hicai-zju Goto Github PK

Name: HICAI-ZJU

Type: Organization

Bio: An AI for Science team from Hangzhou Innovation Center of Zhejiang University.

Location: China

HICAI-ZJU's Projects

Code and Data for the paper: Graph Sampling-based Meta-Learning for Molecular Property Prediction [IJCAI2023]

Official implementation for Learning Invariant Molecular Representation in Latent Discrete Space (NeurIPS 2023)

Code and data for the ACL2024 paper "InstructProtein: Aligning Human and Protein Language via Knowledge Instruction".

Code and data for the Nature Machine Intelligence paper "Knowledge graph-enhanced molecular contrastive learning with functional prompt".

MindSpore implementation for paper "Knowledge graph-enhanced molecular contrastive learning with functional prompt"

Code and Data for the paper: Molecular Contrastive Learning with Chemical Element Knowledge Graph [AAAI 2022]

Code, data and models for the ICLR2024 paper "Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models."

Code and datasets for the ICLR2022 paper "OntoProtein: Protein Pretraining With Gene Ontology Embedding"

Open-Protein is an open source pre-training platform that supports multiple protein pre-training models and downstream tasks.

Code and Data for the paper: Multi-level Protein Structure Pre-training with Prompt Learning [ICLR 2023]

MindSpore implementation for paper "Multi-level Protein Structure Pre-training with Prompt Learning"

NeurIPS 2024 Competition - Scientific Large Language Models for Protein Sequence Understanding

Prompt Engineering for Proteins

Cell-type Annotation for Single-cell Transcriptomics using Deep Learning with a Weighted Graph Neural Network

Scientific Large Language Models: A Survey on Biological & Chemical Domains

SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models

Knowledge-graph-based cell-cell communication inference for spatially resolved transcriptomic data