UCSC adds DeepMind AlphaGenome Variant Impact scores for all 8.8B single-base changes
anshulkundaje · x · 2026-09-11
UCSC Genome Browser has added a new hg38 track of Google DeepMind's AlphaGenome Variant Impact (AVI) scores, with precomputed scores for roughly 8.8 billion possible single-base substitutions across the human genome.
Key points:
- AVI combines AlphaGenome's predictions of regulatory effects (expression, splicing, chromatin accessibility, TF binding across hundreds of cell types) with AlphaMissense predictions for protein-altering changes, outputting a single PHRED-scaled score (10 = top 10% genome-wide, 30 = top 0.1%).
- Unlike most prediction scores, AVI covers non-coding variants too — e.g., it flags TERT promoter mutations common in cancer.
- Each alternate allele gets its own subtrack for direct locus-level browsing.
More from Research
- ParetoRSI-Gym benchmarks whether AI agents can recursively self-improve LLMs across domains — Haojin Wang · 2026-10-28
- Stanford's Ψ-0.6 is a unified vision-language world model with adaptive reasoning streams — Stanford · 2026-10-28
- Shanghai AI Lab's OpenESM shows energy-steered models can scale as foundation learners — Shanghai-AI-Laboratory · 2026-10-28
- CellTrack-Bench tests VLMs on microscopic cell tracking, exposing reasoning gaps — biohub · 2026-10-28
- Hybrid LLM agent scores 83.2%, beats nine VLA policies on new SO-101 robot arm benchmark — Truman Hickok · 2026-10-28
- DeepMind researcher: all of mathematics will soon be formalizable, with agents hunting proofs — ChrSzegedy · 2026-10-28