What is it about?

The human genome, proteome, interactome, and other 'omes' all provide extensive one-dimensional information about life, biology, pharmacology and medicine. To use this information in the real world, however, we use words, phrases, sentences and paragraphs to combine multiple dimensions together into a realistic picture that is knowledge and understanding. The next great extension of this multidimensionality is to see the relationships between sentences and paragraphs drawn from different works, including papers, clinical reports, patents, web sites and social media. Just like broad text mining has proven to be of immense value in fields like economics and national intelligence, these broad trends can help us to see the interconnected bits of pharmacological and biomedical information as pieces of a puzzle. Solving this puzzle can help us to break down long standing barriers in understanding the relationships between different diseases, and perceiving new opportunities in treating them.

Featured Image

Why is it important?

Tremendous advances in molecular biology and analytical pathophysiology have given us a great amount of data and threads of highly specialized insight, but we are still far from curing the common cold, let alone Alzheimer's, lupus and diabetes. To truly advance in these oibjectives, we need to weave these threads into a fabric, whose patterns we can see and understand. Text mining helps us to find common patterns spanning these threads, giving us a loom that may help us to crack some of the greatest unsolved challenges in biomedicine.


At a certain point in my scientific career, I began to shift my analytical focus from informatics to information science. As an informatician, I sought to apply learning algorithms to turn data into insight. As an information scientist, I began developing ad hoc techniques for turning insight into actionable hypotheses. That's when, through discussions with my colleague Mary Zgurzynski, I began to understand more about sophisticated existing tools for encoding basic written concepts in ways that could be used to systematize my improvised hypothesis discovery strategies.

Dr Gerald H Lushington
LiS Consulting

Read the Original

This page is a summary of: Can the Written Word Fuel Pharmaceutical Innovation? Part 1. An Emerging Vista from von Economo to COVID-19, Combinatorial Chemistry & High Throughput Screening, July 2022, Bentham Science Publishers, DOI: 10.2174/1386207325666220422135755.
You can read the full text:



The following have contributed to this page