Biology subjects

Darmofal, M.

Publications and source records attributed to Darmofal, M..

3 recordsLinked to original sources

bioRxiv2026

Generalist large language models complement tailor-made predictors for tumor genomics interpretation

General-purpose large language models (LLMs) are trained on large corpora to acquire broad knowledge, but whether LLMs can replace, or augment, task-specific models is unclear. We evaluated LLMs on three real-world, clinically important tumor genomic interpretation tasks, in order of increasing difficulty: (i) distinguishing tumor from non-tumor mutations (n=34,415 variants), (ii) distinguishing driver from passenger mutations (n=13,469 variants), and (iii) inferring cancer type from tumor sequencing reports across multiple assays and institutions (n=102,791 samples). The best general-purpose LLMs performed as well as the benchmark tailor-made predictor for task (i). Ensembling tailor-made models with zero-shot LLMs improved their performance for tasks (i) and (ii). For task (iii), LLMs outperformed or supplemented tailor-made models on out-of-distribution data. Without fine-tuning, current LLMs already can be useful in clinical genomic interpretation by adding complementary expertise to tailor-made, state-of-the-art predictors.

genomics↗

bioRxiv2025

Integrated histopathologic modeling of detailed tumor subtypes and actionable biomarkers

Accurate cancer subtyping with accompanying molecular characterization is critical for precision oncology. While machine learning approaches have been applied to both digital pathology and cancer genomics, previous work has been limited in sample size and has typically aggregated granular cancer subtypes into coarse groupings, likely obfuscating informative molecular and prognostic associations and phenotypic variation of more detailed tumor subtypes. Accordingly, we collated 378,123 hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) with matched targeted DNA clinical sequencing results and OncoTree detailed cancer subtypes from a real-world cohort of 71,142 patients. Using this scaled, granular dataset and a cancer subtype knowledge graph, we developed Mosaic: a family of calibrated machine learning models using H&E WSI embeddings to classify tumors and identify molecular phenotypes across 163 detailed subtypes. The cancer subtyping module (Aeon) achieved an area under the receiver operating characteristic curve (AUROC) of 0.992 overall, with 161/163 subtypes reaching an AUROC [≥] 0.90 and improved performance over a state-of-the-art genomics-based classifier. The genomic inference module (Paladin) achieved an AUROC [≥] 0.80 for 167 pairs of detailed subtypes and genomic targets. We further used the learned histopathologic representations to i) identify key associations of the histopathologic embeddings with clinical biomarkers; ii) identify unsupervised sub-clusters of tumors with genomic determinants of tumor phenotype; iii) specify granular diagnoses for cancers of unknown primary, evaluated by genomic associations and expected clinical outcome distributions; iv) annotate functional significance for variants of uncertain significance (VUS); and v) identify cases that mimic the phenotypic effect of known DNA variants on H&E in the absence of detectable DNA alterations. Taken together, this work advances our understanding of phenotypic variation of granular tumor subtypes, their relevance to enhanced diagnostics, and their potential utility in risk stratification with multimodal machine learning in cancer.

cancer biology↗

bioRxiv2019

Novel patterns of complex structural variation revealed across thousands of cancer genome graphs

Cancer genomes often harbor hundreds of somatic DNA rearrangement junctions, many of which cannot be easily classified into simple (e.g. deletion, translocation) or complex (e.g. chromothripsis, chromoplexy) structural variant classes. Applying a novel genome graph computational paradigm to analyze the topology of junction copy number (JCN) across 2,833 tumor whole genome sequences (WGS), we introduce three complex rearrangement phenomena: pyrgo, rigma, and tyfonas. Pyrgo are "towers" of low-JCN duplications associated with early replicating regions and superenhancers, and are enriched in breast and ovarian cancers. Rigma comprise "chasms" of low-JCN deletions at late-replicating fragile sites in esophageal and other gastrointestinal (GI) adenocarcinomas. Tyfonas are "typhoons" of high-JCN junctions and fold back inversions that are enriched in acral but not cutaneous melanoma and associated with a previously uncharacterized mutational process of non-APOBEC kataegis. Clustering of tumors according to genome graph-derived features identifies subgroups associated with DNA repair defects and poor prognosis.

genomics↗