Off-target Prediction Research Articles

CRISPRoffT: comprehensive database of CRISPR/Cas off-targets.

The CRISPR (clustered regularly interspaced short palindromic repeats)/Cas (CRISPR-associated protein) programmable nuclease system continues to evolve, with in vivo therapeutic gene editing increasingly applied in clinical settings. However, off-target effects remain a significant challenge, hindering its broader clinical application. To enhance the development of gene-editing therapies and the accuracy of prediction algorithms, we developed CRISPRoffT (https://ccsm.uth.edu/CRISPRoffT/). Users can access a comprehensive repository of off-target regions predicted and validated by a diverse range of technologies across various cell lines, Cas enzyme variants, engineered sgRNAs (single guide RNAs) and CRISPR editing systems. CRISPRoffT integrates results of off-target analysis from 74 studies, encompassing 29 experimental prediction techniques, 368 guide sequences, 226164 potential guide and off-target pairs and 8840 validated off-targets. CRISPRoffT features off-target data from different CRISPR approaches (knockout, base editing and prime editing) applied under diverse experimental conditions, including 85 different Cas/guide RNA (gRNA) combinations used across 34 different human and mouse cell lines. CRISPRoffT provides results of comparative analyses for individual guide sequences, genes, cell types, techniques and Cas/gRNA combinations under different conditions. CRISPRoffT is a unique resource providing valuable insights that facilitate the safety-driven design of CRISPR-based therapeutics, inform experimental design, advance the development of computational off-target prediction algorithms and guide RNA design algorithms.

Crispr-SGRU: Prediction of CRISPR/Cas9 Off-Target Activities with Mismatches and Indels Using Stacked BiGRU

CRISPR/Cas9 is a popular genome editing technology, yet its clinical application is hindered by off-target effects. Many deep learning-based methods are available for off-target prediction. However, few can predict off-target activities with insertions or deletions (indels) between single guide RNA and DNA sequence pairs. Additionally, the analysis of off-target data is challenged due to a data imbalance issue. Moreover, the prediction accuracy and interpretability remain to be improved. Here, we introduce a deep learning-based framework, named Crispr-SGRU, to predict off-target activities with mismatches and indels. This model is based on Inception and stacked BiGRU. It adopts a dice loss function to solve the inherent imbalance issue. Experimental results show our model outperforms existing methods for off-target prediction in terms of accuracy and robustness. Finally, we study the interpretability of this model through Deep SHAP and teacher–student-based knowledge distillation, and find it can provide meaningful explanations for sequence patterns regarding off-target activity.

Overcoming CRISPR-Cas9 off-target prediction hurdles: A novel approach with ESB rebalancing strategy and CRISPR-MCA model.

The off-target activities within the CRISPR-Cas9 system remains a formidable barrier to its broader application and development. Recent advancements have highlighted the potential of deep learning models in predicting these off-target effects, yet they encounter significant hurdles including imbalances within datasets and the intricacies associated with encoding schemes and model architectures. To surmount these challenges, our study innovatively introduces an Efficiency and Specificity-Based (ESB) class rebalancing strategy, specifically devised for datasets featuring mismatches-only off-target instances, marking a pioneering approach in this realm. Furthermore, through a meticulous evaluation of various One-hot encoding schemes alongside numerous hybrid neural network models, we discern that encoding and models of moderate complexity ideally balance performance and efficiency. On this foundation, we advance a novel hybrid model, the CRISPR-MCA, which capitalizes on multi-feature extraction to enhance predictive accuracy. The empirical results affirm that the ESB class rebalancing strategy surpasses five conventional methods in addressing extreme dataset imbalances, demonstrating superior efficacy and broader applicability across diverse models. Notably, the CRISPR-MCA model excels in off-target effect prediction across four distinct mismatches-only datasets and significantly outperforms contemporary state-of-the-art models in datasets comprising both mismatches and indels. In summation, the CRISPR-MCA model, coupled with the ESB rebalancing strategy, offers profound insights and a robust framework for future explorations in this field.

Multifaceted computational profiling of thymol and geraniol against the human proteome for bio-repellent alternatives: Toxicity predictions, degradation analysis, and quantum mechanical approaches

With growing interest in natural compounds as alternative mosquito repellents, assessing the toxicity and structure of potential repellent naturals like thymol (monoterpene phenol) and geraniol (monoterpene alcohol) is vital for understanding their stability and human impact. This study aimed to determine the structural, toxicity, and binding profiles of thymol and geraniol using computational predictions, xTB metadynamics, quantum mechanics, and principal component analysis. Toxicity studies using Protox-II, T.E.S.T, and SwissADME indicated that thymol and geraniol belong to toxicity class 4 and 5, respectively, with low toxicity predictions in other endpoints. Overall pharmacokinetic profile was generated via pkCSM. Off-target predictions via SwissTarget Predictions, LigTMap, Pharmapper, and SuperPred showed that these molecules can bind to 614 human proteins. The degradation of thymol and geraniol were performed using xTB metadynamics and the outcomes showed that the degradants for both compounds were stable and had lower toxicity profile. Nine tautomers were generated via quantum mechanics for thymol and four for geraniol, with RMSD ranging from 3.8 to 6.3 Å for thymol and 3.6 to 4 Å for geraniol after superimpositions. DFT studies found that HOMO-LUMO values and electronegativity parameters of thymol and geraniol did not differ significantly from their isomers. Binding affinity studies against 614 proteins, analysed via PCA and violin plots, highlighted the probable range of binding. These multifaceted in-silico findings corroborate the stability and potential utility of thymol and geraniol as safer alternatives in repellent applications.

A systematic method for solving data imbalance in CRISPR off-target prediction tasks

Accurately identifying potential off-target sites in the CRISPR/Cas9 system is crucial for improving the efficiency and safety of editing. However, the imbalance of available off-target datasets has posed a major obstacle in enhancing prediction performance. Despite several prediction models have been developed to address this issue, there remains a lack of systematic research on handling data imbalance in off-target prediction. This article systematically investigates the data imbalance issue in off-target datasets and explores numerous methods to process data imbalance from a novel perspective. First, we highlight the impact of the imbalance problem on off-target prediction tasks by determining the imbalance ratios present in these datasets. Then, we provide a comprehensive review of various sampling techniques and cost-sensitive methods to mitigate class imbalance in off-target datasets. Finally, systematic experiments are conducted on several state-of-the-art prediction models to illustrate the impact of applying data imbalance solutions. The results show that class imbalance processing methods significantly improve the off-target prediction capabilities of the models across multiple testing datasets. The code and datasets used in this study are available at https://github.com/gzrgzx/CRISPR_Data_Imbalance.

AttSiOff: a self-attention-based approach on siRNA design with inhibition and off-target effect prediction

Small interfering RNA (siRNA) is often used for function study and expression regulation of specific genes, as well as the development of small molecule drugs. Selecting siRNAs with high inhibition and low off-target effects from massive candidates is always a great challenge. Increasing experimentally-validated samples can prompt the development of machine-learning-based algorithms, including Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Graph Neural Network (GNN). However, these methods still suffer from limited accuracy and poor generalization in designing potent and specific siRNAs.In this study, we propose a novel approach for siRNA inhibition and off-target effect prediction, named AttSiOff. It combines a self-attention-based siRNA inhibition predictor with an mRNA searching package and an off-target filter. The predictor gives the inhibition score via analyzing the embedding of siRNA and local mRNA sequences, generated from the pre-trained RNA-FM model, as well as other meaningful prior-knowledge-based features. Self-attention mechanism can detect potentially decisive features, which may determine the inhibition of siRNA. It captures global and local dependencies more efficiently than normal convolutions. The tenfold cross-validation results indicate that our model outperforms all existing methods, achieving PCC of 0.81, SPCC of 0.84, and AUC of 0.886. It also reaches better performance of generalization and robustness on cross-dataset validation. In addition, the mRNA searching package could find all mature mRNAs for a given gene name from the GENOMES database, and the off-target filter can calculate the amount of unwanted off-target binding sites, which affects the specificity of siRNA. Experiments on five mature siRNA drugs, as well as a new target gene (AGT), show that AttSioff has excellent convenience and operability in practical applications.Graphical

Prediction of CRISPR/Cas9 off-target activity using multi-scale convolutional neural network

Clustered regularly interspaced short palindromic repeat/CRISPR-associated protein 9 (CRISPR/Cas9) is a new generation of gene editing technology, which relies on single guide RNA to identify specific gene sites and guide Cas9 nuclease to edit specific location in the genome. However, the off-target effect of this technology hampers its development. In recent years, several deep learning models have been developed for predicting the CRISPR/Cas9 off-target activity, which contributes to more efficient and safe gene editing and gene therapy. However, the prediction accuracy remains to be improved. In this paper, we proposed a multi-scale convolutional neural network-based method, designated as CnnCRISPR, for CRISPR/Cas9 off-target prediction. First, we used one-hot encoding method to encode the sgRNA-DNA sequence pair, followed by a bitwise or operation on the two binary matrices. Second, the encoded sequence was fed into the Inception-based network for training and evaluating. Third, the well-trained model was applied to evaluate the off-target situation of the sgRNA-DNA sequence pair. Experiments on public datasets showed CnnCRISPR outperforms existing deep learning-based methods, which provides an effective and feasible method for addressing the off-target problems.

CRISPR-M: Predicting sgRNA off-target effect using a multi-view deep learning network.

Using the CRISPR-Cas9 system to perform base substitutions at the target site is a typical technique for genome editing with the potential for applications in gene therapy and agricultural productivity. When the CRISPR-Cas9 system uses guide RNA to direct the Cas9 endonuclease to the target site, it may misdirect it to a potential off-target site, resulting in an unintended genome editing. Although several computational methods have been proposed to predict off-target effects, there is still room for improvement in the off-target effect prediction capability. In this paper, we present an effective approach called CRISPR-M with a new encoding scheme and a novel multi-view deep learning model to predict the sgRNA off-target effects for target sites containing indels and mismatches. CRISPR-M takes advantage of convolutional neural networks and bidirectional long short-term memory recurrent neural networks to construct a three-branch network towards multi-views. Compared with existing methods, CRISPR-M demonstrates significant performance advantages running on real-world datasets. Furthermore, experimental analysis of CRISPR-M under multiple metrics reveals its capability to extract features and validates its superiority on sgRNA off-target effect predictions.

In silico off-target profiling for enhanced drug safety assessment

Ensuring drug safety in the early stages of drug development is crucial to avoid costly failures in subsequent phases. However, the economic burden associated with detecting drug off-targets and potential side effects through in vitro safety screening and animal testing is substantial. Drug off-target interactions, along with the adverse drug reactions they induce, are significant factors affecting drug safety. To assess the liability of candidate drugs, we developed an artificial intelligence model for the precise prediction of compound off-target interactions, leveraging multi-task graph neural networks. The outcomes of off-target predictions can serve as representations for compounds, enabling the differentiation of drugs under various ATC codes and the classification of compound toxicity. Furthermore, the predicted off-target profiles are employed in adverse drug reaction (ADR) enrichment analysis, facilitating the inference of potential ADRs for a drug. Using the withdrawn drug Pergolide as an example, we elucidate the mechanisms underlying ADRs at the target level, contributing to the exploration of the potential clinical relevance of newly predicted off-target interactions. Overall, our work facilitates the early assessment of compound safety/toxicity based on off-target identification, deduces potential ADRs of drugs, and ultimately promotes the secure development of drugs.

CRISPR-DIPOFF: an interpretable deep learning approach for CRISPR Cas-9 off-target prediction.

CRISPR Cas-9 is a groundbreaking genome-editing tool that harnesses bacterial defense systems to alter DNA sequences accurately. This innovative technology holds vast promise in multiple domains like biotechnology, agriculture and medicine. However, such power does not come without its own peril, and one such issue is the potential for unintended modifications (Off-Target), which highlights the need for accurate prediction and mitigation strategies. Though previous studies have demonstrated improvement in Off-Target prediction capability with the application of deep learning, they often struggle with the precision-recall trade-off, limiting their effectiveness and do not provide proper interpretation of the complex decision-making process of their models. To address these limitations, we have thoroughly explored deep learning networks, particularly the recurrent neural network based models, leveraging their established success in handling sequence data. Furthermore, we have employed genetic algorithm for hyperparameter tuning to optimize these models' performance. The results from our experiments demonstrate significant performance improvement compared with the current state-of-the-art in Off-Target prediction, highlighting the efficacy of our approach. Furthermore, leveraging the power of the integrated gradient method, we make an effort to interpret our models resulting in a detailed analysis and understanding of the underlying factors that contribute to Off-Target predictions, in particular the presence of two sub-regions in the seed region of single guide RNA which extends the established biological hypothesis of Off-Target effects. To the best of our knowledge, our model can be considered as the first model combining high efficacy, interpretability and a desirable balance between precision and recall.

Interpretable CRISPR/Cas9 off-target activities with mismatches and indels prediction using BERT

Off-target effects of CRISPR/Cas9 can lead to suboptimal genome editing outcomes. Numerous deep learning-based approaches have achieved excellent performance for off-target prediction; however, few can predict the off-target activities with both mismatches and indels between single guide RNA (sgRNA) and target DNA sequence pair. In addition, data imbalance is a common pitfall for off-target prediction. Moreover, due to the complexity of genomic contexts, generating an interpretable model also remains challenged. To address these issues, firstly we developed a BERT-based model called CRISPR-BERT for enhancing the prediction of off-target activities with both mismatches and indels. Secondly, we proposed an adaptive batch-wise class balancing strategy to combat the noise exists in imbalanced off-target data. Finally, we applied a visualization approach for investigating the generalizable nucleotide position-dependent patterns of sgRNA-DNA pair for off-target activity. In our comprehensive comparison to existing methods on five mismatches-only datasets and two mismatches-and-indels datasets, CRISPR-BERT achieved the best performance in terms of AUROC and PRAUC. Besides, the visualization analysis demonstrated how implicit knowledge learned by CRISPR-BERT facilitates off-target prediction, which shows potential in model interpretability. Collectively, CRISPR-BERT provides an accurate and interpretable framework for off-target prediction, further contributes to sgRNA optimization in practical use for improved target specificity in CRISPR/Cas9 genome editing. The source code is available at https://github.com/BrokenStringx/CRISPR-BERT.

Combining Off-flow, a Nextflow-coded program, and whole genome sequencing reveals unintended genetic variation in CRISPR/Cas-edited iPSCs

Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-Cas nucleases and human induced pluripotent stem cell (iPSC) technology can reveal deep insight into the genetic and molecular bases of human biology and disease. Undesired editing outcomes, both on-target (at the edited locus) and off-target (at other genomic loci) hinder the application of CRISPR-Cas nucleases. We developed Off-flow, a Nextflow-coded bioinformatic workflow that takes a specific guide sequence and Cas protein input to call four separate off-target prediction programs (CHOPCHOP, Cas-Offinder, CRISPRitz, CRISPR-Offinder) to output a comprehensive list of predicted off-target sites. We applied it to whole genome sequencing (WGS) data to investigate the occurrence of unintended effects in human iPSCs that underwent repair or insertion of disease-related variants by homology-directed repair. Off-flow identified a 3-base-pair-substitution and a mono-allelic genomic deletion at the target loci, KCNQ2, in 2 clones. Unbiased WGS analysis further identified off-target missense variants and a mono-allelic genomic deletion at the targeted locus, GNAQ, in 10 clones. On-target substitution and deletions had escaped standard PCR and Sanger sequencing analysis, while missense variants at other genomic loci were not detected by Off-flow. We used these results to filter out iPSC clones for subsequent functional experiments. Off-flow, which we make publicly available, works for human and mouse genomes currently and can be adapted for other genomes. Off-flow and WGS analysis can improve the integrity of studies using CRISPR/Cas-edited cells and animal models.

YB-1 Is a Novel Target for the Inhibition of α-Adrenergic-Induced Hypertrophy.

Cardiac hypertrophy resulting from sympathetic nervous system activation triggers the development of heart failure. The transcription factor Y-box binding protein 1 (YB-1) can interact with transcription factors involved in cardiac hypertrophy and may thereby interfere with the hypertrophy growth process. Therefore, the question arises as to whether YB-1 influences cardiomyocyte hypertrophy and might thereby influence the development of heart failure. YB-1 expression is downregulated in human heart biopsies of patients with ischemic cardiomyopathy (n = 8), leading to heart failure. To study the impact of reduced YB-1 in cardiac cells, we performed small interfering RNA (siRNA) experiments in H9C2 cells as well as in adult cardiomyocytes (CMs) of rats. The specificity of YB-1 siRNA was analyzed by a miRNA-like off-target prediction assay identifying potential genes. Testing three high-scoring genes by transfecting cardiac cells with YB-1 siRNA did not result in downregulation of these genes in contrast to YB-1, whose downregulation increased hypertrophic growth. Hypertrophic growth was mediated by PI3K under PE stimulation, as well by downregulation with YB-1 siRNA. On the other hand, overexpression of YB-1 in CMs, caused by infection with an adenovirus encoding YB-1 (AdYB-1), prevented hypertrophic growth under α-adrenergic stimulation with phenylephrine (PE), but not under stimulation with growth differentiation factor 15 (GDF15; n = 10-16). An adenovirus encoding the green fluorescent protein (AdGFP) served as the control. YB-1 overexpression enhanced the mRNA expression of the Gq inhibitor regulator of G-protein signaling 2 (RGS2) under PE stimulation (n = 6), potentially explaining its inhibitory effect on PE-induced hypertrophic growth. This study shows that YB-1 protects cardiomyocytes against PE-induced hypertrophic growth. Like in human end-stage heart failure, YB-1 downregulation may cause the heart to lose its protection against hypertrophic stimuli and progress to heart failure. Therefore, the transcription factor YB-1 is a pivotal signaling molecule, providing perspectives for therapeutic approaches.

Abstract A045: Development of automated deep learning-based off-target distribution prediction system for CRISPR-Cas13 system

Abstract CRISPR-Cas13 RNA editing system is a new member of the CRISPR-Cas gene editing system family, which can perform guided editing on RNA sequence. CRISPR-Cas gene editing system is currently one of the breakthrough technologies in life science, which is easy to operate, has a high editing efficiency and theoretically can perform guided editing on genome of any species. CRISPR-Cas9 system is the most commonly used CRISPR-Cas system, but it is mainly applied to DNA. Hence, fornon-destructive gene therapy and RNA virus detection, CRISPR-Cas13 system has its unique advantage. However, there are severe issues limiting its application, the most important one of which is off-target effect, namely the guide RNA points system to the wrong position causing non-targeted region edited, which leading to wrong expression spectrum of the cell. Therefore, based on automated deep learning and transfer learning techniques, this project aims to establishing an off-target distribution prediction system of CRISPR-Cas13 RNA editing system, in order to make high-specificity RNA editing possible. Citation Format: Guohui Chuai, Yanjing Zhu. Development of automated deep learning-based off-target distribution prediction system for CRISPR-Cas13 system [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Tumor Immunology and Immunotherapy; 2023 Oct 1-4; Toronto, Ontario, Canada. Philadelphia (PA): AACR; Cancer Immunol Res 2023;11(12 Suppl):Abstract nr A045.

Genome-wide CRISPR off-target prediction and optimization using RNA-DNA interaction fingerprints

The powerful CRISPR genome editing system is hindered by its off-target effects, and existing computational tools achieved limited performance in genome-wide off-target prediction due to the lack of deep understanding of the CRISPR molecular mechanism. In this study, we propose to incorporate molecular dynamics (MD) simulations in the computational analysis of CRISPR system, and present CRISOT, an integrated tool suite containing four related modules, i.e., CRISOT-FP, CRISOT-Score, CRISOT-Spec, CRISORT-Opti for RNA-DNA molecular interaction fingerprint generation, genome-wide CRISPR off-target prediction, sgRNA specificity evaluation and sgRNA optimization of Cas9 system respectively. Our comprehensive computational and experimental tests reveal that CRISOT outperforms existing tools with extensive in silico validations and proof-of-concept experimental validations. In addition, CRISOT shows potential in accurately predicting off-target effects of the base editors and prime editors, indicating that the derived RNA-DNA molecular interaction fingerprint captures the underlying mechanisms of RNA-DNA interaction among distinct CRISPR systems. Collectively, CRISOT provides an efficient and generalizable framework for genome-wide CRISPR off-target prediction, evaluation and sgRNA optimization for improved targeting specificity in CRISPR genome editing.

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 5years, 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.

Prediction of base editor off-targets by deep learning

Due to the tolerance of mismatches between gRNA and targeting sequence, base editors frequently induce unwanted Cas9-dependent off-target mutations. Here, to develop models to predict such off-targets, we design gRNA-off- target pairs for adenine base editors (ABEs) and cytosine base editors (CBEs) and stably integrate them into the human cells. After five days of editing, we obtain valid efficiency datasets of 54,663 and 55,727 off-targets for ABEs and CBEs, respectively. We use the datasets to train deep learning models, resulting in ABEdeepoff and CBEdeepoff, which can predict off-target sites. We use these tools to predict off-targets for a panel of endogenous loci and achieve Spearman correlation values varying from 0.710 to 0.859. Finally, we develop an integrated tool that is freely accessible via an online web server http://www.deephf.com/#/bedeep/bedeepoff. These tools could facilitate minimizing the off-target effects of base editing.

Federated Learning in Computational Toxicology: An Industrial Perspective on the Effiris Hackathon.

In silico approaches have acquired a towering role in pharmaceutical research and development, allowing laboratories all around the world to design, create, and optimize novel molecular entities with unprecedented efficiency. From a toxicological perspective, computational methods have guided the choices of medicinal chemists toward compounds displaying improved safety profiles. Even if the recent advances in the field are significant, many challenges remain active in the on-target and off-target prediction fields. Machine learning methods have shown their ability to identify molecules with safety concerns. However, they strongly depend on the abundance and diversity of data used for their training. Sharing such information among pharmaceutical companies remains extremely limited due to confidentiality reasons, but in this scenario, a recent concept named "federated learning" can help overcome such concerns. Within this framework, it is possible for companies to contribute to the training of common machine learning algorithms, using, but not sharing, their proprietary data. Very recently, Lhasa Limited organized a hackathon involving several industrial partners in order to assess the performance of their federated learning platform, called "Effiris". In this paper, we share our experience as Roche in participating in such an event, evaluating the performance of the federated algorithms and comparing them with those coming from our in-house-only machine learning models. Our aim is to highlight the advantages of federated learning and its intrinsic limitations and also suggest some points for potential improvements in the method.

Deep-RPA: Vulnerability Classification of a Genome for CRISPR/Cas9 Off-targets

Background: Researchers working in genome engineering are making fast strides to precising the techniques of site-specific gene editing. CRISPR-Cas (Clustered Regularly Interspaced Short Palindromic Repeats) is one of the most recent gene editing techniques. It consists of a Cas9 nuclease and a single guided RNA (sgRNA) that targets DNA at the required target site. Consequently, along with on-targets, genomes may also have multiple off-targets, which is a potential drawback of gene editing techniques. Lab-based assays are used to examine the off-target effects of sgRNA. This challenge makes the technique questionable in terms of cost, time and efficacy. Deep learning techniques have been used efficiently to analyze biological data and calculate off-target sites in the genome. This research aims to identify CRISPR off-targets within the genome as well as predict genome vulnerability for unexpected mutations using a deep learning approach. Method: This study presents a two-step data preprocessing and off-target prediction method that may be used to determine genome instability. A raw DNA sequence was initially preprocessed and subdivided into 20-bp long multiple substrings. These substrings were further categorized into perfect matches and mismatches. Secondly, average weights were assigned based on the CFD (Cutting Frequency Determination) of the off-targets that showed the genome's vulnerability. Finally, the deep neural network model was trained using random genomic data. To identify off-targets and predict genome vulnerability, a Deep-RPA model was trained and tested on the DNA sequence of the Arabidopsis model plant. Results: The results demonstrated the accuracy and validity of Deep-RPA by accurately predicting off-targets and genome vulnerabilities on different sample sequences. The proposed model was evaluated through stratified five-fold cross-validation, which attained an average accuracy of 99 percent for predicting genome vulnerability. The results illustrated satisfactory improvement compared to existing solutions. Conclusion: The proposed design using a 1D CNN has shown significant improvement in text-based sequence analysis and has outperformed current methods by a wide margin.

Massively parallel CRISPR off-target detection enables rapid off-target prediction model building

CRISPR (clustered regularly interspaced short palindromic repeats) genome editing holds tremendous potential in clinical translation. However, the off-target effect has always been a major concern. Here, we have developed a novel sensitive and specific off-target detection method, AID-seq (adaptor-mediated off-target identification by sequencing), that can comprehensively and faithfully detect the low-frequency off targets generated by different CRISPR nucleases (including Cas9 and Cas12a). Based on AID-seq, we developed a pooled strategy to simultaneously identify the on/off targets of multiple gRNAs, as well as using mixed human and human papillomavirus (HPV) genomes to screen the most efficient and safe targets from 416 HPV gRNA candidates for antiviral therapy. Moreover, we used the pooled strategy with 2,069 single-guide RNAs (sgRNAs) at a pool size of about 500 to profile the properties of our newly discovered CRISPR, FrCas9. Importantly, we successfully built an off-target detection model using these off-target data via the CRISPR-Net deep learning method (area under the receiver operating characteristic curve [AUROC]= 0.97, area under the precision recall curve [AUPRC]= 0.29). To our knowledge, AID-seq is the most sensitive and specific invitro off-target detection method to date. And the pooled AID-seq strategy can be used as a rapid and high-throughput platform to select the best sgRNAs and characterize the properties of new CRISPRs. This work was supported by The National Natural Science Foundation of China (grant nos. 32171465 and 82102392), the General Program of Natural Science Foundation of Guangdong Province of China (grant no. 2021A1515012438), Guangdong Basic and Applied Basic Research Foundation (grant no. 2020A1515110170), and the National Ten Thousand Plan-Young Top Talents of China (grant no. 80000-41180002).