- Python implementation of CycPeptMP.
- CycPeptMP is an accurate and efficient model for predicting the membrane permeability of cyclic peptides.
- We designed features for cyclic peptides at the atom, monomer, and peptide levels to concurrently capture both the local sequence variations and global conformational changes in cyclic peptides. We also applied data augmentation techniques at three scales to enhance model training efficiency.
- Python: 3.9.6
- Numpy: 1.25.0
- Pandas: 1.4.4
- Pytorch: 2.0.0 (CUDA: 11.7)
- RDKit: 2022.09.5
- Mordred: 1.2.0
- MOE: 2019.01 (commercial software)
- Original cyclic peptide structure (SMILES) and experimentally determined membrane permeability (LogPexp) used in this study (
data/CycPeptMPDB_Peptide_All.csv) were all sourced from CycPeptMPDB.- Li J., Yanagisawa K., Sugita M., Fujie T., Ohue M., and Akiyama Y. CycPeptMPDB: A Comprehensive Database of Membrane Permeability of Cyclic Peptides, Journal of Chemical Information and Modeling, 63(7): 2240–2250, 2023.
- Correspondence table of peptides and their constituent monomers is summarized in
data/monomer_table.csv. - Data used in this experiment, with duplicates removed (all: 7,451->7,337, PAMPA: 6,941->6,889), is summarized in
desc/peptide_used.csv. - Dataset split index is stored in
data/eval_index/.*_ID.npyshows the CycPeptMPDB peptide ID, and*_index.npyshows the index in sorteddesc/peptide_used.csv.
-
Testset.ipynbPrediction for the test set (and other assay data) shown in the paper by CycPeptMP and other baselines. Please download complete input files
model/input/Trans/60/from Google Drive. -
Newdata.ipynbPrediction for new data.
- Weights of CycPeptMP (60 times augmentation) for three validation runs (
Fusion-60_cv*.cpt). - Weights of fusion model with no augmentation (
Fusion-1_cv*.cpt) and 20 times augmentation (Fusion-20_cv*.cpt) for three validation runs in ablation studies.
- Li J., Yanagisawa K., and Akiyama Y. CycPeptMP: Enhancing Membrane Permeability Prediction of Cyclic Peptides with Multi-Level Molecular Features and Data Augmentation, Briefings in Bioinformatics, accepted.
- Li J., Yanagisawa K., and Akiyama Y. CycPeptMP: Enhancing Membrane Permeability Prediction of Cyclic Peptides with Multi-Level Molecular Features and Data Augmentation, bioRxiv preprint, 2023, 2023.12. 25.573282.
- Jianan Li: [email protected]