Surface-VQMAE: Vector-quantized Masked Auto-encoders on Molecular Surfaces

Authors: Fang Wu, Stan Z. Li

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental extensive experiments on diverse real-life scenarios including binding site scoring, binding affinity prediction, and mutant effect estimation demonstrate its effectiveness.
Researcher Affiliation Collaboration 1School of Engineering, Westlake University. Correspondence to: Stan Z. Li <stan.zq.li@westlake.edu.cn>.
Pseudocode No The paper describes the methods in narrative text and mathematical formulas but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https: //github.com/smiles724/VQMAE.
Open Datasets Yes The unlabeled data for pretraining Surface-VQMAE is procured from PDB-REDO (Joosten et al., 2014).
Dataset Splits Yes These clusters are further randomly divided into the training, validation, and test sets by 95%/0.5%/4.5%, respectively.
Hardware Specification Yes We implement all experiments on 4 A100 GPUs, each with 80G memory.
Software Dependencies No The paper mentions the use of an Adam optimizer and the Ke Ops library, but it does not specify version numbers for these or other key software components like Python or PyTorch.
Experiment Setup Yes During the pretraining stage, Surface-VQMAE is trained with an Adam optimizer (Kingma & Ba, 2014) with a weight decay of 5.e 3 and with β1 = 0.9 and β2 = 0.999. A Reduce LROn Plateau scheduler is employed to automatically adjust the learning rate with a patience of 5 epochs and a minimum learning rate of 1.e 7. The batch size is set to 32 and an initial learning rate is 1.e 4. The maximum iterations are 200K with warmingup iterations of 10K and the validation frequency is 1K iterations. The random seed is fixed as 2023.