scikit-fingerprints/LRGB_Peptides-struct

--- license: cc-by-nc-4.0 task_categories: - tabular-classification - graph-ml - text-classification tags: - chemistry - biology - medical pretty_name: LRGB Peptides-struct size_categories: - 10K<n<100K configs: - config_name: default data_files: - split: train path: "peptides_struct.csv" --- # LRGB Peptides-struct Peptides-struct (Peptides structural) dataset, part of Long Range Graph Benchmark (LRGB) [[1]](#1). It is intended to be used through [scikit-fingerprints](https://github.com/scikit-fingerprints/scikit-fingerprints) library. The task is to predict structural properties of peptides. Note that this is raw data, whereas the original paper [[1]](#1) specifies that targets should be standardized (mean 0, standard deviation 1) before training and evaluation. scikit-fingerprints does this by default in the loader function, otherwise this should be performed manually. | **Characteristic** | **Description** | |:------------------:|:-----------------:| | Tasks | 11 | | Task type | regression | | Total samples | 15535 | | Recommended split | stratified random | | Recommended metric | MAE | ## References <a id="1">[1]</a> Dwivedi, Vijay Prakash, et al. "Long Range Graph Benchmark" Advances in Neural Information Processing Systems 35 (2022): 22326-22340 https://proceedings.neurips.cc/paper_files/paper/2022/hash/8c3c666820ea055a77726d66fc7d447f-Abstract-Datasets_and_Benchmarks.html