Biology subjects

Chen, J. G.

Publications and source records attributed to Chen, J. G..

3 recordsLinked to original sources

bioRxiv2026

FARM: Forecasting Antibiotic Resistance in Mycobacterium tuberculosis using biophysics and machine learning

Antibiotic-resistant tuberculosis remains a major public health challenge, and rapid diagnosis of resistant infections based on genomic markers holds promise for improving time to effective treatment. However, the vast majority of clinically observed variants in resistance-associated genes remain of uncertain significance, limiting the utility of predictors. Here we develop a multimodal forecasting framework, FARM (Forecasting Antibiotic Resistance in Mycobacterium tuberculosis) to determine whether a newly observed mutation in a resistance gene may indeed cause resistance. Our framework combines structural context, biophysical energy features, protein language model features, and mutational AAIndex physicochemical descriptors. Using 345 labeled mutations from the World Health Organization 2021 catalogue, we train interpretable models that distinguish resistance-associated from non-resistance-associated variants with holdout AUCs of 0.843-0.943. In a novel temporal evaluation of 62 mutations reclassified after the training data was released, the selected Combined model achieved 80.7% recall of resistant reclassifications (resistant-class F1=86.8; AUC=0.735). Applied to 4,525 current uncertain-significance mutations, the framework prioritizes 696 candidate resistance mutations, including genes associated with the new antibiotics bedaquiline, delamanid, and pretomanid. These forecasts are intended to support future catalogue updates and experimental follow-up.

bioinformatics↗

bioRxiv2025

Clinical feasibility of spatial transcriptomics using discarded tissue from diagnostic breast biopsies

Spatial transcriptomics holds potential to transform cancer diagnostics, yet significant barriers still limit its clinical translation. First, access to primary patient tissue is often restricted by logistical challenges and patient hesitancy. Second, it remains uncertain whether high-quality spatial transcriptomics data can be generated from clinical biopsy sections as these are collected primarily for diagnostic purposes that do not prioritize RNA-quality. We investigated whether discarded tissue slices, generated during standard pathology procedures, could be repurposed for spatial transcriptomics and alleviate concerns about both tissue availability and quality. Here, we established a pipeline to collect and perform spatial in situ transcriptomics on discarded biopsy material from a breast cancer patient, and digitized matched pathology images, including hematoxylin and eosin and traditional histochemistry stains from adjacent sections. Our results show that spatial transcriptomics data from discarded tissue are concordant with the original pathology report, while also providing additional insights such as accurate cell type annotation, detailed spatial architecture, and quantification of biological processes relevant to breast cancer progression. Altogether, our approach using discarded pathology tissue sections provides a practical and scalable solution that would maximize the scientific value of existing clinical specimens and enable high-resolution tumor microenvironment mapping.

genomics↗

bioRxiv2023

Giotto Suite: a multi-scale and technology-agnostic spatial multi-omics analysis ecosystem

Emerging spatial omics technologies continue to advance the molecular mapping of tissue architecture and the investigation of gene regulation and cellular crosstalk, which in turn provide new mechanistic insights into a wide range of biological processes and diseases. Such technologies provide an increasingly large amount of information content at multiple spatial scales. However, representing and harmonizing diverse spatial datasets efficiently, including combining multiple modalities or spatial scales in a scalable and flexible manner, remains a substantial challenge. Here, we present Giotto Suite, a suite of open-source software packages that underlies a fully modular and integrated spatial data analysis toolbox. At its core, Giotto Suite is centered around an innovative and technology-agnostic data framework embedded in the R software environment, which allows the representation and integration of virtually any type of spatial omics data at any spatial resolution. In addition, Giotto Suite provides both scalable and extensible end-to-end solutions for data analysis, integration, and visualization. Giotto Suite integrates molecular, morphology, spatial, and annotated feature information to create a responsive and flexible workflow for multi-scale, multi-omic data analyses, as demonstrated here by applications to several state-of-the-art spatial technologies. Furthermore, Giotto Suite builds upon interoperable interfaces and data structures that bridge the established fields of genomics and spatial data science, thereby enabling independent developers to create custom-engineered pipelines. As such, Giotto Suite creates an immersive ecosystem for spatial multi-omic data analysis.

bioinformatics↗