Back

BioLLMNet: Enhancing RNA-Interaction Prediction with a Specialized Cross-LLM Transformation Network

Tahmid, M. T.; Abir, A. R.; Bayzid, M. S.

2024-10-03 bioinformatics
10.1101/2024.10.02.616044 bioRxiv
Show abstract

Existing computational methods for the prediction of RNA related interactions often rely heavily on manually crafted features. Language model features for bio-sequences has gain significant popularity in proteomics and genomics. However, during interaction prediction, how language model features from different modalities should be combined to extract the most representative features is yet to be explored. We introduce BioLLMNet, a novel framework that introduces an effective combination approach for multi-modal bio-sequences. BioLLMNet provides a way to transform feature space of different molecules language model features and uses learnable gating mechanism to effectively fuse features. Rigorous evaluations show that BioLLMNet achieves state-of-the-art performance in RNA-protein, RNA-small molecule, and RNA-RNA interactions, outperforming existing methods in RNA-associated interaction prediction.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

1
Bioinformatics
◐ 1204 papers in training set
Top 1%
18.5%
Similar papers in this journal
2
Bioinformatics Advances
◐ 203 papers in training set
Top 0.1%
18.5%
Similar papers in this journal
3
Briefings in Bioinformatics
◐ 354 papers in training set
Top 0.7%
8.9%
Similar papers in this journal
4
IEEE/ACM Transactions on Computational Biology and Bioinformatics
● 38 papers in training set
Top 0.1%
5.5%
Similar papers in this journal
50% of probability mass above
5
RNA
● 189 papers in training set
Top 0.4%
4.8%
Similar papers in this journal
6
Journal of Computational Biology
○ 48 papers in training set
Top 0.2%
3.4%
7
BMC Bioinformatics
○ 457 papers in training set
Top 3%
3.2%
8
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 1%
3.2%
9
PLOS Computational Biology
● 1863 papers in training set
Top 10%
3.1%
10
Scientific Reports
○ 3612 papers in training set
Top 38%
2.6%
11
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 2%
2.4%
12
Frontiers in Genetics
○ 230 papers in training set
Top 2%
1.9%
13
Nucleic Acids Research
◐ 1281 papers in training set
Top 8%
1.9%
14
Genome Biology
○ 637 papers in training set
Top 6%
1.5%
15
PLOS ONE
● 5266 papers in training set
Top 50%
1.3%
16
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
1.1%
17
Journal of Chemical Information and Modeling
● 238 papers in training set
Top 2%
1.1%
18
IEEE Transactions on Computational Biology and Bioinformatics
● 20 papers in training set
Top 0.5%
1.0%
19
iScience
○ 1154 papers in training set
Top 35%
0.8%
20
Frontiers in Bioinformatics
○ 49 papers in training set
Top 1%
0.8%
21
Nature Communications
○ 5641 papers in training set
Top 56%
0.8%
22
Computational Biology and Chemistry
○ 28 papers in training set
Top 1%
0.8%
23
International Journal of Molecular Sciences
○ 494 papers in training set
Top 15%
0.8%
24
ACS Omega
● 105 papers in training set
Top 3%
0.8%
25
BMC Genomics
○ 406 papers in training set
Top 9%
0.6%
26
Computers in Biology and Medicine
○ 128 papers in training set
Top 5%
0.6%
27
Biology Methods and Protocols
◐ 61 papers in training set
Top 3%
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.