Back

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

Badhe, P.

2025-09-01 pharmacology and toxicology
10.1101/2025.08.31.673331 bioRxiv
Show 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.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.