Prompt-Driven Target Identification: A Multi-Omics and Network Biology Case Study of PARP1 Using Swalife PromptStudio

Abstract

Artificial intelligence-assisted scientific prompting is reshaping how biological targets can be rapidly identified and contextualized. In this work, we present the Swalife PromptStudio - Target Identification workflow and illustrate its application to poly(ADP-ribose) polymerase-1 (PARP1), a central regulator of DNA repair and genome integrity. Using structured prompts, we systematically explored literature, pathway databases, and genetic repositories to compile a multi-dimensional profile of PARP1. Prompt-guided mining revealed strong associations with base-excision repair, single-strand break repair, and homologous recombination pathways, positioning PARP1 as a hub in genome stability networks. Disease-mapping identified links to cancer, neurodegeneration, and ischemic injury, while variant-focused prompts highlighted replicated associations such as rs1136410 (Val762Ala) and the pharmacogenomic marker rs1805414. Together, these findings demonstrate the effectiveness of prompt-driven target identification in rapidly assembling actionable biological insights. The framework is scalable and adaptable, offering a reproducible strategy for prioritizing targets across therapeutic areas.