PCQM4Mv2-LSC

Dataset Information
Introduced
2021
License
CC BY 4.0
Homepage
Official Website
Contents

Overview

PCQM4Mv2 is a quantum chemistry dataset originally curated under the PubChemQC project. Based on the PubChemQC, we define a meaningful ML task of predicting DFT-calculated HOMO-LUMO energy gap of molecules given their 2D molecular graphs. The HOMO-LUMO gap is one of the most practically-relevant quantum chemical properties of molecules since it is related to reactivity, photoexcitation, and charge transport. Moreover, predicting the quantum chemical property only from 2D molecular graphs without their 3D equilibrium structures is also practically favorable. This is because obtaining 3D equilibrium structures requires DFT-based geometry optimization, which is expensive on its own.

Variants: PCQM4Mv2-LSC

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Graph Regression ESA (Edge set attention, no positional encodings) An end-to-end attention-based approach for … 2024-02-16
Graph Regression TGT-At Triplet Interaction Improves Graph Transformers: … 2024-02-07
Graph Regression TIGT Topology-Informed Graph Transformer 2024-02-03
Graph Regression Graphormer + GFSA Graph Convolutions Enrich the Self-Attention … 2023-12-07
Graph Regression EGT+SSA The Information Pathways Hypothesis: Transformers … 2023-06-02
Graph Regression EGT+SSA+Self-ensemble The Information Pathways Hypothesis: Transformers … 2023-06-02
Graph Regression GRIT Graph Inductive Biases in Transformers … 2023-05-27
Graph Regression GPTrans-L Graph Propagation Transformer for Graph … 2023-05-19
Graph Regression GPTrans-T Graph Propagation Transformer for Graph … 2023-05-19
Graph Regression Uni-Mol+ Highly Accurate Quantum Chemical Property … 2023-03-16
Graph Regression Transformer-M One Transformer Can Understand Both … 2022-10-04
Graph Regression TokenGT Pure Transformers are Powerful Graph … 2022-07-06
Graph Regression GPS Recipe for a General, Powerful, … 2022-05-25
Graph Regression GRPE-Large GRPE: Relative Positional Encoding for … 2022-01-30
Graph Regression EGT Global Self-Attention as a Replacement … 2021-08-07
Graph Regression EGT + Triangular Attention Global Self-Attention as a Replacement … 2021-08-07
Graph Regression Graphormer Do Transformers Really Perform Bad … 2021-06-09
Graph Regression MLP-Fingerprint OGB-LSC: A Large-Scale Challenge for … 2021-03-17
Graph Regression GIN How Powerful are Graph Neural … 2018-10-01
Graph Regression GCN Semi-Supervised Classification with Graph Convolutional … 2016-09-09

Research Papers

Recent papers with results on this dataset:

External Links: