Back

Deep Learning with Evolutionary Scale Modeling to discover Antibiotic-Resistance Drug against Klebsiella Pneumoniae

Jin, L.; Lei, Z.; Lin, P.; Ma, C.; Zhang, W.; Zhou, J.; Meng, S.; Jiang, Z.; Bu, Y.; Xu, Y.; Wei, N.; Hsu, T.; Qin, G.; Qiu, H.

2024-11-11 bioinformatics
10.1101/2024.11.09.622818 bioRxiv
Show abstract

The development of effective antibiotics is crucial in combating antibiotic-resistant pathogens such as Klebsiella pneumoniae (KP). This study utilizes deep learning, specifically Evolutionary Scale Modeling (ESM), to identify potential drug candidates. By analyzing molecular similarities between known drugs and KP strains, we aim to accelerate the discovery of new treatments and reduce the risks associated with clinical trials. This approach may shed new lights in the field of drug repositioning.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.