Enhancing CRISPR-Cas9 gRNA efficiency prediction by data integration and deep learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Xiang X
PROVIDER: S-EPMC8163799 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:MotivationCRISPR/Cas9 technology has been revolutionizing the field of gene editing in recent years. Guide RNAs (gRNAs) enable Cas9 proteins to target specific genomic loci for editing. However, editing efficiency varies between gRNAs. Thus, computational methods were developed to predict editing efficiency for any gRNA of interest. High-throughput datasets of Cas9 editing efficiencies were produced to train machine-learning models to predict editing efficiency. However, these high-throughput datasets have low correlation with functional and endogenous editing. Another difficulty arises from the fact that functional and endogenous editing efficiency is more difficult to measure, and as a result, functional and endogenous datasets are too small to train accurate machine-learning models on.ResultsWe developed DeepCRISTL, a deep-learning model to predict the on-target efficiency given a gRNA sequence. DeepCRISTL takes advantage of high-throughput datasets to learn general patterns of gRNA on-target editing efficiency, and then uses transfer learning (TL) to fine-tune the model and fit it to the functional and endogenous prediction task. We pre-trained the DeepCRISTL model on more than 150 000 gRNAs, produced through the DeepHF study as a high-throughput dataset of three Cas9 enzymes. We improved the DeepHF model by multi-task and ensemble techniques and achieved state-of-the-art results over each of the three enzymes: up to 0.89 in Spearman correlation between predicted and measured on-target efficiencies. To fine-tune model weights to predict on-target efficiency of functional or endogenous datasets, we tested several TL approaches, with gradual learning being the overall best performer, both when pre-trained on DeepHF and when pre-trained on CRISPROn, another high-throughput dataset. DeepCRISTL outperformed state-of-the-art methods on all functional and endogenous datasets. Using saliency maps, we identified and compared the important features learned by the model in each dataset. We believe DeepCRISTL will improve prediction performance in many other CRISPR/Cas9 editing contexts by leveraging TL to utilize both high-throughput datasets, and smaller and more biologically relevant datasets, such as functional and endogenous datasets.Availability and implementationDeepCRISTL is available via github.com/OrensteinLab/DeepCRISTL.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9235512 | biostudies-literature
Project description:MotivationCRISPR/Cas9 technology has been revolutionizing the field of gene editing. Guide RNAs (gRNAs) enable Cas9 proteins to target specific genomic loci for editing. However, editing efficiency varies between gRNAs and so computational methods were developed to predict editing efficiency for any gRNA of interest. High-throughput datasets of Cas9 editing efficiencies were produced to train machine-learning models to predict editing efficiency. However, these high-throughput datasets have a low correlation with functional and endogenous datasets, which are too small to train accurate machine-learning models on.ResultsWe developed DeepCRISTL, a deep-learning model to predict the editing efficiency in a specific cellular context. DeepCRISTL takes advantage of high-throughput datasets to learn general patterns of gRNA editing efficiency and then fine-tunes the model on functional or endogenous data to fit a specific cellular context. We tested two state-of-the-art models trained on high-throughput datasets for editing efficiency prediction, our newly improved DeepHF and CRISPRon, combined with various transfer-learning approaches. The combination of CRISPRon and fine-tuning all model weights was the overall best performer. DeepCRISTL outperformed state-of-the-art methods in predicting editing efficiency in a specific cellular context on functional and endogenous datasets. Using saliency maps, we identified and compared the important features learned by DeepCRISTL across cellular contexts. We believe DeepCRISTL will improve prediction performance in many other CRISPR/Cas9 editing contexts by leveraging transfer learning to utilize both high-throughput datasets and smaller and more biologically relevant datasets.Availability and implementationDeepCRISTL is available via https://github.com/OrensteinLab/DeepCRISTL.
| S-EPMC11319645 | biostudies-literature
Project description:The CRISPR/Cas9 system is a powerful, revolutionary tool for genome editing. However, it is not without limitations. There are PAM-free and CRISPR-tolerant regions that cannot be modified by the standard CRISPR/Cas9 system, and off-target activity impedes its broader applications. To avoid these drawbacks, we developed a very simple CRISPR/Cas9-assisted gRNA-free one-step (CAGO) genome editing technique which does not require the construction of a plasmid to express a specific gRNA. Instead, a universal N20 sequence with a very high targeting efficiency is inserted into the E. coli chromosome by homologous recombination, which in turn undergoes a double-stranded break by CRISPR/Cas9 and induces an intra-chromosomal recombination event to accomplish the editing process. This technique was shown to be able to edit PAM-free and CRISPR-tolerant regions with no off-target effects in Escherichia coli. When applied to multi-locus editing, CAGO was able to modify one locus in two days with a near 100% editing efficiency. Furthermore, modified CAGO was used to edit large regions of up to 100 kbp with at least 75% efficiency. Finally, genome editing by CAGO only requires a transformation procedure and the construction of a linear donor DNA cassette, which was further simplified by applying a modular design strategy. Although the technique was established in E. coli, it should be applicable to other organisms with only minor modifications.
| S-EPMC5709385 | biostudies-literature
Project description:The CRISPR/Cas9 system is an RNA guided nuclease system that evolved as a mechanism of adaptive immunity in bacteria. This system has been adopted for numerous genome engineering applications in research and recently, therapeutics. The CRISPR/Cas9 system has been largely implemented by delivery of Cas9 as protein, RNA, or plasmid along with a chimeric crRNA-tracrRNA guide RNA (gRNA) under the expression of a pol III promoter, such as U6. Using this approach, multiplex genome engineering has been achieved by delivering several U6-gRNA plasmids targeting multiple loci. However, this approach is limited due to the efficiently of delivering multiple plasmids to a single cell at one time. To augment the capability and accessibility of multiplexed genome engineering, we developed an efficient golden gate based method to assemble gRNAs linked by optimal Csy4 ribonuclease sequences to deliver up to 10 gRNAs as a single gRNA array transcript. Here we report the optimal expression of our guide RNA array under a strong pol II promoter. This system can be implemented alongside the myriad of CRISPR applications, allowing users to model complex biological processes requiring numerous gRNAs.
| S-EPMC6141065 | biostudies-literature
Project description: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.
| S-EPMC6948960 | biostudies-literature
Project description:The current predictive modeling techniques applied to Density Functional Theory (DFT) computations have helped accelerate the process of materials discovery by providing significantly faster methods to scan materials candidates, thereby reducing the search space for future DFT computations and experiments. However, in addition to prediction error against DFT-computed properties, such predictive models also inherit the DFT-computation discrepancies against experimentally measured properties. To address this challenge, we demonstrate that using deep transfer learning, existing large DFT-computational data sets (such as the Open Quantum Materials Database (OQMD)) can be leveraged together with other smaller DFT-computed data sets as well as available experimental observations to build robust prediction models. We build a highly accurate model for predicting formation energy of materials from their compositions; using an experimental data set of [Formula: see text] observations, the proposed approach yields a mean absolute error (MAE) of [Formula: see text] eV/atom, which is significantly better than existing machine learning (ML) prediction modeling based on DFT computations and is comparable to the MAE of DFT-computation itself.
| S-EPMC6874674 | biostudies-literature
Project description:The choice of guide RNA (gRNA) for CRISPR-based gene targeting is an essential step in gene editing applications, but the prediction of gRNA specificity remains challenging. Lack of transparency and focus on point estimates of efficiency disregarding the information on possible error sources in the model limit the power of existing Deep Learning-based methods. To overcome these problems, we present a new approach, a hybrid of Capsule Networks and Gaussian Processes. Our method predicts the cleavage efficiency of a gRNA with a corresponding confidence interval, which allows the user to incorporate information regarding possible model errors into the experimental design. We provide the first utilization of uncertainty estimation in computational gRNA design, which is a critical step toward accurate decision-making for future CRISPR applications. The proposed solution demonstrates acceptable confidence intervals for most test sets and shows regression quality similar to existing models. We introduce a set of criteria for gRNA selection based on off-target cleavage efficiency and its variance and present a collection of pre-computed gRNAs for human chromosome 22. Using Neural Network Interpretation methods, we show that our model rediscovers an established biological factor underlying cleavage efficiency, the importance of the seed region in gRNA.
| S-EPMC8789050 | biostudies-literature
Project description:BACKGROUND:The CRISPR-Cas9 system is a powerful and versatile tool for crop genome editing. However, achieving highly efficient and specific editing in polyploid species can be a challenge. The efficiency and specificity of the CRISPR-Cas9 system depends critically on the gRNA used. Here, we assessed the activities and specificities of seven gRNAs targeting 5-enolpyruvylshikimate-3-phosphate synthase (EPSPS) in hexaploid wheat protoplasts. EPSPS is the biological target of the widely used herbicide glyphosate. RESULTS:The seven gRNAs differed substantially in their on-target activities, with mean indel frequencies ranging from 0% to approximately 20%. There was no obvious correlation between experimentally determined and in silico predicted on-target gRNA activity. The presence of a single mismatch within the seed region of the guide sequence greatly reduced but did not abolish gRNA activity, whereas the presence of an additional mismatch, or the absence of a PAM, all but abolished gRNA activity. Large insertions (?20?bp) of DNA vector-derived sequence were detected at frequencies up to 8.5% of total indels. One of the gRNAs exhibited several properties that make it potentially suitable for the development of non-transgenic glyphosate resistant wheat. CONCLUSIONS:We have established a rapid and reliable method for gRNA validation in hexaploid wheat protoplasts. The method can be used to identify gRNAs that have favourable properties. Our approach is particularly suited to polyploid species, but should be applicable to any plant species amenable to protoplast transformation.
| S-EPMC6829922 | biostudies-literature
Project description:CRISPR/Cas9 technology enables efficient, rapid and cost-effective targeted genomic modification in a wide variety of cellular contexts including cultured cells. Some applications such as generation of double knock-outs, large deletions and paired-nickase cleavage require simultaneous expression of two gRNAs. Although single plasmids that enable multiplex expression of gRNAs have been developed, these require multiple rounds of cloning and/or PCR for generation of the desired construct. Here, we describe a series of vectors that enable generation of customized dual-gRNA expression constructs via an easy one-step golden gate cloning reaction using two annealed oligonucleotide inserts with different overhangs. Through nucleofection of mouse embryonic stem cells, we demonstrate highly efficient cleavage of the target loci using the dual-guide plasmids, which are available as Cas9-nuclease or Cas9-nickase expression constructs, with or without selection markers. These vectors are a valuable addition to the CRISPR/Cas9 toolbox and will be made available to all interested researchers via the Addgene plasmid repository.
| S-EPMC5718404 | biostudies-literature
Project description:Recent years have seen the development of computational tools to assist researchers in performing CRISPR-Cas9 experiment optimally. More specifically, these tools aim to maximize on-target activity (guide efficiency) while also minimizing potential off-target effects (guide specificity) by analyzing the features of the target site. Nonetheless, currently available tools cannot robustly predict experimental success as prediction accuracy depends on the approximations of the underlying model and how closely the experimental setup matches the data the model was trained on. Here, we present an overview of the available computational tools, their current limitations and future considerations. We discuss new trends around personalized health by taking genomic variants into account when predicting target sites as well as discussing other governing factors that can improve prediction accuracy.
| S-EPMC6052051 | biostudies-literature