Tree-structured topic modelling of single-cell gene expression data uncovers hierarchical relationships between immune cell types
Bibliographic record
Abstract
Abstract Immune cells undergo a series of differentiation steps following a lineage-tree structure stemming from hematopoietic stem cells. During differentiation of immune cells in both homeostasis and pathological processes, many gene regulatory mechanisms are shared by fully differentiated immune cell sub-types. In order to characterize these features quantitatively, we propose LaRCH , a tree-structured embedded topic model. In this model, single-cell gene expression profiles are represented by a mixture of topics consisting of latent features that follow an underlying tree structure, mirroring that of cellular differentiation–nested cluster structures. We present findings of our model trained on simulated single-cell RNA sequencing (scRNA-seq) based on cell-sorted bulk RNA-seq data as well as on a scRNA-seq dataset of over 1.2 million cells from healthy individuals and individuals diagnosed with systemic lupus erythematosus (SLE). The cellular topic profiles estimated by our model markedly improve clustering accuracy over traditional latent variable models and illustrate transcriptomic differences between SLE phenotypes, revealing a pivotal role of multiple immune cell types in disease progression and relapse. Ultimately, LaRCH captures the hierarchical context between cellular subtypes by simultaneously identifying shared and distinct latent features amongst subsets of heterogeneous samples of cells.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".