Luca Bertinetto, Oren Kraus, Kian Kenyon-Dean, Ihab Bendidi, Alina Selega, Jordan Sorokin, David Errington, Hayley Donnella
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
RNA sequencing produces rich and diverse datasets of gene expression, offering compelling insights into cellular state and function that have many applications in drug discovery. Modeling such data is challenging due to inherent technical noise and experimental batch effects, as evidenced by many existing transcriptomic foundation models (FMs) underperforming relative to linear baselines. Such results raise the question of whether deep representation learning provides a distinct advantage over the direct use of raw transcript counts. Our work explores this by developing a new self-supervised model, TxFM, with a focus on inductive representation learning evaluations. TxFM employs a masked autoencoding approach tailored to diverse RNA-seq count data, and our ablation study empirically identifies crucial architecture configurations required for strong transfer performance. Additionally, we curate a public training corpus, DiverseRNA-1.4M, and find that TxFM trained on this curated dataset yields high-fidelity gene representations that outperform FMs trained on atlas-scale corpora over 100× larger. Overall, our results indicate that inductive self-supervised learning is a viable modeling approach for transcriptomics representation, provided a careful synthesis of model architecture and training data curation. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2605.31562")
get_code_for_paper("2605.31562")
have("2605.31562")
Connect an agent — have() is free.