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.

Implementing evidence-based strategies for men with biochemically recurrent and advanced prostate cancer: Consensus recommendations from the US Prostate Cancer Conference 2024.

Current US clinical practice guidelines for advanced prostate cancer management contain recommendations based on high-level evidence from randomized controlled trials; however, these guidelines do not address the nuanced clinical questions that are unanswered by prospective trials but nonetheless encountered in day-to-day practice. To address these practical questions, the 2024 US Prostate Cancer Conference (USPCC 2024) was created to generate US-focused expert clinical decision-making guidance for circumstances in which level 1 evidence is lacking. At the second annual USPCC meeting (USPCC 2024), a multidisciplinary panel of experts convened to discuss ongoing clinical challenges related to 5 topic areas: biochemical recurrence; metastatic, castration-sensitive prostate cancer; poly [ADP-ribose] polymerase inhibitors; prostate-specific membrane antigen radioligand therapy; and metastatic, castration-resistant prostate cancer.

Uncertainty-aware genomic deep learning with knowledge distillation.

Deep neural networks (DNNs) have advanced predictive modeling for regulatory genomics, but challenges remain in ensuring the reliability of their predictions and understanding the key factors behind their decision making. Here we introduce DEGU (Distilling Ensembles for Genomic Uncertainty-aware models), a method that integrates ensemble learning and knowledge distillation to improve the robustness and explainability of DNN predictions. DEGU distills the predictions of an ensemble of DNNs into a single model, capturing both the average of the ensemble's predictions and the variability across them, with the latter representing epistemic (or model-based) uncertainty.

Analysis of single-cell CRISPR perturbations indicates that enhancers predominantly act multiplicatively.

A single gene may have multiple enhancers, but how they work in concert to regulate transcription is poorly understood. To analyze enhancer interactions throughout the genome, we developed a generalized linear modeling framework, GLiMMIRS, for interrogating enhancer effects from single-cell CRISPR experiments. We applied GLiMMIRS to a published dataset and tested for interactions between 46,166 enhancer pairs and corresponding genes, including 264 "high-confidence" enhancer pairs.

Interpreting cis-regulatory interactions from large-scale deep neural networks.

The rise of large-scale, sequence-based deep neural networks (DNNs) for predicting gene expression has introduced challenges in their evaluation and interpretation. Current evaluations align DNN predictions with orthogonal experimental data, providing insights into generalization but offering limited insights into their decision-making process. Existing model explainability tools focus mainly on motif analysis, which becomes complex when interpreting longer sequences.