HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Drug Discovery On Tox21

평가 지표

AUC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AUC	Paper Title	Repository
ContextPred	0.781	Strategies for Pre-training Graph Neural Networks
GraphConv + dummy super node	0.854	Learning Graph-Level Representation for Drug Discovery
TrimNet	0.860	TrimNet: learning molecular representation from triplet messages for biomedicine	-
RNN-DFS	0.748	Relational Pooling for Graph Representations
GraphConv	0.846	Convolutional Networks on Graphs for Learning Molecular Fingerprints
Ensemble predictor	0.862	ToxicBlend: Virtual Screening of Toxic Compounds with Ensemble Predictors	-
elEmBERT-V1	0.961	Structure to Property: Chemical Element Embeddings and a Deep Learning Approach for Accurate Prediction of Chemical Properties
GIT-Mol(G+S)	0.759	GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text
SNN (SELU Network)	0.845	Self-Normalizing Neural Networks
SSVAE with multiple SMILES	0.871	All SMILES Variational Autoencoder	-
TrimNet + Perforated Backpropagation	0.885	Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural Networks

0 of 11 row(s) selected.