LEAD OPTIMIZATION

SCOPE: Shape and Color-based Prediction Ensemble

OpenEye’s 3D-QSAR with built-in prediction confidence

SCOPE is OpenEye’s 3D Quantitative Structure–Activity Relationship (3D-QSAR) solution for predicting binding affinity. It uses molecular similarity between aligned ligands as the primary descriptor, combining multiple models with different similarity descriptors and machine learning techniques. The model's prediction is a consensus of individual model predictions.

SCOPE generates easily interpretable maps of where in the model chemical features such as hydrogen bond donors and acceptors contribute positively to binding affinity.

Features

Cutting Edge. Descriptors based on our industry leading OpenEye 3D shape and electrostatic tools (ROCS and EON).
Robust. Prediction provided as consensus of multiple models.
Flexible. Uses your 3D conformers or generates them with OpenEye tools.
Confidence. Prediction confidence based on domain of applicability.
Interpretable. Model interpretation indicating favorable sites of functional groups.

Inspiring new ideas through the interpretation of visual models

A common challenge for 3D-QSAR is interpretation. SCOPE keeps the model readable, helping scientists interpret regions within the active site, indicating preferences for specific features.

SCOPE doesn’t assume anything about the receptor/binding site. It picks out the features that contribute most to the model. These interpretations can inspire new ideas and make the model a useful part of a generative design cycle.

Model interpretation indicating preference sites of molecules

FE-NES and SCOPE combination active learning

Active learning with SCOPE and FE-NES provides medicinal chemists with rank-ordered hit lists and key structural insights into potency drivers, supporting confident SAR-driven design decisions.

Scale Lead Optimization with SCOPE and Binding Free Energy Predictions

Building models from measured affinities is effective but limited by the time and cost required to perform the experiments. SCOPE can be used in active learning workflows to build models based on predicted affinity data from our relative binding free energy tool, FE-NES.

In a retrospective study of a library of over 4500 Tyk2 ligands, ten rounds of active learning with 50 FE-NES predictions each (therefore requiring only 500 FE-NES calculations in total) identified 56 molecules with higher predicted potency than any identified experimentally, providing potential new starting points for a new round of lead optimization.

Read the Science Brief

Innovative science designed in collaboration with industry partners

We developed SCOPE in partnership with multiple drug discovery companies. Leveraging OpenEye’s cutting-edge expertise in 3D shape and electrostatics, this 3D-QSAR approach provides drug discovery scientists with results that are interpretable and actionable for use in drug discovery.

: SCOPE stands for Shape and Color-based Prediction Ensemble. It is OpenEye’s 3D-QSAR method.
: SCOPE uses the well-validated ROCS^® molecular shape- and color-based similarity and the more physically rigorous shape and electrostatic potential similarity from EON. Besides the ROCS- and EON-based similarity descriptors, 2D circular fingerprint (FP) based similarity is also included in some of the individual 3D models.
: Two distinct machine learning approaches, namely kernel Partial Least Squares (kPLS) and Gaussian Process Regression (GPR), are used for model building. These methods are selected for their suitability for building models with small datasets, which is the case for potency models.
: SCOPE offers a cost-effective approach to predict potency or binding affinity. Compute costs may vary depending on whether conformer generation is needed. Our tests average tens of dollars for a typical dataset of hundreds of molecules.

OpenEye's SCOPE workflow combines shape similarity descriptors with machine learning models.

Learn More

SCOPE: From Shape and Color to Binding Affinity, with Confidence. Chen et al. [Preprint] Research Square. September 2026.

3D QSAR Model for Binding Affinity Prediction. Shyamal K. Nath, Jingyi Chen, Ali Mozaffari and Riddhish Pandharkar. Ninth Joint Sheffield Conference on Chemoinformatics, University of Sheffield, UK, June 2023.

New 3D-QSAR Model for Binding Affinity Prediction. Ali Mozaffari, Jingyi Chen, Shyamal K. Nath. ACS Fall Meeting, San Francisco, CA, August 2023.