More Like this

1. Predicting conserved functional interactions for long noncoding RNAs via deep learning

   https://doi.org/10.3389/frnar.2024.1473293  

   Kratz, Megan B; Smith, Keriayn N (October 2024, Frontiers in RNA Research)

   Long noncoding RNA (lncRNA) genes outnumber protein coding genes in the human genome and the majority remain uncharacterized. A major difficulty in generalizing understanding of lncRNA function is the dearth of gross sequence conservation, both for lncRNAs across species and for lncRNAs that perform similar functions within a species. Machine learning based methods which harness vast amounts of information on RNAs are increasingly used to impute certain biological characteristics. This includes interactions with proteins that are important mediators of RNA function, thus enabling the generation of knowledge in contexts for which experimental data are lacking. Here, we applied a natural language-based machine learning approach that enabled us to identify RNA binding protein interactions in lncRNA transcripts, using only RNA sequence as an input. We found that this predictive method is a powerful approach to infer conserved binding across species as distant as human and opossum, even in the absence of sequence conservation, thus informing on sequence-function relationships for these poorly understood RNAs. 

   more » « less
2. Deep learning methods for protein function prediction

   https://doi.org/10.1002/pmic.202300471  

   Boadu, Frimpong; Lee, Ahhyun; Cheng, Jianlin (January 2025, PROTEOMICS)

   Abstract Predicting protein function from protein sequence, structure, interaction, and other relevant information is important for generating hypotheses for biological experiments and studying biological systems, and therefore has been a major challenge in protein bioinformatics. Numerous computational methods had been developed to advance protein function prediction gradually in the last two decades. Particularly, in the recent years, leveraging the revolutionary advances in artificial intelligence (AI), more and more deep learning methods have been developed to improve protein function prediction at a faster pace. Here, we provide an in‐depth review of the recent developments of deep learning methods for protein function prediction. We summarize the significant advances in the field, identify several remaining major challenges to be tackled, and suggest some potential directions to explore. The data sources and evaluation metrics widely used in protein function prediction are also discussed to assist the machine learning, AI, and bioinformatics communities to develop more cutting‐edge methods to advance protein function prediction. 

   more » « less
3. Predicting epistasis across proteins by structural logic

   https://doi.org/10.1073/pnas.2516291123  

   Tang, Michelle; Cromie, Gareth A; Kabir, Anowarul; Timour, Martin S; Ashmead, Julee; Lo, Russell S; Corley, Nathaniel; DiMaio, Frank; Morizono, Hiroki; Caldovic, Ljubica; et al (January 2026, Proceedings of the National Academy of Sciences)

   Accurately predicting the phenotypic consequences of genetic variation is a major challenge for precision medicine. The problem is exacerbated by epistatic interactions, nonadditive effects between genetic variants that produce unexpected phenotypes. Here, we explore an understudied form of positive epistasis: intragenic complementation, in which pairs of loss-of-function variants restore near wild-type protein function. Using mutational scanning in yeast, we identify thousands of such interactions in a clinically important enzyme, human argininosuccinate lyase (ASL). Restoration of protein function is not due to the biochemical properties of the substituted amino acids, but rather to a structural feature of the protein, the active site assembly. We develop a machine learning algorithm that uses protein language model embeddings to predict intragenic complementation in ASL with 99.6% accuracy. Additionally, the model trained on ASL generalizes to a structurally related but sequence-divergent enzyme, fumarase, with accuracy over 90%. Our findings reveal a structural basis for this form of epistasis and provide a predictive framework that could extend to at least 4% of human proteins. 

   more » « less
4. Learning the Structural Diversity of Olfactory Receptors: A Genomic Case Study in Two Longhorn Beetles (Cerambycidae: Lamiinae)

   https://doi.org/10.3390/insects17060587  

   Duncan, Mataya; Sylvester, Terrence; Walden, Emilee; Roa_Lozano, Jenniffer; Turner, Emma; Duncan, Samuel; Mitchell, Robert F; McKenna, Duane D; Adams, Rich (June 2026, Insects)

   Recent advances in machine learning are transforming biological research by offering powerful tools to address complex challenges across the life sciences. In particular, deep learning approaches now enable accurate predictions of protein structure and function, opening new avenues for investigating proteomic diversity in non-model organisms. In this study, we conducted a genomic case study that examines the predicted structure and diversity of odorant receptor (OR) proteins in two species of longhorn beetles (Cerambycidae) with divergent life histories: the highly specialized red milkweed beetle (Tetraopes tetrophthalmus) and the broadly polyphagous Asian longhorned beetle (Anoplophora glabripennis). Using leading predictive algorithms, we inferred the structure of beetle-encoded OR genes, compared confidence scores, and assessed protein diversity across OR families and between the two genomes. Unsupervised clustering applied to pairwise protein comparisons revealed an expected strong correlation between structure and sequence, while supporting the evolutionary classification of previously predicted OR groups and revealing new evidence of previously unrecognized OR subclusters. Notably, we identify specific proteins exhibiting substantial structural divergence despite relatively low sequence divergence with other paralogs, suggesting potential outliers subject to unusual evolutionary processes. These results highlight the utility of statistical learning for uncovering patterns of protein evolution and structural diversity in understudied insect genomes. 

   more » « less
5. Improving protein function prediction by learning and integrating representations of protein sequences and function labels

   https://doi.org/10.1093/bioadv/vbae120  

   Boadu, Frimpong; Cheng, Jianlin (August 2024, Bioinformatics Advances)

   Zhu, Shanfeng (Ed.)

   Abstract MotivationAs fewer than 1% of proteins have protein function information determined experimentally, computationally predicting the function of proteins is critical for obtaining functional information for most proteins and has been a major challenge in protein bioinformatics. Despite the significant progress made in protein function prediction by the community in the last decade, the general accuracy of protein function prediction is still not high, particularly for rare function terms associated with few proteins in the protein function annotation database such as the UniProt. ResultsWe introduce TransFew, a new transformer model, to learn the representations of both protein sequences and function labels [Gene Ontology (GO) terms] to predict the function of proteins. TransFew leverages a large pre-trained protein language model (ESM2-t48) to learn function-relevant representations of proteins from raw protein sequences and uses a biological natural language model (BioBert) and a graph convolutional neural network-based autoencoder to generate semantic representations of GO terms from their textual definition and hierarchical relationships, which are combined together to predict protein function via the cross-attention. Integrating the protein sequence and label representations not only enhances overall function prediction accuracy, but delivers a robust performance of predicting rare function terms with limited annotations by facilitating annotation transfer between GO terms. Availability and implementationhttps://github.com/BioinfoMachineLearning/TransFew. 

   more » « less