Engineering topics
Publications and source records attributed to Hong, Zhi.
We report the findings of a hackathon focused on exploring the diverse applications of large language models in molecular and materials science.
Scientific articles have long been the primary means of disseminating scientific discoveries. Over the centuries, valuable data and potentially groundbreaking insights have been collected and buried deep in the mountain of publications. In materials engineering, such data are spread across technical handbooks specification sheets, journal articles, and laboratory notebooks in myriad formats. Extracting information from papers on a large scale has been a tedious and time-consuming job to which few researchers have wanted to devote their limited time and effort, yet is an activity that is essential for modern data-driven design practices. However, in recent years, significant progress has been made by the computer science community on techniques for automated information extraction from free text. Yet, transformative application of these techniques to scientific literature remains elusive-due not to a lack of interest or effort but to technical and logistical challenges. Using the challenges in the materials science literature as a driving motivation, we review the gaps between state-of-the-art information extraction methods and the practical application of such methods to scientific texts, and offer a comprehensive overview of work that can be undertaken to close these gaps.
Researchers worldwide are seeking to repurpose existing drugs or discover new drugs to counter the disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). A promising source of candidates for such studies is molecules that have been reported in the scientific literature to be drug-like in the context of viral research. However, this literature is too large for human review and features unusual vocabularies for which existing named entity recognition (NER) models are ineffective. We report here on a project that leverages both human and artificial intelligence to detect references to such molecules in free text. We present 1) a iterative model-in-the-loop method that makes judicious use of scarce human expertise in generating training data for a NER model, and 2) the application and evaluation of this method to the problem of identifying drug-like molecules in the COVID-19 Open Research Dataset Challenge (CORD-19) corpus of 198,875 papers. We show that by repeatedly presenting human labelers only with samples for which an evolving NER model is uncertain, our human-machine hybrid pipeline requires only modest amounts of non-expert human labeling time (tens of hours to label 1778 samples) to generate an NER model with an F-1 score of 80.5%—on par with that of non-expert humans—and when applied to CORD’19, identifies 10,912 putative drug-like molecules. This enriched the computational screening team’s targets by 3,591 molecules, of which 18 ranked in the top 0.1% of all 6.6 million molecules screened for docking against the 3CLPro protein.