The Cancer Genome Atlas
PulseAugur coverage of The Cancer Genome Atlas — every cluster mentioning The Cancer Genome Atlas across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New method learns to sparsify image tokens for efficient AI reasoning
Researchers have developed a novel method for processing gigapixel whole slide images in vision language models by treating token reduction as a trainable sparsification problem. This approach, detailed in a new arXiv p…
-
BBOmix benchmark launched for biological AI hyperparameter tuning
Researchers have introduced BBOmix, a new open-source tabular benchmark designed for hyperparameter optimization in unsupervised biological representation learning. This benchmark addresses the computational expense of …
-
Graph Mamba framework enhances WSI survival analysis
Researchers have developed a new Graph Mamba survival analysis framework called TopoMamSurv to improve patient prognosis assessment using Whole Slide Images (WSIs). This framework addresses the computational bottleneck …
-
New framework DECAT evaluates multimodal AI for biological understanding
Researchers have developed DECAT, a new framework for evaluating multimodal AI models in oncology. This model-agnostic tool helps determine if a model has learned genuine biological patterns or is relying on spurious co…
-
GLP-1 drugs may reduce cancer progression, new study suggests
New research presented at the American Society of Clinical Oncology meeting suggests that GLP-1 medications, commonly used for diabetes and weight loss, may also reduce the progression of certain cancers. A study analyz…
-
ProtoPathway integrates imaging and genomics for cancer survival prediction
Researchers have developed ProtoPathway, a novel multimodal framework designed for predicting cancer survival. This framework integrates whole slide imaging and transcriptomics data by using biologically grounded repres…
-
New HDMoE framework enhances cancer survival prediction with multimodal data
Researchers have developed a new framework called HDMoE to improve multimodal cancer survival prediction. This hierarchical decoupling-fusion mixture-of-experts approach aims to better integrate data from sources like w…
-
PPI-Net model links protein interactions to disease processes
Researchers have developed PPI-Net, a novel graph neural network designed to connect protein interactions with functional disease processes. This hierarchical model integrates protein-protein interaction networks with p…
-
New Bayesian tree ensemble model tackles high-dimensional causal survival analysis
Researchers have introduced a new Bayesian tree ensemble model designed for causal survival analysis in high-dimensional settings. This model utilizes a horseshoe prior on step heights to achieve adaptive shrinkage, all…
-
Foundation models show modest gains for whole-slide image retrieval in cancer data
A new study published on arXiv evaluates ten different pipelines for whole-slide image retrieval in cancer pathology data. The research found that while the TITAN foundation model performed best, its advantage over patc…
-
Foundation models show promise in classifying atypical mitosis in cancer research
Researchers have benchmarked deep learning and vision foundation models for classifying atypical versus normal mitosis, a crucial indicator of tumor malignancy. The study evaluated end-to-end trained models, linear prob…
-
ASTRA framework unifies pathology foundation models for cancer recognition and localization
Researchers have developed ASTRA, a new framework designed to unify fragmented representations from various pathology foundation models into a cohesive slide-level understanding. This system semantically grounds these r…
-
PathMoG neural network improves cancer survival prediction using multi-omics data
Researchers have developed PathMoG, a novel graph neural network designed for predicting cancer survival rates using multi-omics data. The model organizes genetic information into pathway modules and uses a hierarchical…