CELL-E: A Text-To-Image Transformer for Protein Localization Prediction

Khwaja, Emaad; Song, Yun S.

doi:10.1101/2022.05.27.493774

Cited by 2 publications

(1 citation statement)

References 104 publications

(179 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advances in machine learning have enabled the study of protein properties using either protein sequences or cellular images. Models have been developed that infer different properties of a protein, such as its localization and structure, from the protein sequence [7][8][9][10][11][12] . While the prediction of protein localization based on its sequence allows generalizing to unseen proteins, the localization prediction task cannot capture relative protein abundance among different cellular compartments, contextual differences in localization among single cells, or cell-type specific localization differences among cell lines.…”

Section: Introductionmentioning

confidence: 99%

Prediction of protein subcellular localization in single cells

Zhang,

Tseo,

Bai

et al. 2024

Preprint

View full text Add to dashboard Cite

The subcellular localization of a protein is important for its function and interaction with other molecules, and its mislocalization is linked to numerous diseases. While atlas-scale efforts have been made to profile protein localization across various cell lines, existing datasets only contain limited pairs of proteins and cell lines which do not cover all human proteins. We present a method that uses both protein sequences and cellular landmark images to performPredictions ofUnseenProteins'Subcellular localization (PUPS), which can generalize to both proteins and cell lines not used for model training. PUPS combines a protein language model and an image inpainting model to utilize both protein sequence and cellular images for protein localization prediction. The protein sequence input enables generalization to unseen proteins and the cellular image input enables cell type specific prediction that captures single-cell variability. PUPS' ability to generalize to unseen proteins and cell lines enables us to assess the variability in protein localization across cell lines as well as across single cells within a cell line and to identify the biological processes associated with the proteins that have variable localization. Experimental validation shows that PUPS can be used to predict protein localization in newly performed experiments outside of the Human Protein Atlas used for training. Collectively, PUPS utilizes both protein sequences and cellular images to predict protein localization in unseen proteins and cell lines with the ability to capture single-cell variability.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of protein subcellular localization in single cells

Zhang,

Tseo,

Bai

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer

Khwaja,

Song,

Agarunov

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

We present CELL-E 2, a novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (andvice versa). Protein localization is a challenging problem that requires integrating sequence and image information, which most existing methods ignore. CELL-E 2 extends the work of CELL-E, not only capturing the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enablingde novoprotein design. We train and finetune CELL-E 2 on two large-scale datasets of human proteins. We also demonstrate how to use CELL-E 2 to create hundreds of novel nuclear localization signals (NLS). Results and interactive demos are featured athttps://bohuanglab.github.io/CELL-E_2/.

show abstract

CELL-E: A Text-To-Image Transformer for Protein Localization Prediction

Cited by 2 publications

References 104 publications

Prediction of protein subcellular localization in single cells

Prediction of protein subcellular localization in single cells

CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer

Contact Info

Product

Resources

About