BKBenjamin Kaminow

Benjamin Kaminow

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Benjamin Kaminow has a total of 177 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    How Many Crystal Structures Do You Need to Trust Your Docking Results?

    by Alexander Matthew Payne, Benjamin Kaminow, Hugo I. MacDermott-Opeskin, Iván Pulido, Jenke Scheen, Maria A. Castellanos, Daren Fearon, John D. Chodera, Sukrit Singh

    Structure-based drug discovery relies on the prediction of protein-bound poses of new molecule designs, the accuracy of which can impact downstream prioritization. While it is expected that crystal structures of similar molecules would provide the best template for predicting the poses of new designs, the time and cost required motivates identifying a point of diminishing returns for collecting new structures. Using 403 crystal structures of SARS-CoV-2 main protease from the open science COVID Moonshot project, we explore the tradeoff between the cost and utility of obtaining crystal structures for accurately predicting poses of designed molecules. We observe that similar reference ligands enable superior pose prediction and show that success plateaus after approximately five crystal structures per generic Bemis-Murcko scaffold, exceeding 95% for the campaign’s lead series. This work provides practical recommendations for resource allocation in structure-enabled drug discovery campaigns.

  • Open Access

    Physical priors improve performance of structure-based binding affinity models

    by Benjamin Kaminow, Alexander Matthew Payne, Hugo MacDermott-Opeskin, John D. Chodera, Sukrit Singh

    Structure-based drug discovery is a widely used paradigm for the rational design of novel small molecule therapeutics. However, the benefits conferred by the use of structural information has seen limited adoption in machine learning, where ligand-only ("2D") models are still the industry standard for molecular property or binding affinity prediction. Structure-based ("3D") ML models for binding-affinity prediction promise to present a clear advantage, but have not yet overtaken existing 2D models. Here, we show that physics-based priors can improve predictive performance of structure-based models by comparing different model architectures with varying physical priors on several prediction tasks. We present the Modular Training and Evaluation of Neural Networks ( mtenn ) package, where we decompose affinity prediction into separate steps of embedding structure into learned representations and combining those embeddings into a predicted binding affinity. We consider both E(3)-invariant and E(3)-equivariant architectures to determine the importance of encoding roto-translational inductive biases, as well as different methods for combining learned embeddings. By first optimizing several aspects of model construction using the general purpose PDBBind dataset, we are able to improve the performance and data efficiency of structure-based models. When subsequently trained and evaluated on the COVID Moonshot small molecule drug discovery dataset, our tuned models perform on par with industry standard ligand-only models. Our decomposed model framework highlights that encoding some physical priors improves model performance, while more complex biases such as equivariance offer limited benefit. Additionally, structure-based models generalize better to an unseen target and display higher training efficiency. Overall, these results emphasize that structure-based models benefit from their ability to incorporate physics-informed constraints, giving promising directions for model architecture development. These results also suggest that the strength of these models may be in tasks specifically aimed at generalizability, providing guidelines for their use in early-stage drug discovery campaigns.

  • Open Access

    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 assessment opportunities to assess and accelerate scientific progress, as demonstrated by a breadth of breakthroughs over the last 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 (ASAP) 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 endpoints, using previously undisclosed comprehensive experimental drug discovery datasets 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

    How many crystal structures do you need to trust your docking results?

    by Alexander Matthew Payne, Benjamin Kaminow, Hugo MacDermott-Opeskin, Iván Pulido, Jenke Scheen, Maria A Castellanos, Daren Fearon, John D. Chodera, Sukrit Singh

    Structure-based drug discovery technologies generally require the prediction of putative bound poses of protein:small molecule complexes to prioritize them for synthesis. The predicted structures are used for a variety of downstream tasks such as pose-scoring functions or as a starting point for binding free energy estimation. The accuracy of downstream models depends on how well predicted poses match experimentally-validated poses. Although the ideal input to these downstream tasks would be experimental structures, the time and cost required to collect new experimental structures for synthesized compounds makes obtaining this structure for every input intractable. Thus, leveraging available structural data is required to efficiently extrapolate new designs. Using data from the open science COVID Moonshot project—where nearly every compound synthesized was crystallographically screened—we assess several popular strategies for generating docked poses in a structure-enabled discovery program using both retrospective and prospective analyses. We explore the tradeoff between the cost of obtaining crystal structures and the utility for accurately predicting poses of newly designed molecules. We find that a simple strategy using molecular similarity to identify relevant structures for template-guided docking is successful in predicting poses for the SARS-CoV-2 main viral protease. Further efficiency analysis suggests template-based docking of a scaffold series is a robust strategy even when the quantity of available structural data is limited. The resulting open source pipeline and curated datasets should prove useful for automated modeling of bound poses for downstream scoring, machine learning, and free energy calculation tasks for structure-based drug discovery programs.


  • Open Access

    The Journey of Data: Lessons Learned in Modeling Kinase Affinity, Selectivity, and Resistance [Article v1.0]

    by Raquel López-Ríos de Castro, Jaime Rodríguez-Guerra, David Schaller, Talia B. Kimber, Corey Taylor, Jessica B. White, Michael Backenköhler, Joschka Groß, Alexander M. Payne, Benjamin Kaminow, et al.

    Recent advances in machine learning (ML) are reshaping drug discovery. Structure-based ML methods use physically-inspired models to predict binding affinities from protein:ligand complexes. These methods promise to enable the integration of data for many related targets, which addresses issues related to data scarcity for single targets and could enable generalizable predictions for a broad range of targets, including mutations. In this work, we report our experiences in building KinoML, a novel framework for ML in target-based small molecule drug discovery with an emphasis on structure-enabled methods. KinoML focuses currently on kinases as the relative structural conservation of this protein superfamily, particularly in the kinase domain, means it is possible to leverage data from the entire superfamily to make structure-informed predictions about binding affinities, selectivities, and drug resistance. Some key lessons learned in building KinoML include the importance of reproducible data collection and deposition, the harmonization of molecular data and featurization, and the selection of the right data format to ensure reusability and reproducibility of ML models. As a result, KinoML allows users to easily achieve three tasks: accessing and curating molecular data; featurizing this data with representations suitable for ML applications; and running reproducible ML experiments that require access to ligand, protein, and assay information to predict ligand affinity. Despite KinoML focusing on kinases, this framework can be applied to other proteins. The lessons reported here can help guide the development of platforms for structure-enabled ML in other areas of drug discovery.


  • Open Access

    Figure S1 Legend from High-Throughput Prediction of MHC Class I and II Neoantigens with MHCnuggets

    by Xiaoshan M. Shao, Rohit Bhattacharya, Justin Huang, I.K. Ashok Sivakumar, Collin Tokheim, Lily Zheng, Dylan Hirsch, Benjamin Kaminow, Ashton Omdahl, Maria Bonsack, et al.

  • Open Access

    Figure S1 Legend from High-Throughput Prediction of MHC Class I and II Neoantigens with MHCnuggets

    by Xiaoshan M. Shao, Rohit Bhattacharya, Justin Huang, I.K. Ashok Sivakumar, Collin Tokheim, Lily Zheng, Dylan Hirsch, Benjamin Kaminow, Ashton Omdahl, Maria Bonsack, et al.

  • Open Access

    Supplementary Table 1-9 from High-Throughput Prediction of MHC Class I and II Neoantigens with MHCnuggets

    by Xiaoshan M. Shao, Rohit Bhattacharya, Justin Huang, I.K. Ashok Sivakumar, Collin Tokheim, Lily Zheng, Dylan Hirsch, Benjamin Kaminow, Ashton Omdahl, Maria Bonsack, et al.

  • Open Access

    Supplementary Table 1-9 from High-Throughput Prediction of MHC Class I and II Neoantigens with MHCnuggets

    by Xiaoshan M. Shao, Rohit Bhattacharya, Justin Huang, I.K. Ashok Sivakumar, Collin Tokheim, Lily Zheng, Dylan Hirsch, Benjamin Kaminow, Ashton Omdahl, Maria Bonsack, et al.

  • Open Access

    Figure S1 from High-Throughput Prediction of MHC Class I and II Neoantigens with MHCnuggets

    by Xiaoshan M. Shao, Rohit Bhattacharya, Justin Huang, I.K. Ashok Sivakumar, Collin Tokheim, Lily Zheng, Dylan Hirsch, Benjamin Kaminow, Ashton Omdahl, Maria Bonsack, et al.