretical Studies (HITS) , one of the developers of SabioRK - System for the Analysis of Biochemical Pathways - Reaction Kinetics (http://sabiork.h-its.org/) . I am working on design and maintenance of the information systems to store, query and analyse systems biology data; definition and implementation of methods for the integration of data from multiple sources. In **[SySMO-DB ...

Lukrécia Mertová

Projects: FAIRDOM, BioCreative VII, The BeeProject, SDBV/HITS, Semantic Table Interpretation in Chemistry

Institutions: Heidelberg Institute for Theoretical Studies (HITS gGmbH)

https://orcid.org/0000-0002-7585-4479

Expertise: Data analysis, Computational Systems Biology, Databases, Data Management, Table Curation

Tools: Machine Learning, Python, Java, standards, Data Integration

Ghadeer Mobasher

Projects: PoLiMeR - Polymers in the Liver: Metabolism and Regulation, BioCreative VII, SDBV/HITS

Institutions: Heidelberg Institute for Theoretical Studies (HITS gGmbH)

https://orcid.org/0000-0003-4026-6965

Wolfgang Müller

Projects: SysMO DB, FAIRDOM, ICYSB 2015 - International Practical Course in Systems Biology, de.NBI-SysBio, Regeneration and Repair in Acute-on-Chronic Liver Failure (LiSyM-ACLF - Pillar III), Early Metabolic Injury (LiSyM-EMI - Pillar I), Chronic Liver Disease Progression (LiSyM-DP - Pillar II), LiSyM Core Infrastructure and Management (LiSyM-PD), Liver Function Diagnostics (LiSyM-LiFuDi - Pillar IV), Molecular Steatosis - Imaging & Modeling (LiSyM-MSIM), Multi-Scale Models for Personalized Liver Function Tests (LiSyM-MM-PLF), Model Guided Pharmacotherapy In Chronic Liver Disease (LiSyM-MGP), The Hedgehog Signalling Pathway (LiSyM-JGMMS), Kinetics on the move - Workshop 2016, Example use cases, SBEpo - Systems Biology of Erythropoietin, FAIRDOM & LiSyM & de.NBI Data Structuring Training, MESI-STRAT, INCOME, EnzymeML, PoLiMeR - Polymers in the Liver: Metabolism and Regulation, MS_DILI, GMDS Project Group "FAIRe Dateninfrastrukturen für die Biomedizinische Informatik", COMBINE Multicellular Modelling, COVID-19 Disease Map, COVID-19 related studies and tools in Germany, nfdi4health - German National Research Data Infrastructure for Personal Health Data, NMTrypI - New Medicines for Trypanosomatidic Infections, ModeleXchange initiative, SNAPPER: Synergistic Neurotoxicology APP for Environmental Regulation, BioCreative VII, SDBV ephemeral data exchanges, The BeeProject, SDBV/HITS, MESI-STRAT Review, MESI-Review 2024

Institutions: Heidelberg Institute for Theoretical Studies (HITS gGmbH)

https://orcid.org/0000-0002-4980-3512

Expertise: Software Engineering, Information Retrieval, Human-Computer Interaction, Distributed Systems

Tools: Data Management, Databases, Java, Spring, Grails web development framework, Ruby on Rails, Javascript, SABIO-RK database, Python, SEEK

I am group leader of the SDBV (Scientific Databases and Visualisation) group at the HITS gGmbH, the Heidelberg Institute for Theoretical Studies.

I am interested in finding data. Starting with my master's thesis I have always worked on how to store data in a way that you can find it, and how to make sense out of data that has been stored.

Within FAIRDOM I find interesting to help people to store their data in a way that they make sense even after years.

Advanced Programmes list for this Investigation with search and filtering

Independent Projects

Projects that do not fall under current programmes.

Projects: Manchester Institute for Biotechnology, ICYSB 2015 - International Practical Course in Systems Biology, iRhythmics, INBioPharm, EmPowerPutida, Systo models, MycoSynVac - Engineering Mycoplasma pneumoniae as a broad-spectrum animal vaccine, Multiscale modelling of state transitions in the host-microbiome-brain network, Extremophiles metabolsim, NAD COMPARTMENTATION, Agro-ecological modelling, Bergen(Ziegler lab) project AF-NADase, NAMPT affinity, Stress granules, Modelling COVID-19 epidemics, Bio-crop, ORHIZON, Coastal Data, SASKit: Senescence-Associated Systems diagnostics Kit for cancer and stroke, hybrid sequencing, HOST-PAR, BioCreative VII, Boolean modeling of Parkinson disease map, Orphan cytochrome P450 20a1 CRISPR/Cas9 mutants and neurobehavioral phenotypes in zebrafish, Selective Destruction in Ageing, Viral Metagenomic, Synthetic biology in Synechococcus for bioeconomy applications (SynEco), testproject, SDBV ephemeral data exchanges, Test project, The BeeProject, PHENET, LiceVault, EbN1 Systems Biology, UMRPégase, DeCipher, Heat stress response of the red-tide dinoflagellate Prorocentrum cordatum, middle ear, datamgmt, Institut Pasteur's projects, The nucleus of Prorocentrum cordatum, qpcr, MRC-UNICORN, Test project for Sciender, qPCR, Artificial organelles_Pathogen digestion, Supplementary Information 2 associated with the manuscript entitled " Label free Mass spectrometry proteomics reveals different pathways modulated in THP-1 cells infected with therapeutic failure and drug resistance Leishmania infantum clinical isolates", FAIR Functional Enrichment, PTPN11 mutagenesis, Supplementary Information 2 associated with the manuscript entitled "Label free Mass spectrometry proteomics reveals different pathways modulated in THP-1 cells infected with therapeutic failure and drug resistance Leishmania infantum clinical isolates", iPlacenta- Placenta on a chip, Near Surface Wave-Coherent Measurements of Temperature and Humidity, A Meta-Analysis of Functional Recovery of Aphasia after Stroke by Acupuncture Combined with Language Rehabilitation Training, Phytoplankton phenology in the Bay of Biscay: using remote sensing to assess and raise awareness of climate change impacts on the sea, Master-BIDS, Endometriosis, Vitis Data Crop, MESI-STRAT Review, Establishing an innovative and transnational feed production approach for reduced climate impact of the aquaculture sector and future food supply, ARAX: a web-based computational reasoning system for translational biomedicine, Adaptation of Salmonella enterica, I AM FRONTIER, ., PhD Nicotinic Acetylcholine Receptors, SFB1361 playground, Amaizing, Conspicuous chloroplast with LHC‒PSI/II‒megacomplex and diverse PBPs in the marine dinoflagellate Prorocentrum cordatum, icpm-kth, SDBV/HITS, sample project, TestingSeek, Genomic Medicine, Remodeling of cIV, Virtual Human Platform for Safety Assessment, PROMISEANG, URGI, Matsutake, UNDESIRABLE EFFECTS OF POST COVID-19 VACCINATION: A DESCRIPTIVE STUDY, WINTER 2022, Semantic Table Interpretation in Chemistry, MS identification of L infantum proteins related to their drug resistance patterns for new drug targets identification and ecotoxicological evaluations of their environmental and interspecies impact, the Supplementary materials for paper, ToxiGen - Reproductive toxicity and transgenerational effects of petroleum mixtures in fish, PhotoBoost, Measurement of Fisheries Provisioning Services and its Pressure to Support Sustainability of Fisheries in The Jatigede Reservoir, Indonesia, FIsh data on 2022 in the Jatigede Reservoir, ImmPort - data sharing, MESI-Review 2024, REWIRED: comparative RNA-seq and ATAC-seq in six salmonids and six outgroup telest fishes, REWIRED, Data Repository, APPN Test Project, Enhanced Anticancer Effect of Thymidylate Synthase Dimer Disrupters Promoting Intracellular Accumulation, BIDS, BioRECIPE representation format, UMass Chan BioImage DMS Core_FAIR Metadata Templates, Function, control and engineering of microbial methylotrophy, Pectobacterium pangenome, New Optical Coherence Tomography Biomarkers Identified with Deep Learning for Risk Stratification of Patients with Age-related Macular Degeneration, Virulence-related genes expression in planktonic mixed cultures of Candida albicans and non-albicans Candida species

Web page: Not specified

Advanced Projects list for this Investigation with search and filtering

BioCreative VII

Programme: Independent Projects

Public web page: Not specified

Organisms: Not specified

Advanced Studies list for this Investigation with search and filtering

Chemical named entity recognition and annotation

BioCreative VII

(Show All)

All creators

Olga Krebs

Ghadeer Mobasher

Lukrécia Mertová

Sucheta Ghosh

Bettina Heinlein

Wolfgang Müller

Chemical named entity recognition (NER) is a significant pre-processing task in natural language processing. Identification and extraction of chemical entities from biomedical literature and entities linking to the knowledge base are essential steps for the chemical text-mining pipeline. However, the identification of chemical entities in a biomedical text is a challenging task due to the diverse morphology of chemical entities and the different types of chemical nomenclature. In this work, we ...

Submitter: Olga Krebs

Investigation: Chemical Identification and Indexing in PubMed ...

Assays: Usage of fine-tuned BioBERT for identification of chemical entities, Using semantic search in MesH and PubChem databases for entity linking

Snapshots: No snapshots

Created: 12th Oct 2021 at 17:00, Last updated: 27th Sep 2023 at 14:21

Advanced Assays list for this Investigation with search and filtering

Usage of fine-tuned BioBERT for identification of chemical entities

BioCreative VII

All creators

Ghadeer Mobasher

Lukrécia Mertová

Usage of fine-tuned BioBERT for identification of chemical entities

Submitter: Olga Krebs

Biological problem addressed: Annotation

Investigation: Chemical Identification and Indexing in PubMed ...

Study: Chemical named entity recognition and annotation

Organisms: No organisms

Models: WELT code

SOPs: No SOPs

Data files: BioCreative VII Track 2 - NLM-CHEM

Snapshots: No snapshots

Created: 12th Oct 2021 at 17:14, Last updated: 27th Sep 2023 at 14:21

Using semantic search in MesH and PubChem databases for entity linking

BioCreative VII

All creators

Ghadeer Mobasher

Lukrécia Mertová

Using semantic search in MesH and PubChem databases for entity linking

Submitter: Olga Krebs

Biological problem addressed: Annotation

Investigation: Chemical Identification and Indexing in PubMed ...

Study: Chemical named entity recognition and annotation

Organisms: No organisms

Models: No Models

SOPs: No SOPs

Data files: BioCreative VII Track 2 - NLM-CHEM

Snapshots: No snapshots

Created: 12th Oct 2021 at 17:16, Last updated: 27th Sep 2023 at 14:21

Advanced Data files list for this Investigation with search and filtering

BioCreative VII Track 2 - NLM-CHEM

BioCreative VII

All creators

Ghadeer Mobasher

BC7 NLM-Chem-track data and materials

Creator: Ghadeer Mobasher

Submitter: Ghadeer Mobasher

Investigations: Chemical Identification and Indexing in PubMed ...

Studies: Chemical named entity recognition and annotation

Assays: Usage of fine-tuned BioBERT for identification ..., Using semantic search in MesH and PubChem datab...

External Link

Created: 17th Nov 2021 at 19:56, Last updated: 27th Sep 2023 at 14:21

Advanced Models list for this Investigation with search and filtering

WELT code

PoLiMeR - Polymers in the Liver: Metabolism and Regulation

All creators

Ghadeer Mobasher

This folder contains the python code for developing weighted loss trainer (WeLT) with all the expiremnatal work. Here is the link for our public [GitHub repository] (https://github.com/mobashgr/WELT.git).

Creator: Ghadeer Mobasher

Submitter: Ghadeer Mobasher

Model type: Not specified

Model format: Python code

Environment: Not specified

Organism: Not specified

Investigations: Biomedical named entity recognition, Chemical Identification and Indexing in PubMed ...

Studies: Chemical named entity recognition and annotation, Weighted loss trainer (WELT) approach

Assays: Usage of fine-tuned BioBERT for identification ... and 4 hidden items

Download

Created: 17th Nov 2022 at 17:11, Last updated: 27th Sep 2023 at 14:21

Advanced Publications list for this Investigation with search and filtering

Chemical identification and indexing in full-text articles: an overview of the NLM-Chem track at BioCreative VII

PoLiMeR - Polymers in the Liver: Metabolism and Regulation, BioCreative VII

(Show All)

All authors

Camila Almeida

Antje Chang

Dong-Hyun Kim

Xiangcheng Li

Lukrécia Mertová

Ghadeer Mobasher

Abstract (Expand)

Abstract The BioCreative National Library of Medicine (NLM)-Chem track calls for a community effort to fine-tune automated recognition of chemical names in the biomedical literature. Chemicals are one …erature. Chemicals are one of the most searched biomedical entities in PubMed, and—as highlighted during the coronavirus disease 2019 pandemic—their identification may significantly advance research in multiple biomedical subfields. While previous community challenges focused on identifying chemical names mentioned in titles and abstracts, the full text contains valuable additional detail. We, therefore, organized the BioCreative NLM-Chem track as a community effort to address automated chemical entity recognition in full-text articles. The track consisted of two tasks: (i) chemical identification and (ii) chemical indexing. The chemical identification task required predicting all chemicals mentioned in recently published full-text articles, both span [i.e. named entity recognition (NER)] and normalization (i.e. entity linking), using Medical Subject Headings (MeSH). The chemical indexing task required identifying which chemicals reflect topics for each article and should therefore appear in the listing of MeSH terms for the document in the MEDLINE article indexing. This manuscript summarizes the BioCreative NLM-Chem track and post-challenge experiments. We received a total of 85 submissions from 17 teams worldwide. The highest performance achieved for the chemical identification task was 0.8672 F-score (0.8759 precision and 0.8587 recall) for strict NER performance and 0.8136 F-score (0.8621 precision and 0.7702 recall) for strict normalization performance. The highest performance achieved for the chemical indexing task was 0.6073 F-score (0.7417 precision and 0.5141 recall). This community challenge demonstrated that (i) the current substantial achievements in deep learning technologies can be utilized to improve automated prediction accuracy further and (ii) the chemical indexing task is substantially more challenging. We look forward to further developing biomedical text–mining methods to respond to the rapid growth of biomedical literature. The NLM-Chem track dataset and other challenge materials are publicly available at https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/. Database URL https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/

Authors: Robert Leaman, Rezarta Islamaj, Virginia Adams, Mohammed A Alliheedi, João Rafael Almeida, Rui Antunes, Robert Bevan, Yung-Chun Chang, Arslan Erdengasileng, Matthew Hodgskiss, Ryuki Ida, Hyunjae Kim, Keqiao Li, Robert E Mercer, Lukrécia Mertová, Ghadeer Mobasher, Hoo-Chang Shin, Mujeen Sung, Tomoki Tsujimura, Wen-Chao Yeh, Zhiyong Lu

Date Published: 2023

Publication Type: Journal

DOI: 10.1093/database/baad005

Citation: Database 2023,baad005

Created: 19th Mar 2023 at 12:02, Last updated: 19th Mar 2023 at 12:03

Combining dictionary- and rule-based approximate entity linking with tuned BioBERT

BioCreative VII

(Show All)

All authors

Ghadeer Mobasher

Lukrécia Mertová

Sucheta Ghosh

Olga Krebs

Bettina Heinlein

Wolfgang Müller

Abstract (Expand)

Chemical named entity recognition (NER) is a significant step for many downstream applications like entity linking for the chemical text-mining pipeline. However, the identification of chemical entities … in a biomedical text is a challenging task due to the diverse morphology of chemical entities and the different types of chemical nomenclature. In this work, we describe our approach that was submitted for BioCreative version 7 challenge Track 2, focusing on the ‘Chemical Identification’ task for identifying chemical entities and entity linking, using MeSH. For this purpose, we have applied a two-stage approach as follows (a) usage of fine-tuned BioBERT for identification of chemical entities (b) semantic approximate search in MeSH and PubChem databases for entity linking. There was some friction between the two approaches, as our rule-based approach did not harmonise optimally with partially recognized words forwarded by the BERT component. For our future work, we aim to resolve the issue of the artefacts arising from BERT tokenizers and develop joint learning of chemical named entity recognition and entity linking using pre-trained transformer-based models and compare their performance with our preliminary approach. Next, we will improve the efficiency of our approximate search in reference databases during entity linking. This task is non-trivial as it entails determining similarity scores of large sets of trees with respect to a query tree. Ideally, this will enable flexible parametrization and rule selection for the entity linking search.

Authors: Ghadeer Mobasher, Lukrécia Mertová, Sucheta Ghosh, Olga Krebs, Bettina Heinlein, Wolfgang Müller

Date Published: 11th Nov 2021

Publication Type: Proceedings

DOI: 10.1101/2021.11.09.467905

Citation: biorxiv;2021.11.09.467905v1,[Preprint]

Created: 17th Nov 2021 at 19:44, Last updated: 8th Dec 2022 at 17:26