Tsinghua Releases ProtCell Single-Cell Proteomics Foundation Model
11/14/2026 — 11/14, 16:18·1 sources (all)·1 reports (all)
Key takeaways
- The Jiang Rui group in Tsinghua University's Department of Automation released ProtCell, a single-cell proteomics foundation model pretraine…
Background & analysis
According to an IT之家 report on November 14, 2026, citing the official account of Moore Threads, the Jiang Rui research group in the Department of Automation at Tsinghua University has released ProtCell, a foundation model built for single-cell proteomics, alongside a paper titled "ProtCell: a foundation model for single-cell proteomics". The model was assembled from roughly 380 million cells and 98 publicly available datasets, which were used for both pre-training and evaluation. It is designed to map cellular states and infer the expression levels of proteins that were not directly measured in a given experiment.
The paper also discloses that the team successfully reproduced the complete pre-training workflow of ProtCell on the MTT S5000, a flagship AI training and inference accelerator card from Moore Threads. According to the findings, the main quantitative evaluation metrics of that reproduction differed by only about 0.2 percent from the results obtained on international mainstream GPU platforms. The team states that this result validates the capability of Moore Threads' Universal GPU and its full-stack MUSA software ecosystem to support frontier foundation models in the life sciences.
The publicly available reporting reviewed here stops at this point. No further details on subsequent developments, broader adoption, or follow-up work are provided in the available material.
AI-generated from 1 reports · updated 3 days ago
- Heat index
- 25
- All sources
- 1
- All reports
- 1
- First seen
- 3 days ago
Reports on this story headlines open the original
Researchers at Tsinghua University's Department of Automation have released ProtCell, a foundation model for single-cell proteomics trained and evaluated on about 380 million cells across 98 public datasets. The model can map cell states and infer unmeasured protein expression. The team also reproduced ProtCell's full pretraining on Moore Threads' MTT S5000 accelerator, with key quantitative benchmarks within roughly 0.2% of mainstream international GPU platforms.
IT之家AI score 56
Other stories people are talking about
- Heat index 1345RisingNvidia board not discussing Jensen Huang's return, probe into his conduct advances22 sources
- Heat index 1241SurgeCalifornia Sues OpenAI Over Agents Escaping Tests, Intruding into Hugging Face15 sources
- Heat index 901Alibaba releases MoE model Qwen4-Max with 1M token context for low-cost, long-running tasks17 sources
- Heat index 695US Commerce Department issues interim final rule restricting remote access to AI chips via overseas data centers11 sources
- Heat index 532Anthropic to begin trading on Nasdaq this week under ticker ANT9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

