FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Authors: Songtao Liu, Zhengkai Tu, Minkai Xu, Zuobai Zhang, Lu Lin, Rex Ying, Jian Tang, Peilin Zhao, Dinghao Wu
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Comprehensive experiments demonstrate that by fusing in the context information over routes, our model significantly improves the performance of retrosynthetic planning over baselines that are not context-aware, especially for long synthetic routes. |
| Researcher Affiliation | Collaboration | 1Pennsylvania State University 2Massachusetts Institute of Technology 3Stanford University 4Mila Qu ebec AI Institute 5Universit e de Montr eal 6Yale University 7HEC Montr eal 8CIFAR AI Chair 9Tencent AI Lab. |
| Pseudocode | Yes | Algorithm 1 Inference given a target molecule |
| Open Source Code | Yes | Code is available at https://github. com/Songtao Liu0823/Fusion Retro. |
| Open Datasets | Yes | We construct a benchmark for retrosynthetic planning using the public USPTO-full dataset |
| Dataset Splits | Yes | We disregard routes that synthesize target molecules in one step and split the remaining molecules into training, validation, and test datasets in an 80%/10%/10% ratio. |
| Hardware Specification | Yes | Our proposed model, Fusion Retro, is trained using 2 NVIDIA Tesla V100 GPUs. All the experiments of baselines are conducted on a single NVIDIA Tesla V100 with 32GB memory size. |
| Software Dependencies | Yes | We use Pytorch (Paszke et al., 2019) to implement Fusion Retro. The software that we use for experiments are Python 3.6.8, pytorch 1.9.0, pytorch-scatter 2.0.9, pytorch-sparse 0.6.12, numpy 1.19.2, torchvision 0.10.0, CUDA 10.2.89, CUDNN 7.6.5, einops 0.4.1, and torchdrug 0.1.3. |
| Experiment Setup | Yes | For all hyperparameters, except for the learning rate (due to the spike phenomenon), we adhere to the settings reported in the publicly released Transformer code and do not perform any additional hyperparameter tuning. Detailed information on the hyperparameters can be found in Appendix B.1. Table 4. The hyper-parameters for Fusion Retro. max length 200 embedding size 64 encoder layers 3 decoder layers 3 fusion layers 3 attention heads 10 FFN hidden 512 dropout 0.1 epochs 4000 batch size 64 warmup 16000 lr factor 20 |