A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation
Authors: Yongkang Wang, Xuan Liu, Feng Huang, Zhankun Xiong, Wen Zhang
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The extensive experiments demonstrate that MMCD performs better than other state-of-the-art deep generative methods in generating therapeutic peptides across various metrics, including antimicrobial/anticancer score, diversity, and peptide-docking. Extensive experiments conducted on peptide datasets demonstrate that MMCD surpasses the current state-ofthe-art baselines in generating therapeutic peptides, particularly in terms of antimicrobial/anticancer score, diversity, and pathogen-docking. Experiments Experimental Setups Datasets. Following previous studies (Thi Phan et al. 2022; Zhang et al. 2023a), we collected therapeutic peptide data from public databases, containing two biological types, i.e., antimicrobial peptides (AMP) and anticancer peptides (ACP). Ablation Study To investigate the necessity of each module in MMCD, we conducted several comparisons between MMCD with its variants: |
| Researcher Affiliation | Academia | Yongkang Wang1*, Xuan Liu1*, Feng Huang1, Zhankun Xiong1, Wen Zhang1,2 3 1College of Informatics, Huazhong Agricultural University, Wuhan 430070, China 2Hubei Key Laboratory of Agricultural Bioinformatics, Huazhong Agricultural University, Wuhan 430070, China 3Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, Wuhan 430070, China {wyky481, lx666, fhuang233, xiongzk}@webmail.hzau.edu.cn, zhangwen@mail.hzau.edu.cn |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code, data, and appendix are available on Git Hub (https://github.com/wyky481l/MMCD) |
| Open Datasets | Yes | Following previous studies (Thi Phan et al. 2022; Zhang et al. 2023a), we collected therapeutic peptide data from public databases, containing two biological types, i.e., antimicrobial peptides (AMP) and anticancer peptides (ACP). |
| Dataset Splits | No | The paper mentions compiling datasets and pairing non-therapeutic peptides for contrastive learning but does not specify explicit training, validation, or test splits by percentage, count, or reference to predefined splits. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions components like 'transformer encoder' and 'EGNN' but does not provide specific version numbers for any software libraries, frameworks, or programming languages used (e.g., Python 3.x, PyTorch 1.x). |
| Experiment Setup | No | The paper mentions that 'The implementation details of MMCD and the sampling process of peptide generation can be found in Appendix A.' Without access to Appendix A, the main text does not provide specific hyperparameter values (e.g., learning rate, batch size, epochs) or detailed training configurations. |