An official website of the United States government
Abstract MotivationProtein language models based on the transformer architecture are increasingly improving performance on protein prediction tasks, including secondary structure, subcellular localization, and more. Despite being trained only on protein sequences, protein language models appear to implicitly learn protein structure. This paper investigates whether sequence representations learned by protein language models encode structural information and to what extent. ResultsWe address this by evaluating protein language models on remote homology prediction, where identifying remote homologs from sequence information alone requires structural knowledge, especially in the “twilight zone” of very low sequence identity. Through rigorous testing at progressively lower sequence identities, we profile the performance of protein language models ranging from millions to billions of parameters in a zero-shot setting. Our findings indicate that while transformer-based protein language models outperform traditional sequence alignment methods, they still struggle in the twilight zone. This suggests that current protein language models have not sufficiently learned protein structure to address remote homology prediction when sequence signals are weak. Availability and implementationWe believe this opens the way for further research both on remote homology prediction and on the broader goal of learning sequence- and structure-rich representations of protein molecules. All code, data, and models are made publicly available.
more »
« less
Drive, filter, and stick: A protein sorting conspiracy in photoreceptors
The sorting of proteins into different functional compartments is a fundamental cellular task. In this issue, Maza et al. (2019. J. Cell Biol. https://doi.org/10.1083/jcb.201906024) demonstrate that distinct protein populations are dynamically generated in specialized regions of photoreceptors via an interplay of protein-membrane affinity, impeded diffusion, and driven transport.
more »
« less
- Award ID(s):
- 1848057
- PAR ID:
- 10126928
- Publisher / Repository:
- DOI PREFIX: 10.1083
- Date Published:
- Journal Name:
- Journal of Cell Biology
- Volume:
- 218
- Issue:
- 11
- ISSN:
- 0021-9525
- Page Range / eLocation ID:
- p. 3533-3534
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Thermal green protein Q66E (TGP-E) has previously shown increased thermal stability compared to thermal green protein (TGP), a thermal stable fluorescent protein produced through consensus and surface protein engineering. In this paper, we describe the protein crystal structure of TGP-E to 2.0 Å. This structure reveals alterations in the hydrogen bond network near the chromophore that may result in the observed increase in thermal stability. We compare the very stable TGP-E protein to the structure of a yellow mutant version of this protein YTP-E E148D. The structure of this mutant protein reveals the rationale for the observed low quantum yield and directions for future protein engineering efforts.more » « less
-
Abstract MotivationMillions of protein sequences have been generated by numerous genome and transcriptome sequencing projects. However, experimentally determining the function of the proteins is still a time consuming, low-throughput, and expensive process, leading to a large protein sequence-function gap. Therefore, it is important to develop computational methods to accurately predict protein function to fill the gap. Even though many methods have been developed to use protein sequences as input to predict function, much fewer methods leverage protein structures in protein function prediction because there was lack of accurate protein structures for most proteins until recently. ResultsWe developed TransFun—a method using a transformer-based protein language model and 3D-equivariant graph neural networks to distill information from both protein sequences and structures to predict protein function. It extracts feature embeddings from protein sequences using a pre-trained protein language model (ESM) via transfer learning and combines them with 3D structures of proteins predicted by AlphaFold2 through equivariant graph neural networks. Benchmarked on the CAFA3 test dataset and a new test dataset, TransFun outperforms several state-of-the-art methods, indicating that the language model and 3D-equivariant graph neural networks are effective methods to leverage protein sequences and structures to improve protein function prediction. Combining TransFun predictions and sequence similarity-based predictions can further increase prediction accuracy. Availability and implementationThe source code of TransFun is available at https://github.com/jianlin-cheng/TransFun.more » « less
-
Abstract MotivationComputational methods for compound–protein affinity and contact (CPAC) prediction aim at facilitating rational drug discovery by simultaneous prediction of the strength and the pattern of compound–protein interactions. Although the desired outputs are highly structure-dependent, the lack of protein structures often makes structure-free methods rely on protein sequence inputs alone. The scarcity of compound–protein pairs with affinity and contact labels further limits the accuracy and the generalizability of CPAC models. ResultsTo overcome the aforementioned challenges of structure naivety and labeled-data scarcity, we introduce cross-modality and self-supervised learning, respectively, for structure-aware and task-relevant protein embedding. Specifically, protein data are available in both modalities of 1D amino-acid sequences and predicted 2D contact maps that are separately embedded with recurrent and graph neural networks, respectively, as well as jointly embedded with two cross-modality schemes. Furthermore, both protein modalities are pre-trained under various self-supervised learning strategies, by leveraging massive amount of unlabeled protein data. Our results indicate that individual protein modalities differ in their strengths of predicting affinities or contacts. Proper cross-modality protein embedding combined with self-supervised learning improves model generalizability when predicting both affinities and contacts for unseen proteins. Availability and implementationData and source codes are available at https://github.com/Shen-Lab/CPAC. Supplementary informationSupplementary data are available at Bioinformatics online.more » « less
-
Abstract MotivationProtein function prediction, based on the patterns of connection in a protein–protein interaction (or association) network, is perhaps the most studied of the classical, fundamental inference problems for biological networks. A highly successful set of recent approaches use random walk-based low-dimensional embeddings that tend to place functionally similar proteins into coherent spatial regions. However, these approaches lose valuable local graph structure from the network when considering only the embedding. We introduce GLIDER, a method that replaces a protein–protein interaction or association network with a new graph-based similarity network. GLIDER is based on a variant of our previous GLIDE method, which was designed to predict missing links in protein–protein association networks, capturing implicit local and global (i.e. embedding-based) graph properties. ResultsGLIDER outperforms competing methods on the task of predicting GO functional labels in cross-validation on a heterogeneous collection of four human protein–protein association networks derived from the 2016 DREAM Disease Module Identification Challenge, and also on three different protein–protein association networks built from the STRING database. We show that this is due to the strong functional enrichment that is present in the local GLIDER neighborhood in multiple different types of protein–protein association networks. Furthermore, we introduce the GLIDER graph neighborhood as a way for biologists to visualize the local neighborhood of a disease gene. As an application, we look at the local GLIDER neighborhoods of a set of known Parkinson’s Disease GWAS genes, rediscover many genes which have known involvement in Parkinson’s disease pathways, plus suggest some new genes to study. Availability and implementationAll code is publicly available and can be accessed here: https://github.com/kap-devkota/GLIDER. Supplementary informationSupplementary data are available at Bioinformatics online.more » « less
