Answers are grounded in this paper and cite their sources.
Analysis shows improved multi-disease classification accuracy in T cell receptors, suggesting scalable approaches for health profiling.
Background: Machine learning models trained on paratope-similarity networks have shown superior accuracy compared with clonotype-based models in binary disease classification. However, the computational demands of paratope networks hinder their use on large datasets and multi-disease classification. Methods: We reanalyzed publicly available T cell receptor (TCR) repertoire data from 1,421 donors across 15 disease groups and a large control group, encompassing approximately 81 million TCR sequences. To address computational bottlenecks, we replaced the paratope-similarity network approach (Paratope Cluster Occupancy or PCO) with a new pipeline Fast Approximate Clustering Techniques (FACTS) which comprises of four main steps: (1) high-dimensional vector encoding of sequences; (2) efficient clustering of vectors; (3) donor-level feature construction from cluster distributions; and (4) gradient-boosted decision tree classification for multi-class disease prediction. Findings: FACTS processed 10⁷ sequences in under 120 CPU hours. Using only TCR data, and evaluated with 3-fold cross-validation, it achieved a mean ROC AUC of 0.99 across 16 disease classes. Compared with the recently reported Mal-ID model, FACTS achieved higher donor-level classification accuracy for BCR (0.840 vs. 0.740), TCR (0.862 vs. 0.751), and combined BCR+TCR datasets (0.898 vs. 0.853). FACTS also preserved biologically meaningful signals, as shown by unsupervised t-SNE projections revealing distinct disease-associated and age-associated clusters. Interpretation: Paratope-based encoding with FACTS-derived features provides a scalable and biologically grounded approach for adaptive immune receptor (AIR) repertoire classification. The resulting classifier achieves superior multi-disease diagnostic performance while maintaining interpretability, supporting its potential for clinical and population-scale health profiling. Funding: This study was supported by the Japan Society for the Promotion of Science (JSPS) KAKENHI [JA23H034980] and by the Japan Agency for Medical Research and Development (AMED) [JP21am0101001].
No takes yet. Share an insight, caveat, or question.
Jiravejchakul et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: