ChIEDiff: trained weights, generated molecules, measurements, and evaluation receptors

Data and weights accompanying the ChIEDiff code release(https://github.com/DannyJPark/ChIEDiff, DOI 10.5281/zenodo.23000085). FILES crossdocked_v1.1_rmsd1.0_pocket10_processed_final.lmdb.gz (1.07 GB) The processed CrossDocked2020 training set, gzipped. Decompresses to a 4.07 GB LMDB of 166,500 records. It carries the Vina affinity labels the training objective reads, and crossdocked_pocket10_pose_split.pt in the code repository indexes its byte-sorted key order, so use this file rather than rebuilding one. chiediff_receptors.tar.gz (59 MB) The CrossDocked2020 test receptors with their PDBQT files and reference ligands, and chain-remapped copies of them. The remapped copies matter: twelve receptors encode their chain copies only in the segID column, which Biopython ignores, so measuring against the originals silently uses a partial receptor for those pockets. chiediff_weights_iter1195000.pt (33 MB) Trained weights, iteration 1,195,000, selected by validation loss. chiediff_generated_molecules.pt (65 MB) The generated molecules with their docking scores. This file is the authoritative record of molecule IDENTITY. The sampler is not reproducible at the level of individual molecules: the affinity position gradient is a second backward pass over a graph the first retained, and re-traversing it accumulates in a different float order each time, which the 1000-step sampler amplifies. Two runs of the same code produce different molecules. A fresh run reproduces the reported statistics, not these molecules. chiediff_measurements.tar.gz (59 MB) Per-pocket measurement outputs for these molecules: exported SDFs, Vina, SMINA/Vinardo and GNINA docking, PoseCheck, ProLIF and PoseBusters. Unpacking this lets a reproducer start from aggregation instead of re-docking. SHA256SUMS Checksums for the five files above. LICENSING The weights, generated molecules and measurements are released CC-BY-4.0. The receptor files and the processed training set are derived from CrossDocked2020, which is dedicated to the public domain under CC0 1.0, and remain CC0. REPRODUCTION The code repository holds the aggregate CSVs behind the reported tables and prints themwith no download required. This archive is needed to re-measurefrom the molecules, to sample from the trained weights, or to train from scratch.