ProtCLIP: Function-Informed Protein Multi-Modal Learning
Preprint
Abstract
Multi-modality pre-training paradigm that aligns protein sequences and biological descriptions has learned general protein representations and achieved promising performance in various downstream applications. However, these works were still unable to replicate the extraordinary success of language-supervised visual foundation models due to the ineffective usage of aligned protein-text paired data and the lack of an effective function-informed pre-training paradigm. To address these issues, this paper curates a large-scale protein-text paired dataset called ProtAnno with a property-driven sampling strategy, and introduces a novel function-informed protein pre-training paradigm. Specifically, the sampling strategy determines selecting probability based on the sample confidence and property coverage, balancing the data quality and data quantity in face of large-scale noisy data. Furthermore, motivated by significance of the protein specific functional mechanism, the proposed paradigm explicitly model protein static and dynamic functional segments by two segment-wise pre-training objectives, injecting fine-grained information in a function-informed manner. Leveraging all these innovations, we develop ProtCLIP, a multi-modality foundation model that comprehensively represents function-aware protein embeddings. On 22 different protein benchmarks within 5 types, including protein functionality classification, mutation effect prediction, cross-modal transformation, semantic similarity inference and protein-protein interaction prediction, our ProtCLIP consistently achieves SOTA performance, with remarkable improvements of 75% on average in five cross-modal transformation benchmarks, 59.9% in GO-CC and 39.7% in GO-BP protein function prediction. The experimental results verify the extraordinary potential of ProtCLIP serving as the protein multi-modality foundation model.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Group-On: Boosting One-Shot Segmentation with Supportive Query2025
- A text-guided protein design frameworkNature Machine Intelligence, 2025
- Illuminating protein space with a programmable generative modelNature, 2023
- Evolutionary-scale prediction of atomic-level protein structure with a language modelScience, 2023
- Building a knowledge graph to enable precision medicineScientific Data, 2023
- ProtTrans: Toward Understanding the Language of Life Through Self-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Structure-based protein function prediction using graph convolutional networksNature Communications, 2021
- Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequencesProceedings of the National Academy of Sciences, 2021
- DeepLoc: prediction of protein subcellular localization using deep learningBioinformatics, 2017
- The SWISS-PROT protein sequence database and its supplement TrEMBL in 2000Nucleic Acids Research, 2000