Artificial Intelligence Assistance with CRISPR to Optimize Drug Development
Year: 2026
Type: article
Abstract: Drug development remains a costly and time-consuming process since identifying therapeutic targets that are both biologically relevant and clinically effective remains challenging. New technologies including bulk RNA sequencing, single-cell RNA sequencing, CRISPR screens and AI are enabling new target discovery opportunities, but there are still a number of challenges in bringing the heterogeneous data sets together. This paper describes how AI-assisted integration of these three technologies can improve drug development. This paper explains in detail how Bulk RNA sequencing can detect differentially expressed genes, how Single-cell RNA sequencing can uncover cell-specific expression patterns, how CRISPR screening can identify dependencies of genes in disease-related phenotypes, and how AI models can recognize complex molecular patterns and prioritize targets for therapeutic intervention using these complementary datasets. With AI support and current technologies, researchers could decrease false-positive target identification and enhance drug sensitivity forecasting. This paper suggest a way to improve the precision-drug-discovery strategies. But there are still issues with data heterogeneity and with model interpretability. To address the remaining challenges, interpretable AI models that combine multi-omics, functional genomic, and patient-derived data should be developed in the future.
Source: Theoretical and Natural Science
Author: Huijun Yu
Institution: University of California System
Language: English
Subfield: Drug Discovery
Domain: Life Sciences
Open Access status: hybrid
OpenAlex ID: W7225734806
FWCI:
Cites:
Cited by:
Related to: