ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy
원문 초록
Large-scale cell microscopy screens are used in drug discovery and molecular biology research to study the effects of millions of chemical and genetic perturbations on cells. To use these images in downstream analysis, we need models that can map each image into a feature space that represents diverse biological phenotypes consistently, in the sense that perturbations with similar biological effects have similar representations. In this work, we present the largest foundation model for cell microscopy data to date, a new 1.9 billion-parameter ViT-G/8 MAE trained on over 8 billion microscopy image crops. Compared to a previous published ViT-L/8 MAE, our new model achieves a 60% improvement in linear separability of genetic perturbations and obtains the best overall performance on whole-genome biological relationship recall and replicate consistency benchmarks. Beyond scaling, we developed two key methods that improve performance: (1) training on a curated and diverse dataset; and, (2) using biologically motivated linear probing tasks to search across each transformer block for the best candidate representation of whole-genome screens. We find that many self-supervised vision transformers, pretrained on either natural or microscopy images, yield significantly more biologically meaningful representations of microscopy images in their intermediate blocks than in their typically used final blocks. More broadly, our approach and results provide insights toward a general strategy for successfully building foundation models for large-scale biological data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Exploring Non-contrastive Self-supervised Representation Learning for Image-based Profiling
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
Assay2Mol: large language model-based drug design using BioAssay context
Dual Dimensions Geometric Representation Learning Based Document Dewarping
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
토론
이 논문과 연결된 포럼 글이 아직 없습니다.