HomeFull speed ahead. Keep track of advancements in every frontier

TheTechno Optimist.

Virtual Cell ChallengeArc Institute—

Virtual Cell Challenge

by Arc InstituteUS

PilotStage 3 of 5

Second round launched 20 Aug 2026, testing on six cell types the models haven't seen.

Updated 20 Aug 2026Checked 25 Sep0 updates this week

Milestones

Next · 2026 winners announced
  1. First Virtual Cell Challenge announcedJun 2025Complete.
  2. 2026 challenge launches20 Aug 2026Complete.
  3. 2026 winners announcedNot yet reached.

Most important updates

  • 20 Aug 2026
  • 2025

Upcoming

  1. 22 Oct 20262026 Virtual Cell Challenge: final test set releasedin 12 days (next)
  2. Nov 20262026 Virtual Cell Challenge winners announced
  3. 5 Nov 20262026 Virtual Cell Challenge: submission deadline

Physics limits

  • Measuring a cell destroys it and misses most moleculesSingle-cell sequencing breaks the cell open and captures only about 10 to 20% of its mRNA. Each cell is seen once, as a noisy snapshot, never over time.
  • Too many combinations to testWith about 20,000 genes, there are some 200 million pairs of genes to switch off together, across hundreds of cell types. Experiments can only ever sample a sliver.
  • Cells in a dish are not a patientLab cells lack the tissues, immune system, blood flow and decades of disease history of a real body. Signals found in dishes often vanish in people, so trials remain the real test.

How it works

3 parts
A sequencer flow cell: single-cell gene readouts like the challenge's data are read on glass chips like this
A sequencer flow cell: single-cell gene readouts like the challenge's data are read on glass chips like thisPhoto: Cirosantilli2 · CC BY-SA 4.0 (opens commons.wikimedia.org)
Data

Fresh, unseen experiments

Arc switches off genes one at a time in human cells with CRISPR and measures thousands of genes' activity in each single cell.

Task

Predict the response

Teams build models that predict how a cell's gene activity changes; in 2026, in cell types the models have never seen.

Score

Judged on held-back data

Predictions are scored against measurements kept secret until the end, so models can't be tuned to the answers.

Update log

2 updates

Thu 20 Aug

  • Minor: BlogResearch

2025

  • Minor: BlogResearch

About Arc Institute

The team behind Virtual Cell Challenge

Arc Institute

Evo DNA AI, virtual cell, bridge editing

Nonprofit research institute in Palo Alto founded in 2021 by Patrick Hsu, Silvana Konermann and Patrick Collison, with Stanford, Berkeley and UCSF. It funds scientists without grant applications and builds shared tools like the Evo DNA models.

  • Evo 2 (Feb 2025, with NVIDIA) learned from DNA of all known life and can predict effects of mutations and write new sequences.
  • In 2024 Arc researchers showed 'bridge RNAs' that guide enzymes to insert, delete or flip DNA.
  • The second Virtual Cell Challenge launched on 20 Aug 2026.

arcinstitute.org (opens arcinstitute.org)Company profile →

Founded
20215 yrs
Headquarters
United States
Status
Private
Valuation
private
Works in
BiotechSynthetic biologyAI
Coverage
2 programs · 4 updateslatest 20 Aug 2026checked 25 Sep
Partners
NVIDIA (opens nvidia.com)Stanford University (opens stanford.edu)
People
Patrick Hsu (opens arcinstitute.org)Co-founder and core investigatorSilvana Konermann (opens arcinstitute.org)Co-founder and executive directorPatrick Collison (opens en.wikipedia.org)Co-founder
Primer