deep-learning

CRISPR made cutting the genome easy; the hard part was knowing what would happen next. Which guide will actually cut? And once the cell repairs the break, what sequence will you be left with — long dismissed as random? Machine learning answered both. Guide-activity models like DeepSpCas9 and DeepCpf1 predict which guides work from sequence alone. Then the surprise: inDelphi showed template-free repair is ‘predictable and capable of precise repair,’ hitting a single dominant genotype at 5–11% of sites; FORECasT confirmed outcomes ‘are not random, but depend on DNA sequence’ across a billion measured events. The idea generalized — BE-Hive predicts base-editing outcomes at R≈0.9, PRIDICT predicts prime-editing efficiency and even flags the pegRNAs worth trying. It’s the design half of the perturbation the virtual cell tries to predict the response to, and the design brain of the design→edit→measure loop a self-driving lab runs. The honest frontier is our native language: benchmarks are still thin, outcomes are cell-line-dependent, and a predicted genotype stays a hypothesis until sequencing agrees.

A self-driving cell-biology lab where AI agents plan, run and adapt live-cell experiments across a cluster of instruments.

Building AI-powered data-driven human whole-cell models

An agent-first platform that deploys bioimage AI models as autoscaling, agent-readable interfaces on cloud or HPC — and powers the “test run” feature on the BioImage Model Zoo. Described in a 2026 preprint.

A community-driven, fully open repository where standardized deep-learning models can be shared, tested in the browser, and deployed across imaging tools.

Cell morphology, learned from image-based spatial proteomics, is shown to predict molecular phenotypes — bridging single-cell imaging and proteomics.

A collaborative community roadmap surveying how deep learning is applied across microscopy — image restoration, detection, segmentation, classification, tracking, and multimodal fusion — with its possibilities and limitations.

Large-scale immunofluorescence profiling maps how SARS-CoV-2 reshuffles the host protein landscape across 602 proteins, then screens approved drugs against the changed targets — yielding a 100,000-image public resource and pinpointing elesclomol as an antiviral modulator.

A universal deep-learning approach for accurate FISH spot detection across imaging-based spatial-omics datasets.

A framework that makes deep-learning pipelines for microscopy flexible, shareable, and reproducible across computing environments.