Texas A&M scientists use AlphaFold to screen every pairing of human mitochondrial proteins and publish the likely partners free
Texas A&M AgriLife Research reported on November 5th, 2026 on work in the Texas A&M Department of Biochemistry and Biophysics. Its scientists used an AI tool to look for which human mitochondrial proteins work together. The tool is AlphaFold-Multimer, which Google DeepMind built to predict the shapes proteins form together. The team ran it on every possible pairing of about 1,100 mitochondrial proteins. Out of 630,003 possible pairs it catalogued 2,895 likely interactions, and the release says more than half had never been reported before. It also gave 85 previously uncharacterized proteins their first probable partners. About two years of lab work followed and confirmed several predicted partnerships in yeast and human cells. The predictions are posted free as MitoMatch. The paper appeared in Nature Communications. The release says cures for mitochondria linked diseases may still be far into the future.
How to take part
The work is described on AgriLife Today, which names a media relations contact, and the paper is open to read. The predictions are posted free as MitoMatch. A research result is not a public proceeding and has no window for comment.
Where
1 county. In College Station-Bryan.
Timeline
- filed
The paper is published online in Nature Communications
- filed
Texas A&M AgriLife reports the screen and its predictions
- Today
How this decision moved
One dated line per check, oldest first. A line that says nothing changed means somebody looked and it had not.
- 2026-11-08
Admitted on AgriLife's own release and the paper's published abstract. The release counts the likely interactions and says only that several were confirmed in the lab.
- 2026-11-11
The Texas A&M screen of mitochondrial protein pairs is still published and still free to search online.
The evidence
Every fact above rests on one of these. The words are the source's own.
the team used an AI tool to screen every possible pairing of about 1,100 human mitochondrial proteinsAgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
Out of the 630,003 possible protein pairs, the team cataloged 2,895 likely interactions.AgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
More than half of them had never been reported before.AgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
the study also gave 85 previously uncharacterized proteins their first probable partnersAgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
Google DeepMind created and unveiled AFM in 2022 to predict the three-dimensional shapes that proteins form together.AgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
About two years of laboratory experiments followed, confirming several of the predicted partnerships in yeast and human cells.AgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
The team made its predictions available as a free online resource, MitoMatchAgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
mutations in nearly 30% of mitochondrial proteins have been linked to human diseasesAgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
Cures for mitochondria-linked diseases may still be far into the futureAgriLife Today, Artificial intelligence points researchers toward new disease targets hidden in mitochondria Primary source, official · agrilifetoday.tamu.edu
we repurpose the protein structure prediction algorithm AlphaFold Multimer (AFM) as a classification model to predict protein-protein interactions of the entire human mitochondrial proteomeEurope PMC record, The predicted interactome of the human mitochondrial proteome, Nature Communications Primary source, official · ebi.ac.uk
Department of Biochemistry and Biophysics, Texas A&M University, College Station, TX, USA.Europe PMC record, The predicted interactome of the human mitochondrial proteome, Nature Communications Primary source, official · ebi.ac.uk
Questions about this decision
Answered from the record itself. Every answer is assembled from stored fields, so an answer the record has no basis for is left out rather than guessed.
What is this decision?
Texas A&M AgriLife Research reported on November 5th, 2026 on work in the Texas A&M Department of Biochemistry and Biophysics. Its scientists used an AI tool to look for which human mitochondrial proteins work together. The tool is AlphaFold-Multimer, which Google DeepMind built to predict the shapes proteins form together. The team ran it on every possible pairing of about 1,100 mitochondrial proteins. Out of 630,003 possible pairs it catalogued 2,895 likely interactions, and the release says more than half had never been reported before. It also gave 85 previously uncharacterized proteins their first probable partners. About two years of lab work followed and confirmed several predicted partnerships in yeast and human cells. The predictions are posted free as MitoMatch. The paper appeared in Nature Communications. The release says cures for mitochondria linked diseases may still be far into the future.
Who decides it?
Texas A&M AgriLife Research decides. The record names the deciding body for every entry it carries.
Can the public take part?
The work is described on AgriLife Today, which names a media relations contact, and the paper is open to read. The predictions are posted free as MitoMatch. A research result is not a public proceeding and has no window for comment. No dated public window is on the record. The deciding body is named and reachable.
Where in Texas does it apply?
It covers Brazos County in the College Station-Bryan, TX area.
Has it been decided?
It has been decided. The dates on the item page carry when.
What happens next?
No future date is on the record. The last dated step on it was filed on November 5th.
When did it start?
The earliest date on its record is August 25th, 2026.
What kind of decision is it?
It is filed under research and science.
What sources back it?
Two sources back it. Two of them are primary.
Is it on the ERCOT grid?
Yes. It sits inside the ERCOT interconnection.
When was it last checked?
Every fact on it was last verified against its source on November 11th, 2026.
Cite this
Texas AI Docket, Texas A&M scientists use AlphaFold to screen every pairing of human mitochondrial proteins and publish the likely partners free. Tracked since August 25th, 2026. Last verified November 11th, 2026. https://texasaidocket.com/item/tx-2026-0244/. Reuse permitted under CC BY 4.0 with attribution. The same entry is in the docket JSON as item tx-2026-0244.
Beat
Filed under Research and science, with every other decision on that beat.