A comprehensive map of human glucokinase variant activity

Gersing, Sarah; Cagiada, Matteo; Gebbia, Marinella; Gjesing, Anette P.; Coté, Atina G.; Seesankar, Gireesh; Li, Roujia; Tabet, Daniel; Stein, Amelie; Gloyn, Anna L.; Hansen, Torben; Roth, Frederick P.; Lindorff‐Larsen, Kresten; Hartmann‐Petersen, Rasmus

doi:10.1186/s13059-023-02935-8

Cited by 24 publications

(8 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Variants that decrease GCK activity can cause maturity-onset diabetes of the young (MODY) ( 44 ). AlphaMissense pathogenicity correlates with MAVE data measuring the fitness of auxotrophic yeast strains expressing human GCK variants in the presence of glucose ( 45 ) (Spearman correlation: 0.53), outperforming ESM1v, EVE, and ESM1b (Spearman correlation: 0.49, 0.48, and 0.45, respectively; fig. S5B).…”

Section: Alphamissense Achieves State-of-the-art Agreement With Multi...mentioning

confidence: 87%

“…Each dot represents a different protein variant, colored according to AlphaMissense classification thresholds. The shape indicates the clinical label ( 45 ). The dashed line shows the linear fit between in vitro measurement and AlphaMissense pathogenicity.…”

Section: Alphamissense Achieves State-of-the-art Agreement With Multi...mentioning

confidence: 99%

“…3F). AlphaMissense pathogenicity is associated with decreased fasting glucose in patients harboring missense variants in GCK (Spearman correlation: −0.49) ( 45 ). AlphaMissense pathogenicity exhibits a log-linear relationship with in vitro GCK activity measurements for 36 clinical variants (Spearman correlation: −0.65; Fig.…”

Section: Alphamissense Achieves State-of-the-art Agreement With Multi...mentioning

confidence: 99%

See 2 more Smart Citations

Accurate proteome-wide missense variant effect prediction with AlphaMissense

Cheng,

Novati,

Pan

et al. 2023

Science

626

218

View full text Add to dashboard Cite

The vast majority of missense variants observed in the human genome are of unknown clinical significance. We present AlphaMissense, an adaptation of AlphaFold fine-tuned on human and primate variant population frequency databases to predict missense variant pathogenicity. By combining structural context and evolutionary conservation, our model achieves state-of-the-art results across a wide range of genetic and experimental benchmarks, all without explicitly training on such data. The average pathogenicity score of genes is also predictive for their cell, capable of identifying short essential genes that existing statistical approaches are underpowered to detect. As a resource to the community, we provide a database of predictions for all possible human single amino acid substitutions and classify 89% of missense variants as either likely benign or likely pathogenic.

show abstract

Section: Alphamissense Achieves State-of-the-art Agreement With Multi...mentioning

confidence: 87%

Section: Alphamissense Achieves State-of-the-art Agreement With Multi...mentioning

confidence: 99%

Section: Alphamissense Achieves State-of-the-art Agreement With Multi...mentioning

confidence: 99%

See 1 more Smart Citation

Accurate proteome-wide missense variant effect prediction with AlphaMissense

Cheng,

Novati,

Pan

et al. 2023

Science

626

218

View full text Add to dashboard Cite

show abstract

“…In order to shed light on the molecular effects that lead to these disorders, the GCK activity of 8570 single-site variants have been experimental assessed using functional complementation yeast assays [ 52 ]. We used this set of variants as independent test set to assess the fitness predictors.…”

Section: Resultsmentioning

confidence: 99%

FiTMuSiC: leveraging structural and (co)evolutionary data for protein fitness prediction

Tsishyn,

Cia,

Hermans

et al. 2024

Hum Genomics

View full text Add to dashboard Cite

Systematically predicting the effects of mutations on protein fitness is essential for the understanding of genetic diseases. Indeed, predictions complement experimental efforts in analyzing how variants lead to dysfunctional proteins that in turn can cause diseases. Here we present our new fitness predictor, FiTMuSiC, which leverages structural, evolutionary and coevolutionary information. We show that FiTMuSiC predicts fitness with high accuracy despite the simplicity of its underlying model: it was among the top predictors on the hydroxymethylbilane synthase (HMBS) target of the sixth round of the Critical Assessment of Genome Interpretation challenge (CAGI6) and performs as well as much more complex deep learning models such as AlphaMissense. To further demonstrate FiTMuSiC’s robustness, we compared its predictions with in vitro activity data on HMBS, variant fitness data on human glucokinase (GCK), and variant deleteriousness data on HMBS and GCK. These analyses further confirm FiTMuSiC’s qualities and accuracy, which compare favorably with those of other predictors. Additionally, FiTMuSiC returns two scores that separately describe the functional and structural effects of the variant, thus providing mechanistic insight into why the variant leads to fitness loss or gain. We also provide an easy-to-use webserver at https://babylone.ulb.ac.be/FiTMuSiC, which is freely available for academic use and does not require any bioinformatics expertise, which simplifies the accessibility of our tool for the entire scientific community.

show abstract

“…It relies on only a few biologically meaningful parameters and is robust to low variability in the input MSA. GEMME proved instrumental for investigating the interplay between protein stability and function, and elucidating disease mechanisms (Abildgaard et al 2023;Cagiada et al 2023;Gersing et al 2023;Tiemann et al 2023;Tsuboyama et al 2023). Combining GEMME with a fast MSA generation algorithm allows for producing proteome-wide substitution score matrices within a few days (Abakarova et al 2023).…”

Section: Mainmentioning

confidence: 99%

VespaG: Expert-guided protein Language Models enable accurate and blazingly fast fitness prediction

Marquet,

Schlensok,

Abakarova

et al. 2024

Preprint

View full text Add to dashboard Cite

Exhaustive experimental annotation of the effect of all known protein variants remains daunting and expensive, stressing the need for scalable effect predictions. We introduce VespaG, a blazingly fast single amino acid variant effect predictor, leveraging embeddings of protein Language Models as input to a minimal deep learning model. To overcome the sparsity of experimental training data, we created a dataset of 39 million single amino acid variants from the human proteome applying the multiple sequence alignment-based effect predictor GEMME as a pseudo standard-of-truth. Assessed against the ProteinGym Substitution Benchmark (217 multiplex assays of variant effect with 2.5 million variants), VespaG achieved a mean Spearman correlation of 0.48 +/- 0.01, matching state-of-the-art methods such as GEMME, TranceptEVE, PoET, AlphaMissense, and VESPA. VespaG reached its top-level performance several orders of magnitude faster, predicting all mutational landscapes of the human proteome in 30 minutes on a consumer laptop (12-core CPU, 16 GB RAM).

show abstract

A comprehensive map of human glucokinase variant activity

Cited by 24 publications

References 103 publications

Accurate proteome-wide missense variant effect prediction with AlphaMissense

Accurate proteome-wide missense variant effect prediction with AlphaMissense

FiTMuSiC: leveraging structural and (co)evolutionary data for protein fitness prediction

VespaG: Expert-guided protein Language Models enable accurate and blazingly fast fitness prediction

Contact Info

Product

Resources

About