Author

Siddhi Ramesh

University of ChicagoORCID 0000-0003-2225-4864Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 2 Assay:imaging· 2 Research Focus:batch correction / integration· 1 Research Focus:cell type annotation· 1 Approach:deep learning· 1 Research Focus:dimensionality reduction· 1 Research Focus:drug response / drug discovery· 1 Approach:matrix factorization· 1

Frequent Co-Authors

Alexander T. PearsoniD· 2 shared James M. DolezaliD· 2 shared Sara E. KochannyiD· 2 shared Anni VirtaneniD· 1 shared Brad Feiger· 1 shared Charles M. PerouiD· 1 shared Cheng FaniD· 1 shared Elena Nevins· 1 shared

Activity by Year

2024-2026 · peak 1/yr

Co-Author Collaboration Network

10 top collaborators · 33 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

2 shared papersBioinformatics

Alexander T. PearsonORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

BioinformaticsbioRxivPreprintJul 8, 2026

FEATMAP: Targeted Correction of Acquisition Signatures Harmonizes Medical Foundation Model Embeddings and Enables Robust Task Generalization

Leonhard Donle, Michael Phillips, Farieda Gaber…·Ernst Lengyel

FEATMAP corrects acquisition signatures in medical foundation model embeddings to improve cross-condition similarity and task generalization without retraining.

DOI 10.64898/2026.07.02.736184

imagingstatistical model

𝕏 PostBluesky

Cancer BiologyScience AdvancesPeer-reviewedNov 15, 2024

Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features

Frederick Matthew Howard, Hanna M. Hieromnimon, Siddhi Ramesh…·Alexander T. Pearson

This paper introduces HistoXGAN, a GAN that reconstructs cancer histology from latent features, showing it retains tumor grade, histologic subtype, and gene expression patterns across 29 cancer types.

35 citations

imagingdeep learning

𝕏 PostBluesky