Back

Toward mastering the cell language by learning to generate

Chen, Y.; Bian, H.; Wei, L.; Jia, J.; Dong, X.; Li, Y.; Zhao, Y.; Wu, X.; Li, C.; Luo, E.; Xiao, C.; Hao, M.; Zhang, X.

2024-12-11 bioinformatics
10.1101/2024.01.25.577152 bioRxiv
Show abstract

Cells can be viewed as complex stories written by coordinated expression of genes. The success of AI large language models (LLMs) in mastering the human language inspired us to develop a large AI model scMulan with 368 million parameters to generate cell transcriptomics with designated attributes by learning the cell language. We defined a unified c-sentence to incorporate cell transcriptomics and meta-attributes, and pre-trained scMulan on the equivalence of 100 million human cells. Experiments showed that scMulan can generate designated pseudo transcriptomics, predict missing attributes of cells, reconstruct unobserved cells along functional gradients, and can help to identify driving regulators of cell fates. The generated data passed tests of current tools and can reflect the underlying biology.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Nature Machine Intelligence
61 papers in training set
Top 0.1%
23.2%
2
Nature Communications
4913 papers in training set
Top 16%
10.4%
3
Nature
575 papers in training set
Top 4%
6.5%
4
Cell Systems
167 papers in training set
Top 2%
5.0%
5
Science
429 papers in training set
Top 6%
5.0%
50% of probability mass above
6
Genome Biology
555 papers in training set
Top 3%
2.7%
7
Cell
370 papers in training set
Top 9%
2.4%
8
Advanced Science
249 papers in training set
Top 8%
2.4%
9
eLife
5422 papers in training set
Top 35%
2.1%
10
Cell Research
49 papers in training set
Top 0.8%
2.1%
11
Nature Methods
336 papers in training set
Top 4%
1.9%
12
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 30%
1.8%
13
Science Advances
1098 papers in training set
Top 16%
1.7%
14
Frontiers in Genetics
197 papers in training set
Top 5%
1.7%
15
Cell Genomics
162 papers in training set
Top 3%
1.7%
16
Briefings in Bioinformatics
326 papers in training set
Top 4%
1.5%
17
PLOS Computational Biology
1633 papers in training set
Top 17%
1.5%
18
Genome Research
409 papers in training set
Top 3%
1.4%
19
Genome Medicine
154 papers in training set
Top 5%
1.4%
20
iScience
1063 papers in training set
Top 21%
1.3%
21
Bioinformatics
1061 papers in training set
Top 8%
1.1%
22
Genomics, Proteomics & Bioinformatics
171 papers in training set
Top 5%
0.9%
23
PLOS ONE
4510 papers in training set
Top 63%
0.9%
24
Scientific Reports
3102 papers in training set
Top 70%
0.9%
25
Nature Biotechnology
147 papers in training set
Top 7%
0.8%
26
Communications Biology
886 papers in training set
Top 20%
0.8%
27
Nature Medicine
117 papers in training set
Top 5%
0.8%
28
Nature Computational Science
50 papers in training set
Top 2%
0.8%
29
Cancer Research
116 papers in training set
Top 4%
0.7%
30
Nucleic Acids Research
1128 papers in training set
Top 19%
0.7%