arXiv subjects

Peter K. Koo

Publications and source records attributed to Peter K. Koo.

6 recordsLinked to original sources

arXiv2026

Toward Interpretable and Generalizable AI in Regulatory Genomics

Deciphering how DNA sequence encodes gene regulation remains a central challenge in biology. Advances in machine learning and functional genomics have enabled sequence-to-function (seq2func) models that predict molecular regulatory readouts directly from DNA sequence. These models are now widely used for variant effect prediction, mechanistic interpretation, and regulatory sequence design. Despite strong performance on held-out genomic regions, their ability to generalize across genetic variation and cellular contexts remains inconsistent. Here we examine how architectural choices, training data, and prediction tasks shape the behavior of seq2func models. We synthesize how interpretability methods and evaluation practices have probed learned cis-regulatory organization and highlighted systematic failure modes, clarifying why strong predictive accuracy can fail to translate into robust regulatory understanding. We argue that progress will require reframing seq2func models as continually refined systems, in which targeted perturbation experiments, systematic evaluation, and iterative model updates are tightly coupled through AI-experiment feedback loops. Under this framework, seq2func models become self-improving tools that progressively deepen their mechanistic grounding and more reliably support biological discovery.

q-bio.GN↗

arXiv2025

Explainable AI for computational pathology identifies model limitations and tissue biomarkers

Deep learning models show promise in digital pathology, but their opaque decision-making processes limit trust and clinical adoption. To address this challenge, we present HIPPO, an explainable AI method for analyzing weakly-supervised multiple-instance learning (MIL) models that are widely used in whole slide image analysis. HIPPO constructs counterfactual whole slide images by systematically removing or adding selected tissue regions, providing a principled way to quantify how specific histologic areas influence model predictions under the MIL framework. This enables rigorous model interpretation, quantitative hypothesis testing, bias detection, and performance evaluation that extend beyond standard metrics. We demonstrate HIPPO across key clinical tasks, such as breast metastasis detection in axillary lymph nodes, prognostication in breast cancer and melanoma, and IDH mutation classification in gliomas. In metastasis detection, HIPPO uncovered critical model limitations undetectable by standard performance metrics or attention-based methods. For prognostic prediction, HIPPO outperformed attention by providing more nuanced insights into tissue elements influencing outcomes. In a proof-of-concept study, HIPPO facilitated hypothesis generation to identify melanoma patients who may benefit from immunotherapy. In IDH mutation classification, HIPPO more robustly identified the pathology regions responsible for false negatives compared to attention, suggesting its potential to outperform attention in explaining model decisions. In summary, HIPPO expands the explainable AI toolkit for computational pathology by enabling deeper insights into model behavior. This framework supports the trustworthy development, deployment, and regulation of weakly-supervised models in clinical and research settings, promoting their broader adoption in digital pathology.

q-bio.TO↗

arXiv2025

Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models

Transcriptomic assays such as the PAM50-based ROR-P score guide recurrence risk stratification in non-metastatic, ER-positive, HER2-negative breast cancer but are not universally accessible. Histopathology is routinely available and may offer a scalable alternative. We introduce MAKO, a benchmarking framework evaluating 12 pathology foundation models and two non-pathology baselines for predicting ROR-P scores from H&E-stained whole slide images using attention-based multiple instance learning. Models were trained and validated on the Carolina Breast Cancer Study and externally tested on TCGA BRCA. Several foundation models outperformed baselines across classification, regression, and survival tasks. CONCH achieved the highest ROC AUC, while H-optimus-0 and Virchow2 showed top correlation with continuous ROR-P scores. All pathology models stratified CBCS participants by recurrence similarly to transcriptomic ROR-P. Tumor regions were necessary and sufficient for high-risk predictions, and we identified candidate tissue biomarkers of recurrence. These results highlight the promise of interpretable, histology-based risk models in precision oncology.

q-bio.TO↗

arXiv2025

Reusable specimen-level inference in computational pathology

Foundation models for computational pathology have shown great promise for specimen-level tasks and are increasingly accessible to researchers. However, specimen-level models built on these foundation models remain largely unavailable, hindering their broader utility and impact. To address this gap, we developed SpinPath, a toolkit designed to democratize specimen-level deep learning by providing a zoo of pretrained specimen-level models, a Python-based inference engine, and a JavaScript-based inference platform. We demonstrate the utility of SpinPath in metastasis detection tasks across nine foundation models. SpinPath may foster reproducibility, simplify experimentation, and accelerate the adoption of specimen-level deep learning in computational pathology research.

eess.IV↗

arXiv2022

Evaluating histopathology transfer learning with ChampKit

Histopathology remains the gold standard for diagnosis of various cancers. Recent advances in computer vision, specifically deep learning, have facilitated the analysis of histopathology images for various tasks, including immune cell detection and microsatellite instability classification. The state-of-the-art for each task often employs base architectures that have been pretrained for image classification on ImageNet. The standard approach to develop classifiers in histopathology tends to focus narrowly on optimizing models for a single task, not considering the aspects of modeling innovations that improve generalization across tasks. Here we present ChampKit (Comprehensive Histopathology Assessment of Model Predictions toolKit): an extensible, fully reproducible benchmarking toolkit that consists of a broad collection of patch-level image classification tasks across different cancers. ChampKit enables a way to systematically document the performance impact of proposed improvements in models and methodology. ChampKit source code and data are freely accessible at https://github.com/kaczmarj/champkit .

q-bio.QM↗

arXiv2016

Systems-level approach to uncovering diffusive states and their transitions from single particle trajectories

The stochastic motions of a diffusing particle contain information concerning the particle's interactions with binding partners and with its local environment. However, accurate determination of the underlying diffusive properties, beyond normal diffusion, has remained challenging when analyzing particle trajectories on an individual basis. Here, we introduce the maximum likelihood estimator (MLE) for confined diffusion and fractional Brownian motion. We demonstrate that this MLE yields improved estimation over traditional mean square displacement analyses. We also introduce a model selection scheme (that we call mleBIC) that classifies individual trajectories to a given diffusion mode. We demonstrate the statistical limitations of classification via mleBIC using simulated data. To overcome these limitations, we introduce a new version of perturbation expectation-maximization (pEMv2), which simultaneously analyzes a collection of particle trajectories to uncover the system of interactions which give rise to unique normal and/or non-normal diffusive states within the population. We test and evaluate the performance of pEMv2 on various sets of simulated particle trajectories, which transition among several modes of normal and non-normal diffusion, highlighting the key considerations for employing this analysis methodology.

physics.bio-ph↗