Back

Precious3GPT: Multimodal Multi-Species Multi-Omics Multi-Tissue Transformer for Aging Research and Drug Discovery

Galkin, F.; Naumov, V.; Pushkov, S.; Sidorenko, D.; Urban, A.; Zagirova, D.; Alawi, K. M.; Aliper, A.; Gumerov, R.; Kalashnikov, A.; Mukba, S.; Pogorelskaya, A.; Ren, F.; Shneyderman, A.; Tang, Q.; Xiao, D.; Tyshkovskiy, A.; Ying, K.; Gladyshev, V. N.; Zhavoronkov, A.

2024-07-25 bioinformatics
10.1101/2024.07.25.605062 bioRxiv
Show abstract

We present a multimodal multi-species multi-omics multi-tissue transformer for aging research and drug discovery capable of performing multiple tasks such as age prediction across species, target discovery, tissue, sex, and disease sample classification, drug sensitivity prediction, replication of omics response and prediction of biological and phenotypic response to compound treatment. This model combines textual, tabular, and knowledge graph-derived representations of biological experiments to provide insights into molecular-level biological processes. We demonstrate that P3GPT has developed an intuition for the interactions between compounds, pathologies, and gene regulation in the context of multiple species and tissues. In these areas, it outperforms existing LLMs and we highlight its utility in diverse case studies. P3GPT is a general model that may be used as a target identification tool, aging clock, digital laboratory, and scientific assistant. The model is intended as a community resource available open source as well as via a Discord server.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 22%
7.7%
Similar papers in this journal
2
Patterns
○ 78 papers in training set
Top 0.1%
7.1%
Similar papers in this journal
3
Nature Aging
○ 60 papers in training set
Top 0.3%
6.6%
Similar papers in this journal
4
Nucleic Acids Research
◐ 1281 papers in training set
Top 4%
5.0%
Similar papers in this journal
5
Cell Systems
○ 201 papers in training set
Top 0.9%
5.0%
Similar papers in this journal
6
iScience
○ 1154 papers in training set
Top 3%
4.7%
7
Briefings in Bioinformatics
◐ 354 papers in training set
Top 2%
4.2%
8
Bioinformatics
◐ 1204 papers in training set
Top 5%
4.2%
9
Bioinformatics Advances
◐ 203 papers in training set
Top 1%
4.2%
10
GeroScience
○ 109 papers in training set
Top 0.6%
3.9%
50% of probability mass above
11
Molecular Systems Biology
○ 162 papers in training set
Top 0.6%
3.3%
12
Nature Methods
○ 385 papers in training set
Top 3%
3.1%
13
npj Aging
○ 22 papers in training set
Top 0.1%
3.1%
14
Advanced Science
○ 286 papers in training set
Top 3%
2.4%
15
PLOS Computational Biology
● 1863 papers in training set
Top 12%
2.4%
16
eLife
● 5828 papers in training set
Top 46%
2.1%
17
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 3%
2.1%
18
Nature Machine Intelligence
○ 70 papers in training set
Top 1%
2.1%
19
Scientific Reports
○ 3612 papers in training set
Top 47%
2.1%
20
Genome Medicine
○ 183 papers in training set
Top 3%
1.7%
21
Cell Reports Medicine
○ 153 papers in training set
Top 3%
1.3%
22
Genome Biology
○ 637 papers in training set
Top 7%
1.1%
23
Aging Cell
○ 165 papers in training set
Top 2%
1.1%
24
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 3%
1.1%
25
Communications Chemistry
○ 48 papers in training set
Top 1.0%
1.0%
26
Cell Reports
○ 1498 papers in training set
Top 25%
1.0%
27
Cell Reports Methods
○ 165 papers in training set
Top 3%
0.9%
28
BMC Bioinformatics
○ 457 papers in training set
Top 6%
0.8%
29
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 42%
0.8%
30
Cell Genomics
○ 172 papers in training set
Top 5%
0.6%

"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.