Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.21943

Panoramic modelling of single-cell transcriptomes at scale with CellNet

Xiaoqing Lian·Pei Liu·Jiahui Tan·Luoda Tan·Chaoyi Li·Quan Zou·Chen Lin·Xiangxiang Zeng
View original source ↗Read source document ↗Export metadata ↓

Abstract

Comprehensively characterizing cellular diversity is critical for understanding tissue development, identifying disease-associated populations and investigating gene programmes linked to specialized functions. Advances in single-cell profiling reveal additional cell-specific transcripts and molecular associations, yet many foundation models represent only a restricted portion of this increasingly rich molecular information. Here we present CellNet, which enables panoramic modelling of single-cell transcriptomes by integrating DNA-derived gene identities and measured RNA expression in a shared image representation. Pretrained on 231 million cell profiles spanning 40 species, CellNet improves rare-population and condition-associated state recognition in evaluated cohorts while retaining competitive general cell representations. It predicts withheld coding-gene expression and selected non-coding targets in total-RNA data, and recovers lineage-specific expression patterns in spatial measurements. Prediction also extends across species, including to targets without expression-pretraining exposure. Its gene representations retrieve known non-coding modules and developmental or neural programmes, including from sparsely detected RNA queries. Together, these results establish CellNet as a scalable framework for interpreting cellular diversity through increasingly comprehensive transcriptomic measurements.

Explore related subjects

q-bio.GN

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Xiaoqing Lian, Pei Liu, Jiahui Tan, Luoda Tan, Chaoyi Li, Quan Zou, Chen Lin, Xiangxiang Zeng. 2026-10-15. Panoramic modelling of single-cell transcriptomes at scale with CellNet. https://arxiv.org/abs/2610.21943

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations

Prediction of the transcriptional response of a cell to a genetic perturbation is a central problem in the computational modeling of gene regulation. Perturbations of the same gene can produce different transcriptional responses depending on the targeted locus, such as an alternative transcription start site or a distal regulatory element, and gene-level perturbation models represent these distinct interventions with a single gene identifier. We introduce STRAND, a generative model that encodes the regulatory DNA sequence at the perturbation locus and uses this encoding to parameterize a conditional transport process from control to perturbed single-cell states. Sequence conditioning enables zero-shot prediction for perturbation targets absent from training and supports locus-resolved inputs at 128 bp model resolution within a 524 kb sequence window. On CRISPRi screens in K562, Jurkat, and RPE1 cells, STRAND achieves the best average rank on few-shot and unseen-gene benchmarks, with gains of up to 33% in perturbation discrimination, and improves transfer to held-out cell lines by up to 0.12 in $Δ$Pearson. Ablation studies attribute these gains to sequence conditioning and to conditional transport. At the locus level, STRAND distinguishes alternative transcription start sites and validated regulatory elements that gene-identifier models represent as a single perturbation. STRAND is available at https://github.com/mims-harvard/STRAND.

q-bio.GN↗
arXiv2026

Reading Between the Reads: A Decade On, Revisiting Sequencing Protocol Annotation in the Sequence Read Archive

Background: Experimental metadata are essential for interpreting archived sequencing data. In 2015, Alnasir and Shanahan examined the annotation of fragmentation, adapter ligation and enrichment in the Sequence Read Archive (SRA). This study revisits those measurements using the original SQL keyword definitions on a September 2026 NCBI metadata snapshot reconstructed in the historical SRAdb schema. Results: The contemporary database contained 41,593,302 experiments, compared with 419,620 in 2013. In library_construction_protocol, the proportion matching all three historical keyword groups declined from 4.06% to 1.42%. The protocol field was NULL in 67.65% of contemporary experiments. Searching design_description alongside the protocol field increased combined three-step keyword detection to 1,197,367 experiments (2.88%), with most additional matches occurring where the protocol field was NULL. Coverage varied across sequencing library strategies, ranging from 0.26% for AMPLICON to 7.69% for RNA-Seq. Independent comparison of 150 sampled experiment records against source XML confirmed agreement in all historical keyword classifications. Conclusions: The original criteria identify a smaller proportion of experiments in the designated protocol field than a decade earlier. Additional preparation-related terminology is detectable in general experiment descriptions, exposing the limitations of searches restricted to one metadata field. Differences among sequencing strategies complicate historical comparisons as preparation methods evolve. The findings support more consistent protocol annotation and the need to distinguish keyword occurrence from the adequacy of experimental documentation.

q-bio.GN↗
arXiv2026

pyTransRate: 1 reference-free quality assessment of de novo transcriptome assemblies with current aligners and quantifiers

Summary: The original software TransRate scores a de novo transcriptome assembly by mapping the reads it was built from back to it, with no reference required. Its last release (1.0.3) depends on Ruby 2.2 and on aligner and quantifier versions that can no longer be installed on most systems. pyTransRate is a Python reimplementation of the TransRate method built on snap-aligner 2.0.5 and salmon 2.7.0. In 5,031 paired comparisons (39 assembly-level metrics on each of 129 public assemblies), it reproduces the original sequence metrics and read counts exactly and ranks assemblies consistently with 1.0.3 (Spearman rho = 0.94 for assembly score, 0.98 for good-mapping rate), although its read-based scores are not numerically interchangeable with the original. It also reads gzip- and bgzip-compressed input directly. Availability and Implementation: pyTransRate is implemented in Python 3 and is freely available under the MIT license at https://github.com/macmanes-lab/pytransrate. It runs on Linux and macOS; snap-aligner and salmon are installed from Bioconda. Supplementary information: Supplementary data are available online. Supplementary Table S1 lists the assembly and read accessions for every assembly analyzed; Supplementary Table S2 gives per-assembly values from both implementations.

q-bio.GN↗