Ghadeer Mobasher

SDBV group using Hub

PoLiMeR is funded through the EU Marie Skłodowska-Curie Innovative Training Network (ITN), which drives scientific excellence and innovation. ITNs bring together universities, research institutes, industry and clinical partners from across the world to train researchers to doctorate level.

Metabolic diseases are a burden on the European population and health care system. It is increasingly recognised that individual differences with respect to history, lifestyle, and genetic make-up affect disease ...

BioCreative VII

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).

In biomedical text mining, named entity recognition (NER) is an important task used to extract information from biomedical articles. Improving the NER’s performance will directly have a positive impact on extracting relations between those entities. In recent years, deep learning has become the main research direction of NER due to the development of effective models. Language transformer models like e.g. BERT are frequently used because they enable the specialisation of models by domain-specific ...

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 ...

Biomedical pre-trained language models (BioPLMs) have been achieving state-of-the-art results for various biomedical text mining tasks. However, prevailing fine-tuning approaches naively train BioPLMs on targeted datasets without considering the class distributions. This is problematic, especially with dealing with imbalanced biomedical gold-standard datasets for named entity recognition (NER). Regardless of the high-performing SOTA fine-tuned NER models, they are biased towards other (O) tags ...

Usage of fine-tuned BioBERT for identification of chemical entities

Using semantic search in MesH and PubChem databases for entity linking

BC7 NLM-Chem-track data and materials

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).