Automatic Recognition of Bioinformatics Software Names in Scientific Literature

Bioinformatics software and databases are essential tools in modern life science research, yet their mentions in scientific literature are often inconsistent and difficult to identify systematically at scale. The lack of a comprehensive, up-to-date catalog of these resources impedes automated biomedical knowledge extraction and streamlined data analysis workflows. To address this challenge, we introduce SNAIL, a hybrid named entity recognition (NER) framework designed to automatically identify bioinformatics software and database (SW/DB) names from biomedical texts. SNAIL integrates complementary lexical and semantic modeling strategies. The lexical component captures orthographic patterns and contextual cues characteristic of SW/DB names, while the semantic component leverages contextual embeddings from transformer-based language models such as SciBERT, combined with an explicit token-masking strategy to enhance entity-focused representations. A large training corpus was constructed automatically through a hybrid pipeline that combines citation-hinted extraction with large language model-assisted distillation. Evaluation on two independent benchmark datasets and real-world research articles shows that SNAIL substantially outperforms existing approaches, including domain-specific tools like bioNerDS2 and general-purpose large language models such as ChatGPT, Gemini, Grok, and Claude. Applying SNAIL to large-scale literature analysis further reveals distinct journal-level preferences across bioinformatics subfields. These results demonstrate that SNAIL provides an accurate and scalable solution for identifying bioinformatics resources in scientific texts, enabling systematic meta-analyses of tool usage and emerging research trends.

via ArXiv CL+LG