Steffen Hirte

Steffen Hirte

Auto-generated profile, based on publicly available information

Steffen Hirte

University of Vienna

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 June 2022 in Natural Product Reports
Verified
Journal Article
Open access
PDF file
Ya ChenYa Chen
Ya Chen
CRCara Rosenkranz
Cara Rosenkranz
SHSteffen Hirte
Steffen Hirte
Johannes KirchmairJohannes Kirchmair
Johannes Kirchmair
This cheminformatics study investigates the ring systems present in natural products and their coverage by ring systems observed in synthetic compounds.

24 January 2019 in Biomolecules
Verified
Journal Article
Open access
PDF file
Ya ChenYa Chen
Ya Chen
CSConrad Stork
Conrad Stork
SHSteffen Hirte
Steffen Hirte
Johannes KirchmairJohannes Kirchmair
Johannes Kirchmair
Natural products (NPs) remain the most prolific resource for the development of small-molecule drugs. Here we report a new machine learning approach that allows the identification of natural products with high accuracy. The method also generates similarity maps, which highlight atoms that contribute significantly to the classification of small molecules as a natural product or synthetic molecule. The method can hence be utilized to (i) identify natural products in large molecular libraries, (ii) quantify the natural product-likeness of small molecules, and (iii) visualize atoms in small molecules that are characteristic of natural products or synthetic molecules. The models are based on random forest classifiers trained on data sets consisting of more than 265,000 to 322,000 natural products and synthetic molecules. Two-dimensional molecular descriptors, MACCS keys and Morgan2 fingerprints were explored. On an independent test set the models reached areas under the receiver operating characteristic curve (AUC) of 0.997 and Matthews correlation coefficients (MCCs) of 0.954 and higher. The method was further tested on data from the Dictionary of Natural Products, ChEMBL and other resources. The best-performing models are accessible as a free web service at http://npscout.zbh.uni-hamburg.de/npscout.

11 August 2021 in Pharmaceuticals
Verified
Journal Article
Open access
PDF file
AWAnke Wilm
Anke Wilm
MLMarina Garcia de Lomana
Marina Garcia de Lomana
CSConrad Stork
Conrad Stork
NMNeann Mathai
Neann Mathai
SHSteffen Hirte
Steffen Hirte
Johannes KirchmairJohannes Kirchmair
Johannes Kirchmair
In recent years, a number of machine learning models for the prediction of the skin sensitization potential of small organic molecules have been reported and become available. These models generally perform well within their applicability domains but, as a result of the use of molecular fingerprints and other non-intuitive descriptors, the interpretability of the existing models is limited. The aim of this work is to develop a strategy to replace the non-intuitive features by predicted outcomes of bioassays. We show that such replacement is indeed possible and that as few as ten interpretable, predicted bioactivities are sufficient to reach competitive performance. On a holdout data set of 257 compounds, the best model (“Skin Doctor CP:Bio”) obtained an efficiency of 0.82 and an MCC of 0.52 (at the significance level of 0.20). Skin Doctor CP:Bio is available free of charge for academic research. The modeling strategies explored in this work are easily transferable and could be adopted for the development of more interpretable machine learning models for the prediction of the bioactivity and toxicity of small organic compounds.

Verified
Journal Article
Open access
PDF file
NFNingning Fan
Ningning Fan
SHSteffen Hirte
Steffen Hirte
Johannes KirchmairJohannes Kirchmair
Johannes Kirchmair
Methods for the pairwise comparison of 2D and 3D molecular structures are established approaches in virtual screening. In this work, we explored three strategies for maximizing the virtual screening performance of these methods: (i) the merging of hit lists obtained from multi-compound screening using a single screening method, (ii) the merging of the hit lists obtained from 2D and 3D screening by parallel selection, and (iii) the combination of both of these strategies in an integrated approach. We found that any of these strategies led to a boost in virtual screening performance, with the clearest advantages observed for the integrated approach. On test sets for virtual screening, covering 50 pharmaceutically relevant proteins, the integrated approach, using sets of five query molecules, yielded, on average, an area under the receiver operating characteristic curve (AUC) of 0.84, an early enrichment among the top 1% of ranked compounds (EF1%) of 53.82 and a scaffold recovery rate among the top 1% of ranked compounds (SRR1%) of 0.50. In comparison, the 2D and 3D methods on their own (when using a single query molecule) yielded AUC values of 0.68 and 0.54, EF1% values of 19.96 and 17.52, and SRR1% values of 0.20 and 0.17, respectively. In conclusion, based on these results, the integration of 2D and 3D methods, via a (balanced) parallel selection strategy, is recommended, and, in particular, when combined with multi-query screening.

7 April 2022 in Cells
Verified
Journal Article
Open access
PDF file
SHSteffen Hirte
Steffen Hirte
Oliver BurkOliver Burk
Oliver Burk
Ammar TahirAmmar Tahir
Ammar Tahir
Matthias SchwabMatthias Schwab
Matthias Schwab
Björn WindshügelBjörn Windshügel
Björn Windshügel
Johannes KirchmairJohannes Kirchmair
Johannes Kirchmair
The pregnane X receptor (PXR) regulates the metabolism of many xenobiotic and endobiotic substances. In consequence, PXR decreases the efficacy of many small-molecule drugs and induces drug-drug interactions. The prediction of PXR activators with theoretical approaches such as machine learning (ML) proves challenging due to the ligand promiscuity of PXR, which is related to its large and flexible binding pocket. In this work we demonstrate, by the example of random forest models and support vector machines, that classifiers generated following classical training procedures often fail to predict PXR activity for compounds that are dissimilar from those in the training set. We present a novel regularization technique that penalizes the gap between a model’s training and validation performance. On a challenging test set, this technique led to improvements in Matthew correlation coefficients (MCCs) by up to 0.21. Using these regularized ML models, we selected 31 compounds that are structurally distinct from known PXR ligands for experimental validation. Twelve of them were confirmed as active in the cellular PXR ligand-binding domain assembly assay and more hits were identified during follow-up studies. Comprehensive analysis of key features of PXR biology conducted for three representative hits confirmed their ability to activate the PXR.

29 September 2025 in ChemRxiv
Verified
Preprint
Open access
PDF file
SHSteffen Hirte
Steffen Hirte
VSVincent-Alexander Scholz
Vincent-Alexander Scholz
Johannes KirchmairJohannes Kirchmair
Johannes Kirchmair
Machine learning models are transforming data-driven research across scientific disciplines, yet their deployment as accessible and reliable web services remains a significant challenge. We introduce the NERDD framework, a scalable, maintainable, and secure microservices platform designed to support the sustainable delivery of machine learning services in scientific environments. Built in Python, NERDD provides a modular infrastructure for deploying predictive and generative models, with native support for chemistry-specific tasks such as molecular property prediction, atom-level inference, and molecular generation. Through standardized configuration files and containerized modules, the framework enables seamless integration of in silico models and interaction via a REST API and an intuitive web interface. Leveraging technologies like Apache Kafka, Kubernetes, and Ceph, NERDD ensures high availability, fault tolerance, and dynamic scalability. As an open-source solution, it empowers researchers across disciplines to deploy machine learning models in a reproducible and maintainable manner, while offering specialized capabilities for cheminformatics.