MOTIVATION: T cell receptors (TCRs) are fundamental components of the adaptive immune system, recognizing specific antigens for targeted immune responses. Understanding their sequence patterns is crucial for designing effective vaccines and immunotherapies. However, the vast diversity of TCR sequences and complex binding mechanisms pose significant challenges in generating TCRs that are specific to a particular epitope. RESULTS: Here, we propose TCR-epiDiff, a diffusion-based deep learning model for generating epitope-specific TCRs and predicting TCR-epitope binding. TCR-epiDiff integrates epitope information during TCR sequence embedding using ProtT5-XL and employs a denoising diffusion probabilistic model for sequence generation. Using external validation datasets, we demonstrate the ability to generate biologically plausible, epitope-specific TCRs. Furthermore, we leverage the model's encoder to develop a TCR-epitope binding predictor that shows robust performance on the external validation data. Our approach provides a comprehensive solution for both de novo generation of epitope-specific TCRs and TCR-epitope binding prediction. This capability provides valuable insights into immune diversity and has the potential to advance targeted immunotherapies. AVAILABILITY AND IMPLEMENTATION: The data and source codes for our experiments are available at: https://github.com/seoseyeon/TCR-epiDiff.

Deep neural networks easily suffer from weak generalization caused by overfitting on biased data. One popular remedy to alleviate this issue is sample reweighting methods that adaptively adjust the importance of biased samples. Separate from the effort to reduce bias, recent works show that the generalization power can be improved by auxiliary tasks. Inspired by the two lines of works, we extend the sample reweighting methods to auxiliary tasks. In this paper, we propose a novel auxiliary learning framework that improves the primary task by adaptively adjusting the weights of samples from multiple tasks rather than samples from a single task using a weighting function. The weighting function is optimized by meta-learning along the gradient of the loss for meta-data, which is a small unbiased validation data. We also present a task-activation score that indicates the correlation between the learning tendency of the training samples and meta-data samples. This score is utilized as a regularizer for meta-learning objective. Our framework can obtain powerful representations for the primary task on biased data by automatically identifying effective combinations of tasks. Our experiments demonstrate that our proposed method consistently outperforms all baselines and state-of-the-art methods on both corrupted labels and class imbalance settings.

MOTIVATION: Bulk tumor samples used for high-throughput molecular profiling are often an admixture of cancer cells and non-cancerous cells, which include immune and stromal cells. The mixed composition can confound the analysis and affect the biological interpretation of the results, and thus, accurate prediction of tumor purity is critical. Although several methods have been proposed to predict tumor purity using high-throughput molecular data, there has been no comprehensive study on machine learning-based methods for the estimation of tumor purity. RESULTS: We applied various machine learning models to estimate tumor purity. Overall, the models predicted the tumor purity accurately and showed a high correlation with well-established gold standard methods. In addition, we identified a small group of genes and demonstrated that they could predict tumor purity well. Finally, we confirmed that these genes were mainly involved in the immune system. AVAILABILITY: The machine learning models constructed for this study are available at https://github.com/BonilKoo/ML_purity.

Mutation hotspots are either solitary amino acid residues or stretches of amino acids that show elevated mutation frequency in cancer-related genes, but their prevalence and biological relevance are not completely understood. Here, we developed a Smith-Waterman algorithm-based mutation hotspot discovery method, MutClustSW, to identify mutation hotspots of either single or clustered amino acid residues. We identified 181 missense mutation hotspots from COSMIC and TCGA mutation databases. In addition to 77 single amino acid residue hotspots (42.5 percent) including well-known mutation hotspots such as IDH1 (p.R132) and BRAF (p.V600), we identified 104 mutation hotspots (57.5 percent) as clusters or stretches of multiple amino acids, and the hotspots on MUC2, EPPK1, KMT2C, and TP53 were larger than 50 amino acids. Twelve of 27 nonsense mutation hotspots (44.4 percent) were observed in four cancer-related genes, TP53, ARID1A, CDKN2A, and PTEN, suggesting that truncating mutations on some tumor suppressor genes are not randomly distributed as previously assumed. We also show that hotspot mutations have higher mutation allele frequency than non-hotspots, and the hotspot information can be used to prioritize the cancer drivers. Together, the proposed algorithm and the mutation hotspot information can serve as valuable resources in the selection of functional driver mutations and associated genes.

Motivation: Single-individual haplotyping (SIH) is critical in genomic association studies and genetic diseases analysis. However, most genomic analysis studies do not perform haplotype-phasing analysis due to its complexity. Several computational methods have been developed to solve the SIH problem, but these approaches have not generated sufficiently reliable haplotypes. Results: Here, we propose a novel SIH algorithm, called PEATH (Probabilistic Evolutionary Algorithm with Toggling for Haplotyping), to achieve more accurate and reliable haplotyping. The proposed PEATH method was compared to the most recent algorithms in terms of the phased length, N50 length, switch error rate and minimum error correction. The PEATH algorithm consistently provides the best phase and N50 lengths, as long as possible, given datasets. In addition, verification of the simulation data demonstrated that the PEATH method outperforms other methods on high noisy data. Additionally, the experimental results of a real dataset confirmed that the PEATH method achieved comparable or better accuracy. Availability and implementation: Source code of PEATH is available at https://github.com/jcna99/PEATH. Contact: [email protected] or [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

Various real-world biomedical classification tasks suffer from the imbalanced data problem which tends to make the prediction performance of some classes significantly decrease. In this paper, we present an active example selection method with naiumlve Bayes classifier (AESNB) as a solution for the imbalanced data problem. The proposed method starts with a small balanced subset of training examples. A naive Bayes classifier is trained incrementally by actively selecting and adding informative examples regardless of the original class distribution. Informative examples are defined as examples that produce high error scores by the current classifier. We examined the performance of AESNB algorithm by using five imbalanced biomedical datasets. Our experimental results show that the naiumlve Bayes classifier with our active example selection method achieves a competitive classification performance compared to the classifier with sampling or cost-sensitive methods.

BACKGROUND: MicroRNAs (miRNAs) are small noncoding RNAs, which play significant roles as posttranscriptional regulators. The functions of animal miRNAs are generally based on complementarity for their 5' components. Although several computational miRNA target-gene prediction methods have been proposed, they still have limitations in revealing actual target genes. RESULTS: We implemented miTarget, a support vector machine (SVM) classifier for miRNA target gene prediction. It uses a radial basis function kernel as a similarity measure for SVM features, categorized by structural, thermodynamic, and position-based features. The latter features are introduced in this study for the first time and reflect the mechanism of miRNA binding. The SVM classifier produces high performance with a biologically relevant data set obtained from the literature, compared with previous tools. We predicted significant functions for human miR-1, miR-124a, and miR-373 using Gene Ontology (GO) analysis and revealed the importance of pairing at positions 4, 5, and 6 in the 5' region of a miRNA from a feature selection experiment. We also provide a web interface for the program. CONCLUSION: miTarget is a reliable miRNA target gene prediction tool and is a successful application of an SVM classifier. Compared with previous tools, its predictions are meaningful by GO analysis and its performance can be improved given more training examples.