FMFloriane Montanari

Floriane Montanari

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

Floriane Montanari has a total of 247 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Identification of non-covalent inhibitors for the atypical peroxiredoxin PRDX5 as a therapeutic strategy in malignant pleural mesothelioma

    by Josep Monserrat, Floriane Montanari, Victor Laurent, Pierre-Benoit Ancey, Nicolas Jean, Cécilia Jeannu, Guimin Wang, Genshu You, Qiancheng Shen, Alice Mac Kain, et al.

    Malignant pleural mesothelioma (MPM) is an aggressive asbestos-linked cancer with limited therapeutic options and a dismal 5-year survival rate of ~5%. While aberrant production of reactive oxygen and nitrogen species (ROS/RNS) is a hallmark of MPM, targeted approaches to exploit these redox vulnerabilities remain scarce. Here, using the MOSAIC multimodal cancer patient atlas, we identify Peroxiredoxin 5 (PRDX5) as being significantly upregulated in the epithelioid subtype of MPM. We show that MPM cells exhibit enhanced resistance to nitrosative and oxidative stress compared to healthy mesothelial cells, a phenotype correlated with basal PRDX5 expression. Next, utilising a machine learning guided discovery pipeline, we identified three putative allosteric pockets in PRDX5 and conducted a virtual screen of 3.6 million compounds. High-throughput biochemical validation of 452 candidates yielded 36 non-covalent hits, including sub-micromolar inhibitors. These findings establish PRDX5 as a novel, subtype specific therapeutic target in MPM and provide a chemical framework for the development of next-generation redox-modulating oncology treatments.

  • Top Cited Papers

    A Computational Community Blind Challenge on Pan-Coronavirus Drug Discovery Data

    by Hugo MacDermott-Opeskin, Jenke Scheen, Cas Wognum, Joshua T. Horton, Devany West, Alexander Matthew Payne, Maria A. Castellanos, Sean Colby, Edward Griffen, David Cousins, et al.

    Computational blind challenges offer critical, unbiased opportunities to assess and accelerate scientific progress, as demonstrated by a breadth of breakthroughs over the past decade. We report the outcomes and key insights from an open science community blind challenge focused on computational methods in drug discovery, using lead optimization data from the AI-driven Structure-enabled Antiviral Platform Discovery Consortium's pan-coronavirus antiviral discovery program, in partnership with Polaris and the OpenADMET project. This collaborative initiative invited global participants from both academia and industry to develop and apply computational methods to predict the biochemical potency and crystallographic ligand poses of small molecules against key coronavirus targets, Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) and Middle East Respiratory Syndrome Coronavirus (MERS-CoV) main protease (Mpro), as well as multiple ADMET assay end points, using previously undisclosed comprehensive experimental drug discovery data sets as benchmarks. By evaluating submissions across multiple tasks and compounds, we established performance leaderboards and conducted meta-analyses to assess methodological strengths, common pitfalls, and areas for improvement. This analysis provides a foundation for best practices in real-world machine learning evaluation, grounded in community-driven benchmarking. We also highlight how next-generation platforms, such as Polaris, enable rigorous challenge design, embedded evaluation frameworks, and broad community engagement. This paper reports the collective findings of the challenge, offering a high-level overview of the data, evaluation infrastructure, and top-performing strategies. We further provide context and support for the accompanying papers authored by the challenge participants in this special issue, which explore individual approaches in greater depth. Together, these contributions aim to advance reproducible, trustworthy, and high-impact computational methods in drug discovery, and to explore best practices and pitfalls in future blind challenge design and execution, including planned initiatives for the OpenADMET project.


  • Open Access

    OKN4395, a first-in-class EP2/EP4/DP1 triple antagonist reprograms prostanoid-driven immunosuppression to restore antitumor immunity

    by Maximilien Grandclaudon, Morgane Boulch, Anna Thaller, Jonathan Sabio-Ortiz, Alexandre Grimaldi, Marie Goxe, Agnes Knopf, Marie V Daugan, Eva Huehn, Carmela Gnerre, et al.

    Immune checkpoint inhibitors, particularly T cell targeting anti-PD(L)1 therapies, have revolutionised the treatment landscape for solid malignancies, but challenges related to non-responsiveness and the development of treatment resistance continue to be observed. An additional immunosuppressive axis relates to prostaglandin signaling downstream of cyclooxygenase-2 (COX2), where COX2 inhibitors have shown clinical promise in re-engaging both T and non-T cell immune compartments, yet have suffered from toxicity concerns. We report here the preclinical characterization of OKN4395, a highly potent and specific first-in-class triple antagonist of EP2, EP4, and DP1, major tumor immunosuppressive receptors downstream of COX2. OKN4395 restores immune function on both T cells and NK cells in vitro. Additionally, OKN4395 acts synergistically with anti-PD1 to increase speed and depth of antitumor activity. Overall, these findings robustly support the clinical investigation of OKN4395 in an ongoing Phase 1 trial ( NCT06789172 ) as an innovative cancer immunotherapy for solid tumors, as a single agent and in combination with anti-PD1 therapy.

  • Open Access

    Predicting Liver-Related In Vitro Endpoints with Machine Learning to Support Early Detection of Drug-Induced Liver Injury

    by Marina Garcia de Lomana, Domenico Gadaleta, Marian Raschke, Robert Fricke, Floriane Montanari

    Drug-induced liver injury (DILI) is a major cause of drug development failures and postmarket drug withdrawals, posing significant challenges to public health and pharmaceutical research. The biological mechanisms leading to DILI are highly complex and the adverse reaction is often difficult to foresee. Hence, mechanistic insights into DILI, as well as machine learning models to predict molecular events that trigger adverse outcomes, pharmacokinetics and pharmacodynamics in the liver, are essential tools for understanding and preventing DILI. In this study, we collected a comprehensive data set of 28 in vitro endpoints related to liver toxicity and function, as well as data specific to DILI, to explore the potential of multi-task learning for their prediction. We demonstrate the benefits of ensemble modeling and provide an uncertainty estimation based on the standard deviation of the predictions to define an applicability domain for the models. Available assays at Bayer for two of the endpoints (Bile salt export pump (BSEP) inhibition and phospholipidosis) were run on a set of public compounds and used for further evaluation (data provided in the Supporting Information). Additionally, we conducted an in-depth data analysis of the relationships among the different endpoints, as well as with DILI. The presented models can be used to derive a "Virtual Liver Safety Profile" showcasing the predicted activity of a compound on the selected endpoints to support the prioritization of assays and the elucidation of modes of action.


  • Open Access

    Enhancing Interpretability in Molecular Property Prediction with Contextual Explanations of Molecular Graphical Depictions

    by Marco Bertolini, Linlin Zhao, Floriane Montanari, Djork-Arné Clevert

    The field of explainable AI applied to molecular property prediction models has often been reduced to deriving atomic contributions. This has impaired the interpretability of such models, as chemists rather think in terms of larger, chemically meaningful structures, which often do not simply reduce to the sum of their atomic constituents. We develop an explanatory strategy yielding both local as well as more complex structural attributions. We derive such contextual explanations in pixel space, exploiting the property that a molecule is not merely encoded through a collection of atoms and bonds, as is the case for string- or graph-based approaches. We provide evidence that the proposed explanation method satisfies desirable properties, namely sparsity and invariance with respect to the molecule’s symmetries, to a larger degree that the SMILES-based counterpart model. Nonetheless, they correlate as expected with these string-based explanation as well as with ground truths, when available. Contextual explanations thus maintain the accuracy of the original explanations while improving their interpretability.


  • Open Access

    Solvmate - A hybrid physical/ML approach to solvent recommendation leveraging a rank-based problem framework

    by Jan Wollschläger, Floriane Montanari

    The solubility in a given organic solvent is a key parameter in the synthesis, analysis and chemical processing of an active pharmaceutical ingredient. In this work, we introduce a new tool for organic solvent recommendation that ranks possible solvent choices requiring only the SMILES representation of the solvents and solute involved. We report on three additional innovations: First, a differential/relative approach to solubility prediction is employed, in which solubility is modeled using pairs of measurements with the same solute but different solvents. We show that a relative framing of solubility as ranking solvents improves over a corresponding absolute solubility model across a diverse set of selected features. Second, a novel semiempirical featurization based on extended tight-binding (xtb) is applied to both the solvent and the solute, thereby providing physically meaningful representations of the problem at hand. Third, we provide an open-source implementation of this practical and convenient tool for organic solvent recommendation. Taken together, this work could be of benefit to those working in diverse areas, such as chemical engineering, material science, or synthesis planning.

  • Open Access

    Predicting the Mitochondrial Toxicity of Small Molecules: Insights from Mechanistic Assays and Cell Painting Data

    by Marina Garcia de Lomana, Paula Andrea Marin Zapata, Floriane Montanari

    Mitochondrial toxicity is a significant concern in the drug discovery process, as compounds that disrupt the function of these organelles can lead to serious side effects, including liver injury and cardiotoxicity. Different in vitro assays exist to detect mitochondrial toxicity at varying mechanistic levels: disruption of the respiratory chain, disruption of the membrane potential, or general mitochondrial dysfunction. In parallel, whole cell imaging assays like Cell Painting provide a phenotypic overview of the cellular system upon treatment and enable the assessment of mitochondrial health from cell profiling features. In this study, we aim to establish machine learning models for the prediction of mitochondrial toxicity, making the best use of the available data. For this purpose, we first derived highly curated datasets of mitochondrial toxicity, including subsets for different mechanisms of action. Due to the limited amount of labeled data often associated with toxicological endpoints, we investigated the potential of using morphological features from a large Cell Painting screen to label additional compounds and enrich our dataset. Our results suggest that models incorporating morphological profiles perform better in predicting mitochondrial toxicity than those trained on chemical structures alone (up to +0.08 and +0.09 mean MCC in random and cluster cross-validation, respectively). Toxicity labels derived from Cell Painting images improved the predictions on an external test set up to +0.08 MCC. However, we also found that further research is needed to improve the reliability of Cell Painting image labeling. Overall, our study provides insights into the importance of considering different mechanisms of action when predicting a complex endpoint like mitochondrial disruption as well as into the challenges and opportunities of using Cell Painting data for toxicity prediction.


  • Open Access

    A Fast and Interpretable Deep Learning Approach for Accurate Electrostatics-Driven pKa Predictions in Proteins

    by Pedro B.P.S. Reis, Marco Bertolini, Floriane Montanari, Walter Rocchia, Miguel Machuqueiro, Djork-Arné Clevert

    Existing computational methods for estimating pKa values in proteins rely on theoretical approximations and lengthy computations. In this work, we use a data set of 6 million theoretically determined pKa shifts to train deep learning models, which are shown to rival the physics-based predictors. These neural networks managed to infer the electrostatic contributions of different chemical groups and learned the importance of solvent exposure and close interactions, including hydrogen bonds. Although trained only using theoretical data, our pKAI+ model displayed the best accuracy in a test set of ∼750 experimental values. Inference times allow speedups of more than 1000× compared to physics-based methods. By combining speed, accuracy, and a reasonable understanding of the underlying physics, our models provide a game-changing solution for fast estimations of macroscopic pKa values from ensembles of microscopic values as well as for many downstream applications such as molecular docking and constant-pH molecular dynamics simulations.


  • Open Access

    ChemInformatics Model Explorer (CIME): exploratory analysis of chemical model explanations

    by Christina Humer, Henry Heberle, Floriane Montanari, Thomas Wolf, Florian Huber, Ryan Henderson, Julian Heinrich, Marc Streit

    The introduction of machine learning to small molecule research– an inherently multidisciplinary field in which chemists and data scientists combine their expertise and collaborate - has been vital to making screening processes more efficient. In recent years, numerous models that predict pharmacokinetic properties or bioactivity have been published, and these are used on a daily basis by chemists to make decisions and prioritize ideas. The emerging field of explainable artificial intelligence is opening up new possibilities for understanding the reasoning that underlies a model. In small molecule research, this means relating contributions of substructures of compounds to their predicted properties, which in turn also allows the areas of the compounds that have the greatest influence on the outcome to be identified. However, there is no interactive visualization tool that facilitates such interdisciplinary collaborations towards interpretability of machine learning models for small molecules. To fill this gap, we present CIME (ChemInformatics Model Explorer), an interactive web-based system that allows users to inspect chemical data sets, visualize model explanations, compare interpretability techniques, and explore subgroups of compounds. The tool is model-agnostic and can be run on a server or a workstation.


  • Open Access

    Img2Mol – accurate SMILES recognition from molecular graphical depictions

    by Djork-Arné Clevert, Tuan Le, Robin Winter, Floriane Montanari

    The automatic recognition of the molecular content of a molecule's graphical depiction is an extremely challenging problem that remains largely unsolved despite decades of research.