# MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling

arXiv: https://arxiv.org/abs/2402.10387 · HTML: https://mlsanity.com/paper/2402.10387/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 60 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 25 of 25)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [Optimization of Molecules via Deep Reinforcement Learning](https://mlsanity.com/paper/1810.08678/) (2018)
- [Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets](https://mlsanity.com/paper/2205.07249/) (2022)
- [Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)](https://mlsanity.com/paper/1503.01057/) (2015)
- [3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction](https://mlsanity.com/paper/2303.03543/) (2023)
- [MARS: Markov Molecular Sampling for Multi-objective Drug Discovery](https://mlsanity.com/paper/2103.10432/) (2021)
- [Exploring Chemical Space with Score-based Out-of-distribution Generation](https://mlsanity.com/paper/2206.07632/) (2022)
- [Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning](https://mlsanity.com/paper/1903.04703/) (2019)
- [DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations](https://mlsanity.com/paper/2201.09637/) (2022)
- [Reinforced Genetic Algorithm for Structure-based Drug Design](https://mlsanity.com/paper/2211.16508/) (2022)
- [LIMO: Latent Inceptionism for Targeted Molecule Generation](https://mlsanity.com/paper/2206.09010/) (2022)
- [Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning](https://mlsanity.com/paper/2004.14308/) (2020)
- [Autonomous discovery in the chemical sciences part II: Outlook](https://mlsanity.com/paper/2003.13755/) (2020)
- [Overview of Gaussian process based multi-fidelity techniques with variable relationship between fidelities](https://mlsanity.com/paper/2006.16728/) (2020)
- [Deep Multi-Fidelity Active Learning of High-dimensional Outputs](https://mlsanity.com/paper/2012.00901/) (2020)
- [Multi-fidelity Hierarchical Neural Processes](https://mlsanity.com/paper/2206.04872/) (2022)
- [Multi-Fidelity Active Learning with GFlowNets](https://mlsanity.com/paper/2306.11715/) (2023)
- [Disentangled Multi-Fidelity Deep Bayesian Active Learning](https://mlsanity.com/paper/2305.04392/) (2023)

## Built on by (most cited first, 2 of 2)

- [Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation](https://mlsanity.com/paper/2405.17066/) (2024)
- [Active learning for affinity prediction of antibodies](https://mlsanity.com/paper/2406.07263/) (2024)

## Abstract (arXiv)

Current generative models for drug discovery primarily use molecular docking to evaluate the quality of generated compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. We propose a multi-fidelity approach, Multi-Fidelity Bind (MFBind), to achieve the optimal trade-off between accuracy and computational cost. MFBind integrates docking and binding free energy simulators to train a multi-fidelity deep surrogate model with active learning. Our deep surrogate model utilizes a pretraining technique and linear prediction heads to efficiently fit small amounts of high-fidelity data. We perform extensive experiments and show that MFBind (1) outperforms other state-of-the-art single and multi-fidelity baselines in surrogate modeling, and (2) boosts the performance of generative models with markedly higher quality compounds.