Learning to quantify uncertainty in off-target activity for CRISPR guide RNAs
Open accessPublished version of a preprint
Abstract
CRISPR-based genome editing technologies have revolutionised the field of molecular biology, offering unprecedented opportunities for precise genetic manipulation. However, off-target effects remain a significant challenge, potentially leading to unintended consequences and limiting the applicability of CRISPR-based genome editing technologies in clinical settings. Current literature predominantly focuses on point predictions for off-target activity, which may not fully capture the range of possible outcomes and associated risks. Here, we present crispAI, a neural network architecture-based approach for predicting uncertainty estimates for off-target cleavage activity, providing a more comprehensive risk assessment and facilitating improved decision-making in single guide RNA (sgRNA) design. Our approach makes use of the count noise model Zero Inflated Negative Binomial (ZINB) to model the uncertainty in the off-target cleavage activity data. In addition, we present the first-of-its-kind genome-wide sgRNA efficiency score, crispAI-aggregate, enabling prioritization among sgRNAs with similar point aggregate predictions by providing richer information compared to existing aggregate scores. We show that uncertainty estimates of our approach are calibrated and its predictive performance is superior to the state-of-the-art in silico off-target cleavage activity prediction methods. The tool and the trained models are available at https://github.com/furkanozdenn/crispr-offtarget-uncertainty.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Development and Applications of CRISPR-Cas9 for Genome Engineering
Hsu, P. D., Lander, E. S., & Zhang, F. (2014) · Cell · doi:10.1016/j.cell.2014.05.010 · Cited by 5,762 · see citing works
Genome-scale CRISPR-Cas9 knockout screening in human cells
Shalem, O., Sanjana, N. E., Hartenian, E., Shi, X., Scott, D. A., Mikkelsen, T. S., Heckl, D., Ebert, B. L., Root, D. E., Doench, J. G., et al. (2014) · Science · doi:10.1126/science.1247005 · Cited by 5,234 · see citing works
DNA targeting specificity of RNA-guided Cas9 nucleases
Hsu, P. D., Scott, D. A., Weinstein, J. A., Ran, F. A., Konermann, S., Agarwala, V., Li, Y., Fine, E. J., Wu, X., Shalem, O., et al. (2013) · Nature Biotechnology · doi:10.1038/nbt.2647 · Cited by 4,741 · see citing works
Optimized sgRNA design to maximize activity and minimize off-target effects of CRISPR-Cas9
Doench, J. G., Fusi, N., Sullender, M., Hegde, M., Vaimberg, E. W., Donovan, K. F., Smith, I., Tothova, Z., Wilen, C., Orchard, R., et al. (2016) · Nature Biotechnology · doi:10.1038/nbt.3437 · Cited by 4,637 · see citing works
Genetic screens in human cells using the CRISPR-Cas9 system
Wang, T., Wei, J. J., Sabatini, D. M., & Lander, E. S. (2014) · Science · doi:10.1126/science.1246981 · Cited by 2,856 · see citing works
CRISPOR: intuitive guide selection for CRISPR/Cas9 genome editing experiments and screens
Concordet, J., & Haeussler, M. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky354 · Cited by 2,354 · see citing works
Bae, S., Park, J., & Kim, J.-S. (2014) · Bioinformatics · doi:10.1093/bioinformatics/btu048 · Cited by 2,339 · see citing works
GUIDE-seq enables genome-wide profiling of off-target cleavage by CRISPR-Cas nucleases
Tsai, S. Q., Zheng, Z., Nguyen, N. T., Liebers, M., Topkar, V. V., Thapar, V., Wyvekens, N., Khayter, C., Iafrate, A. J., Le, L. P., et al. (2015) · Nature Biotechnology · doi:10.1038/nbt.3117 · Cited by 2,268 · see citing works
Normalization and microbial differential abundance strategies depend upon data characteristics
Weiss, S. J., Xu, Z. Z., Peddada, S. D., Amir, A., Bittinger, K. L., González, A., Lozupone, C., Zaneveld, J., Vázquez‐Baeza, Y., Birmingham, A., et al. (2017) · Microbiome · doi:10.1186/s40168-017-0237-y · Cited by 2,123 · see citing works
Rational design of highly active sgRNAs for CRISPR-Cas9-mediated gene inactivation
Doench, J. G., Hartenian, E., Graham, D. B., Tothova, Z., Hegde, M., Smith, I., Sullender, M., Ebert, B. L., Xavier, R. J., & Root, D. E. (2014) · Nature Biotechnology · doi:10.1038/nbt.3026 · Cited by 1,617 · see citing works
Analysis of off-target effects of CRISPR/Cas-derived RNA-guided endonucleases and nickases
Cho, S. W., Kim, S., Kim, Y., Kweon, J., Kim, H. S., Bae, S., & Kim, J.-S. (2014) · Genome Research · doi:10.1101/gr.162339.113 · Cited by 1,356 · see citing works
Off-target Effects in CRISPR/Cas9-mediated Genome Engineering
Zhang, X.-H., Tee, L. Y., Wang, X.-G., Huang, Q.-S., & Yang, S.-H. (2015) · Molecular Therapy - Nucleic Acids · doi:10.1038/mtna.2015.37 · Cited by 1,273 · see citing works
Proceedings of the 3rd International Conference on Neural Information Processing Systems
Lippmann, R. P., Moody, J. E., & Touretzky, D. S. (1990) · Cited by 1,204 · see citing works
CHOPCHOP: a CRISPR/Cas9 and TALEN web tool for genome editing
Montague, T. G., Cruz, J. M. B. S., Gagnon, J. A., Church, G. M., & Valen, E. (2014) · Nucleic Acids Research · doi:10.1093/nar/gku410 · Cited by 1,203 · see citing works
Pooling across cells to normalize single-cell RNA sequencing data with many zero counts
L. Lun, A. T., Bach, K., & Marioni, J. C. (2016) · Genome Biology · doi:10.1186/s13059-016-0947-7 · Cited by 1,108 · see citing works
CCTop: An intuitive, flexible and reliable CRISPR/Cas9 target prediction tool
Stemmer, M., Thumberger, T., del Sol Keyer, M., Wittbrodt, J., & Mateo, J. L. (2015) · PLoS ONE · doi:10.1371/journal.pone.0124633 · Cited by 1,088 · see citing works
Single-cell RNA-seq denoising using a deep count autoencoder
Eraslan, G., Simon, L. M., Mircea, M., Mueller, N. S., & Theis, F. J. (2019) · Nature Communications · doi:10.1038/s41467-018-07931-2 · Cited by 1,084 · see citing works
Applications of CRISPR technologies in research and beyond
Barrangou, R., & Doudna, J. A. (2016) · Nature Biotechnology · doi:10.1038/nbt.3659 · Cited by 1,005 · see citing works
Digenome-seq: Genome-wide profiling of CRISPR-cas9 off-target effects in human cells
Kim, D., Bae, S., Park, J., Kim, E., Kim, S., Yu, H. R., Hwang, J., Kim, J.-I., & Kim, J.-S. (2015) · Nature Methods · doi:10.1038/nmeth.3284 · Cited by 992 · see citing works
CRISPR-Cas Systems in Bacteria and Archaea: Versatile Small RNAs for Adaptive Defense and Regulation
Bhaya, D., Davison, M., & Barrangou, R. (2011) · Annual Review of Genetics · doi:10.1146/annurev-genet-110410-132430 · Cited by 914 · see citing works
CIRCLE-Seq: A highly sensitive in vitro screen for genome-wide CRISPR-cas9 nuclease off-targets
Tsai, S. Q., Nguyen, N. T., Malagon-Lopez, J., Topkar, V. V., Aryee, M. J., & Joung, J. K. (2017) · Nature Methods · doi:10.1038/nmeth.4278 · Cited by 814 · see citing works
A Python library for probabilistic analysis of single-cell omics data
Gayoso, A., Lopez, R., Xing, G., Boyeau, P., Valiollah Pour Amiri, V., Hong, J., Wu, K., Jayasuriya, M., Mehlman, E., Langevin, M., et al. (2022) · Nature Biotechnology · doi:10.1038/s41587-021-01206-w · Cited by 789 · see citing works
Bias, robustness and scalability in single-cell differential expression analysis
Soneson, C., & Robinson, M. D. (2018) · Nature Methods · doi:10.1038/nmeth.4612 · Cited by 770 · see citing works
DeepCRISPR: Optimized CRISPR guide RNA design by deep learning
Chuai, G., Ma, H., Yan, J., Chen, M., Hong, N., Xue, D., Zhou, C., Zhu, C., Chen, K., Duan, B., et al. (2018) · Genome biology · doi:10.1186/s13059-018-1459-4 · Cited by 641 · see citing works
Lin, Y., Cradick, T. J., Brown, M. T., Deshmukh, H., Ranjan, P., Sarode, N., Wile, B. M., Vertino, P. M., Stewart, F. J., & Bao, G. (2014) · Nucleic Acids Research · doi:10.1093/nar/gku402 · Cited by 634 · see citing works
Sequence determinants of improved CRISPR sgRNA design
Xu, H., Xiao, T., Chen, C.-H., Li, W., Meyer, C. A., Wu, Q., Wu, D., Cong, L., Zhang, F., Liu, J. S., et al. (2015) · Genome Research · doi:10.1101/gr.191452.115 · Cited by 625 · see citing works
CRISPR-Cas: biology, mechanisms and relevance
Hille, F., & Charpentier, E. (2016) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2015.0496 · Cited by 503 · see citing works
Latest Developed Strategies to Minimize the Off-Target Effects in CRISPR-Cas-Mediated Genome Editing
Naeem, M., Majeed, S., Hoque, M. Z., & Ahmad, I. (2020) · Cells · doi:10.3390/cells9071608 · Cited by 457 · see citing works
Mapping the genomic landscape of CRISPR-Cas9 cleavage
Cameron, P., Fuller, C. K., Donohoue, P. D., Jones, B. N., Thompson, M. S., Carter, M. M., Gradia, S., Vidal, B., Garner, E., Slorach, E. M., et al. (2017) · Nature Methods · doi:10.1038/nmeth.4284 · Cited by 443 · see citing works
Target specificity of the CRISPR‐Cas9 system
Wu, X., Kriz, A. J., & Sharp, P. A. (2014) · Quantitative Biology · doi:10.1007/s40484-014-0030-x · Cited by 373 · see citing works
Prediction of off-target activities for the end-to-end design of CRISPR guide RNAs
Listgarten, J., Weinstein, M., Kleinstiver, B. P., Sousa, A. A., Joung, J. K., Crawford, J., Gao, K., Hoang, L., Elibol, M., Doench, J. G., et al. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-017-0178-6 · Cited by 336 · see citing works
CHANGE-seq reveals genetic and epigenetic effects on CRISPR–Cas9 genome-wide activity
Lazzarotto, C. R., Malinin, N. L., Li, Y., Zhang, R., Yang, Y., Lee, G., Cowley, E., He, Y., Lan, X., Jividen, K., et al. (2020) · Nature Biotechnology · doi:10.1038/s41587-020-0555-7 · Cited by 283 · see citing works
Highly Parallel Profiling of Cas9 Variant Specificity
Schmid-Burgk, J. L., Gao, L., Li, D., Gardner, Z., Strecker, J., Lash, B., & Zhang, F. (2020) · Molecular Cell · doi:10.1016/j.molcel.2020.02.023 · Cited by 197 · see citing works
Predicting nucleosome positioning using a duration Hidden Markov Model
Xi, L., Fondufe‐Mittendorf, Y. N., Xia, L., et al. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-346 · Cited by 167 · see citing works
CRISPR-Cas9 off-targeting assessment with nucleic acid duplex energy parameters
Alkan, F., Wenzel, A., Anthon, C., Havgaard, J. H., & Gorodkin, J. (2018) · Genome biology · doi:10.1186/s13059-018-1534-x · Cited by 167 · see citing works
Naught all zeros in sequence count data are the same
Silverman, J. D., Roche, K. E., Mukherjee, S., & David, L. A. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.09.014 · Cited by 167 · see citing works
Sherkatghanad, Z., Abdar, M., Charlier, J., & Makarenkov, V. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad131 · Cited by 117 · see citing works
Lin, J., Zhang, Z., Zhang, S., Chen, J., & Wong, K. (2020) · Advanced Science · doi:10.1002/advs.201903562 · Cited by 101 · cited 5× · see citing works
“…trend for the ground truth CHANGE-seq detected activity values for four different coefficient of variation intervals (i.e., [0,10], [10,20], [20,30], [30,40]), where the detected frequency values for crispAI-predicted distributions with lower coefficient of variation values are higher than…”
BackgroundMethodInfluentialDeep learning improves the ability of sgRNA off-target propensity prediction
Liu, Q., Cheng, X., Liu, G., Li, B., & Liu, X. (2020) · BMC Bioinformatics · doi:10.1186/s12859-020-3395-z · Cited by 88 · see citing works
Liu, Q., He, D., & Xie, L. (2019) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1007480 · Cited by 85 · see citing works
Genome-wide CRISPR off-target prediction and optimization using RNA-DNA interaction fingerprints
Chen, Q., Chuai, G., Zhang, H., Tang, J., Duan, L., Guan, H., Li, W., Li, W., Wen, J., Zuo, E., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-42695-4 · Cited by 82 · see citing works
A unified statistical framework for single cell and bulk RNA sequencing data
Zhu, L., Lei, J., Devlin, B., & Roeder, K. (2018) · The Annals of Applied Statistics · doi:10.1214/17-aoas1110 · Cited by 77 · see citing works
Systematic decomposition of sequence determinants governing CRISPR/Cas9 specificity
Fu, R., He, W., Dou, J., Villarreal, O. D., Bedford, E., Wang, H. H., Hou, C., Zhang, L., Wang, Y., Ma, D., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-28028-x · Cited by 56 · see citing works
Synergizing CRISPR/Cas9 off-target predictions for ensemble insights and practical applications
Zhang, S., Li, X., Lin, Q., & Wong, K. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty748 · Cited by 38 · see citing works
Benchmarking and integrating genome-wide CRISPR off-target detection and prediction
Yan, J., Xue, D., Chuai, G., Gao, Y., Zhang, G., & Liu, Q. (2020) · Nucleic Acids Research · doi:10.1093/nar/gkaa930 · Cited by 34 · see citing works
Data imbalance in CRISPR off-target prediction
Gao, Y., Chuai, G., Yu, W., Qu, S., & Liu, Q. (2019) · Briefings in Bioinformatics · doi:10.1093/bib/bbz069 · Cited by 31 · see citing works
Zhang, Y., Long, Y., Yin, R., & Kwoh, C. K. (2020) · IEEE Access · doi:10.1109/access.2020.2989454 · Cited by 31 · see citing works
Mak, J. K., Störtz, F., & Mináry, P. (2022) · BMC Genomics · doi:10.1186/s12864-022-09012-7 · Cited by 24 · see citing works
piCRISPR: Physically informed deep learning models for CRISPR/Cas9 off-target cleavage prediction
Störtz, F., Mak, J. K., & Mináry, P. (2023) · Artificial Intelligence in the Life Sciences · doi:10.1016/j.ailsci.2023.100075 · Cited by 24 · see citing works
Zenil, H., & Mináry, P. (2019) · Nucleic Acids Research · doi:10.1093/nar/gkz750 · Cited by 19 · see citing works
Kirillov, B., Savitskaya, E. E., Panov, M., Ogurtsov, A. Y., Shabalina, S. A., Koonin, E. V., & Severinov, K. (2021) · Nucleic Acids Research · doi:10.1093/nar/gkab1065 · Cited by 17 · see citing works
Shvets, A. A., & Kolomeisky, A. B. (2017) · Biophysical Journal · doi:10.1016/j.bpj.2017.08.013 · Cited by 14 · see citing works
piCRISPR: Physically informed deep learning models for CRISPR/Cas9 off-target cleavage predictionPreprint
Störtz, F., Mak, J. Y. W., & Minary, P. (2021) · bioRxiv · doi:10.1101/2021.11.16.468799 · Cited by 12 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 2
- [13]Chen S.-A.A., Tran E. Optimizing precision genome editing through machine learning. Forest. 2019; 85: 1– 39.
- [40]Kuleshov V., Fenner N., Ermon S. Accurate uncertainties for deep learning using calibrated regression. International conference on machine learning. 2018; PMLR 2796– 2804.
- Authors
- Özden, F., & Minary, P.
- Affiliations
- University of Oxford (GB)
- Department of Computer Science, University of Oxford , Oxford OX1 3QD ,
- Corresponding author
- Özden, Furkan
- Venue
- Nucleic Acids Research
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-09-14
- Volume
- 52
- Issue
- 18
- Pages
- e87-e87
- ISSN
- 0305-1048 (ISSN-L)
- 1362-4962
- PMC
- PMC11472043
- OpenAlex
- W4402553713
- Cited by
- 21
- References
- 54
- Citations by year
- 2026: 11 · 2025: 9 · 2024: 1
- FWCI
- 2.85
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Nucleic Acids Research (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › CRISPR and Genetic Engineering
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA regulation and disease
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA Interference and Gene Delivery
- Keywords
- guide RNA design, uncertainty quantification, zero-inflated negative binomial regression, neural network prediction, risk assessment
- MeSH terms
- Gene Editing, RNA, Guide, CRISPR-Cas Systems, Humans, Neural Networks, Computer, Uncertainty, Clustered Regularly Interspaced Short Palindromic Repeats, CRISPR-Cas Systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
