Author

John Abel

PathAI (United States)

Listed by name: these papers carry no ORCID for this author, so different people with the same name may be mixed together.

Biology Disciplines

Click to filter author papers

Cancer Biology· 1 Immunology· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:cell type annotation· 2 Organism:human· 2 Assay:bulk RNA-seq· 1 Assay:CITE-seq· 1 Approach:contrastive learning· 1 Approach:deep learning· 1 Research Focus:gene regulatory network inference· 1 Assay:imaging· 1

Frequent Co-Authors

Amaro N Taylor-WeineriD· 1 shared Anthony J. CoyleiD· 1 shared Archit KhoslaiD· 1 shared Bahar RahsepariD· 1 shared Brinda Vijaykumar· 1 shared Chintan ParmariD· 1 shared Christophe O. BenoistiD· 1 shared Daniel C. PregiboniD· 1 shared

Activity by Year

2025-2025 · peak 2/yr

Co-Author Collaboration Network

10 top collaborators · 21 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

1 shared paperCancer Biology

Amaro N Taylor-WeinerORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

REPTRA: Mapping Immune T Cell Receptor Activity from Full Sequences with a Debiased Contrastive Loss

John Abel, Brinda Vijaykumar, Neel Patel, Anthony J. Coyle, Christophe O. Benoist, Daniel C. Pregibon

The paper introduces REPTRA, a contrastive learning model for TCR-epitope recognition using full TCR sequences and a debiased loss function, showing improved performance and highlighting the importance of CDR1 and CDR2.

bioRxiv · Oct 22, 2025 · PreprintImmunology

Spatial mapping of immunosuppressive cancer-associated fibroblast gene signatures in H&E-stained images using additive multiple instance learning

Miles Markey, Juhyun Kim, Zvi Goldstein, Ylaine Gerardin, Jacqueline A. Brosnan‐Cashman, Syed Ashar Javed, Dinkar Juyal, Harshith Pagidela, Limin Yu, Bahar Rahsepar, John Abel, Stephanie R. Hennek, Archit Khosla, Amaro N Taylor-Weiner, Chintan Parmar

This paper introduces aMIL, a machine learning method that predicts CAF gene signatures from H&E images, revealing spatial patterns linked to immunosuppression in tumors.

Modern Pathology · Apr 11, 2025Peer-reviewedCancer Biology