TABLE 4.
MDL-based tools and software packages related to CRISPR systems.
| Name | Main functionality | Input | Cell type | Interface | Model | Year | Source |
|---|---|---|---|---|---|---|---|
| C-RNNCrispr Zhang et al. (2020) | It predicts sgRNA on-target activity. It is a transfer learning approach by using small-sized datasets to fine-tune | Datasets to fine-tune | 4 cell line | Standalone software | CNN and BGRU | 2020 | https://github.com/Peppags/C_RNNCrispr |
| CRISPRpred Muhammad Rafid et al. (2020) | It predicts sgRNA on-target activity | Position independent and position specific features | Human | Standalone software | SVM and random forest | 2020 | https://github.com/Rafid013/CRISPRpredSEQ |
| DeepCpf1 Kwon et al. (2019) | It predicts the activity of AsCpf1 (location of all targetable sequences and efficiency of each; information on GC contents, positions, strands, and DeepCpf1 scores.) | Cell line types, information on the sequences of a target and its surroundings, and References sequences | All genome | Web tool | CNN | 2019 | http://deepcrispr.info/ |
| DeepHF Wang et al. (2019a) | It predicts SpCas9 activity for each gRNA (all targetable sequences, restriction sites, strands, and predicted efficiency) | Various types of SpCas9 nucleases, DNA sequences | All genomes | Web tool | CNN | 2019 | http://www.DeepHF.com/ |
| CINDEL Iyombe. (2019) | It predicts the indel frequencies of CRISPR/Cas12 with TTTV PAM sequence (targetable sequences, positions, strands, GC contents, and INDEL scores) | References sequences | Web tool | - | 2019 | http://big.hanyang.ac.kr/cindel | |
| DeepSpCas9 Kim et al. (2019) | It predicts SpCas9 activity for each gRNA (positions, GC content, and DeepSpCas9 scores) | Target sequence information with its surroundings, and gene symbols | Human | Web tool | CNN | 2019 | http://deepcrispr.info/DeepSpCas9 |
| Microhomology-Predictor Hwang et al. (2021) | It predicts the deletion patterns by calculating the scores of possible deletion patterns produced by a MMEJ pathway following DNA cleavage by ZFNs, TALENs, or Cas9. All possible deletion patterns and the pattern scores can be checked | Target sites with high out-of-frame scores | All genome | Web tool | - | 2019 | http://www.rgenome.net/mich-calculator |
| inDelphi Cloney. (2019) | It predicts the spectrum of cut-site, possible sgRNA sequences, predicted mutation patterns, possible frameshift codons, and their frequencies | Sequences of both sides of cleavage in various cell types | Human and mouse | Standalone software | - | 2019 | https://indelphi.giffordlab.mit.edu |
| FORECasT Allen et al. (2019) | It predicts editing outcomes (possible mutation patterns and predicted frequencies of the mutation patterns and frame shifts) of the CRISPR/Cas9 system with NGG PAM. | Target DNA sequences and the cleavage sites | Most of genomes | Web tool | - | 2018 | https://partslab.sanger.ac.uk/FORECasT |
| CRISPR-GNL Wang et al. (2019b) | It is an algorithm for CRISPR on-target activity prediction | Normalized gene editing activity from 8,101 gRNAs and 2,488 features | human, mouse, zebrafishDrosophila, Cioa intestinalis | Stand alone application | regression models | 2019 | https://github.com/TerminatorJ/GNL_Scorer |
| DeepCRISPR Chuai et al. (2018) | It predicts whole genome on and off-target profiles | sgRNA sequences with an NGG PAM | Human | Web tool | CNN | 2018 | http://www.deepcrispr.net/ |
| TUSCAN Wilson et al. (2018) | It predicts the degree of CRISPR/Cas9 activity and classifies them into active and inactive categories | All genome | Software | Random forest | 2018 | https://github.com/BauerLab/TUSCAN | |
| SgRNAScorer Chari et al. (2017) | It identifies sgRNA sites and their activities for any PAM sequence of interest | Sequence with a defined spacer length and PAM sequence | Human and mouse | Web tool | SVM | 2017 | https://sgrnascorer.cancer.gov/ |
| CRF Wang and Liang. (2017)* | CRF uses a classifier to filter out invalid CRISPR arrays from all putative candidates | DNA/RNA sequence in FASTA format | Bacteria and archaea | Web tool | Random forest | 2017 | http://bioinfolab.miamioh.edu/crf/home.php |
| GE-CRISPR Kaur et al. (2016) | It predicts and analyses sgRNAs efficiency and gives information like secondary structure of sgRNA, PAM, start and end of coordinates, and GC% | Desired gene or genome sequence in FASTA format | In any trained model | SVM | 2016 | http://bioinfo.imtech.res.in/manojk/gecrispr/ | |
| CRISPRscan Moreno-Mateos et al. (2015) | It’s a predictive sgRNA-scoring algorithm that captures the sequence features affecting the activity of CRISPR/Cas9 in vivo | DNA sequence | Fish | Web tool | Linier regression | 2015 | http://www.crisprscan.org/ |
| WU-CRISPR Wong et al. (2015) | It predicts potential sgRNAs and scores of them | Gene IDs | Human and mouse | Web tool and stand-alone software | SVM | 2015 | http://crispr.wustl.edu |
| SSC Xu et al. (2015) | It’s a program for predicting editing activity of SpCas9 and giving all possible targets with the efficiency scores of various editing modes such as knockout, CRISPRi, or CRISPRa | Target sequences with the length of spacers (19 nt or 20 nt) as | Web tool | Elastic Net | 2015 | http://cistrome.org/SSC/ | |
| CRISPRstrand Alkhnbashi et al. (2014) | It determines the crRNA-encoding strand at CRISPR loci by predicting the correct orientation of repeats. It also determines whether repeats lie on the forward or reverse strand | Attribute type, attribute order, size of the terminal regions, number of blocks within the terminal regions | Bacteria and archaea | Integrated in CRISPRmap web server | graph kernels | 2014 | http://rna.informatik.uni-freiburg.de/CRISPRmap |
*Means the tools are free of charge to access.