Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
A Plug-and-Play Quaternion Message-Passing Module for Molecular Conformation Representation
Authors: Angxiao Yue, Dixin Luo, Hongteng Xu
AAAI 2024 | Venue PDF | LLM Run Details | Input Tokens: 19,434 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,175 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on various molecular datasets show that plugging our QMP module into existing invariant GNNs leads to consistent and significant improvements in molecular conformation representation and downstream tasks. |
| Researcher Affiliation | Academia | Angxiao Yue1, Dixin Luo2, Hongteng Xu1,3* 1Gaoling School of Artifical Intelligence, Renmin University of China, Beijing, China 2School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 3 Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the QMP module and its steps in prose and with mathematical formulas, but it does not include a clearly labeled 'Pseudocode' or 'Algorithm' block. |
| Open Source Code | Yes | The code is available at https://github.com/Angxiao Yue/QMP. |
| Open Datasets | Yes | We conduct experiments on three datasets, including MD17 (Chmiela et al. 2017), MD17@CCSD (Chmiela et al. 2018), and OC20 (Chanussot et al. 2021b). |
| Dataset Splits | Yes | We train each model using 1,000 conformations and 1,000 for validation, with the remaining used for testing. |
| Hardware Specification | Yes | To ensure experimental fairness, we conduct the experiments using the same hyperparameter settings and hardware environment (NVIDIA Ge Force RTX 3090). |
| Software Dependencies | No | The paper mentions using 'DIG2 framework (Liu et al. 2021a)' and 'Open Catalyst Project (OCP) framework3 (Chanussot et al. 2021a)' but does not specify version numbers for these frameworks or any other software dependencies like Python, PyTorch, etc. |
| Experiment Setup | Yes | To ensure experimental fairness, we conduct the experiments using the same hyperparameter settings and hardware environment (NVIDIA Ge Force RTX 3090). |