Miaozhe Huo

Ribonucleic acid (RNA) foundation models (FMs) are reshaping computational biology, using self-supervised pretraining on massive transcriptomic corpora to acquire generalisable molecular representations. Developed initially for sequence annotation and expression prediction, they are increasingly applied to plant science, supporting tasks from gene function inference to regulatory element discovery and stress-response modelling in both model and orphan crop species. This review surveys RNA FMs with a focus on plant-relevant applications. We catalogue the major model families, including DNABERT-derived RNA adaptations, PlantRNA-FM, and Nucleotide Transformer variants, comparing their pretraining objectives, input modalities, and evaluation protocols. We examine how these models are deployed across plant genomics, transcriptomics, and functional annotation pipelines, highlighting the opportunities and the constraints arising from species-specific data gaps, limited experimental validation, and interpretability challenges. Across applications, the decisive constraint is no longer architecture but data: corpus breadth, condition-resolved benchmarks, and experimentally anchored validation now dominate the marginal gains available from model design. We close with the key open questions and a roadmap for integrating RNA FMs into the plant systems biology toolkit, emphasising benchmark design, cross-species transfer, and experimentally grounded validation. Throughout, every claim about what a model can do is held to three questions of evidence: what data the model was trained on, which benchmark supports the claim, and whether experimental validation in a plant system exists.

Plant growth-promoting rhizobacteria (PGPR) can support crop growth and protection, but their performance varies across strains, hosts, soils, and management conditions. Colonization measurements can help explain this variation, although persistence, microbial function, and plant benefit are distinct outcomes. This critical review examines how genome-informed models could prioritize strains for defined colonization tasks. We connect the ecology of dispersal, attachment, competition, and persistence with phenotype measurements, sequence representations, and validation design. Protein language models, DNA-based encoders, pan-genome features, and multi-task learning provide candidate tools, supported mainly by applications to related prediction problems. Their value for strain-level persistence must be assessed against phenotype-based and simpler genomic baselines under matched evaluation conditions. We organize the evidence around three application directions, examine assumptions about laboratory-to-field transfer, functional annotation, and trait independence, and propose a metadata schema and benchmark framework. Independent strain and soil holdouts, endpoint-specific measurements, and prospective field studies are central to assessing added predictive value. The resulting framework is a proposal for testing when genomic information and model complexity improve strain prioritization, with scope determined by the available labels and validation setting.

Background: V gene segments of the T cell receptor (TCR) β chain (TRBV) are crucial for antigen recognition, yet previous studies have treated them as fixed categories and neglected repertoire-specific immune dynamics that inform functional diversity. Methods: We introduce ClareV, a contrastive learning framework that partitions T cell receptor repertoires into V gene-specific groups to extract data-driven embeddings capturing these dynamics. We evaluated ClareV across three TCR repertoire cohorts spanning cytomegalovirus (CMV), gastric cancer, and multi-cancer settings. Results: In the Emerson2017 CMV cohort, the ClareV Random Forest (RF) Fusion model improved AUC by 14.3% over the strongest V-family usage-only baseline (linear SVM) and by 13.3% over the strongest V-gene usage-only baseline (Random Forest). These results indicate that ClareV embeddings capture additional repertoire-level information beyond V-frequency summaries. Ablation studies showed that frequency-weighted bagging and contrastive V-bag learning both contributed to performance, outperforming simple pooling and non-contrastive learned-bag controls. In the CMV cohort, downstream embedding analyses showed that ClareV representations partially recapitulated IMGT-defined V-gene structure while retaining a CMV-responsive, non-sequence component that was largely orthogonal to classical V-usage signals. Discussion: These findings support adaptive V-gene representations as a compact feature space that complements V-frequency summaries for repertoire-level classification.

The T-cell receptor (TCR) is a fundamental component of the adaptive immune system, playing a crucial role in the development and progression of autoimmune diseases through its remarkable diversity and antigen specificity. Advances in high-throughput sequencing technologies and multi-omics data integration have revolutionized the ability to characterize TCR repertoires at unprecedented resolution. Coupled with emerging machine learning methodologies, these advances have opened new avenues for unraveling the complex immunopathology underlying autoimmune disorders. This review comprehensively summarizes current knowledge on the dynamic regulation of TCR repertoires in autoimmune diseases, highlighting key processes such as central tolerance failure, clonal expansion of autoreactive T cells, and regulatory T cell dysfunction, as well as the influences of genetic predisposition and immunosenescence on shaping TCR diversity. This review also provides a 3 that demonstrates how to analyze publicly available TCR repertoire datasets. We compare V and J gene usage profiles and CDR3 summary features across clinical labels to characterize between-group variation and to inform feature engineering for downstream machine learning models. Furthermore, we detail various machine learning-based diagnostic models that utilize gene usage patterns and CDR3 sequence features to accurately classify autoimmune disease status, alongside recent breakthroughs in predicting TCR-epitope binding specificity. These computational approaches not only enhance diagnostic precision but also provide mechanistic insights into immune recognition and autoreactivity. By integrating immunological principles with data-driven techniques, this work aims to offer a robust theoretical framework and practical guidance for future research in immunology and precision medicine. Ultimately, the convergence of TCR repertoire profiling and machine learning promises to drive innovative strategies for early diagnosis, personalized therapy, and improved clinical management of autoimmune diseases, enabling the transition to antigen-specific tolerogenic therapies.

Background Systemic Lupus Erythematosus (SLE) is a complex autoimmune disorder characterized by abnormal T-cell responses, which significantly contribute to the disease’s immune pathology. The Complementarity Determining Region 3 (CDR3) of the TCRβ chain is pivotal for T-cell specificity, thereby positioning it as a promising target for enhancing diagnostic accuracy and gaining deeper mechanistic insights into SLE. To address these diagnostic limitations in SLE, our team developed DeepTAPE, a deep learning-based diagnostic framework that utilizes CDR3 sequences to achieve robust diagnostic performance for SLE. Results Building upon the foundation established by DeepTAPE, we devised a novel diagnostic approach that effectively integrates a TCR classifier to quantify SLE disease activity. Furthermore, this methodology employs advanced deep learning models for the bio-mining of valuable and efficient preliminary diagnostic biomarkers. As a result, this approach generates an autoimmune risk score (ARS) indicative of SLE probability. Notably, this ARS metric exhibited a strong correlation with disease activity, functioning as a quantitative clinical marker that complements traditional indices such as the SLE Disease Activity Index (SLEDAI). In addition, through a comprehensive analysis of immune repertoire data, we identified SLE-specific amino acid motifs within the CDR3 sequences, including critical 3-mer and gapped-mer oligopeptides. These motifs facilitated rapid and accurate preliminary screening for SLE, achieving an area under the curve (AUC) of 0.908, thereby significantly outperforming other candidate biomarkers. Moreover, our model revealed potential SLE-associated antigens and genes, such as CD109 and INS, which provide new insights into the immunological mechanisms underlying the disease. Conclusion This study highlights the potential of DeepTAPE not only as a diagnostic tool but also as a platform for biomarker discovery in SLE. By deepening our understanding of the immunological characteristics and mechanisms associated with SLE, this work lays a solid foundation for advancing targeted therapies and personalized medicine in autoimmune diseases. Consequently, our findings may pave the way for improved patient outcomes and more effective treatment strategies in the management of SLE.