A Deep Learning Approach to Antibiotic Discovery

Stokes, Jonathan; Yang, Kevin; Swanson, Kyle L.; Jin, Wengong; Cubillos-Ruiz, Andrés; Donghia, Nina M.; MacNair, Craig R.; French, Shawn; Carfrae, Lindsey A; Bloom-Ackermann, Zohar; Tran, Victoria M.; Chiappino-Pepe, Anush; Badran, Ahmed H.; Andrews, Ian W.; Chory, Emma J.; Church, George M.; Brown, Eric D.; Jaakkola, Tommi S.; Barzilay, Regina; Collins, James J.

doi:10.1016/j.cell.2020.04.001

Cited by 138 publications

(92 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Digital technologies such as whole-genome sequencing, machine learning, mass spectrometry and predictive modeling are likely to transform the clinical management of bacterial infections in the coming decades. Exciting developments in machine learning are, for the first time, enabling the rapid discovery of novel classes of antimicrobial compounds ( 75 ) and the rapid identification of bacterial pathogens in the clinic ( 5 ). Advances in mass spectrometry-based metabolomics are enabling the rapid discovery of antimicrobial mechanisms of action ( 76 ).…”

Section: Discussionmentioning

confidence: 99%

Digital Insights Into Nucleotide Metabolism and Antibiotic Treatment Failure

Lopatkin

Yang

2021

Front. Digit. Health

View full text Add to dashboard Cite

Nucleotide metabolism plays a central role in bacterial physiology, producing the nucleic acids necessary for DNA replication and RNA transcription. Recent studies demonstrate that nucleotide metabolism also proactively contributes to antibiotic-induced lethality in bacterial pathogens and that disruptions to nucleotide metabolism contributes to antibiotic treatment failure in the clinic. As antimicrobial resistance continues to grow unchecked, new approaches are needed to study the molecular mechanisms responsible for antibiotic efficacy. Here we review emerging technologies poised to transform understanding into why antibiotics may fail in the clinic. We discuss how these technologies led to the discovery that nucleotide metabolism regulates antibiotic drug responses and why these are relevant to human infections. We highlight opportunities for how studies into nucleotide metabolism may enhance understanding of antibiotic failure mechanisms.

show abstract

Section: Discussionmentioning

confidence: 99%

Digital Insights Into Nucleotide Metabolism and Antibiotic Treatment Failure

Lopatkin

Yang

2021

Front. Digit. Health

View full text Add to dashboard Cite

show abstract

“…With only a handful of antibiotic target proteins, bacteria are only a few genetic mutations away from becoming completely resistant to several antibiotic molecules. As such, the antibiotic resistance crisis will likely not be solved by developing the next novel antibiotic molecule 3 , 4 . Therefore, understanding the mechanisms of antibiotic resistance and developing strategies to counteract the evolution of antibiotic resistance will be crucial to combat this public health predicament.…”

Section: Introductionmentioning

confidence: 99%

A trimethoprim derivative impedes antibiotic resistance evolution

et al. 2021

View full text Add to dashboard Cite

The antibiotic trimethoprim (TMP) is used to treat a variety of Escherichia coli infections, but its efficacy is limited by the rapid emergence of TMP-resistant bacteria. Previous laboratory evolution experiments have identified resistance-conferring mutations in the gene encoding the TMP target, bacterial dihydrofolate reductase (DHFR), in particular mutation L28R. Here, we show that 4’-desmethyltrimethoprim (4’-DTMP) inhibits both DHFR and its L28R variant, and selects against the emergence of TMP-resistant bacteria that carry the L28R mutation in laboratory experiments. Furthermore, antibiotic-sensitive E. coli populations acquire antibiotic resistance at a substantially slower rate when grown in the presence of 4’-DTMP than in the presence of TMP. We find that 4’-DTMP impedes evolution of resistance by selecting against resistant genotypes with the L28R mutation and diverting genetic trajectories to other resistance-conferring DHFR mutations with catalytic deficiencies. Our results demonstrate how a detailed characterization of resistance-conferring mutations in a target enzyme can help identify potential drugs against antibiotic-resistant bacteria, which may ultimately increase long-term efficacy of antimicrobial therapies by modulating evolutionary trajectories that lead to resistance.

show abstract

“…Das bildet -stark vereinfacht gesprochen -eine Abstraktion der vielen Inputs auf allgemeinere Begriffe nach. Diese Netzwerke sind komplexer zu trainieren ("back-propagation" und andere Schritte), schaffen aber, oft mit weiteren Strategien aus der künstlichen Intelligenzforschung weiter verbessert, auch Erstaunliches, etwa optische Bilderkennung von Leukämiezellen durch verbesserte Schwarmoptimierung (Sahlol et al 2020) oder die automatische Erkennung der Sekundärstruktur und von Oligonukleotiden in elektronenmikroskopischen Aufnahmen (Mostosi et al 2020), sodass mit diesem Deep learning Ansatz schließlich sogar Antibiotika entdeckt werden können (Stokes et al 2020) oder die Energiepotentiale und damit auch die dreidimensionale Struktur von Proteinen (Senior et al 2020).…”

Section: Tp+fn Tp+fp+tn+fnunclassified

Wir können über uns nachdenken – der Computer nicht

Dandekar

Kunz

2021

Bioinformatik

View full text Add to dashboard Cite

A Deep Learning Approach to Antibiotic Discovery

Cited by 138 publications

References 0 publications

Digital Insights Into Nucleotide Metabolism and Antibiotic Treatment Failure

Digital Insights Into Nucleotide Metabolism and Antibiotic Treatment Failure

A trimethoprim derivative impedes antibiotic resistance evolution

Wir können über uns nachdenken – der Computer nicht

Contact Info

Product

Resources

About