Back

DeepNEU(C): Introducing aiCRISPRL, a hybrid AI stem cell and organoid simulation platform with broad gene editing capabilities and applications

Esmail, S.; Danter, W. R.

2022-06-19 genomics
10.1101/2022.06.18.496679 bioRxiv
Show abstract

CRISPR-Cas9 (clustered regularly interspaced short palindromic repeats/CRISPR-associated nuclease 9) provides powerful gene-editing tools that are applicable for gene therapy of a variety of diseases including, but not limited to cancer, rare diseases, and heart disease. In the current study, we first re-examined our artificial stem cell and organoid simulations that were generated by our literature validated DeepNEU AI platform from the perspective of gene-editing. We then evaluated the aiCRISPRL (aiCRISPR-Like) application of the DeepNEU platform by directly comparing the CRISPR-Cas9 gene-editing approach with the DeepNEU derived aiCRISPRL capabilities using artificial simulated HeLa cells (aiHeLa). To accomplish this, we evaluated the aiCRISPRL like capabilities of DeepNEU to introduce a series of specific mutations into the MutS homolog 2 (MSH2) gene to assess DNA Mismatch Repair (MMR). This approach permits a comparative assessment of CRISPR-Cas9 and aiCRISPRL technologies following the introduction of specific MSH2 mutations. When combined with our previous body of gene editing research, the current data indicates that aiCRISPRL is an advanced AI platform technology that can be used for rapid prototyping and multiple scenario simulation in genomic research to complement wet-lab based gene-editing technologies.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

1
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 0.1%
9.5%
Similar papers in this journal
2
Scientific Reports
○ 3612 papers in training set
Top 11%
6.6%
Similar papers in this journal
3
Methods
○ 34 papers in training set
Top 0.1%
6.2%
Similar papers in this journal
4
PLOS ONE
● 5266 papers in training set
Top 28%
5.4%
Similar papers in this journal
5
International Journal of Molecular Sciences
○ 494 papers in training set
Top 2%
5.1%
Similar papers in this journal
6
Gigabyte
● 62 papers in training set
Top 0.2%
4.3%
7
BMC Bioinformatics
○ 457 papers in training set
Top 2%
4.0%
8
PLOS Computational Biology
● 1863 papers in training set
Top 9%
4.0%
9
Bioinformatics Advances
◐ 203 papers in training set
Top 2%
3.2%
10
Frontiers in Genetics
○ 230 papers in training set
Top 1%
3.1%
50% of probability mass above
11
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 2%
2.6%
12
Artificial Intelligence in the Life Sciences
○ 13 papers in training set
Top 0.1%
2.6%
13
Genes
○ 144 papers in training set
Top 1%
2.4%
14
BMC Genomics
○ 406 papers in training set
Top 3%
2.4%
15
Computational Biology and Chemistry
○ 28 papers in training set
Top 0.3%
2.1%
16
BMC Medical Genomics
○ 50 papers in training set
Top 0.4%
2.1%
17
Briefings in Bioinformatics
◐ 354 papers in training set
Top 4%
1.9%
18
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.7%
19
GigaScience
◐ 212 papers in training set
Top 3%
1.4%
20
Life
○ 29 papers in training set
Top 0.4%
1.3%
21
Heliyon
○ 152 papers in training set
Top 6%
1.1%
22
Human Mutation
○ 34 papers in training set
Top 0.4%
1.1%
23
The CRISPR Journal
○ 39 papers in training set
Top 0.4%
0.9%
24
Cells
○ 249 papers in training set
Top 6%
0.9%
25
Artificial Intelligence in Medicine
○ 17 papers in training set
Top 0.7%
0.9%
26
Genomics
○ 64 papers in training set
Top 2%
0.8%
27
Nucleic Acids Research
◐ 1281 papers in training set
Top 14%
0.8%
28
Database
◐ 61 papers in training set
Top 0.9%
0.8%
29
npj Systems Biology and Applications
○ 125 papers in training set
Top 2%
0.8%
30
Genomics, Proteomics & Bioinformatics
188 papers in training set
Top 2%
0.7%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.