Cheminformatics articles within Nature Chemistry

Featured

  • Article
    | Open Access

    High-throughput experimentation (HTE) has great utility for chemical synthesis. However, robust interpretation of high-throughput data remains a challenge. Now, a flexible analyser has been developed on the basis of a machine learning-statistical analysis framework, which can reveal hidden chemical insights from historical HTE data of varying scopes, sizes and biases.

    • Emma King-Smith
    • , Simon Berritt
    •  & Alpha A. Lee

  • News & Views |

    The application of machine learning to big data, to make quantitative predictions about reaction outcomes, has been fraught with failure. This is because so many chemical-reaction data are not fit for purpose, but predictions would be less error-prone if synthetic chemists changed their reaction design and reporting practices.

    • Jacqueline M. Cole

  • Q&A |

    Jeremy Frey, professor of physical chemistry at the University of Southampton and principal investigator for the AI3SD Network+, talks with Nature Chemistry about the perils of uncertainty in the quality of machine learning data and the synergies between AI and other technologies.

    • Russell Johnson

  • Article |

    Machine learning has now been shown to enable the de novo design of abiotic nuclear-targeting miniproteins. To achieve this, high-throughput experimentation was combined with a directed evolution-inspired deep-learning approach in which the molecular structures of natural and unnatural residues are represented as topological fingerprints. The designed miniproteins, called Mach proteins, are non-toxic and can efficiently deliver antisense cargo in mice.

    • Carly K. Schissel
    • , Somesh Mohapatra
    •  & Bradley L. Pentelute

  • Article |

    Analysis of the thermodynamics of protein–N-glycan interactions perturbed by mutations has revealed an enthalpy–entropy compensation that depends on the electronics of the interacting side chains. Machine-learned and statistical models showed that protein–N-glycan interactions highly correlate with stereoelectronic effects, and that a major part of protein–N-glycan interactions can be explained using the energetic rules of frontier molecular orbital interactions.

    • Maziar S. Ardejani
    • , Louis Noodleman
    •  & Jeffery W. Kelly

  • Article |

    A selection-based screen has now revealed preferences in small-molecule chemotypes that bind RNA as well as preferences in the RNA motifs that bind small molecules. Analysis of these data enabled the design of a small molecule that selectively binds a non-coding microRNA and upregulates expression of vascular endothelial growth factor A.

    • Hafeez S. Haniff
    • , Laurent Knerr
    •  & Matthew D. Disney

  • Article |

    Secondary-sphere interactions serve a fundamental role in controlling the reactivity and selectivity of organometallic and enzyme catalysts, but their study in organocatalytic systems is scarce. Now, it has been shown that the in situ secondary-sphere modification of organocatalysts combined with machine-learning techniques can uncover reaction mechanisms and streamline catalyst optimization.

    • Vasudevan Dhayalan
    • , Santosh C. Gadekar
    •  & Anat Milo

  • Review Article |

    Biochemical and cellular assays are often plagued by false positive readouts elicited by nuisance compounds. A significant proportion of those compounds are aggregators. This Review discusses the basis for colloidal aggregation, experimental methods for detecting aggregates and analyses recent progress in computer-based systems for detecting colloidal aggregation with particular emphasis on machine learning [In the online version of this Review originally published, the graphical abstract image was incorrectly credited to ‘Reven T.C. Wurman / Alamy Stock Photo’ this has now been corrected].

    • Daniel Reker
    • , Gonçalo J. L. Bernardes
    •  & Tiago Rodrigues

  • Review Article |

    Natural products are a prime source of innovative molecular fragments and privileged scaffolds for drug discovery and chemical biology. Advanced machine-learning approaches can help analyse and design synthetically accessible, natural-product-derived, compound libraries and provide insight into the high selectivity of such compounds.

    • Tiago Rodrigues
    • , Daniel Reker
    •  & Gisbert Schneider

  • News & Views |

    How complex is it to synthesize a given molecular target? Can this be answered by a computer? Now, a model of synthetic complexity that factors in methodology developments has resulted in a complexity index that evolves alongside them.

    • Johann Gasteiger

  • Article |

    Natural products provide a rich source of leads for drug discovery. Now, a computational method is available that can be used to identify the macromolecular targets of these compounds. Much like medicinal chemists' reasoning, the software infers target information by comparing the substructures with those of drugs and other natural products with known targets.

    • Daniel Reker
    • , Anna M. Perna
    •  & Gisbert Schneider

  • Editorial |

    Nature Chemistry signed up for a Twitter account in March 2009. More than 5,000 tweets later, what have we learned and how do we use it?

  • Thesis |

    Bruce Gibb ponders what the future of chemistry research might look like if we take a more data-driven approach.

    • Bruce C. Gibb

  • Article |

    Natural products populate areas of chemical space not occupied by average synthetic molecules. Here, an analysis of more than 180,000 natural product structures results in a library of 2,000 natural-product-derived fragments, which resemble the properties of the natural products themselves and give access to novel inhibitor chemotypes.

    • Björn Over
    • , Stefan Wetzel
    •  & Herbert Waldmann

  • Editorial |

    Experimental data is the foundation on which science is built. Providing easier ways to find and search it is one way in which new online technologies can help to advance research.

Browse broader subjects

Browse Cheminformatics across other nature.com journals