# DOCKSTRING: easy molecular docking yields better benchmarks for ligand design

arXiv: https://arxiv.org/abs/2110.15486 · HTML: https://mlsanity.com/paper/2110.15486/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 111 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining](https://mlsanity.com/paper/2006.09191/) (2020)
- [Learning Multimodal Graph-to-Graph Translation for Molecular Optimization](https://mlsanity.com/paper/1812.01070/) (2018)
- [NeVAE: A Deep Generative Model for Molecular Graphs](https://mlsanity.com/paper/1802.05283/) (2018)
- [Mol-CycleGAN - a generative model for molecular optimization](https://mlsanity.com/paper/1902.02119/) (2019)
- [Accelerating high-throughput virtual screening through molecular pool-based active learning](https://mlsanity.com/paper/2012.07127/) (2020)
- [Protein-Ligand Scoring with Convolutional Neural Networks](https://mlsanity.com/paper/1612.02751/) (2016)
- [Guiding Deep Molecular Optimization with Genetic Exploration](https://mlsanity.com/paper/2007.04897/) (2020)
- [AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery](https://mlsanity.com/paper/1510.02855/) (2015)
- [Autonomous discovery in the chemical sciences part II: Outlook](https://mlsanity.com/paper/2003.13755/) (2020)
- [Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning](https://mlsanity.com/paper/2012.11293/) (2020)
- [Reinforced Molecular Optimization with Neighborhood-Controlled Grammars](https://mlsanity.com/paper/2011.07225/) (2020)
- [Goal-directed Generation of Discrete Structures with Conditional Generative Models](https://mlsanity.com/paper/2010.02311/) (2020)
- [A deep-learning view of chemical space designed to facilitate drug discovery](https://mlsanity.com/paper/2002.02948/) (2020)
- [Bayesian Variational Optimization for Combinatorial Spaces](https://mlsanity.com/paper/2011.02004/) (2020)

## Built on by (most cited first, 30 of 35)

- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [Exploring Chemical Space with Score-based Out-of-distribution Generation](https://mlsanity.com/paper/2206.07632/) (2022)
- [A Systematic Survey of Automatic Prompt Optimization Techniques](https://mlsanity.com/paper/2502.16923/) (2025)
- [Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison](https://mlsanity.com/paper/2511.07919/) (2025)
- [A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences](https://mlsanity.com/paper/2406.04739/) (2024)
- [Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction](https://mlsanity.com/paper/2205.02708/) (2022)
- [Graph Neural Networks for Molecules](https://mlsanity.com/paper/2209.05582/) (2022)
- [Searching for High-Value Molecules Using Reinforcement Learning and Transformers](https://mlsanity.com/paper/2310.02902/) (2023)
- [Stochastic Gradient Descent for Gaussian Processes Done Right](https://mlsanity.com/paper/2310.20581/) (2023)
- [Tanimoto Random Features for Scalable Molecular Machine Learning](https://mlsanity.com/paper/2306.14809/) (2023)
- [An end-to-end attention-based approach for learning on graphs](https://mlsanity.com/paper/2402.10793/) (2024)
- [Inversion-based Latent Bayesian Optimization](https://mlsanity.com/paper/2411.05330/) (2024)
- [Self-focusing virtual screening with active design space pruning](https://mlsanity.com/paper/2205.01753/) (2022)
- [Re-evaluating sample efficiency in de novo molecule generation](https://mlsanity.com/paper/2212.01385/) (2022)
- [Pareto Optimization to Accelerate Multi-Objective Virtual Screening](https://mlsanity.com/paper/2310.10598/) (2023)
- [Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation](https://mlsanity.com/paper/2503.06337/) (2025)
- [Computational modeling of semantic change](https://mlsanity.com/paper/2304.06337/) (2023)
- [Batched Bayesian optimization by maximizing the probability of including the optimum](https://mlsanity.com/paper/2410.06333/) (2024)
- [Efficient Adaptive Data Acquisition via Pretrained Belief Representations](https://mlsanity.com/paper/2606.25197/) (2026)
- [Conditional Neural Processes for Molecules](https://mlsanity.com/paper/2210.09211/) (2022)
- [In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement](https://mlsanity.com/paper/2410.03124/) (2024)
- [Preferential Multi-Objective Bayesian Optimization for Drug Discovery](https://mlsanity.com/paper/2503.16841/) (2025)
- [Hash Collisions in Molecular Fingerprints: Effects on Property Prediction and Bayesian Optimization](https://mlsanity.com/paper/2511.17078/) (2025)
- [An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization](https://mlsanity.com/paper/2210.16099/) (2022)
- [Smiles2Dock: an open large-scale multi-task dataset for ML-based molecular docking](https://mlsanity.com/paper/2406.05738/) (2024)
- [Understanding active learning of molecular docking and its applications](https://mlsanity.com/paper/2406.12919/) (2024)
- [Look the Other Way: Designing 'Positive' Molecules with Negative Data via Task Arithmetic](https://mlsanity.com/paper/2507.17876/) (2025)
- [APEX: Approximate-but-exhaustive search for ultra-large combinatorial synthesis libraries](https://mlsanity.com/paper/2510.24380/) (2025)
- [MolLIBRA: Genetic Molecular Optimization with Multi-Fingerprint Surrogates and Text-Molecule Aligned Critic](https://mlsanity.com/paper/2602.07002/) (2026)

## Abstract (arXiv)

The field of machine learning for drug discovery is witnessing an explosion of novel methods. These methods are often benchmarked on simple physicochemical properties such as solubility or general druglikeness, which can be readily computed. However, these properties are poor representatives of objective functions in drug design, mainly because they do not depend on the candidate's interaction with the target. By contrast, molecular docking is a widely successful method in drug discovery to estimate binding affinities. However, docking simulations require a significant amount of domain knowledge to set up correctly which hampers adoption. To this end, we present DOCKSTRING, a bundle for meaningful and robust comparison of ML models consisting of three components: (1) an open-source Python package for straightforward computation of docking scores; (2) an extensive dataset of docking scores and poses of more than 260K ligands for 58 medically-relevant targets; and (3) a set of pharmaceutically-relevant benchmark tasks including regression, virtual screening, and de novo design. The Python package implements a robust ligand and target preparation protocol that allows non-experts to obtain meaningful docking scores. Our dataset is the first to include docking poses, as well as the first of its size that is a full matrix, thus facilitating experiments in multiobjective optimization and transfer learning. Overall, our results indicate that docking scores are a more appropriate evaluation objective than simple physicochemical properties, yielding more realistic benchmark tasks and molecular candidates.