An Overview and Comparative Analysis of CRISPR-SpCas9 gRNA Activity Prediction Tools

TY - JOUR

T1 - An Overview and Comparative Analysis of CRISPR-SpCas9 gRNA Activity Prediction Tools

AU - Yuan, Hao

AU - Song, Chunping

AU - Xu, Huixin

AU - Sun, Ying

AU - Anthon, Christian

AU - Bolund, Lars

AU - Lin, Lin

AU - Benabdellah, Karim

AU - Lee, Ciaran

AU - Hou, Yong

AU - Gorodkin, Jan

AU - Luo, Yonglun

PY - 2025/4/1

Y1 - 2025/4/1

N2 - Design of guide RNA (gRNA) with high efficiency and specificity is vital for successful application of the CRISPR gene editing technology. Although many machine learning (ML) and deep learning (DL)-based tools have been developed to predict gRNA activities, a systematic and unbiased evaluation of their predictive performance is still needed. Here, we provide a brief overview of in silico tools for CRISPR design and assess the CRISPR datasets and statistical metrics used for evaluating model performance. We benchmark seven ML and DL-based CRISPR-Cas9 editing efficiency prediction tools across nine CRISPR datasets covering six cell types and three species. The DL models CRISPRon and DeepHF outperform the other models exhibiting greater accuracy and higher Spearman correlation coefficient across multiple datasets. We compile all CRISPR datasets and in silico prediction tools into a GuideNet resource web portal, aiming to facilitate and streamline the sharing of CRISPR datasets. Furthermore, we summarize features affecting CRISPR gene editing activity, providing important insights into model performance and the further development of more accurate CRISPR prediction models.

AB - Design of guide RNA (gRNA) with high efficiency and specificity is vital for successful application of the CRISPR gene editing technology. Although many machine learning (ML) and deep learning (DL)-based tools have been developed to predict gRNA activities, a systematic and unbiased evaluation of their predictive performance is still needed. Here, we provide a brief overview of in silico tools for CRISPR design and assess the CRISPR datasets and statistical metrics used for evaluating model performance. We benchmark seven ML and DL-based CRISPR-Cas9 editing efficiency prediction tools across nine CRISPR datasets covering six cell types and three species. The DL models CRISPRon and DeepHF outperform the other models exhibiting greater accuracy and higher Spearman correlation coefficient across multiple datasets. We compile all CRISPR datasets and in silico prediction tools into a GuideNet resource web portal, aiming to facilitate and streamline the sharing of CRISPR datasets. Furthermore, we summarize features affecting CRISPR gene editing activity, providing important insights into model performance and the further development of more accurate CRISPR prediction models.

UR - http://www.scopus.com/inward/record.url?scp=105001292655&partnerID=8YFLogxK

U2 - 10.1089/crispr.2024.0058

DO - 10.1089/crispr.2024.0058

M3 - Review

C2 - 40151952

SN - 2573-1599

VL - 8

SP - 89

EP - 104

JO - The CRISPR Journal

JF - The CRISPR Journal

IS - 2

ER -