Author

John-William Sidhom

Johns Hopkins UniversityORCID 0000-0002-5575-0285Unclaimed 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

Organism:human· 5 Approach:deep learning· 4 Research Focus:differential expression· 3 Approach:statistical model· 3 Research Focus:cell type annotation· 2 Research Focus:drug response / drug discovery· 2 Research Focus:variant calling· 2 Assay:whole-exome sequencing· 2

Frequent Co-Authors

Alexander Spyridon BarasiD· 6 shared Drew M. PardolliD· 2 shared Jordan AnayaiD· 2 shared Craig A. CummingsiD· 1 shared Faisal MahmoodiD· 1 shared H. Benjamin LarmaniD· 1 shared Manish A. ShahiD· 1 shared Megan Wind-Rotolo· 1 shared

Activity by Year

2018-2026 · peak 2/yr

Co-Author Collaboration Network

10 top collaborators · 18 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

6 shared papersBioinformatics

Alexander Spyridon BarasORCID

Mutual co-authors in cluster

Author profile →

6 papers

Recent·Most cited

A Foundation Model for the Cancer Genome

John-William Sidhom, Alexander Spyridon Baras, Olivier Elemento, Manish A. Shah

TESSERA is a foundation model for the cancer genome that uses self-supervised learning to predict variant pathogenicity, tumour typing, and treatment response, revealing interpretable biomarkers for chemotherapy selection.

bioRxiv · Jun 1, 2026 · PreprintBioinformatics

Aggregation Tool for Genomic Concepts (ATGC): A deep learning framework for somatic mutations and other sparse genomic measures

Jordan Anaya, John-William Sidhom, Faisal Mahmood, Alexander Spyridon Baras

The paper introduces a deep learning framework for genomic data that aggregates and predicts somatic mutations and other sparse genomic measures using attention-based multiple instance learning.

Nature Biomedical Engineering · Nov 2, 2023Peer-reviewedBioinformatics

Probabilistic mixture models improve calibration of panel-derived tumor mutational burden in the context of both tumor-normal and tumor-only sequencing

Jordan Anaya, John-William Sidhom, Craig A. Cummings, Alexander Spyridon Baras

This paper introduces probabilistic mixture models to calibrate panel-derived tumor mutational burden (TMB) to exomic TMB, showing improved accuracy over linear regression.

Cancer Research Communications · Feb 24, 2023Peer-reviewedBioinformatics

DeepTCR: a deep learning framework for understanding T-cell receptor sequence signatures within complex T-cell repertoires

John-William Sidhom, H. Benjamin Larman, Petra Ross-MacDonald, Megan Wind-Rotolo, Drew M. Pardoll, Alexander S. Baras

DeepTCR uses deep learning to analyze T-cell receptor sequences, improving classification and prediction in immunology and clinical settings.

bioRxiv · Dec 23, 2019 · PreprintBioinformatics

Convolving Pre-Trained Convolutional Neural Networks at Various Magnifications to Extract Diagnostic Features for Digital Pathology

John-William Sidhom, Alexander Spyridon Baras

The paper applies transfer learning using ResNet50 to extract diagnostic features from digital pathology images of breast lesions at various magnifications for classification into histological labels.

bioRxiv · May 30, 2018 · PreprintBioinformatics

AI-MHC: an allele-integrated deep learning framework for improving Class I & Class II HLA-binding predictions

John-William Sidhom, Drew M. Pardoll, Alexander Spyridon Baras

AI-MHC improves Class I and Class II HLA-binding predictions using a deep learning framework that integrates allele information and achieves state-of-the-art performance.

bioRxiv · May 25, 2018 · PreprintBioinformatics