Recent advances in machine learning applications in metabolic engineering.

The success of CRISPR-mediated gene perturbation studies is highly dependent on the quality of gRNAs, and several tools have been developed to enable optimal gRNA design. However, these tools are not all adaptable to the latest CRISPR modalities or nucleases, nor do they offer comprehensive annotation methods for advanced CRISPR applications. Here, we present a new ecosystem of R packages, called crisprVerse, that enables efficient gRNA design and annotation for a multitude of CRISPR technologies. This includes CRISPR knockout (CRISPRko), CRISPR activation (CRISPRa), CRISPR interference (CRISPRi), CRISPR base editing (CRISPRbe) and CRISPR knockdown (CRISPRkd). The core package, crisprDesign, offers a user-friendly and unified interface to add off-target annotations, rich gene and SNP annotations, and on- and off-target activity scores. These functionalities are enabled for any RNA- or DNA-targeting nucleases, including Cas9, Cas12, and Cas13. The crisprVerse ecosystem is open-source and deployed through the Bioconductor project ( https://github.com/crisprVerse ). 

/pdf/a-comprehensive-bioconductor-ecosystem-for-the-design-of-2ptjbbw0.pdf

A comprehensive Bioconductor ecosystem for the design of CRISPR guide RNAs across nucleases and technologies

MOTIVATION
The CRISPR/Cas9 system is widely used for genome editing. The editing efficiency of CRISPR/Cas9 is mainly determined by the guide RNA (gRNA). Although many computational algorithms have been developed in recent years, it is still a challenge to select optimal bioinformatics tools for gRNA design in different experimental settings.


RESULTS
We performed a comprehensive comparison analysis of fifteen public algorithms for gRNA design, using fifteen experimental gRNA datasets. Based on this analysis, we identified the top-performing algorithms, with which we further implemented various computational strategies to build ensemble models for performance improvement. Validation analysis indicates that the new ensemble model had improved performance over any individual algorithm alone at predicting gRNA efficacy under various experimental conditions.


AVAILABILITY
The new sgRNA design tool is freely accessible as a web application via https://crisprdb.org. The source code and stand-alone version is available at Figshare (https://doi.org/10.6084/m9.figshare.21295863) and Github (https://github.com/wang-lab/CRISPRDB).


SUPPLEMENTARY INFORMATION
Supplementary data are available at Bioinformatics online.

Evaluation of efficiency prediction algorithms and development of ensemble model for CRISPR/Cas9 gRNA selection

Gene editing has great potential in treating diseases caused by well-characterized molecular alterations. The introduction of clustered regularly interspaced short palindromic repeats (CRISPR)/CRISPR-associated protein 9 (Cas9)-based gene-editing tools has substantially improved the precision and efficiency of gene editing. The CRISPR/Cas9 system offers several advantages over the existing gene-editing approaches, such as its ability to target practically any genomic sequence, enabling the rapid development and deployment of novel CRISPR-mediated knock-out/knock-in methods. CRISPR/Cas9 has been widely used to develop cancer models, validate essential genes as druggable targets, study drug-resistance mechanisms, explore gene non-coding areas, and develop biomarkers. CRISPR gene editing can create more-effective chimeric antigen receptor (CAR)-T cells that are durable, cost-effective, and more readily available. However, further research is needed to define the CRISPR/Cas9 system's pros and cons, establish best practices, and determine social and ethical implications. This review summarizes recent CRISPR/Cas9 developments, particularly in cancer research and immunotherapy, and the potential of CRISPR/Cas9-based screening in developing cancer precision medicine and engineering models for targeted cancer therapy, highlighting the existing challenges and future directions. Lastly, we highlight the role of artificial intelligence in refining the CRISPR system's on-target and off-target effects, a critical factor for the broader application in cancer therapeutics. 

/pdf/integration-of-crispr-cas9-with-artificial-intelligence-for-15c6m9da.pdf

Integration of CRISPR/Cas9 with artificial intelligence for improved cancer therapeutics

ACCESS Metrics & More Article Recommendations ■ CONTENTS Functional Basics of Cas12 and Cas13 208 Nuclease Activity of Cas12a 208 Nuclease Activity of Cas13a 208 Quantitative Determination of trans-Cleavage Kinetics of Cas Enzymes 209 trans-Cleavage Kinetics of Cas12 and Cas13 212 trans-Cleavage Kinetics of Cas12 and Its Contributing Factors 212 trans-Cleavage Kinetics of Cas13 and Its Contributing Factors 212 Nucleic Acid Detection Sensitivity Achieved by trans-Cleavage Activity of Cas Enzymes 213 Relations between the trans-Cleavage Kinetics and the Limit of Detection 213 Prediction of Performance Aided by Machine Learning 214 Challenges of trans-Cleavage and Signal Amplification in Live Cells 214 Concluding Remarks and Perspectives 214 Author Information 215 Corresponding Author 215 Authors 215 Notes 215 Biographies 215 Acknowledgments 215 References 216

https://pubs.acs.org/doi/pdf/10.1021/acs.analchem.2c04555

Signal Amplification by the trans-Cleavage Activity of CRISPR-Cas Systems: Kinetics and Performance

Abstract The clustered regularly interspaced short palindromic repeat (CRISPR)/CRISPR-associated protein 9 (Cas9) system has become a successful and promising technology for gene-editing. To facilitate its effective application, various computational tools have been developed. These tools can assist researchers in the guide RNA (gRNA) design process by predicting cleavage efficiency and specificity and excluding undesirable targets. However, while many tools are available, assessment of their application scenarios and performance benchmarks are limited. Moreover, new deep learning tools have been explored lately for gRNA efficiency prediction, but have not been systematically evaluated. Here, we discuss the approaches that pertain to the on-target activity problem, focusing mainly on the features and computational methods they utilize. Furthermore, we evaluate these tools on independent datasets and give some suggestions for their usage. We conclude with some challenges and perspectives about future directions for CRISPR–Cas9 guide design.

CRISPR–Cas9 gRNA efficiency prediction: an overview of predictive tools and the role of deep learning

Abstract The development of the CRISPR-Cas9 technology has provided a simple yet powerful system for genome editing. Current gRNA design tools serve as an important platform for the efficient application of the CRISPR systems. However, most of the existing tools are black-box models that suffer from limitations, such as variable performance and unclear mechanism of decision making. Here, we introduce CRISPRedict, an interpretable gRNA efficiency prediction model for CRISPR-Cas9 gene editing. Its strength lies in the fact that it can accurately predict efficient guide RNAs—with equivalent performance to state-of-the-art tools—while being a simple linear model. Implemented as a user-friendly web server, CRISPRedict offers (i) quick and accurate predictions across various experimental conditions (e.g. U6/T7 transcription); (ii) regression and classification models for scoring gRNAs and (iii) multiple visualizations to explain the obtained results. Given its performance, interpretability, and versatility, we expect that it will assist researchers in the gRNA design process and facilitate genome editing research. CRISPRedict is available for use at http://www.crispredict.org/.

/pdf/crispredict-a-crispr-cas9-web-tool-for-interpretable-3mui4bed.pdf

CRISPRedict: a CRISPR-Cas9 web tool for interpretable efficiency predictions

The development of the CRISPR-Cas9 technology has provided a simple yet powerful system for targeted genome editing. Compared with previous gene-editing tools, the CRISPR-Cas9 system identifies target sites by the complementarity between the guide RNA (gRNA) and the DNA sequence, which is less expensive and time-consuming, as well as more precise and scalable. To effectively apply the CRISPR-Cas9 system, researchers need to identify target sites that can be cleaved efficiently and for which the candidate gRNAs have little or no cleavage at other genomic locations. For this reason, numerous computational approaches have been developed to predict cleavage efficiency and exclude undesirable targets. However, current design tools cannot robustly predict experimental success as prediction accuracy depends on the assumptions of the underlying model and how closely the experimental setup matches the training data. Moreover, the most successful tools implement complex machine learning and deep learning models, leading to predictions that are not easily interpretable. Here, we introduce CRISPRedict, a simple linear model that provides accurate and inter-pretable predictions for guide design. Comprehensive evaluation on twelve independent datasets demonstrated that CRISPRedict has an equivalent performance with the currently most accurate tools and outperforms the remaining ones. Moreover, it has the most robust performance for both U6 and T7 data, illustrating its applicability to tasks under different conditions. Therefore, our system can assist researchers in the gRNA design process by providing accurate and explainable predictions. These predictions can then be used to guide genome editing experiments and make plausible hypotheses for further investigation. The source code of CRISPRedict along with instructions for use is available at https://github.com/VKonstantakos/CRISPRedict.

CRISPRedict: The case for simple and interpretable efficiency prediction for CRISPR-Cas9 gene editing

Duchenne Muscular Dystrophy (DMD) is a neuromuscular disorder caused by the absence of the dystrophin protein. If left untreated, it causes movement problems at the age of 10-12 years, and death occurs in the 20-30 years due to heart failure. There is currently no cure for this disease, only symptomatic treatment. Genome editing approaches like the CRISPR-Cas9 technology can provide new opportunities to ameliorate the disease by eliminating DMD mutations and restoring dystrophin expression. While it is true that on-target activity can be influenced by the guide specificity, the proposed approach focuses on the devastating results that off-target cleavage can cause (e.g., unexpected mutations). This is why reducing off-target effects is the first priority in guide design. The rapid growth of the Artificial Intelligence field has helped researchers employ artificial feature extraction and Machine Learning approaches to evaluate the potential off-target scores. This work presents our approach in evaluating off-targets of CRISPR-Cas9 gene editing specifically for the DMD disorder, using Machine Learning. We offer a comparison between four regression methods that predict the insertions-deletions (indels) produced based on a pair guide RNA and the equivalent off-target and evaluate the results using the Spearman correlation metric. We propose the most suitable method, a Decision Tree Regressor, for this problem and a comparison of the results with some state-of-art tools. The performance of our tool with Cross Validation is better than the independent performance of the other tools except from Elevation which performed about as good as ours.

Vasileios Konstantakos

Papers

CRISPR–Cas9 gRNA efficiency prediction: an overview of predictive tools and the role of deep learning

CRISPRedict: a CRISPR-Cas9 web tool for interpretable efficiency predictions

CRISPRedict: The case for simple and interpretable efficiency prediction for CRISPR-Cas9 gene editing

Modeling the off-target effects of CRISPR-Cas9 experiments for the treatment of Duchenne Muscular Dystrophy