PegaPlus─Interactive Machine Learning by Human Observation for Efficient Clustering and Analysis of Structure-Activity Data

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Approximately 50% reduction in refinement steps with PegaPlus compared to purely manual clustering approach

• Primary Outcome: Number of expert refinement steps required to achieve satisfactory compound clustering of HTS data

• Nnt Or Sensitivity: Not applicable in the traditional clinical sense; no NNT, sensitivity, or specificity metrics reported. No clustering quality metrics (e.g., purity, adjusted Rand index) are provided in the abstract.

• Confidence Interval: Not reported

Clinical Application

The tool is freely accessible via an open web server (pegaplus.zbh.uni-hamburg.de), requiring no local installation. Feasibility in practice depends on internet access, browser compatibility, and user willingness to engage with an interactive visual interface. Integration into existing drug discovery informatics pipelines is not described. This study has no direct relevance to PBS listing, TGA regulatory processes, or RACGP clinical guidelines, as it is a preclinical cheminformatics tool. However, it is relevant to Australian pharmaceutical research institutions, medicinal chemistry groups within universities and the CSIRO, and biotechnology companies engaged in early drug discovery. Australian researchers at institutions such as Monash Institute of Pharmaceutical Sciences, the Walter and Eliza Hall Institute, and WEHI may find utility in this tool for SAR-driven lead optimisation programs. No TGA or PBS implications arise from this publication. Medicinal chemists, computational chemists, and drug discovery scientists engaged in early-phase SAR analysis of HTS compound libraries. Not directly applicable to clinical patient care.

Abstract

In the early stages of drug discovery, the identification of molecular series with lead-like properties is essential for structure-activity relationship studies. A common first step is to cluster data derived from high-throughput screening (HTS). This data then needs to be exhaustively refined by an expert to identify bioactive compound classes. Here, we present the novel, interactive, and visual approach named PegaPlus for the analysis of HTS data, facilitating the incorporation of expert knowledge with the strategy of learning by observation. PegaPlus uses a tailored variant of a stochastic proximity embedding algorithm to visualize the clustered data in a two-dimensional plane via a web interface. The user can iteratively modify the proposed compound clustering by dragging data points in the drawing plane. At each step, an online support vector machine learns and improves its clustering predictions by incorporating user modifications and the molecular features of the compounds. The visualization is also updated based on the user's input and molecular similarity. PegaPlus was developed with the exploratory process in mind and allows the user to freely organize molecules on the drawing plane, or filter them by various molecular properties. Our evaluation shows that PegaPlus reduces the number of refinement steps needed by half in comparison to the purely manual approach on multiple data sets. These results demonstrate how an interactive machine learning approach can reliably support medicinal chemists and automate time-consuming, manual refinement tasks. The PegaPlus web server is openly available at pegaplus.zbh.uni-hamburg.de.

References

1. 1.Fährrolfes, R., Sieg, J., Flachsenberg, F., & Rarey, M. (2026). PegaPlus─Interactive machine learning by human observation for efficient clustering and analysis of structure-activity data. Journal of Chemical Information and Modeling. Advance online publication. https://doi.org/10.1021/acs.jcim.6c00524