CREMP-CycPeptMPDB: Conformer-rotamer ensembles of macrocyclic peptides for machine learning with permeability annotations

<p>CREMP-CycPeptMPDB: A resource generated for the rapid development and evaluation of machine learning models for permeable macrocyclic peptides. CREMP-CycPeptMPDB contains 3,258 unique macrocyclic peptides and their high-quality structural ensembles generated using the Conformer-Rotamer Ensemble Sampling Tool (CREST). Altogether, this dataset contains nearly 8.7 million unique macrocycle geometries, each annotated with energies derived from semi-empirical tight-binding DFT calculations and with experimental membrane permeability measurements obtained from the <a href="http://cycpeptmpdb.com/" target="_blank" rel="noopener">CycPeptMPDB</a> database. We anticipate that this dataset will enable the development of machine learning models that can improve peptide design and optimization for novel therapeutics.</p> <p>This dataset complements the <a title="CREMP" href="../doi/10.5281/zenodo.7931444" target="_blank" rel="noopener">CREMP dataset</a>, which contains a larger selection of conformer ensembles for homodetic macrocyclic peptides.</p> <p>We provide the data in two available formats, either as Python pickle files, which provide quick read access with RDKit version 2022.09.5 or later, and as text-based SDF files with associated metadata in JSON format. Each file is named based on its amino acid sequence, with residues separated by periods, using standard one-letter codes with lowercase letters representing D-amino acids and "Me" prefixes representing <em>N</em>-methylated amino acids. The sequences are in no particular order, e.g., "C.R.E.M.P" and "R.E.M.P.C" correspond to the same peptide macrocycle. The filename extensions are ".pickle", ".sdf", and ".json".</p> <p>Each file in the &ldquo;pickle&rdquo; folder contains a Python dictionary with amino acid sequence, SMILES, CREST metadata, and a single RDKit molecule object containing all conformers. All files in the folder were compressed into a single &ldquo;pickle.tar.gz&rdquo; archive. In the &ldquo;sdf_and_json&rdquo; folder, each individual SDF file contains all conformers, each associated with its own JSON file that contains CREST metadata. Similarly, all are compressed into another single archive, &ldquo;sdf_and_json.tar.bz2&rdquo;. A single summary CSV file is also provided containing &rdquo;sequence&rdquo;, &ldquo;smiles&rdquo;, &ldquo;num_monomers&rdquo;, &ldquo;num_atoms&rdquo;, &ldquo;num_heavy_atoms&rdquo;, along with the CREST metadata &ldquo;totalconfs&rdquo;, &ldquo;uniqueconfs&rdquo;, &ldquo;lowestenergy&rdquo;, &ldquo;poplowestpct&rdquo;, &ldquo;temperature&rdquo;, &ldquo;ensembleenergy&rdquo;, &ldquo;ensembleentropy&rdquo;, and &ldquo;ensemblefreeenergy&rdquo;. The number of unique conformers with different 3D structures is given by &ldquo;uniqueconfs&rdquo;, while &ldquo;totalconfs&rdquo; includes the number of rotamers in addition.</p> <p>The unzipped sizes of the archives are approximately 13 GB for "pickle.tar.gz" and 84 GB for "sdf_and_json.tar.bz2". If you encounter errors when trying to load the pickle files, please make sure your RDKit version is at least 2022.09.5. If that doesn't work, try other Python versions.</p>