JHJoshua Hesse

Joshua Hesse

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Joshua Hesse has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Decoding antibiotic modes of action from multimodal cellular responses

    by Stephan Sieber, Joshua Hesse, Dominik Schum, Laura Leidel, Leonard Gareis, Jennifer Herrmann, Rolf Mueller

    Antibiotic resistance continues to rise, yet most new drug candidates act through long-established targets. Faster mode of action (MoA) assessment would enable more effective prioritization of screening hits and help identify compounds with novel mechanisms. In this study, we aimed to develop a scalable framework for MoA inference from antibiotic-induced cellular response profiles in Escherichia coli. We generated a multimodal dataset spanning more than 50 antibiotics, including proteome profiles, chemical structure descriptors, inhibitory concentrations and growth dynamics, and used it to build MAPPER (Mode of Action Prediction via Proteomics-Enhanced Representation), a framework comprising a fixed multimodal predictor and an uncertainty module. MAPPER accurately classified antibiotics across nine mechanistic classes, flagged compounds with likely novel mechanisms and retained predictive power in proteomics-only transfer experiments across mass spectrometry platforms and external data. Together, these results establish MAPPER as an innovative tool for MoA prediction and novelty detection, enabling prioritization of antibacterial candidates with distinct mechanisms.

  • Open Access

    Decoding antibiotic modes of action from multimodal cellular responses

    by Joshua Hesse, Dominik Schum, Laura Leidel, Leonard R. Gareis, Jennifer Herrmann, Rolf Müller, Stephan A. Sieber

    Antibiotic resistance continues to rise, yet most new drug candidates act through long-established targets. Faster mode of action (MoA) assessment would enable more effective prioritization of screening hits and help identify compounds with novel mechanisms. In this study, we aimed to develop a scalable framework for MoA inference from antibiotic-induced cellular response profiles in Escherichia coli . We generated a multimodal dataset spanning more than 50 antibiotics, including proteome profiles, chemical structure descriptors, inhibitory concentrations and growth dynamics, and used it to build MAPPER (Mode of Action Prediction via Proteomics-Enhanced Representation), a framework comprising a fixed multimodal predictor and an uncertainty module. MAPPER accurately classified antibiotics across nine mechanistic classes, flagged compounds with likely novel mechanisms and retained predictive power in proteomics-only transfer experiments across mass spectrometry platforms and external data. Together, these results establish MAPPER as an innovative tool for MoA prediction and novelty detection, enabling prioritization of antibacterial candidates with distinct mechanisms.

  • Open Access

    Generative Deep Learning Pipeline Yields Potent Gram-Negative Antibiotics

    by Martin F. Köllen, Maximilian G. Schuh, Robin Kretschmer, Joshua Hesse, Dominik Schum, Junhong Chen, Annkathrin I. Bohne, Dominik P. Halter, Stephan A. Sieber

    The escalating crisis of multiresistant bacteria demands the rapid discovery of novel antibiotics that transcend the limitations imposed by the biased chemical space of current libraries. To address this challenge, we introduce an innovative deep learning-driven pipeline for de novo antibiotic design. Our unique approach leverages a chemical language model to generate structurally unprecedented antibiotic candidates. The model was trained on a diverse chemical space of drug-like molecules and natural products. We then applied transfer learning using a data set of diverse antibiotic scaffolds to refine its generative capabilities. Using predictive modeling and expert curation, we prioritized the most promising compounds for synthesis. This pipeline identified a lead candidate with potent activity against methicillin-resistant Staphylococcus aureus. We then performed iterative refinement by synthesizing 40 derivatives of the lead compound. This effort produced a suite of active compounds, with 30 showing activity against S. aureus and 17 against Escherichia coli. Among these, lead compound D8 exhibited remarkable submicromolar and single-digit micromolar potency against the aforementioned pathogens, respectively. Mechanistic investigations point to the reductive generation of reactive species as its primary mode of action. This work validates a deep-learning pipeline that explores chemical space to generate antibiotic candidates. This process yields a potent nitrofuran derivative and a set of experimentally validated scaffolds to seed future antibiotic development.


  • Open Access

    Machine Learning-Driven Data Valuation for Optimizing High-Throughput Screening Pipelines

    by Joshua Hesse, Davide Boldini, Stephan A. Sieber

    In the rapidly evolving field of drug discovery, high-throughput screening (HTS) is essential for identifying bioactive compounds. This study introduces a novel application of data valuation, a concept for evaluating the importance of data points based on their impact, to enhance drug discovery pipelines. Our approach improves active learning for compound library screening, robustly identifies true and false positives in HTS data, and identifies important inactive samples in an imbalanced HTS training, all while accounting for computational efficiency. We demonstrate that importance-based methods enable more effective batch screening, reducing the need for extensive HTS. Machine learning models accurately differentiate true biological activity from assay artifacts, streamlining the drug discovery process. Additionally, importance undersampling aids in HTS data set balancing, improving machine learning performance without omitting crucial inactive samples. These advancements could significantly enhance the efficiency and accuracy of drug development.


  • Open Access

    Data Valuation: A novel approach for analyzing high throughput screen data using machine learning

    by Joshua Hesse, Davide Boldini, Stephan Sieber

    In the rapidly evolving field of drug discovery, High Throughput Screening (HTS) is a pivotal technique for identifying promising compounds. Despite its wide usage, the primary challenge remains in efficiently sifting through vast chemical libraries to discern true bioactive compounds from false positives. This study introduces a novel application of data valuation methods in machine learning to address this challenge, offering a multi-faceted approach to improving drug discovery pipelines. Our comprehensive strategy encompasses enhancing active learning for efficient compound library screening, robust identification of false and true positives in primary HTS data, and optimizing HTS datasets for machine learning applications through targeted undersampling. We demonstrate that influence-based methods enable more effective batch screening of chemical libraries, thereby reducing the need for extensive HTS, and provide significant advancements over current false positive detection techniques. This is achieved by employing machine learning models that accurately distinguish between true biological activity and assay artifacts, thereby streamlining the drug discovery process. Furthermore, our method applies smart undersampling to balance HTS datasets, enhancing the performance of machine learning algorithms without the risk of omitting crucial inactive samples. The implications of these developments are far-reaching, offering a potential paradigm shift in the efficiency and accuracy of drug development processes. We provide a benchmarking platform to facilitate the application of these methods, ensuring easy integration and modification for a broad range of datasets, thus propelling the scientific community towards more effective drug discovery methodologies (Available on GitHub at: https://github.com/JoshuaHesse/DataValuationPlatform).