OntoProtein: Protein Pretraining With Gene Ontology Embedding

Abstract

Self-supervised protein language models have proved their effectiveness in learning the proteins representations. With the increasing computational power, current protein language models pre-trained with millions of diverse sequences can advance the parameter scale from million-level to billion-level and achieve remarkable improvement. However, those prevailing approaches rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better protein representations. We argue that informative biology knowledge in KGs can enhance protein representation with external knowledge. In this work, we propose OntoProtein, the first general framework that makes use of structure in GO (Gene Ontology) into protein pre-training models. We construct a novel large-scale knowledge graph that consists of GO and its related proteins, and gene annotation texts or protein sequences describe all nodes in the graph. We propose novel contrastive learning with knowledge-aware negative sampling to jointly optimize the knowledge graph and protein embedding during pre-training. Experimental results show that OntoProtein can surpass state-of-the-art methods with pre-trained protein language models in TAPE benchmark and yield better performance compared with baselines in protein-protein interaction and protein function prediction 1 .

Chebifier: automating semantic classification in ChEBI to accelerate data-driven discovery

“… 32 This illustrates the broad-ranging importance of incorporating domain knowledge into data-driven discovery methods. A similar approach in the domain of proteins is OntoProtein, 36 which uses the Gene Ontology to augment the information available for a protein language model.…”

Retrieved Sequence Augmentation for Protein Representation Learning

“…Following Rao et al (2019) and Rao et al (2021), we compare our model with vanilla protein representation models, including LSTM(Liu, 2017), Transformers(Vaswani et al, 2017) and pre-trained models ESM-1b(Rives et al, 2019), ProtBERT(Elnaggar et al, 2020). We also compare with state-of-the-art knowledge-augmentation models: Potts Model(Balakrishnan et al, 2011), MSA Transformer(Rao et al, 2021) that inject evolutionary knowledge through MSA, OntoProtein(Zhang et al, 2022) that uses gene ontology knowledge graph to augment protein representations and PMLM(He et al, 2021b) that uses pair-wise pretraining to improve co-evolution awareness. We use the reported results of LSTM from Zhang et al (2021); Xu et al (2022).…”

Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design

“…Inspired by the great success of protein pre-training [9,57,47,31,54,12], a few works attempt to transfer these techniques to the antibody pre-training since the specificity of antibody [51,50]. Ruffolo et al [38] first propose an antibody-specific language model AntiBERTy to aid understanding of immune repertoires by training on antibody sequence data.…”