MEDICAL INFORMATICS IV
NATURAL LANGUAGE PROCESSING IN BIOINFORMATICS
Yazarlar:
Orçun TAŞAR
Çiğdem SELÇUKCAN EROL
Yayıncı:
İstanbul Üniversitesi Yayınları
As in many other areas, with the increase in the volume of data produced in the fields of mainly biology and medicine, both the data and the processes of transforming it into information began to become more complex. Therefore, it was inevitable that the bioinformatics discipline, which has great capabilities for the transformation and organization of data in the related domains, needed new tools. Bioinformatics practices have been greatly enhanced by the incorporation of machine learning and deep learning (methodologies, particularly over the last decade. Structured data has long been used in ML and DL studies to derive predictive outcomes in the clinical and biomedical worlds, and now, with the advent of natural language processing (NLP) within artificial intelligence practices, it is also possible to process unstructured textual data. NLP approaches, which can now be used in the development of automated systems for time-consuming, costly, and error-prone routine tasks, can even be used to detect biomedical elements relationships that have been in the literature for a long time but have never been noticed before. Thanks to innovative bioinformatics and AI-powered NLP techniques, the fields of biology, genetics, medicine, and pharmaceuticals are rapidly transforming. In this book chapter, the use cases of NLP within bioinformatics on data in the fields of biology and medicine are discussed with current real-life examples