Eric and Wendy Schmidt Center

AI tool predicts potential drug targets by analyzing cell images

Corie Lok — Tue, 13 May 2025 16:53:23 +0000

With AI, researchers predict the location of virtually any protein within a human cell

By Corie Lok May 19, 2025

With AI, researchers predict the location of virtually any protein within a human cell

Trained with a joint understanding of protein and cell behavior, the model could help with diagnosing disease and developing new drugs.

By Adam Zewe, MIT News

May 19, 2025

Credit: Courtesy of the researchers; MIT News

Collaborating models

Many existing protein prediction models can only make predictions based on the protein and cell data on which they were trained or are unable to pinpoint a protein’s location within a single cell.

To overcome these limitations, the researchers created a two-part method for prediction of unseen proteins’ subcellular location, called PUPS.

The first part utilizes a protein sequence model to capture the localization-determining properties of a protein and its 3D structure based on the chain of amino acids that forms it.

“Different cells within a cell line exhibit different characteristics, and our model is able to understand that nuance,” Tseo says.

A deeper understanding

In addition, the fact that PUPS is trained on proteins and cell lines at the same time helps it develop a deeper understanding of where in a cell image proteins tend to localize.

PUPS can even understand, on its own, how different parts of a protein’s sequence contribute separately to its overall localization.

Because PUPS can generalize to unseen proteins, it can capture changes in localization driven by unique protein mutations that aren’t included in the Human Protein Atlas.

Adapted from an MIT News story.

Funding

Paper cited:

Zhang, X et al. Prediction of protein subcellular localization in single cells. Nature Methods. Online May 13, 2025. DOI: 10.1038/s41592-025-02696-1

Tags:

#WhyIScience Q&A: A systems biologist develops computational tools to bring scale to cell experiments

adicorat — Tue, 20 Aug 2024 14:00:00 +0000

With AI, researchers predict the location of virtually any protein within a human cell

By Corie Lok May 19, 2025

With AI, researchers predict the location of virtually any protein within a human cell

Trained with a joint understanding of protein and cell behavior, the model could help with diagnosing disease and developing new drugs.

By Adam Zewe, MIT News

May 19, 2025

Credit: Courtesy of the researchers; MIT News

Collaborating models

Many existing protein prediction models can only make predictions based on the protein and cell data on which they were trained or are unable to pinpoint a protein’s location within a single cell.

To overcome these limitations, the researchers created a two-part method for prediction of unseen proteins’ subcellular location, called PUPS.

The first part utilizes a protein sequence model to capture the localization-determining properties of a protein and its 3D structure based on the chain of amino acids that forms it.

“Different cells within a cell line exhibit different characteristics, and our model is able to understand that nuance,” Tseo says.

A deeper understanding

In addition, the fact that PUPS is trained on proteins and cell lines at the same time helps it develop a deeper understanding of where in a cell image proteins tend to localize.

PUPS can even understand, on its own, how different parts of a protein’s sequence contribute separately to its overall localization.

Because PUPS can generalize to unseen proteins, it can capture changes in localization driven by unique protein mutations that aren’t included in the Human Protein Atlas.

Adapted from an MIT News story.

Funding

Paper cited:

Zhang, X et al. Prediction of protein subcellular localization in single cells. Nature Methods. Online May 13, 2025. DOI: 10.1038/s41592-025-02696-1

Tags:

Researchers identify cheap and effective biomarkers for DCIS tumor stage

tulrich@broadinstitute.org — Thu, 25 Jul 2024 16:05:54 +0000

With AI, researchers predict the location of virtually any protein within a human cell

By Corie Lok May 19, 2025

With AI, researchers predict the location of virtually any protein within a human cell

Trained with a joint understanding of protein and cell behavior, the model could help with diagnosing disease and developing new drugs.

By Adam Zewe, MIT News

May 19, 2025

Credit: Courtesy of the researchers; MIT News

Collaborating models

Many existing protein prediction models can only make predictions based on the protein and cell data on which they were trained or are unable to pinpoint a protein’s location within a single cell.

To overcome these limitations, the researchers created a two-part method for prediction of unseen proteins’ subcellular location, called PUPS.

The first part utilizes a protein sequence model to capture the localization-determining properties of a protein and its 3D structure based on the chain of amino acids that forms it.

“Different cells within a cell line exhibit different characteristics, and our model is able to understand that nuance,” Tseo says.

A deeper understanding

In addition, the fact that PUPS is trained on proteins and cell lines at the same time helps it develop a deeper understanding of where in a cell image proteins tend to localize.

PUPS can even understand, on its own, how different parts of a protein’s sequence contribute separately to its overall localization.

Because PUPS can generalize to unseen proteins, it can capture changes in localization driven by unique protein mutations that aren’t included in the Human Protein Atlas.

Adapted from an MIT News story.

Funding

Paper cited:

Zhang, X et al. Prediction of protein subcellular localization in single cells. Nature Methods. Online May 13, 2025. DOI: 10.1038/s41592-025-02696-1

Tags: