Back

FlashBind: Towards Accurate and Efficient Structure-based Virtual Screening

Jiang, S.; Chen, Y.; Krishnan, A.; Zhang, Y.; Jin, W.

2026-04-08 molecular biology
10.64898/2025.12.22.695983 bioRxiv
Show abstract

Accurate prediction of protein-ligand interactions is central to computational drug discovery. Recent foundation models such as Boltz-2 have achieved remarkable accuracy in binding affinity prediction, yet their prohibitive computational cost remains a major barrier to large-scale virtual screening. Here we introduce FlashBind, a lightweight structure-based model that achieves a 50x speedup over Boltz-2 at inference time by replacing expensive structure prediction with a fast docking model and substituting costly PairFormer modules with a streamlined EGNN architecture. FlashBind matches Boltz-2 on standard virtual screening benchmarks and demonstrates superior generalization to enzyme-substrate specificity prediction. To evaluate real-world applicability, we apply FlashBind to target-based antibiotic screening against the essential bacterial proteins in E. coli and show that FlashBind substantially outperforms Boltz-2 and other virtual screening baselines. Notably, several top-ranked candidates exhibit potent inhibition of DnaG and effective bacterial growth inhibition against E. coli in wet-lab validation. Together, these results demonstrate that FlashBind bridges the gap between accuracy and efficiency, enabling ultra-fast, high-fidelity screening of massive chemical libraries for drug discovery.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nature Communications
4913 papers in training set
Top 5%
18.6%
2
Journal of Chemical Information and Modeling
207 papers in training set
Top 0.7%
7.2%
3
The Lancet Infectious Diseases
71 papers in training set
Top 0.3%
6.4%
4
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 11%
6.4%
5
Nucleic Acids Research
1128 papers in training set
Top 4%
4.9%
6
Cell Systems
167 papers in training set
Top 3%
4.3%
7
Nature Methods
336 papers in training set
Top 2%
4.3%
50% of probability mass above
8
Nature Biotechnology
147 papers in training set
Top 2%
4.2%
9
Science
429 papers in training set
Top 8%
4.0%
10
Advanced Science
249 papers in training set
Top 5%
3.6%
11
PLOS ONE
4510 papers in training set
Top 42%
3.1%
12
Nature Machine Intelligence
61 papers in training set
Top 1%
2.1%
13
eLife
5422 papers in training set
Top 38%
1.9%
14
Nature
575 papers in training set
Top 12%
1.3%
15
Cell Genomics
162 papers in training set
Top 4%
1.2%
16
Cell Discovery
54 papers in training set
Top 4%
1.2%
17
ACS Central Science
66 papers in training set
Top 2%
1.1%
18
Chemical Science
71 papers in training set
Top 2%
1.0%
19
Scientific Reports
3102 papers in training set
Top 69%
1.0%
20
PLOS Computational Biology
1633 papers in training set
Top 22%
0.9%
21
Communications Biology
886 papers in training set
Top 19%
0.9%
22
Cell Reports
1338 papers in training set
Top 32%
0.8%
23
Genome Medicine
154 papers in training set
Top 8%
0.7%
24
Journal of the American Chemical Society
199 papers in training set
Top 5%
0.7%
25
Science Advances
1098 papers in training set
Top 30%
0.7%
26
Nature Chemical Biology
104 papers in training set
Top 4%
0.7%
27
Structure
175 papers in training set
Top 3%
0.7%
28
Nature Genetics
240 papers in training set
Top 8%
0.7%
29
iScience
1063 papers in training set
Top 37%
0.6%
30
Cell Reports Medicine
140 papers in training set
Top 9%
0.6%