Evidence map›Paper›PMID 41292913›Full record

ArticlebioRxiv : the preprint server for biology2025

Heimdall: A Modular Framework for Tokenization in Single-Cell Foundation Models.

Ellie Haber, Shahul Alam, Nicholas Ho, Renming Liu, Evan Trop, Shaoheng Liang, Muyu Yang, Spencer Krieger, Jian Ma

Abstract readPreprint
PubMed Full text at PMC Publisher
In one paragraph

Article in bioRxiv : the preprint server for biology, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

9 authors.

Ellie HaberMachine Learning Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Shahul AlamRay and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Nicholas HoRay and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Renming LiuRay and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Evan TropMachine Learning Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Shaoheng LiangRay and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Muyu YangRay and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Spencer KriegerRay and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.ORCID 0000-0002-2822-022X
Jian MaRay and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.ORCID 0000-0002-4202-5834

Funding

Multiscale Analyses of 4D Nucleome Structure and Function by Comprehensive Multimodal Data IntegrationUM1HG011593 · NHGRI · CARNEGIE-MELLON UNIVERSITY · PI ALBER, FRANK, BELMONT, ANDREW STEVEN · 2020 to 2024
$10.4M
Integrated Interdisciplinary, inter-university PhD Program Computational Biology (T32)T32EB009403 · NIBIB · UNIVERSITY OF PITTSBURGH AT PITTSBURGH · PI BAHAR, IVET, BAR-JOSEPH, ZIV · 2009 to 2023
$4.4M
Computational Methods for Next-Generation Comparative GenomicsR01HG007352 · NHGRI · UNIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN · PI MA, JIAN · 2014 to 2023
$2.8M
Computational methods for studying single-cell 3D genomeR01HG012303 · NHGRI · CARNEGIE-MELLON UNIVERSITY · PI DUAN, ZHIJUN, MA, JIAN · 2022 to 2025
$2.2M
Spatial omics technologies to map the senescent cell microenvironmentUH3CA268202 · NCI · BROWN UNIVERSITY · PI MA, JIAN, NERETTI, NICOLA · 2023 to 2025
$2.2M
Three-dimensional mapping and modeling of combinatorial interactions underlying biomolecular condensates in olfactory neuronsR21DA061481 · NIDA · CALIFORNIA INSTITUTE OF TECHNOLOGY · PI GUTTMAN, MITCHELL, LOMVARDAS, STAVROS · 2024 to 2025
$465k
Integrative Machine Learning for Common Fund Spatial OmicsR03OD039980 · OD · CARNEGIE-MELLON UNIVERSITY · PI MA, JIAN · 2025 to 2025
$286k
NCI NIH HHS UH3 CA268202NHGRI NIH HHS R01 HG007352NHGRI NIH HHS R01 HG012303NHGRI NIH HHS UM1 HG011593NIBIB NIH HHS T32 EB009403NIDA NIH HHS R21 DA061481NIH HHS R03 OD039980
6 · The paper itself

Abstract

Foundation models trained on single-cell RNA-sequencing (scRNA-seq) data have rapidly become powerful tools for single-cell analysis. Their performance, however, depends critically on how cells are tokenized into model inputs - a design space that remains poorly understood. Here, we present Heimdall, a comprehensive framework and open-source toolkit for systematically evaluating tokenization strategies in single-cell foundation models (scFMs). Heimdall decomposes each scFM into modular components: a gene identity encoder (

Identifiers

PMID41292913
PMCPMC12642435

What Socratic holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.