Most ebook files are in PDF format, so you can easily read them using various software such as Foxit Reader or directly on the Google Chrome browser.
Some ebook files are released by publishers in other formats such as .awz, .mobi, .epub, .fb2, etc. You may need to install specific software to read these formats on mobile/PC, such as Calibre.
Please read the tutorial at this link: https://ebookbell.com/faq
We offer FREE conversion to the popular formats you request; however, this may take some time. Therefore, right after payment, please email us, and we will try to provide the service as quickly as possible.
For some exceptional file formats or broken links (if any), please refrain from opening any disputes. Instead, email us first, and we will try to assist within a maximum of 6 hours.
EbookBell Team
5.0
110 reviewsSUMMARYThe antimicrobial resistance crisis necessitates structurally distinct antibiotics. While deep learning approaches can identify antibacterial compounds from existing libraries, structural novelty remains limited.Here, we developed a generative artificial intelligence framework for designing de novo antibiotics throughtwo approaches: a fragment-based method to comprehensively screen >107 chemical fragments in silicoagainst Neisseria gonorrhoeae or Staphylococcus aureus, subsequently expanding promising fragments,and an unconstrained de novo compound generation, each using genetic algorithms and variational autoencoders. Of 24 synthesized compounds, seven demonstrated selective antibacterial activity. Two lead compounds exhibited bactericidal efficacy against multidrug-resistant isolates with distinct mechanisms ofaction and reduced bacterial burden in vivo in mouse models of N. gonorrhoeae vaginal infection and methicillin-resistant S. aureus skin infection. We further validated structural analogs for both compound classes asantibacterial. Our approach enables the generative deep-learning-guided design of de novo antibiotics,providing a platform for mapping uncharted regions of chemical space.
