Biology subjects

Pearson, A. T.

Publications and source records attributed to Pearson, A. T..

18 recordsLinked to original sources

bioRxiv2026

FEATMAP: Targeted Correction of Acquisition Signatures Harmonizes Medical Foundation Model Embeddings and Enables Robust Task Generalization

AO_SCPLOWBSTRACTC_SCPLOWMedical foundation models compress biomedical data into embeddings that support diverse downstream clinical tasks. However, successful model deployment is hampered by performance degradation on external data. It is recognized that embeddings capture acquisition signatures, such as hardware and technical differences, in addition to biology. Effective harmonization must remove the acquisition signature while preserving biological signals, a trade-off that current methods fail to balance adequately. Input-level normalization fails to eliminate acquisition signatures from embeddings, whereas embedding-level methods adjust features in an untargeted manner. We present FEATMAP, a harmonization approach that models acquisition signatures as geometric distortions between manifolds of similarly arranged embeddings. Using paired data that isolate the effect of acquisition signatures, FEATMAP fits a single global affine transformation per foundation model to correct acquisition signatures directly in the embedding space. This targeted, reusable correction aims to preserve biological and demographic variation while harmonizing across acquisition signatures. Across scanner and foundation-model harmonization in digital pathology and field-strength harmonization in brain MRI, FEATMAP improves cross-condition embedding similarity, reduces performance gaps without retraining, and suggests potential for the alignment of disparate embedding spaces.

bioinformatics↗

bioRxiv2026

Enhancing Predictive Accuracy in Immunotherapy Models through Data Integration and Parameter Identifiability

Immune checkpoint inhibitors (ICIs), a class of immunotherapy, offer promising benefits but face challenges such as low response rates to be used as a broadly effective treatment for all patients. In this study, we use a set of ordinary different equation (ODE) models and bladder cancer in vivo data as a case study to outline a biologically informed, data-driven framework for formulating, calibrating and validating immunotherapy models, and thus ensuring their predictive reliability. We consider multiple treatment scenarios and distinct immune cell-mediated killing mechanisms for tumor cells of different antigenicity. By integrating sensitivity analysis and identifiability analysis with targeted experimental design, we demonstrate how mathematical models can move beyond qualitative insight to quantitative prediction. We generate virtual cohorts to show that insufficient data integration leads to systematically overestimated therapeutic benefits of ICIs. We also explore dosing schedules that enhance survival or reduce dosage without compromising survival.

cell biology↗

bioRxiv2024

Association of oropharyngeal cancer recurrence with tumor-intrinsic and immune-mediated sequelae of reduced genomic instability

BackgroundLimited understanding of the biology predisposing certain human papillomavirus-related (HPV+) oropharyngeal squamous cell carcinomas (OPSCCs) to relapse impedes therapeutic personalization. We aimed to identify molecular traits that distinguish recurrence-prone tumors. Methods50 HPV+ OPSCCs that later recurred (cases) and 50 non-recurrent controls matched for stage, therapy, and smoking history were RNA-sequenced. Groups were compared by gene set enrichment analysis, and select differences were validated by immunohistochemistry. Features discriminating groups were scored in each tumor using gene set variation analysis, and scores were evaluated for recurrence prediction ability. ResultsCases downregulated pathways linked to anti-tumor immunity (FDR-adjusted p<.05) and contained fewer tumor-infiltrating lymphocytes (p<.001), including cytotoxic T-cells (p=.005). Cases also upregulated pathways related to cell division and other aspects of tumor progression. Upregulated and downregulated pathways were respectively used to define a tumor progression score (TPS) and immune suppression score (ISS) for each tumor. Correlation between TPS and ISS (r=.603, p<.001) was potentially explained by observed upregulation of DNA repair pathways in cases, which might enhance their progression directly and by limiting cytosolic DNA-induced inflammation. Accordingly, cases contained fewer double-strand breaks based on staining for phospho-RPA32 (p=.006) and {gamma}-H2AX (p=.005) and downregulated pro-inflammatory components of the cytoplasmic DNA sensing pathway. A combined score derived from TPS and ISS optimized recurrence prediction and stratified survival in a manner generalizable to three external cohorts. ConclusionsWe provide novel evidence that limiting genomic instability makes tumor-intrinsic and immune-mediated contributions to HPV+ OPSCC recurrence risk, opening opportunities to detect and target this treatment-resistant biology.

cancer biology↗

bioRxiv2024

Counterfactual Diffusion Models for Mechanistic Explainability of Artificial Intelligence Models in Pathology

Deep learning can extract predictive and prognostic biomarkers from histopathology whole slide images. However, explainable artificial intelligence approaches widely used in digital pathology, such as attention heatmaps and class activation mapping, offer only limited interpretability regarding the features captured by classifiers. Here, we present MoPaDi (Morphing histoPathology Diffusion), a framework for generating counterfactual explanations for histopathology images that reveal which morphological or style features drive classifier predictions. MoPaDi combines diffusion autoencoders with task-specific multiple instance learning classifiers to manipulate images and flip predictions by modifying relevant features. We evaluated the framework on multiple datasets spanning colorectal, breast, liver, and lung cancers, including tissue type, cancer subtype, and biomarker (microsatellite instability) classification tasks. We assessed counterfactual explanations through quantitative analyses, pathologists evaluations, and independent foundation model-based classifiers. We found that MoPaDi was able to generate realistic counterfactual histopathology images, enabling pathologists to identify morphological features associated with the change in model predictions. Unlike conventional reviews of highly attended regions typical in digital pathology, MoPaDi explanations enabled pathologists to directly identify morphological features driving the classifiers predictions from a limited number of top-contributing tiles. Consistent with the literature, our biomarker classifier associated high microsatellite instability with mucinous differentiation, glandular patterns, and lymphocytic infiltration. Furthermore, MoPaDi revealed that changes in classifier predictions were mainly driven by morphological alterations rather than staining differences. Overall, MoPaDi is a practical framework for counterfactual explanations in computational pathology that reveals model-specific drivers of classification and increases trust in deep learning models.

bioinformatics↗

bioRxiv2024

Agent-Based Modeling of Virtual Tumors Reveals the Critical Influence of Microenvironmental Complexity on Immunotherapy Efficacy

Since the introduction of the first immune checkpoint inhibitor (ICI), immunotherapy has changed the landscape of molecular therapeutics for cancers. However, ICIs do not work equally well on all cancers and for all patients. There has been a growing interest in using mathematical and computational models to optimize clinical responses. Ordinary differential equations (ODEs) have been widely used for mechanistic modeling in immuno-oncology and immunotherapy because they allow rapid simulations of temporal changes in the cellular and molecular populations involved. Nonetheless, ODEs cannot describe the spatial structure in the tumor microenvironment or quantify the influence of spatially-dependent characteristics of tumor-immune dynamics. For these reasons, agent-based models (ABMs) have gained popularity because they can model more detailed phenotypic and spatial heterogeneity that better reflect the complexity seen in vivo. In the context of anti-PD-1 ICIs, we compare treatment outcomes simulated from an ODE model and an ABM to show the importance of including spatial components in computational models of cancer immunotherapy. We consider tumor cells of high and low antigenicity and two distinct cytotoxic T lymphocyte (CTL) killing mechanisms. The preferred mechanism differs based on the antigenicity of tumor cells. Our ABM reveals varied phenotypic shifts within the tumor and spatial organization of tumor and CTLs, despite similarities in key immune parameters, initial conditions of simulation, and early temporal trajectories of the cell populations.

cancer biology↗

bioRxiv2024

Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features

Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of novel molecular features. These approaches distill cancer histologic images into high-level features which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network - HistoXGAN - capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a virtual biopsy.

cancer biology↗

bioRxiv2023

Mathematical Model Predicts Tumor Control Patterns Induced by Fast and Slow CTL Killing Mechanisms

Immunotherapy has dramatically transformed the cancer treatment landscape largely due to the efficacy of immune checkpoint inhibitors (ICIs). Although ICIs have shown promising results for many patients, the low response rates in many cancers highlight the ongoing challenges in cancer treatment. Cytotoxic T lymphocytes (CTLs) execute their cell-killing function via two distinct mechanisms: a fast-acting, perforin-mediated process and a slower, Fas ligand (FasL)-driven path-way. Evidence also suggests that the preferred killing mechanism of CTLs depends on the anti-genicity of tumor cells. To determine the critical factors affecting responses to ICIs, we construct an ordinary differential equation model describing in vivo tumor-immune dynamics in the presence of active or blocked PD-1/PD-L1 immune checkpoint. Specifically, we identify important aspects of the tumor-immune landscape that affect tumor size and composition in the short and long term. By generating a virtual cohort with differential tumor and immune attributes, we also simulate the therapeutic outcomes of immune checkpoint blockade in a heterogenous population. In this way, we identify key tumor and immune characteristics that are associated with tumor elimination, dor-mancy, and escape. Our analysis sheds light on which fraction of a population potentially responds well to ICIs and ways to enhance therapeutic outcomes with combination therapy.

cancer biology↗

bioRxiv2023

Validating a low-cost, open-source, locally manufactured workstation and computational pipeline for automated histopathology evaluation using deep learning

Deployment and access to state-of-the-art diagnostic technologies remains a fundamental challenge in providing equitable global cancer care to low-resource settings. The expansion of digital pathology in recent years and its interface with computational biomarkers provides an opportunity to democratize access to personalized medicine. Here we describe a low-cost platform for digital side capture and computational analysis composed of open-source components. The platform provides low-cost ($200) digital image capture from glass slides and is capable of real-time computational image analysis using an open-source deep learning (DL) algorithm and Raspberry Pi ($35) computer. We validate the performance of deep learning models performance using images captured from the open-source workstation and show similar model performance when compared against significantly more expensive standard institutional hardware.

pathology↗

bioRxiv2023

Latent transcriptional programs reveal histology-encoded tumor features spanning tissue origins

Precision medicine in cancer treatment depends on deciphering tumor phenotypes to reveal the underlying biological processes. Molecular profiles, including transcriptomics, provide an information-rich tumor view, but their high-dimensional features and assay costs can be prohibitive for clinical translation at scale. Recent studies have suggested jointly leveraging histology and genomics as a strategy for developing practical clinical biomarkers. Here, we use machine learning techniques to identify de novo latent transcriptional processes in squamous cell carcinomas (SCCs) and to accurately predict their activity levels directly from tumor histology images. In contrast to analyses focusing on pre-specified, individual genes or sample groups, our latent space analysis reveals sets of genes associated with both histologically detectable features and clinically relevant processes, including immune response, collagen remodeling, and fibrosis. The results demonstrate an approach for discovering clinically interpretable histological features that indicate complex, potentially treatment-informing biological processes.

cancer biology↗

bioRxiv2022

Comparing scientific abstracts generated by ChatGPT to original abstracts using an artificial intelligence output detector, plagiarism detector, and blinded human reviewers

BackgroundLarge language models such as ChatGPT can produce increasingly realistic text, with unknown information on the accuracy and integrity of using these models in scientific writing. MethodsWe gathered ten research abstracts from five high impact factor medical journals (n=50) and asked ChatGPT to generate research abstracts based on their titles and journals. We evaluated the abstracts using an artificial intelligence (AI) output detector, plagiarism detector, and had blinded human reviewers try to distinguish whether abstracts were original or generated. ResultsAll ChatGPT-generated abstracts were written clearly but only 8% correctly followed the specific journals formatting requirements. Most generated abstracts were detected using the AI output detector, with scores (higher meaning more likely to be generated) of median [interquartile range] of 99.98% [12.73, 99.98] compared with very low probability of AI-generated output in the original abstracts of 0.02% [0.02, 0.09]. The AUROC of the AI output detector was 0.94. Generated abstracts scored very high on originality using the plagiarism detector (100% [100, 100] originality). Generated abstracts had a similar patient cohort size as original abstracts, though the exact numbers were fabricated. When given a mixture of original and general abstracts, blinded human reviewers correctly identified 68% of generated abstracts as being generated by ChatGPT, but incorrectly identified 14% of original abstracts as being generated. Reviewers indicated that it was surprisingly difficult to differentiate between the two, but that the generated abstracts were vaguer and had a formulaic feel to the writing. ConclusionChatGPT writes believable scientific abstracts, though with completely generated data. These are original without any plagiarism detected but are often identifiable using an AI output detector and skeptical human reviewers. Abstract evaluation for journals and medical conferences must adapt policy and practice to maintain rigorous scientific standards; we suggest inclusion of AI output detectors in the editorial process and clear disclosure if these technologies are used. The boundaries of ethical and acceptable use of large language models to help scientific writing remain to be determined.

scientific communication and education↗

bioRxiv2022

Carcinoma associated mesenchymal stem cells promote ovarian cancer metastasis by increasing tumor heterogeneity through direct mitochondrial transfer

Ovarian cancer is characterized by early, diffuse metastatic spread with most women presenting with extensive abdominal metastasis at the time of diagnosis. Prior work demonstrated carcinoma-associated mesenchymal stem cells (CA-MSCs) enhance ovarian cancer metastasis through a process of direct cellular interaction and formation of heterocellular CA-MSC and tumor cell complexes. In this study, we demonstrated that CA-MSCs enhance metastasis by increasing tumor cell heterogeneity through mitochondrial donation. We showed that CA-MSCs directly interacted with ovarian cancer cells via tunneling nanotubules (TNTs), and CA-MSCs used these TNTs to transfer live mitochondria to adjacent ovarian cancer cells. This mitochondrial donation preferentially occurred with ovarian cancer cells that had the lowest mitochondrial mass, as quantified using live, actively respiring mitochondrial labeling. These mito poor cancer cells demonstrated decreased proliferation, increased sensitivity to chemotherapy, and decreased oxidative phosphorylation compared to mito rich cancer cells. CA-MSCs rescued the phenotypes of mito poor cancer cells, restoring their proliferative capacity, increasing chemotherapy resistance, and increasing oxidative phosphorylation. We validated these findings in a fully autologous system using CA-MSCs and cancer cells derived from the same patient to prevent confounding effects of cellular response to foreign organelle/DNA. Using a knockdown of the mitochondrial motor protein, MIRO1, in CA-MSCs, we demonstrated that mitochondrial transfer is necessary for the CA-MSC-mediated rescue of mito poor cancer cells. Mitochondria of CA-MSC origin persisted in tumor cells over multiple passages. Importantly, CA-MSC mitochondrial donation occurred in vivo, significantly enhanced tumor cell heterogeneity and decreased survival in an orthotopic ovarian cancer mouse model. Collectively, this work identified CA-MSC mitochondrial transfer as a critical mediator of ovarian cancer cell survival, heterogeneity, and metastasis, and blocking CA-MSC mitochondrial transfer represents a unique therapeutic target in ovarian cancer.

cancer biology↗

bioRxiv2022

Self-supervised deep learning for pan-cancer mutation prediction from histopathology

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from tissue morphology, but it is unclear how well these predictions generalize to external datasets. Here, we present a deep learning pipeline based on self-supervised feature extraction which achieves a robust predictability of genetic alterations in two large multicentric datasets of seven tumor types.

cancer biology↗

bioRxiv2022

Multimodal Prediction of Breast Cancer Recurrence Assays and Risk of Recurrence

Gene expression-based recurrence assays are strongly recommended to guide the use of chemotherapy in hormone receptor-positive, HER2-negative breast cancer, but such testing is expensive, can contribute to delays in care, and may not be available in low-resource settings. Here, we describe the training and independent validation of a deep learning model that predicts recurrence assay result and risk of recurrence using both digital histology and clinical risk factors. We demonstrate that this approach outperforms an established clinical nomogram (area under the receiver operating characteristic curve of 0.833 versus 0.765 in an external validation cohort, p = 0.003), and can identify a subset of patients with excellent prognoses who may not need further genomic testing.

cancer biology↗

bioRxiv2021

Classical Mathematical Models for Prediction of Response to Chemotherapy and Immunotherapy

Classical mathematical models of tumor growth have shaped our understanding of cancer and have broad practical implications for treatment scheduling and dosage. However, even the simplest textbook models have been barely validated in real world-data of human patients. In this study, we fitted a range of differential equation models to tumor volume measurements of patients undergoing chemotherapy or cancer immunotherapy for solid tumors. We used a large dataset of 1472 patients with three or more measurements per target lesion, of which 652 patients had six or more data points. We show that the early treatment response shows only moderate correlation with the final treatment response, demonstrating the need for nuanced models. We then perform a head-to-head comparison of six classical models which are widely used in the field: the Exponential, Logistic, Classic Bertalanffy, General Bertalanffy, Classic Gompertz and General Gompertz model. Several models provide a good fit to tumor volume measurements, with the Gompertz model providing the best balance between goodness of fit and number of parameters. Similarly, when fitting to early treatment data, the general Bertalanffy and Gompertz models yield the lowest mean absolute error to forecasted data, indicating that these models could potentially be effective at predicting treatment outcome. In summary, we provide a quantitative benchmark for classical textbook models and state-of-the art models of human tumor growth. We publicly release an anonymized version of our original data, providing the first benchmark set of human tumor growth data for evaluation of mathematical models. Author SummaryMathematical oncology uses quantitative models for prediction of tumor growth and treatment response. The theoretical foundation of mathematical oncology is provided by six classical mathematical models: the Exponential, Logistic, Classic Bertalanffy, General Bertalanffy, Classic Gompertz and General Gompertz model. These models have been introduced decades ago, have been used in thousands of scientific articles and are part of textbooks and curricula in mathematical oncology. However, these models have not been systematically tested in clinical data from actual patients. In this study, we have collected quantitative tumor volume measurements from thousands of patients in five large clinical trials of cancer immunotherapy. We use this dataset to systematically investigate how accurately mathematical models can describe tumor growth, showing that there are pronounced differences between models. In addition, we show that two of these models can predict tumor response to immunotherapy and chemotherapy at later time points when trained on early tumor growth dynamics. Thus, our article closes a conceptual gap in the literature and at the same time provides a simple tool to predict response to chemotherapy and immunotherapy on the level of individual patients.

cancer biology↗

bioRxiv2020

The Impact of Digital Histopathology Batch Effect on Deep Learning Model Accuracy and Bias

The Cancer Genome Atlas (TCGA) is one of the largest biorepositories of digital histology. Deep learning (DL) models have been trained on TCGA to predict numerous features directly from histology, including survival, gene expression patterns, and driver mutations. However, we demonstrate that these features vary substantially across tissue submitting sites in TCGA for over 3,000 patients with six cancer subtypes. Additionally, we show that histologic image differences between submitting sites can easily be identified with DL. This site detection remains possible despite commonly used color normalization and augmentation methods, and we quantify the digital image characteristics constituting this histologic batch effect. As an example, we show that patient ethnicity within the TCGA breast cancer cohort can be inferred from histology due to site-level batch effect, which must be accounted for to ensure equitable application of DL. Batch effect also leads to overoptimistic estimates of model performance, and we propose a quadratic programming method to guide validation that abrogates this bias.

bioinformatics↗

bioRxiv2019

Pan-cancer image-based detection of clinically actionable genetic alterations

Precision treatment of cancer relies on genetic alterations which are diagnosed by molecular biology assays.1 These tests can be a bottleneck in oncology workflows because of high turnaround time, tissue usage and costs.2 Here, we show that deep learning can predict point mutations, molecular tumor subtypes and immune-related gene expression signatures3,4 directly from routine histological images of tumor tissue. We developed and systematically optimized a one-stop-shop workflow and applied it to more than 4000 patients with breast5, colon and rectal6, head and neck7, lung8,9, pancreatic10, prostate11 cancer, melanoma12 and gastric13 cancer. Together, our findings show that a single deep learning algorithm can predict clinically actionable alterations from routine histology data. Our method can be implemented on mobile hardware14, potentially enabling point-of-care diagnostics for personalized cancer treatment in individual patients.

genetics↗

bioRxiv2019

Deep learning detects virus presence in cancer histology

Oncogenic viruses like human papilloma virus (HPV) or Epstein Barr virus (EBV) are a major cause of human cancer. Viral oncogenesis has a direct impact on treatment decisions because virus-associated tumors can demand a lower intensity of chemotherapy and radiation or can be more susceptible to immune check-point inhibition. However, molecular tests for HPV and EBV are not ubiquitously available.\n\nWe hypothesized that the histopathological features of virus-driven and non-virus driven cancers are sufficiently different to be detectable by artificial intelligence (AI) through deep learning-based analysis of images from routine hematoxylin and eosin (HE) stained slides. We show that deep transfer learning can predict presence of HPV in head and neck cancer with a patient-level 3-fold cross validated area-under-the-curve (AUC) of 0.89 [0.82; 0.94]. The same workflow was used for Epstein-Barr virus (EBV) driven gastric cancer achieving a cross-validated AUC of 0.80 [0.70; 0.92] and a similar performance in external validation sets. Reverse-engineering our deep neural networks, we show that the key morphological features can be made understandable to humans.\n\nThis workflow could enable a fast and low-cost method to identify virus-induced cancer in clinical trials or clinical routine. At the same time, our approach for feature visualization allows pathologists to look into the black box of deep learning, enabling them to check the plausibility of computer-based image classification.

cancer biology↗

bioRxiv2019

Identifying predictors of HPV-related head and neck squamous cell carcinoma progression and survival through patient-derived models

Therapeutic innovation for human papilloma virus-related (HPV+) head and neck squamous cell carcinomas (HNSCCs) is impaired by inadequate biomarkers and preclinical models. This study addressed both limitations using the largest panel of HPV+ HNSCC patient-derived xenografts (PDXs) and organoids described to date. Whole exome profiles of the PDXs were compared to those of HPV+ human tumors and cell lines, and genetic features of the models were analyzed relative to their growth properties and outcomes of their patients of origin. PDX engraftment enriched for negatively prognostic NOTCH1 mutations while preserving multiple features lost in existing cell lines, including PIK3CA mutations, TRAF3 deletion, and absence of EGFR amplification. Observation of more mutations in faster-growing models facilitated identification of an association between mutational burden and local progression in both HPV+ and HPV-HNSCCs. Reduced E7 and p16INK4A levels found in a PDX from a lethal case led to detection of a similar profile among recurrent HPV+ HNSCCs in two patient cohorts, where low E2F target gene expression downstream of E7 predicted recurrence and mortality. Our findings bridge a critical gap in preclinical models for HPV+ HNSCCs and simultaneously reveal novel applications for mutational burden and E2F target dysregulation in biomarker development.

cancer biology↗