Biology subjects

Sidhom, J.-W.

Publications and source records attributed to Sidhom, J.-W..

6 recordsLinked to original sources

bioRxiv2026

A Foundation Model for the Cancer Genome

AO_SCPLOWBSTRACTC_SCPLOWCancer is a disease of the genome, in which somatic mutations and copy-number alterations determine tumour identity, clinical behaviour, and response to therapy. Consortium-scale sequencing has profiled hundreds of thousands of tumours,1,2 yet clinical interpretation still proceeds one alteration at a time against hand-curated knowledgebases,3,4 often ignoring co-occurring alterations and the genome-wide copy-number pattern. Self-supervised foundation models pretrained on unlabelled corpora5 have produced transferable representations in adjacent biological domains6-8 by learning joint structure across many features, yet no comparable model exists for the cancer genome. Here we present TESSERA (Tumour Embeddings via Self-Supervised Encoding and Reconstruction of Alterations), a foundation model for the cancer genome; we pretrain it on somatic single-nucleotide variants and copy-number segments through masked-token reconstruction within each modality and a contrastive objective across modalities. A single representation, produced once and reused without retraining, supports variant pathogenicity prediction, pan-cancer tumour typing, unsupervised molecular subtyping, prognostic stratification, and counterfactual treatment-effect estimation that yields predictive chemotherapy-selection biomarkers in real-world cohorts. These biomarkers are interpretable: each surfaces the co-occurring alterations underlying the prediction, exposing biology that single-gene rules miss. In metastatic colorectal cancer, where the FOLFOX-vs-FOLFIRI choice is currently guided by toxicity rather than tumour biology, the model uncovers a candidate predictive biomarker: a three-feature rule (TP53+/KRAS+/17p-) selecting patients who derive substantially greater benefit from FOLFOX than FOLFIRI.

bioinformatics↗

bioRxiv2020

Aggregation Tool for Genomic Concepts (ATGC): A deep learning framework for sparse genomic measures and its application to tumor mutational burden

Deep learning can extract meaningful features from data given enough training examples. Large-scale genomic data are well suited for this class of machine learning algorithms; however, for many of these data the labels are at the level of the sample instead of at the level of the individual genomic measures. Conventional approaches to this data statically featurise and aggregate the measures separately from prediction. We propose to featurise, aggregate, and predict with a single trainable end-to-end model by turning to attention-based multiple instance learning. This allows for direct modelling of instance importance to sample-level classification in addition to trainable encoding strategies of genomic descriptions, such as mutations. We first demonstrate this approach by successfully solving synthetic tasks conventional approaches fail. Subsequently we applied the approach to somatic variants and achieved best-in-class performance when classifying tumour type or microsatellite status, while simultaneously providing an improved level of model explainability. Our results suggest that this framework could lead to biological insights and improve performance on tasks that aggregate information from sets of genomic data.

bioinformatics↗

bioRxiv2020

Analysis of SARS-CoV-2 specific T-cell receptors in ImmuneCode reveals cross-reactivity to immunodominant Influenza M1 epitope

Adaptive Biotechnologies and Microsoft have recently partnered to release ImmuneCode, a database containing SARS-CoV-2 specific T-cell receptors derived through MIRA, a T-cell receptor (TCR) sequencing based sequencing approach to identify antigen-specific TCRs. Herein, we query the extent of cross reactivity between these derived SARS-CoV-2 specific TCRs and other known antigens present in McPas-TCR, a manually curated catalogue of pathology-associated TCRs. We reveal cross reactivity between SARS-CoV-2 specific TCRs and the immunodominant Influenza GILGFVFTL M1 epitope, suggesting the importance of further work in characterizing the implications of prior Influenza exposure or co-exposure to the pathology of SARS-CoV-2 illness.

immunology↗

bioRxiv2018

DeepTCR: a deep learning framework for revealing structural concepts within TCR Repertoire

Deep learning algorithms have been utilized to achieve enhanced performance in pattern-recognition tasks, such as in image and vocal recognition 1,2. The ability to learn complex patterns in data has tremendous implications in the genomics and immunology worlds, where sequence motifs become learned features that can be used to predict functionality, guiding our understanding of disease and basic biology 3-6. T-cell receptor (TCR) sequencing assesses the diversity of the adaptive immune system, where complex structural patterns in the TCR can be used to model its antigenic interaction. We present DeepTCR, a broad collection of unsupervised and supervised deep learning methods able to uncover structure in highly complex and large TCR sequencing data by learning a joint representation of a given TCR by its CDR3 sequences, V/D/J gene usage, and HLA background in which the T-cells reside. We demonstrate the utility of deep learning to provide an improved featurization of the TCR across multiple human and murine datasets, including improved classification of antigen-specific TCRs in both unsupervised and supervised learning tasks, understanding immunotherapy-related shaping of repertoire in the murine setting, and predicting response to checkpoint blockade immunotherapy from pre-treatment tumor biopsies in a clinical trial of melanoma. Our results show the flexibility and capacity for deep neural networks to handle the complexity of high-dimensional TCR genomic data for both descriptive and predictive purposes across basic science and clinical research.

bioinformatics↗

bioRxiv2018

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

Deep learning is an area of artificial intelligence that has received much attention in the past few years due to both an increase in computational power with the increased use of graphics processing units (GPUs) for computational analyses and the performance of these class of algorithms on visual recognition tasks. They have found utility in applications ranging from image search to facial recognition for security and social media purposes. Their continued success has propelled their use across many new domains including the medical field, in areas of radiology and pathology in particular, as these fields are thought to be driven by visual recognition tasks. In this paper, we present an application of deep learning, termed transfer learning, using ResNet50, a pre-trained convolutional neural network (CNN) to act as a feature-detector at various magnifications to identify low and high level features in digital pathology images of various breast lesions for the purpose of classifying them correctly into the labels of normal, benign, in-situ, or invasive carcinoma as provided in the ICIAR 2018 Breast Cancer Histology Challenge (BACH).

bioinformatics↗

bioRxiv2018

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

MotivationThe immune system has potential to present a wide variety of peptides to itself as a means of surveillance for pathogenic invaders. This means of surveillances allows the immune system to detect peptides derives from bacterial, viral, and even oncologic sources. However, given the breadth of the epitope repertoire, in order to study immune responses to these epitopes, investigators have relied on in-silico prediction algorithms to help narrow down the list of candidate epitopes, and current methods still have much in the way of improvement.\n\nResultsWe present Allele-Integrated MHC (AI-MHC), a deep learning architecture with improved performance over the current state-of-the-art algorithms in human Class I and Class II MHC binding prediction. Our architecture utilizes a convolutional neural network that improves prediction accuracy by 1) allowing one neural network to be trained on all peptides for all alleles of a given class of MHC molecules by making the allele an input to the net and 2) introducing a global max pooling operation with an optimized kernel size that allows the architecture to achieve translational invariance in MHC-peptide binding analysis, making it suitable for sequence analytics where a frame of interest needs to be learned in a longer, variable length sequence. We assess AI-MHC against internal independent test sets and compare against all algorithms in the IEDB automated server benchmarks, demonstrating our algorithm achieves state-of-the-art for both Class I and Class II prediction.\n\nAvailability and ImplementationAI-MHC can be used via web interface at baras.pathology.jhu.edu/AI-MHC\n\nContactjsidhom1@jhmi.edu

bioinformatics↗