Predicting prime editing efficiency and product purity by deep learning

Mathis, Nicolas; Allam, Ahmed; Kissling, Lucas; Marquart, Kim Fabiano; Schmidheini, Lukas; Solari, Cristina; Balázs, Zsolt; Krauthammer, Michael; Schwank, Gerald

doi:10.1038/s41587-022-01613-7

Cited by 56 publications

(72 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fourth, current state-of-the-art technologies for improving prime editing efficiency mainly rely on enhancing the robustness of the prime editing core complex 10,11,[13][14][15] , machine learning-based prediction of target site efficiencies 10,14,15 , and transient suppression of the MMR pathway 11,12 . While these approaches have yielded encouraging results (especially when used in combination), there are notable limitations.…”

Section: Discussionmentioning

confidence: 99%

“…A counterpoint to this promise is that the efficiency of prime editing at an endogenous locus is generally low and highly variable across target sites 1,[10][11][12] . Factors impacting this efficiency are likely to include: 1) the properties of the prime editing ribonucleoprotein (RNP) complex itself; 2) the primary sequence of the target and programmed edit; 3) trans-acting factors such as the endogenous DNA repair proteins involved in the installation of edits; and 4) the cis-chromatin context where the target resides.…”

Section: Introductionmentioning

confidence: 99%

“…For the second factor, the impact of the target sequence and the edit sequence has been examined in the context of various kinds of edits (e.g. substitutions and indels), and corresponding machine learning models have been generated to facilitate design 10,14,15 . For the third factor, a rate-limiter for prime editing is DNA mismatch repair (MMR), which detects the intermediate product of prime editing and efficiently repairs the edited strand.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Chromatin context-dependent regulation and epigenetic manipulation of prime editing

Chen

Martin

et al. 2023

Preprint

View full text Add to dashboard Cite

Prime editing is a powerful means of introducing precise changes to specific locations in mammalian genomes. However, the widely varying efficiency of prime editing across target sites of interest has limited its adoption in the context of both basic research and clinical settings. Here, we set out to exhaustively characterize the impact of the cis-chromatin environment on prime editing efficiency. Using a newly developed and highly sensitive method for mapping the genomic locations of a randomly integrated "sensor", we identify specific epigenetic features that strongly correlate with the highly variable efficiency of prime editing across different genomic locations. Next, to assess the interaction of trans-acting factors with the cis-chromatin environment, we develop and apply a pooled genetic screening approach with which the impact of knocking down various DNA repair factors on prime editing efficiency can be stratified by cis-chromatin context. Finally, we demonstrate that we can dramatically modulate the efficiency of prime editing through epigenome editing, i.e. altering chromatin state in a locus-specific manner in order to increase or decrease the efficiency of prime editing at a target site. Looking forward, we envision that the insights and tools described here will broaden the range of both basic research and therapeutic contexts in which prime editing is useful.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Chromatin context-dependent regulation and epigenetic manipulation of prime editing

Chen

Martin

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, some studies have deployed self-explaining deep learning models for CRISPR outcome predictions, in which the interpretability is performed by an attention module, intrinsic to the neural network [40][41][42]. Among these, AttCRISPR [40] is an ensemble of CNN and RNN methods trained on the DeepHF dataset [43].…”

Section: Explainable DL and Genome Engineeringmentioning

confidence: 99%

The Promise of Explainable Deep Learning for Omics Data Analysis: Adding New Discovery Tools to AI

Santorsola¹,

Lescai²

2023

Preprint

View full text Add to dashboard Cite

Deep learning has already revolutionised the way we process a wide range of data, in many areas of our daily life. The ability to learn abstractions and relationships from heterogeneous data, has provided impressively accurate prediction and classification tools to handle increasingly big datasets. This has a significant impact on the growing wealth of omics datasets, with the unprecedented opportunity for a better understanding of the complexity of living organisms. While this revolution is transforming the way we analyse these data, explainable deep learning is emerging as an additional tool with the potential to change the way we interpret biological data. Explainability addresses critical issues such as transparency, so important when computational tools are introduced especially in clinical environments. Moreover, it empowers artificial intelligence with the capability to provide new insights in the input data, thus adding an element of discovery to these already powerful resources. In this review we provide an overview of the transformative effects explainable deep learning is having on multiple sectors, ranging from genome engineering and genomics, from radiomics to drug design and clinical trials. We offer a perspective to life scientists, to better understand the potential of these tools, and a motivation to implement them in their research, by suggesting learning resources they can use to move their first steps in this field.

show abstract

“…Furthermore, current evidence suggests that there is little predictability in pegRNA design and efficacy, and although efforts have been made to further elucidate design criteria of pegRNAs, only little improvement has been made in this regard since the initial description of prime editors by Anzalone and colleagues (Anzalone et al, 2019;Kim H. K. et al, 2021). Thus, identifying novel effective pegRNAs is currently accomplished by labor-intensive manual screening, which has been somewhat aided by pegRNA design tools developed by us and others (Anderson et al, 2021;Chow et al, 2021;Hsu et al, 2021;Hwang et al, 2021;Siegner et al, 2021;Standage-Beier et al, 2021;Mathis et al, 2023). Alternatively, candidate pegRNAs can be identified using large-scale screening approaches, allowing simultaneous testing of a high number of pegRNAs for new targets (Kim H. K. et al, 2021;Jang et al, 2021;Yarnall et al, 2022).…”

Section: In Vivo Prime Editing Of Hscs Is On the Horizonmentioning

confidence: 99%

Prime editing in hematopoietic stem cells—From ex vivo to in vivo CRISPR-based treatment of blood disorders

Wolff

Mikkelsen

2023

Front. Genome Ed.

View full text Add to dashboard Cite

Prime editing of human hematopoietic stem cells has the potential to become a safe and efficient way of treating diseases of the blood directly in patients. By allowing site-targeted gene intervention without homology-directed repair donor templates and DNA double-stranded breaks, the invention of prime editing fuels the exploration of alternatives to conventional recombination-based ex vivo genome editing of hematopoietic stem cells. Prime editing is as close as we get today to a true genome editing drug that does not require a separate DNA donor. However, to adapt the technology to perform in vivo gene correction, key challenges remain to be solved, such as identifying effective prime editing guide RNAs for clinical targets as well as developing efficient vehicles to deliver prime editors to stem cells in vivo. In this review, we summarize the current progress in delivery of prime editors both in vitro and in vivo and discuss future challenges that need to be adressed to allow in vivo prime editing as a cure for blood disorders.

show abstract

Predicting prime editing efficiency and product purity by deep learning

Cited by 56 publications

References 44 publications

Chromatin context-dependent regulation and epigenetic manipulation of prime editing

Chromatin context-dependent regulation and epigenetic manipulation of prime editing

The Promise of Explainable Deep Learning for Omics Data Analysis: Adding New Discovery Tools to AI

Prime editing in hematopoietic stem cells—From ex vivo to in vivo CRISPR-based treatment of blood disorders

Contact Info

Product

Resources

About