Beyond Annotation: Leveraging Raw RNA‑seq Reads via

<p dir="ltr">The poster presents a new foundation-model approach that bypasses traditional RNA-seq preprocessing and instead learns directly from raw reads to detect early-stage cancers across multiple tissue types. The work reframes early detection as a sequence-level inference prob...

Full description

Saved in:
Bibliographic Details
Main Author: Sang Lee (22750319) (author)
Other Authors: Ryan Kim (22750338) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852014397598203904
author Sang Lee (22750319)
author2 Ryan Kim (22750338)
author2_role author
author_facet Sang Lee (22750319)
Ryan Kim (22750338)
author_role author
dc.creator.none.fl_str_mv Sang Lee (22750319)
Ryan Kim (22750338)
dc.date.none.fl_str_mv 2025-12-01T05:45:55Z
dc.identifier.none.fl_str_mv 10.6084/m9.figshare.30749084.v1
dc.relation.none.fl_str_mv https://figshare.com/articles/poster/Beyond_Annotation_Leveraging_Raw_RNA_seq_Reads_via/30749084
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Genomics and transcriptomics
Gene expression (incl. microarray and other genome-wide approaches)
AI
Cancer
Oncology
RNA
transcriptomics approach uncovers novel roles
cfRNA
RNA-seq approach
dc.title.none.fl_str_mv Beyond Annotation: Leveraging Raw RNA‑seq Reads via
dc.type.none.fl_str_mv Image
Poster
info:eu-repo/semantics/publishedVersion
image
description <p dir="ltr">The poster presents a new foundation-model approach that bypasses traditional RNA-seq preprocessing and instead learns directly from raw reads to detect early-stage cancers across multiple tissue types. The work reframes early detection as a sequence-level inference problem rather than a gene-expression problem. Instead of relying on annotated transcripts or fixed reference genomes, the model ingests fragment-level patterns, error signatures, splicing signals, and coverage irregularities that typically get discarded during alignment.</p><p dir="ltr">The visual layout highlights three layers of innovation:</p><ol><li>an architecture trained end-to-end on billions of raw read tokens;</li><li>a representation space that captures cancer-specific perturbations invisible to conventional pipelines;</li><li>multi-cancer classifiers demonstrating improved sensitivity on early-stage disease, particularly in low-tumor-fraction settings.</li></ol><p dir="ltr">Figures show the contrast between aligned vs raw-read signal loss, the model’s latent space separating tumor vs non-tumor samples, and cross-cohort performance benchmarks. The final section outlines translational pathways—from early liquid biopsy screening to integration with cfRNA-based multi-omics signals.</p><p dir="ltr">The overall message is clear: annotated RNA-seq has reached its ceiling, and treating raw reads as a high-dimensional language unlocks a new direction for early cancer detection.</p>
eu_rights_str_mv openAccess
id Manara_50e123b3dd32db3e808237a2931836da
identifier_str_mv 10.6084/m9.figshare.30749084.v1
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30749084
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Beyond Annotation: Leveraging Raw RNA‑seq Reads viaSang Lee (22750319)Ryan Kim (22750338)Genomics and transcriptomicsGene expression (incl. microarray and other genome-wide approaches)AICancerOncologyRNAtranscriptomics approach uncovers novel rolescfRNARNA-seq approach<p dir="ltr">The poster presents a new foundation-model approach that bypasses traditional RNA-seq preprocessing and instead learns directly from raw reads to detect early-stage cancers across multiple tissue types. The work reframes early detection as a sequence-level inference problem rather than a gene-expression problem. Instead of relying on annotated transcripts or fixed reference genomes, the model ingests fragment-level patterns, error signatures, splicing signals, and coverage irregularities that typically get discarded during alignment.</p><p dir="ltr">The visual layout highlights three layers of innovation:</p><ol><li>an architecture trained end-to-end on billions of raw read tokens;</li><li>a representation space that captures cancer-specific perturbations invisible to conventional pipelines;</li><li>multi-cancer classifiers demonstrating improved sensitivity on early-stage disease, particularly in low-tumor-fraction settings.</li></ol><p dir="ltr">Figures show the contrast between aligned vs raw-read signal loss, the model’s latent space separating tumor vs non-tumor samples, and cross-cohort performance benchmarks. The final section outlines translational pathways—from early liquid biopsy screening to integration with cfRNA-based multi-omics signals.</p><p dir="ltr">The overall message is clear: annotated RNA-seq has reached its ceiling, and treating raw reads as a high-dimensional language unlocks a new direction for early cancer detection.</p>2025-12-01T05:45:55ZImagePosterinfo:eu-repo/semantics/publishedVersionimage10.6084/m9.figshare.30749084.v1https://figshare.com/articles/poster/Beyond_Annotation_Leveraging_Raw_RNA_seq_Reads_via/30749084CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/307490842025-12-01T05:45:55Z
spellingShingle Beyond Annotation: Leveraging Raw RNA‑seq Reads via
Sang Lee (22750319)
Genomics and transcriptomics
Gene expression (incl. microarray and other genome-wide approaches)
AI
Cancer
Oncology
RNA
transcriptomics approach uncovers novel roles
cfRNA
RNA-seq approach
status_str publishedVersion
title Beyond Annotation: Leveraging Raw RNA‑seq Reads via
title_full Beyond Annotation: Leveraging Raw RNA‑seq Reads via
title_fullStr Beyond Annotation: Leveraging Raw RNA‑seq Reads via
title_full_unstemmed Beyond Annotation: Leveraging Raw RNA‑seq Reads via
title_short Beyond Annotation: Leveraging Raw RNA‑seq Reads via
title_sort Beyond Annotation: Leveraging Raw RNA‑seq Reads via
topic Genomics and transcriptomics
Gene expression (incl. microarray and other genome-wide approaches)
AI
Cancer
Oncology
RNA
transcriptomics approach uncovers novel roles
cfRNA
RNA-seq approach