A systematic evaluation of nucleotide properties for CRISPR sgRNA design

Unveiling Off-Target Mutations in CRISPR Guide RNAs: Implications for Gene Region Specificity

The revolutionary CRISPR-Cas9 technology has revolutionized genetic engineering, and it holds immense potential for therapeutic interventions. However, the presence of off-target mutations and mismatch capacity poses significant challenges to its safe and precise implementation. In this study, we explore the implications of off-target effects on critical gene regions, including exons, introns, and intergenic regions. Leveraging a benchmark dataset and using innovative data preprocessing techniques, we have put forth the advantages of categorical encoding over one-hot encoding in training machine learning classifiers. Crucially, we use latent class analysis (LCA) to uncover subclasses within the off-target range, revealing distinct patterns of gene region disruption. Our comprehensive approach not only highlights the critical role of model complexity in CRISPR applications but also offers a transformative off-target scoring procedure based on ML classifiers and LCA. By bridging the gap between traditional target-off scoring and comprehensive model analysis, our study advances the understanding of off-target effects and opens new avenues for precision genome editing in diverse biological contexts. This work represents a crucial step toward ensuring the safety and efficacy of CRISPR-based therapies, underscoring the importance of responsible genetic manipulation for future therapeutic applications.

Benchmarking deep learning methods for predicting CRISPR/Cas9 sgRNA on- and off-target activities

In silico design of single guide RNA (sgRNA) plays a critical role in clustered regularly interspaced, short palindromic repeats/CRISPR-associated protein 9 (CRISPR/Cas9) system. Continuous efforts are aimed at improving sgRNA design with efficient on-target activity and reduced off-target mutations. In the last 5 years, an increasing number of deep learning-based methods have achieved breakthrough performance in predicting sgRNA on- and off-target activities. Nevertheless, it is worthwhile to systematically evaluate these methods for their predictive abilities. In this review, we conducted a systematic survey on the progress in prediction of on- and off-target editing. We investigated the performances of 10 mainstream deep learning-based on-target predictors using nine public datasets with different sample sizes. We found that in most scenarios, these methods showed superior predictive power on large- and medium-scale datasets than on small-scale datasets. In addition, we performed unbiased experiments to provide in-depth comparison of eight representative approaches for off-target prediction on 12 publicly available datasets with various imbalanced ratios of positive/negative samples. Most methods showed excellent performance on balanced datasets but have much room for improvement on moderate- and severe-imbalanced datasets. This study provides comprehensive perspectives on CRISPR/Cas9 sgRNA on- and off-target activity prediction and improvement for method development.

Increasing Genome Editing Efficiency of Cas9 Nucleases by the Simultaneous Use of Transcriptional Activators and Histone Acetyltransferase Activator

The CRISPR-Cas9 system shows diverse levels of genome editing activities on eukaryotic chromatin, and high-efficiency sgRNA targets are usually desired in application. In this study, we show that chromatin open status is a pivotal determinant of the Cas9 editing activity in mammalian cells, and increasing chromatin accessibility can efficiently improve Cas9 genome editing. However, the strategy that increases chromatin openness by fusing the VP64 transcriptional activation domain at the C-terminus of Cas9 can only promote genome editing activity slightly at most tested CRISPR-Cas9 targets in Lenti-X 293T cells. Under the enlightenment that histone acetylation increases eukaryotic chromatin accessibility, we developed a composite strategy to further improve genome editing by activating histone acetylation. We demonstrate that promoting histone acetylation using the histone acetyltransferase activator YF-2 can improve the genome editing by Cas9 and, more robustly, by the Cas9 transcriptional activator (Cas9-AD). This strategy holds great potential to enhance CRISPR-Cas9 genome editing and to enable broader CRISPR gRNA target choices for experiments in eukaryotes.

Could artificial intelligence revolutionize the development of nanovectors for gene therapy and mRNA vaccines?

Gene therapy enables the introduction of nucleic acids like DNA and RNA into host cells, and is expected to revolutionize the treatment of a wide range of diseases. This growth has been further accelerated by the discovery of CRISPR/Cas technology, which allows accurate genomic editing in a broad range of cells and organisms in vitro and in vivo. Despite many advances in gene delivery and the development of various viral and non-viral gene delivery vectors, the lack of highly efficient non-viral systems with low cellular toxicity remains a challenge. The application of cutting-edge technologies such as artificial intelligence (AI) has great potential to find new paradigms to solve this issue. Herein, we review AI and its major subfields including machine learning (ML), neural networks (NNs), expert systems, deep learning (DL), computer vision and robotics. We discuss the potential of AI-based models and algorithms in the design of targeted gene delivery vehicles capable of crossing extracellular and intracellular barriers by viral mimicry strategies. We finally discuss the role of AI in improving the function of CRISPR/Cas systems, developing novel nanobots, and mRNA vaccine carriers.

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

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 15 public algorithms for gRNA design, using 16 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 AND IMPLEMENTATION

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.

Characterizing genes associated with cancer using the CRISPR/Cas9 system: A systematic review of genes and methodological approaches

The CRISPR/Cas9 system enables a versatile set of genomes editing and genetic-based disease modeling tools due to its high specificity, efficiency, and accessible design and implementation. In cancer, the CRISPR/Cas9 system has been used to characterize genes and explore different mechanisms implicated in tumorigenesis. Different experimental strategies have been proposed in recent years, showing dependency on various intrinsic factors such as cancer type, gene function, mutation type, and technical approaches such as cell line, Cas9 expression, and transfection options. However, the successful methodological approaches, genes, and other experimental factors have not been analyzed. We, therefore, initially considered more than 1,300 research articles related to CRISPR/Cas9 in cancer to finally examine more than 400 full-text research publications. We summarize findings regarding target genes, RNA guide designs, cloning, Cas9 delivery systems, cell enrichment, and experimental validations. This analysis provides valuable information and guidance for future cancer gene validation experiments.

Computational tools and resources for CRISPR/Cas genome editing

The past decade has witnessed a rapid evolution in identifying more versatile clustered regularly interspaced short palindromic repeats (CRISPR)/CRISPR-associated protein (Cas) nucleases and their functional variants as well as in developing precise CRISPR/Cas-derived genome editors. The programmable and robust features of the genomic editors provide an effective RNA-guided platform for fundamental life science research and subsequent applications in diverse scenarios, including biomedical innovation and targeted crop improvement. One of the most essential principles is to guide alterations in genomic sequences or genes in the intended manner without undesired off-target impacts, which strongly depends on the efficiency and specificity of single guide RNA (sgRNA)-directed recognition of targeted DNA sequences. Recent advances in empirical scoring algorithms and machine learning models have facilitated sgRNA design and off-target prediction. In this review, we first briefly introduced the different features of CRISPR/Cas tools that should be taken into consideration to achieve specific purposes. Secondly, we focused on the computer-assisted tools and resources that are widely used in designing sgRNAs and analyzing CRISPR/Cas-induced on- and off-target mutations. Thirdly, we provide insights on the limitations of available computational tools that surely help researchers of this field for further optimization. Lastly, we suggested a simple but effective workflow for choosing and applying web-based resources and tools for CRISPR/Cas genome editing.

Sequence-specific prediction of the efficiencies of adenine and cytosine base editors

Base editors, including adenine base editors (ABEs)1 and cytosine base editors (CBEs)2,3, are widely used to induce point mutations. However, determining whether a specific nucleotide in its genomic context can be edited requires time-consuming experiments. Furthermore, when the editable window contains multiple target nucleotides, various genotypic products can be generated. To develop computational tools to predict base-editing efficiency and outcome product frequencies, we first evaluated the efficiencies of an ABE and a CBE and the outcome product frequencies at 13,504 and 14,157 target sequences, respectively, in human cells. We found that there were only modest asymmetric correlations between the activities of the base editors and Cas9 at the same targets. Using deep-learning-based computational modeling, we built tools to predict the efficiencies and outcome frequencies of ABE- and CBE-directed editing at any target sequence, with Pearson correlations ranging from 0.50 to 0.95. These tools and results will facilitate modeling and therapeutic correction of genetic diseases by base editing.

Deep learning improves the ability of sgRNA off-target propensity prediction

BACKGROUND

CRISPR/Cas9 system, as the third-generation genome editing technology, has been widely applied in target gene repair and gene expression regulation. Selection of appropriate sgRNA can improve the on-target knockout efficacy of CRISPR/Cas9 system with high sensitivity and specificity. However, when CRISPR/Cas9 system is operating, unexpected cleavage may occur at some sites, known as off-target. Presently, a number of prediction methods have been developed to predict the off-target propensity of sgRNA at specific DNA fragments. Most of them use artificial feature extraction operations and machine learning techniques to obtain off-target scores. With the rapid expansion of off-target data and the rapid development of deep learning theory, the existing prediction methods can no longer satisfy the prediction accuracy at the clinical level.

RESULTS

Here, we propose a prediction method named CnnCrispr to predict the off-target propensity of sgRNA at specific DNA fragments. CnnCrispr automatically trains the sequence features of sgRNA-DNA pairs with GloVe model, and embeds the trained word vector matrix into the deep learning model including biLSTM and CNN with five hidden layers. We conducted performance verification on the data set provided by DeepCrispr, and found that the auROC and auPRC in the "leave-one-sgRNA-out" cross validation could reach 0.957 and 0.429 respectively (the Pearson value and spearman value could reach 0.495 and 0.151 respectively under the same settings).

CONCLUSION

Our results show that CnnCrispr has better classification and regression performance than the existing states-of-art models. The code for CnnCrispr can be freely downloaded from https://github.com/LQYoLH/CnnCrispr.

An overview and metanalysis of machine and deep learning-based CRISPR gRNA design tools

The CRISPR-Cas9 system has become the most promising and versatile tool for genetic manipulation applications. Albeit the technology has been broadly adopted by both academic and pharmaceutic societies, the activity (on-target) and specificity (off-target) of CRISPR-Cas9 are decisive factors for any application of the technology. Several in silico gRNA activity and specificity predicting models and web tools have been developed, making it much more convenient and precise for conducting CRISPR gene editing studies. In this review, we present an overview and comparative analysis of machine and deep learning (MDL)-based algorithms, which are believed to be the most effective and reliable methods for the prediction of CRISPR gRNA on- and off-target activities. As an increasing number of sequence features and characteristics are discovered and are incorporated into the MDL models, the prediction outcome is getting closer to experimental observations. We also introduced the basic principle of CRISPR activity and specificity and summarized the challenges they faced, aiming to facilitate the CRISPR communities to develop more accurate models for applying.

Computational approaches for effective CRISPR guide RNA design and evaluation

The Clustered Regularly Interspaced Short Palindromic Repeat (CRISPR)/ CRISPR-associated (Cas) system has emerged as the main technology for gene editing. Successful editing by CRISPR requires an appropriate Cas protein and guide RNA. However, low cleavage efficiency and off-target effects hamper the development and application of CRISPR/Cas systems. To predict cleavage efficiency and specificity, numerous computational approaches have been developed for scoring guide RNAs. Most scores are empirical or trained by experimental datasets, and scores are implemented using various computational methods. Herein, we discuss these approaches, focusing mainly on the features or computational methods they utilise. Furthermore, we summarise these tools and give some suggestions for their usage. We also recommend three versatile web-based tools with user-friendly interfaces and preferable functions. The review provides a comprehensive and up-to-date overview of computational approaches for guide RNA design that could help users to select the optimal tools for their research.

An Overview of Computational Tools of Nucleic Acid Binding Site Prediction for Site-specific Proteins and Nucleases

Understanding the interaction mechanism of proteins and nucleic acids is one of the most fundamental problems for genome editing with engineered nucleases. Due to some limitations of experimental investigations, computational methods have played an important role in obtaining the knowledge of protein-nucleic acid interaction. Over the past few years, dozens of computational tools have been used for identification of nucleic acid binding site for site-specific proteins and design of site-specific nucleases because of their significant advantages in genome editing. Here, we review existing widely-used computational tools for target prediction of site-specific proteins as well as off-target prediction of site-specific nucleases. This article provides a list of on-line prediction tools according to their features followed by the description of computational methods used by these tools, which range from various sequence mapping algorithms (like Bowtie, FetchGWI and BLAST) to different machine learning methods (such as Support Vector Machine, hidden Markov models, Random Forest, elastic network and deep neural networks). We also make suggestions on the further development in improving the accuracy of prediction methods. This survey will provide a reference guide for computational biologists working in the field of genome editing.

SpCas9 activity prediction by DeepSpCas9, a deep learning-based model with high generalization performance

We evaluated SpCas9 activities at 12,832 target sequences using a high-throughput approach based on a human cell library containing single-guide RNA-encoding and target sequence pairs. Deep learning-based training on this large dataset of SpCas9-induced indel frequencies led to the development of a SpCas9 activity-predicting model named DeepSpCas9. When tested against independently generated datasets (our own and those published by other groups), DeepSpCas9 showed high generalization performance. DeepSpCas9 is available at http://deepcrispr.info/DeepSpCas9.

Evaluation of the effects of sequence length and microsatellite instability on single-guide RNA activity and specificity

Clustered regularly interspaced short palindromic repeats (CRISPR)/Cas9 technology is effective for genome editing and now widely used in life science research. However, the key factors determining its editing efficiency and off-target cleavage activity for single-guide RNA (sgRNA) are poorly documented. Here, we systematically evaluated the effects of sgRNA length on genome editing efficiency and specificity. Results showed that sgRNA 5'-end lengths can alter genome editing activity. Although the number of predicted off-target sites significantly increased after sgRNA length truncation, sgRNAs with different lengths were highly specific. Because only a few predicted off-targets had detectable cleavage activity as determined by Target capture sequencing (TargetSeq). Interestingly, > 20% of the predicted off-targets contained microsatellites for selected sgRNAs targeting the dystrophin gene, which can produce genomic instability and interfere with accurate assessment of off-target cleavage activity. We found that sgRNA activity and specificity can be sensitively detected by TargetSeq in combination with in silico prediction. Checking whether the on- and off-targets contain microsatellites is necessary to improve the accuracy of analyzing the efficiency of genome editing. Our research provides new features and novel strategies for the accurate assessment of CRISPR sgRNA activity and specificity.

An overview of designing and selection of sgRNAs for precise genome editing by the CRISPR-Cas9 system in plants

A large number of computational tools have been documented in recent years for identification of target-specific valid single-guide (sg) RNAs (18-20 nucleotide long sequence) that is an important component for the efficient utilization of the CRISPR-Cas9 (clustered regularly interspaced short palindromic repeats-CRISPR-associated Protein) system. Despite optimization of Cas9, other major concerns are on-target efficiency and off-target activity that depend upon the sequence(s) of target-specific sgRNA(s). However, a very little attention has been paid for identification of the best-hit sgRNA for precise targeting as well as minimizing the off-target effects. The aim of this present work is to offer comparative insight into existing CRISPR software tools with their unique features (including targeted genome) and utilities. These available web tools were found to be designed based upon only a few limited mathematical models. Among all these available web tools, three (Benchling, Desktop and CRISPR-P) have been curated as exclusively available for plant genome-editing purpose. These three software tools have been comprehensively described and analyzed with single same target enquiry from two randomly selected genes (IDM2 and IDM3 from Arabidopsis thaliana). Interestingly, all these selected tools generated different results (sgRNAs) even for the same query. In fact, the sequence of sgRNA is considered an important parameter to determine the efficiency and specificity of sgRNAs for precise genome editing. Thus, there is an urgent requirement to pay attention for a validated sgRNA-designing tool for precise DNA editing in plants. In conclusion, this work will encourage building up a consensus for developing a universal valid sgRNA designing for different organisms including plants.

GRIBCG: a software for selection of sgRNAs in the design of balancer chromosomes

BACKGROUND

Balancer chromosomes are tools used by fruit fly geneticists to prevent meiotic recombination. Recently, CRISPR/Cas9 genome editing has been shown capable of generating inversions similar to the chromosomal rearrangements present in balancer chromosomes. Extending the benefits of balancer chromosomes to other multicellular organisms could significantly accelerate biomedical and plant genetics research.

RESULTS

Here, we present GRIBCG (Guide RNA Identifier for Balancer Chromosome Generation), a tool for the rational design of balancer chromosomes. GRIBCG identifies single guide RNAs (sgRNAs) for use with Streptococcus pyogenes Cas9 (SpCas9). These sgRNAs would efficiently cut a chromosome multiple times while minimizing off-target cutting in the rest of the genome. We describe the performance of this tool on six model organisms and compare our results to two routinely used fruit fly balancer chromosomes.

CONCLUSION

GRIBCG is the first of its kind tool for the design of balancer chromosomes using CRISPR/Cas9. GRIBCG can accelerate genetics research by providing a fast, systematic and simple to use framework to induce chromosomal rearrangements.

Optimized libraries for CRISPR-Cas9 genetic screens with multiple modalities

The creation of genome-wide libraries for CRISPR knockout (CRISPRko), interference (CRISPRi), and activation (CRISPRa) has enabled the systematic interrogation of gene function. Here, we show that our recently-described CRISPRko library (Brunello) is more effective than previously published libraries at distinguishing essential and non-essential genes, providing approximately the same perturbation-level performance improvement over GeCKO libraries as GeCKO provided over RNAi. Additionally, we present genome-wide libraries for CRISPRi (Dolcetto) and CRISPRa (Calabrese), and show in negative selection screens that Dolcetto, with fewer sgRNAs per gene, outperforms existing CRISPRi libraries and achieves comparable performance to CRISPRko in detecting essential genes. We also perform positive selection CRISPRa screens and demonstrate that Calabrese outperforms the SAM approach at identifying vemurafenib resistance genes. We further compare CRISPRa to genome-scale libraries of open reading frames (ORFs). Together, these libraries represent a suite of genome-wide tools to efficiently interrogate gene function with multiple modalities.

Review of CRISPR/Cas9 sgRNA Design Tools

The adaptive immunity system in bacteria and archaea, Clustered Regularly Interspaced Short Palindromic Repeats, CRISPR-associate (CRISPR/Cas), has been adapted as a powerful gene editing tool and got a broad application in genome research field due to its ease of use and cost-effectiveness. The performance of CRISPR/Cas relies on well-designed single-guide RNA (sgRNA), so a lot of bioinformatic tools have been developed to assist the design of highly active and specific sgRNA. These tools vary in design specifications, parameters, genomes and so on. To help researchers to choose their proper tools, we reviewed various sgRNA design tools, mainly focusing on their on-target efficiency prediction model and off-target detection algorithm.