SynDesign: web-based prime editing guide RNA design and evaluation tool for saturation genome editing.

Saturation genome editing (SGE) enables in-depth functional evaluation of disease-associated genes and variants by generating all possible single nucleotide variants (SNVs) within a given coding region. Although prime editing can be employed for inducing these SNVs, designing efficient prime editing guide RNAs (pegRNAs) can be challenging and time-consuming. Here, we present SynDesign, an easy-to-use webtool for the design, evaluation, and construction precision pegRNA libraries for SGE with synonymous mutation markers. SynDesign offers a simple yet powerful interface that automates the generation of all feasible pegRNA designs for a target gene or variant of interest. The pegRNAs are selected using the state-of-the-art models to predict prime editing efficiencies for various prime editors and cell types. Top-scoring pegRNA designs are further enhanced using synonymous mutation markers which improve pegRNA efficiency by diffusing the cellular mismatch repair mechanism and serve as sequence markers for improved identification of intended edits following deep sequencing. SynDesign is expected to facilitate future research using SGE to investigate genes or variants of interest associated with human diseases. SynDesign is freely available at https://deepcrispr.info/SynDesign without a login process.

Deep learning models to predict the editing efficiencies and outcomes of diverse base editors.

Applications of base editing are frequently restricted by the requirement for a protospacer adjacent motif (PAM), and selecting the optimal base editor (BE) and single-guide RNA pair (sgRNA) for a given target can be difficult. To select for BEs and sgRNAs without extensive experimental work, we systematically compared the editing windows, outcomes and preferred motifs for seven BEs, including two cytosine BEs, two adenine BEs and three C•G to G•C BEs at thousands of target sequences. We also evaluated nine Cas9 variants that recognize different PAM sequences and developed a deep learning model, DeepCas9variants, for predicting which variants function most efficiently at sites with a given target sequence. We then develop a computational model, DeepBE, that predicts editing efficiencies and outcomes of 63 BEs that were generated by incorporating nine Cas9 variants as nickase domains into the seven BE variants. The predicted median efficiencies of BEs with DeepBE-based design were 2.9- to 20-fold higher than those of rationally designed SpCas9-containing BEs.

Massively parallel evaluation and computational prediction of the activities and specificities of 17 small Cas9s.

Recently, various small Cas9 orthologs and variants have been reported for use in in vivo delivery applications. Although small Cas9s are particularly suited for this purpose, selecting the most optimal small Cas9 for use at a specific target sequence continues to be challenging. Here, to this end, we have systematically compared the activities of 17 small Cas9s for thousands of target sequences. For each small Cas9, we have characterized the protospacer adjacent motif and determined optimal single guide RNA expression formats and scaffold sequence. High-throughput comparative analyses revealed distinct high- and low-activity groups of small Cas9s. We also developed DeepSmallCas9, a set of computational models predicting the activities of the small Cas9s at matched and mismatched target sequences. Together, this analysis and these computational models provide a useful guide for researchers to select the most suitable small Cas9 for specific applications.

Prediction of efficiencies for diverse prime editing systems in multiple cell types.

Applications of prime editing are often limited due to insufficient efficiencies, and it can require substantial time and resources to determine the most efficient pegRNAs and prime editors (PEs) to generate a desired edit under various experimental conditions. Here, we evaluated prime editing efficiencies for a total of 338,996 pairs of pegRNAs including 3,979 epegRNAs and target sequences in an error-free manner. These datasets enabled a systematic determination of factors affecting prime editing efficiencies. Then, we developed computational models, named DeepPrime and DeepPrime-FT, that can predict prime editing efficiencies for eight prime editing systems in seven cell types for all possible types of editing of up to 3 base pairs. We also extensively profiled the prime editing efficiencies at mismatched targets and developed a computational model predicting editing efficiencies at such targets. These computational models, together with our improved knowledge about prime editing efficiency determinants, will greatly facilitate prime editing applications.

Prediction of Base Editing Efficiencies and Outcomes Using DeepABE and DeepCBE.

Adenine base editors (ABEs) and cytosine base editors (CBEs) have been widely used to introduce disease-relevant point mutations at target DNA sites of interest. However, the introduction of point mutations using base editors can be difficult due to low editing efficiencies and/or the existence of multiple target nucleotides within the base editing window at the target site. Thus, previous works have relied heavily on experimentally evaluating the base editing efficiencies and outcomes using time-consuming and labor-intensive multi-step experimental processes. DeepABE and DeepCBE are deep learning-based computational models to predict the efficiencies and outcome frequencies of ABE and CBE at given target DNA sites, in silico. Here, we describe the step-by-step procedure for the accurate determination of specific target nucleotides for ABE or CBE editing on the online available web tool, (DeepBaseEditor, https://deepcrispr.info/DeepBaseEditor ).

High-throughput functional evaluation of human cancer-associated mutations using base editors.

Comprehensive phenotypic characterization of the many mutations found in cancer tissues is one of the biggest challenges in cancer genomics. In this study, we evaluated the functional effects of 29,060 cancer-related transition mutations that result in protein variants on the survival and proliferation of non-tumorigenic lung cells using cytosine and adenine base editors and single guide RNA (sgRNA) libraries. By monitoring base editing efficiencies and outcomes using surrogate target sequences paired with sgRNA-encoding sequences on the lentiviral delivery construct, we identified sgRNAs that induced a single primary protein variant per sgRNA, enabling linking those mutations to the cellular phenotypes caused by base editing. The functions of the vast majority of the protein variants (28,458 variants, 98%) were classified as neutral or likely neutral; only 18 (0.06%) and 157 (0.5%) variants caused outgrowing and likely outgrowing phenotypes, respectively. We expect that our approach can be extended to more variants of unknown significance and other tumor types.

Recording of elapsed time and temporal information about biological events using Cas9.

DNA has not been utilized to record temporal information, although DNA has been used to record biological information and to compute mathematical problems. Here, we found that indel generation by Cas9 and guide RNA can occur at steady rates, in contrast to typical dynamic biological reactions, and the accumulated indel frequency can be a function of time. By measuring indel frequencies, we developed a method for recording and measuring absolute time periods over hours to weeks in mammalian cells. These time-recordings were conducted in several cell types, with different promoters and delivery vectors for Cas9, and in both cultured cells and cells of living mice. As applications, we recorded the duration of chemical exposure and the lengths of elapsed time since the onset of biological events (e.g., heat exposure and inflammation). We propose that our systems could serve as synthetic "DNA clocks."

Predicting the efficiency of prime editing guide RNAs in human cells.

Prime editing enables the introduction of virtually any small-sized genetic change without requiring donor DNA or double-strand breaks. However, evaluation of prime editing efficiency requires time-consuming experiments, and the factors that affect efficiency have not been extensively investigated. In this study, we performed high-throughput evaluation of prime editor 2 (PE2) activities in human cells using 54,836 pairs of prime editing guide RNAs (pegRNAs) and their target sequences. The resulting data sets allowed us to identify factors affecting PE2 efficiency and to develop three computational models to predict pegRNA efficiency. For a given target sequence, the computational models predict efficiencies of pegRNAs with different lengths of primer binding sites and reverse transcriptase templates for edits of various types and positions. Testing the accuracy of the predictions using test data sets that were not used for training, we found Spearman's correlations between 0.47 and 0.81. Our computational models and information about factors affecting PE2 efficiency will facilitate practical application of prime 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.

Prediction of the sequence-specific cleavage activity of Cas9 variants.

Several Streptococcus pyogenes Cas9 (SpCas9) variants have been developed to improve an enzyme's specificity or to alter or broaden its protospacer-adjacent motif (PAM) compatibility, but selecting the optimal variant for a given target sequence and application remains difficult. To build computational models to predict the sequence-specific activity of 13 SpCas9 variants, we first assessed their cleavage efficiency at 26,891 target sequences. We found that, of the 256 possible four-nucleotide NNNN sequences, 156 can be used as a PAM by at least one of the SpCas9 variants. For the high-fidelity variants, overall activity could be ranked as SpCas9 ≥ Sniper-Cas9 > eSpCas9(1.1) > SpCas9-HF1 > HypaCas9 ≈ xCas9 >> evoCas9, whereas their overall specificities could be ranked as evoCas9 >> HypaCas9 ≥ SpCas9-HF1 ≈ eSpCas9(1.1) > xCas9 > Sniper-Cas9 > SpCas9. Using these data, we developed 16 deep-learning-based computational models that accurately predict the activity of these variants at any target sequence.

High-throughput analysis of the activities of xCas9, SpCas9-NG and SpCas9 at matched and mismatched target sequences in human cells.

The applications of clustered regularly interspaced short palindromic repeats (CRISPR)-based genome editing can be limited by a lack of compatible protospacer adjacent motifs (PAMs), insufficient on-target activity and off-target effects. Here, we report an extensive comparison of the PAM-sequence compatibilities and the on-target and off-target activities of Cas9 from Streptococcus pyogenes (SpCas9) and the SpCas9 variants xCas9 and SpCas9-NG (which are known to have broader PAM compatibility than SpCas9) at 26,478 lentivirally integrated target sequences and 78 endogenous target sites in human cells. We found that xCas9 has the lowest tolerance for mismatched target sequences and that SpCas9-NG has the broadest PAM compatibility. We also show, on the basis of newly identified non-NGG PAM sequences, that SpCas9-NG and SpCas9 can edit six previously unedited endogenous sites associated with genetic diseases. Moreover, we provide deep-learning models that predict the activities of xCas9 and SpCas9-NG at the target sequences. The resulting deeper understanding of the activities of xCas9, SpCas9-NG and SpCas9 in human cells should facilitate their use.

3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents.

Intelligent agents gather information and perceive semantics within the environments before taking on given tasks. The agents store the collected information in the form of environment models that compactly represent the surrounding environments. The agents, however, can only conduct limited tasks without an efficient and effective environment model. Thus, such an environment model takes a crucial role for the autonomy systems of intelligent agents. We claim the following characteristics for a versatile environment model: accuracy, applicability, usability, and scalability. Although a number of researchers have attempted to develop such models that represent environments precisely to a certain degree, they lack broad applicability, intuitive usability, and satisfactory scalability. To tackle these limitations, we propose 3-D scene graph as an environment model and the 3-D scene graph construction framework. The concise and widely used graph structure readily guarantees usability as well as scalability for 3-D scene graph. We demonstrate the accuracy and applicability of the 3-D scene graph by exhibiting the deployment of the 3-D scene graph in practical applications. Moreover, we verify the performance of the proposed 3-D scene graph and the framework by conducting a series of comprehensive experiments under various conditions.

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.

Korean Variant Archive (KOVA): a reference database of genetic variations in the Korean population.

Despite efforts to interrogate human genome variation through large-scale databases, systematic preference toward populations of Caucasian descendants has resulted in unintended reduction of power in studying non-Caucasians. Here we report a compilation of coding variants from 1,055 healthy Korean individuals (KOVA; Korean Variant Archive). The samples were sequenced to a mean depth of 75x, yielding 101 singleton variants per individual. Population genetics analysis demonstrates that the Korean population is a distinct ethnic group comparable to other discrete ethnic groups in Africa and Europe, providing a rationale for such independent genomic datasets. Indeed, KOVA conferred 22.8% increased variant filtering power in addition to Exome Aggregation Consortium (ExAC) when used on Korean exomes. Functional assessment of nonsynonymous variant supported the presence of purifying selection in Koreans. Analysis of copy number variants detected 5.2 deletions and 10.3 amplifications per individual with an increased fraction of novel variants among smaller and rarer copy number variable segments. We also report a list of germline variants that are associated with increased tumor susceptibility. This catalog can function as a critical addition to the pre-existing variant databases in pursuing genetic studies of Korean individuals.

General rules for functional microRNA targeting.

The functional rules for microRNA (miRNA) targeting remain controversial despite their biological importance because only a small fraction of distinct interactions, called site types, have been examined among an astronomical number of site types that can occur between miRNAs and their target mRNAs. To systematically discover functional site types and to evaluate the contradicting rules reported previously, we used large-scale transcriptome data and statistically examined whether each of approximately 2 billion site types is enriched in differentially downregulated mRNAs responding to overexpressed miRNAs. Accordingly, we identified seven non-canonical functional site types, most of which are novel, in addition to four canonical site types, while also removing numerous false positives reported by previous studies. Extensive experimental validation and significantly elevated 3' UTR sequence conservation indicate that these non-canonical site types may have biologically relevant roles. Our expanded catalog of functional site types suggests that the gene regulatory network controlled by miRNAs may be far more complex than currently understood.

Fourier-based shape feature extraction technique for computer-aided B-Mode ultrasound diagnosis of breast tumor.

Early detection of breast tumor is critical in determining the best possible treatment approach. Due to its superiority compared with mammography in its possibility to detect lesions in dense breast tissue, ultrasound imaging has become an important modality in breast tumor detection and classification. This paper discusses the novel Fourier-based shape feature extraction techniques that provide enhanced classification accuracy for breast tumor in the computer-aided B-mode ultrasound diagnosis system. To demonstrate the effectiveness of the proposed method, experiments were performed using 4,107 ultrasound images with 2,508 malignancy cases. Experimental results show that the breast tumor classification accuracy of the proposed technique was 15.8%, 5.43%, 17.32%, and 13.86% higher than the previous shape features such as number of protuberances, number of depressions, lobulation index, and dissimilarity, respectively.