Sign in

Arc Institute

@arcinstitute.org
2.4K followers 18 following 460 posts

A full-stack institute for AI and biology research.

PostsRepliesMedia
Arc Institute @arcinstitute.org · 02/10/2026
Here's what that looks like in practice. For this year's Virtual Cell Challenge, we ran identical Perturb-seq protocols in six cell lines, profiled 30M+ cells, then selected perturbations with strong (≥80%) median knockdown. Go behind the scenes in this blog post: arcinstitute.org/news/behind-...
arcinstitute.org
Generating high-quality Perturb-seq data for the 2026 Virtual Cell Challenge | Arc Institute
At Arc, we believe virtual cell models can fill a critical gap: predicting the effects of genetic mutations, environmental changes, and small molecule treatments in biological systems we cannot readil...
000
Arc Institute @arcinstitute.org · 02/10/2026
Virtual cell models are only as good as the data they learn from. To predict how any cell type responds to a perturbation, models need high-quality causal data generated across contexts, so technical noise doesn't masquerade as biology.
100
Arc Institute @arcinstitute.org · 23/09/2026
Minerva is built for researchers looking for non-coding elements and RNA-protein systems that homology searches can’t reach. Code and Minerva-MLM checkpoints and Colab notebooks are available for predictions and fine-tuning. Now on @biorxivpreprint.bsky.social: www.biorxiv.org/content/10.6...
biorxiv.org
Coevolutionary mining of prokaryotic non-coding elements with a genome language model
Microbial genomes encode compact molecular machines and diverse non-coding RNAs (ncRNAs) essential to gene regulation, pathogenesis, and many foundational biotechnologies. However, annotation remains ...
052
Arc Institute @arcinstitute.org · 23/09/2026
In prophages, Unknown Group 27 reverse transcriptase loci hold arrays of roughly 150nt mcRNA units, diverse in sequence but sharing a predicted structure. Expressed in E. coli, all five systems reverse transcribed the central hairpin of each unit into 50-100nt ssDNA.
100
Arc Institute @arcinstitute.org · 23/09/2026
In Pseudomonas, the TwoAYGGAY RNA family extends well past its Rfam annotation, with three further hairpins and a 3’ pseudoknot on an elongated basal stem. A covariance model rebuilt on the Minerva predictions found 16,086 matches across 1,148 of 1,324 strains.
210
Arc Institute @arcinstitute.org · 23/09/2026
Across 150 bacterial genomes, Minerva predicted 62,083 loci carrying at least two neighboring hairpins, and 70.2% of those sit outside existing annotations. The full scan took 100 minutes on one H100.
100
Arc Institute @arcinstitute.org · 23/09/2026
For any portion of a genome, Minerva returns a map of which positions pair with which, including pseudoknots and overlapping hairpins that are hard to capture otherwise. Nothing needs to be aligned first, and one pass per region is fast enough to scan a whole genome.
100
Arc Institute @arcinstitute.org · 23/09/2026
Many important bacterial non-coding RNAs and structural elements remain undiscovered. To help, David Li, Garyk Brixi, Michael Fischbach, @brianhie.bsky.social & team introduce Minerva, which uses a genome language model to predict RNA base pairing, repeats, & other interactions from sequence alone.
12212
Arc Institute @arcinstitute.org · 15/09/2026
Want to join Arc? We're hiring experts in disease bio, computational bio, functional genomics, and NGS for our Tech Centers, plus postdocs and research associates in our Core Labs. All roles are based in Palo Alto, and are on-site or hybrid. Learn more or apply here: lnkd.in/gyfgqR3n
arcinstitute.org
Jobs | Arc Institute
Arc Institute is an independent nonprofit research organization headquartered in Palo Alto, California.
045
Arc Institute @arcinstitute.org · 08/09/2026
PRDX1 clears hydrogen peroxide that free iron turns into DNA-damaging hydroxyl radicals. This work identifies PRDX1 and its upstream genes as potential druggable targets to pair with DDR inhibitors or to use in cancers already deficient in DNA repair. See in NChemBio: www.nature.com/articles/s41...
nature.com
Chemogenomic maps reveal a PRDX1-dependent iron–damage axis in the DNA damage response - Nature Chemical Biology
Large-scale CRISPR dependency mapping reveals 1,000+ genes that modify cellular outcomes to DNA damage response drugs. Loss of PRDX1, acting through a PAX7–MRGBP–IREB2 pathway, broadly sensitized cell...
020
Arc Institute @arcinstitute.org · 08/09/2026
The team then repeated the screens in PRDX1 knockout cells. Knocking down IREB2, PAX7, or MRGBP restored growth under DNA-PK inhibition and lowered γH2AX. All three lowered labile iron, and chelating iron partly rescued the cells, indicating PRDX1 protects the genome from iron-driven oxidation.
100
Arc Institute @arcinstitute.org · 08/09/2026
The team asked whether antioxidants could substitute for PRDX1. Catalase, SOD1, trolox, glutathione, and NAC offered no protection. Relocalizing PRDX3 or PRDX4 from the mitochondria or ER to the cytosol restored resistance, identifying the damaging ROS as nucleocytoplasmic.
100
Arc Institute @arcinstitute.org · 08/09/2026
Six genes consistently sensitized cells to all inhibitors when repressed. One was PRDX1, a peroxiredoxin that reduces hydrogen peroxide. Knocking it down raised γH2AX and sensitized cells to the PARP, ATR, ATM, and DNA-PK inhibitors.
100
Arc Institute @arcinstitute.org · 08/09/2026
More than 1,200 genes made cells more sensitive to a single inhibitor when repressed, and 300+ made them resistant. The olaparib combinations added 300 more sensitizers. All 32 screens are searchable at ddri-screens.gilbertlab.arcinstitute.org
100
Arc Institute @arcinstitute.org · 08/09/2026
The team screened a genome-scale CRISPRi library in A549 lung cancer cells against the PARP inhibitor olaparib and against inhibitors of the repair kinases including ATR, ATM, DNA-PK, and WEE1. They screened each drug on its own as well as combined with olaparib.
100
Arc Institute @arcinstitute.org · 08/09/2026
Loss of function for 1 gene can make a cancer cell resist a DNA damage response (DDR) inhibitor, while another gene can make it easy to kill. Arc Core Investigator Luke Gilbert and collaborators mapped both across five DDR inhibitors and found loss of PRDX1 sensitizes cells to all five.
141
Arc Institute @arcinstitute.org · 03/09/2026
Find out about the diversity of eukaryotic terminal electron acceptors in a @cp-trendsbiochem.bsky.social companion review: www.cell.com/trends/bioch...
cell.com
The diversity of terminal electron acceptors across eukaryotes
The flow of electrons is essential for life. To sustain metabolic flux, organisms efficiently transfer electrons to terminal electron acceptors, which range from inorganic nutrients to intracellularly...
000
Arc Institute @arcinstitute.org · 03/09/2026
Read about BCAA fermentation on bioRxiv: www.biorxiv.org/content/10.6...
biorxiv.org
Branched-chain amino acid fermentation as an alternative mammalian electron sink
Hypoxia disrupts mitochondrial respiration and increases the NADH/NAD+ ratio, causing reductive stress. To maintain redox homeostasis, mammalian cells divert electrons toward fermentation. While ferme...
100
Arc Institute @arcinstitute.org · 03/09/2026
In people, BCHAs serve primarily as a biomarker of reductive stress. They rise with resistance exercise, COVID-19, and heavy drinking. But, in mice, another isoform of lactate dehydrogenase, LDHC, has evolved to support a highly specific function: hypermotility in sperm.
100
Arc Institute @arcinstitute.org · 03/09/2026
Instead of a new source, BCHAs are generated by lactate dehydrogenase A (LDHA), the same enzyme that drives canonical lactate fermentation. In hypoxia, mitochondria stop oxidizing branched-chain ketoacids, which pile up in the cytosol and trigger LDHA to reduce them instead.
100
Arc Institute @arcinstitute.org · 03/09/2026
It started with a Jain lab dataset on hypoxia-enriched metabolites in mice (jain-lab-ucsf.github.io/hypoxia-meta...). Across all organs and timepoints, three molecules kept popping up: all branched-chain hydroxyacids (BCHAs), a product of fermentation in unicellular organisms, but not in mammals.
100
Arc Institute @arcinstitute.org · 03/09/2026
Our ancestors emerged on a primitive Earth that lacked oxygen. Isha Jain, Ayush Midha and team found a surprising way that we still use their coping strategies today. arcinstitute.org/news/ancient...
arcinstitute.org
The ancient anaerobic pathways still at work inside our cells | Arc Institute
Life as we know it depends on the flow of electrons. From single-celled organisms to human neurons, the thermodynamics of this energy flow remain the same: fuel oxidation strips electrons from nutrien...
141
Arc Institute @arcinstitute.org · 02/09/2026
Interested in this type of research? The Zhou Lab is hiring a postdoc: job-boards.greenhouse.io/arcinstitute...
job-boards.greenhouse.io
Postdoctoral Researcher, Zhou Lab
Palo Alto, CA
010
Arc Institute @arcinstitute.org · 02/09/2026
In Cancer Cell, Zhou led a computational team to predict how chronic stress speeds glioma growth from single-cell RNA-seq data, finding stress-associated macrophages mediate brain-bone marrow crosstalk, shielding the tumor so it grows faster. www.cell.com/cancer-cell/...
cell.com
Macrophage-mediated brain-bone marrow crosstalk promotes chronic stress-induced glioma growth
Yang et al. demonstrate that chronic stress accelerates glioma growth by inducing bone-marrow-derived C5aR1+ stress-associated macrophages (SAMs) in tumor-bearing mice. Stress-induced sympathetic nerv...
110
Arc Institute @arcinstitute.org · 02/09/2026
In Cell, he released Spatial Hi-C-RNA with collaborators. It maps both genome-wide chromatin architecture and gene expression in intact tissue at near-single-cell resolution. Chromatin surfaces structural variants so it’s useful for tracking tumor subclones. www.cell.com/cell/fulltex...
cell.com
Integrative spatial profiling of 3D genome organization and gene expression in tissue
Spatial Hi-C-RNA simultaneously maps genome architecture and gene expression from the same tissue, revealing how spatial genome organization shapes cellular identity, development, and tumor evolution ...
110
Arc Institute @arcinstitute.org · 02/09/2026
In @science.org, Zhou and team mapped 3D genome organization and DNA methylation across 86,689 nuclei from 16 human tissues, resolving 35 cell types and 206 subtypes. In the brain, every epigenetic layer agrees. In the body, it’s a different story. www.science.org/doi/10.1126/...
science.org
Human body single-cell atlas of three-dimensional genome organization and DNA methylation
Higher-order chromatin structure and DNA methylation are critical for gene regulation, but how these vary across the human body remains unclear. We performed multiomic profiling of three-dimensional (...
2275
Arc Institute @arcinstitute.org · 02/09/2026
Science Fellow Jingtian Zhou builds single-cell and computational frameworks to probe the 3D genome. His work tells us more about how the epigenome and transcriptome interact to shape cell state and complex disease: arcinstitute.org/news/jingtia...
arcinstitute.org
Why Jingtian Zhou is building high-resolution maps of the 3D genome | Arc Institute
Each cell in our body inherits the same DNA, yet becomes one of hundreds of cell types. We make immune cells that hunt down viruses, brain cells that pattern our memories, and pacemaker cells that gen...
150
Arc Institute @arcinstitute.org · 26/08/2026
You can sign up or follow the progress at virtualcellchallenge.org. Thank you to the over 2,500 people who have registered so far.
virtualcellchallenge.org
Virtual Cell Challenge
The challenge, hosted by Arc Institute at virtualcellchallenge.org and sponsored by NVIDIA, 10x Genomics, and Ultima Genomics, is focused on a fundamental challenge in biology. Entrants will use AI mo...
000
Arc Institute @arcinstitute.org · 26/08/2026
We share our rationale and evaluation approach for the competition in a commentary published today in Cell. Our goal is for this event to build a new community of machine learning researchers, computational biologists, and experimentalists. www.cell.com/cell/fulltex...
cell.com
Virtual Cell Challenge 2026: Benchmarking zero-shot generalization across cellular contexts
The Virtual Cell Challenge returns in 2026 with a more demanding test of biological generalization: zero-shot prediction across multiple independent cellular contexts. Participants will build models t...
161
Arc Institute @arcinstitute.org · 26/08/2026
Nearly 300 teams have already submitted to the Virtual Cell Challenge leaderboard to see how their initial models rank on this year’s six metrics. Here’s the current standing:
121
Arc Institute @arcinstitute.org · 20/08/2026
Join the over 1,800 people who have already signed up to compete for $175,000 in prizes. Register at virtualcellchallenge.org. Thank you again to NVIDIA, @10xgenomics.bsky.social, and Ultima Genomics for sponsoring this year’s competition.
virtualcellchallenge.org
Virtual Cell Challenge
The challenge, hosted by Arc Institute at virtualcellchallenge.org and sponsored by NVIDIA, 10x Genomics, and Ultima Genomics, is focused on a fundamental challenge in biology. Entrants will use AI mo...
020
Arc Institute @arcinstitute.org · 20/08/2026
Competitors will receive a validation dataset with 3 cell lines, each containing the non-targeting control profiles plus the CRISPRi knockdown gene IDs to predict for 300 perturbations per cell line. A test set with 3 distinct cell lines will be held out until the final phase (in Oct).
120
Arc Institute @arcinstitute.org · 20/08/2026
We also redesigned the scoring. We're using six complementary metrics, each scaled between the cell context mean and data from a real replicate experiment. The overall score is a single unweighted average over the six metrics and cell contexts.
120
Arc Institute @arcinstitute.org · 20/08/2026
The 2026 Virtual Cell Challenge has begun! Submissions and the leaderboard are now open. This year's task: multi-context generalization and zero-shot prediction. Models will need to predict perturbation responses in cellular contexts with no training data. arcinstitute.org/news/virtual...
arcinstitute.org
The 2026 Virtual Cell Challenge: predicting perturbation responses in cell contexts a model has never seen | Arc Institute
Registration for the 2026 Virtual Cell Challenge is open at virtualcellchallenge.org. This year the task is zero-shot: we are not releasing a training set, and the evaluation dataset is far more expan...
1145
Arc Institute @arcinstitute.org · 17/08/2026
Read the full paper here: jamanetwork.com/journals/jam... And follow John as he builds a roadmap from clinical characterization to structural mechanism and therapeutic development in ABCD: arcinstitute.org/news/john-pl...
arcinstitute.org
John Pluvinage on a new vitamin B12 transport disorder | Arc Institute
Four years ago, John Pluvinage was a neurology resident at UCSF trying to solve one patient's mystery: a 67-year-old woman whose memory and ability to walk were declining, whose bloodwork kept coming ...
020
Arc Institute @arcinstitute.org · 17/08/2026
Five patients received B12 supplementation with or without immunosuppression, and four out of five improved. These treatment effects remain anecdotal, but motivate the team to eventually run a controlled trial.
110
Arc Institute @arcinstitute.org · 17/08/2026
They found that anti-CD320 was associated with a low B12 in the spinal fluid but a normal B12 in the blood, pointing to a potential new disease etiology in these patients.
210
Arc Institute @arcinstitute.org · 17/08/2026
In every patient who carried it, the antibody bound the same stretch of the CD320 extracellular domain. The team created an epitope-specific immunoassay to screen multiple cohorts from all over the world and track prevalence, metabolic consequences, and comorbidities.
100
Arc Institute @arcinstitute.org · 17/08/2026
The team ran proteome-wide phage display on CSF from patients with idiopathic myelopathy and disease controls. Of 20 enriched autoantibodies, they found one (anti-CD320) that targeted a cell-surface receptor on the blood brain barrier and was present in ~50% of patients.
100
Arc Institute @arcinstitute.org · 17/08/2026
Four years ago, a mystery case led Core Investigator @jvpluv to discover a new diagnosis (ABCD). Today his team published one of the largest clinical surveys of unexplained spinal cord disease to date in @JAMANeuro, finding ABCD in roughly half of patients.
163
Arc Institute @arcinstitute.org · 14/08/2026
Here, DPO gave a protein generative model a “preference” for stability. Applied to other high-throughput biological data, the same strategy could give models better “taste” for sequences with a range of useful properties. Access the paper in Nature Methods: www.nature.com/articles/s41...
nature.com
Aligning protein-generative models to experimental fitness with ProteinDPO - Nature Methods
This Article demonstrates that direct preference optimization (DPO) can be used to effectively align an unsupervised structure-conditioned language model with biophysical information. The aligned mode...
010
Arc Institute @arcinstitute.org · 14/08/2026
The team also combined mutations into more complex variants. Every nine-substitution variant increased thermal stability while maintaining strong antibody binding, showing how the model can move beyond individual mutations toward designing proteins with multiple beneficial changes.
100
Arc Institute @arcinstitute.org · 14/08/2026
ProteinDPO identified 6 of 8 known stabilizing mutations reported in earlier H3 and H1 studies, with no HA data in training. Of its top 30 H5 candidates tested, 19 were more thermostable than wild type.
100
Arc Institute @arcinstitute.org · 14/08/2026
The team then applied ProteinDPO to H5N1 hemagglutinin, where improving protein stability is important for vaccine development and is typically tackled through rational design or large-scale experimental screens.
100
Arc Institute @arcinstitute.org · 14/08/2026
Trained only on stability changes in small protein monomers, ProteinDPO generalized to larger proteins with unseen folds and the stability of multi-chain antibodies. It also improved predictions of binding affinity in protein-protein complexes.
100
Arc Institute @arcinstitute.org · 14/08/2026
The resulting ProteinDPO model outperformed both the original ESM-IF1 and supervised fine-tuning at predicting changes in protein stability. It also matched supervised models built for the task alone.
100
Arc Institute @arcinstitute.org · 14/08/2026
Direct Preference Optimization (DPO) aligns LLMs by showing them a preferred and a rejected response to the same prompt. The team applied this to ESM-IF1, using a protein backbone as the prompt, sequences as the response, and higher measured stability as the preference.
100
Arc Institute @arcinstitute.org · 14/08/2026
The same method that teaches an LLM which answers people prefer can teach a protein model which sequences are more stable. This is the basis for ProteinDPO, developed by Innovation Investigator @brianhie.bsky.social, Talal Widatalla, and team.
182
Arc Institute @arcinstitute.org · 13/08/2026
Dive into the engineering principles with the researchers: arcinstitute.org/news/bridge-...
arcinstitute.org
Overcoming the insertion bias in natural bridge recombinase systems for efficient excision | Arc Institute
Programmable biology has arrived in a few different ways, each time defined by a new type of RNA-guided mechanism: RNA interference, then CRISPR systems for programmable cutting of nucleic acids. More...
020
Arc Institute @arcinstitute.org · 13/08/2026
Access the study in @natureportfolio.nature.com: www.nature.com/articles/s41...
nature.com
Structural mechanism governing the directionality of bridge recombination - Nature
Cryo-electron microscopy structures show how IS621 bridge recombinase mediates DNA excision, explaining its natural preference for insertion and informing the design of programmable bridge-editing tec...
100