Marina Abakarova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marina Abakarova has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Elodie Laine
Sorbonne Universite
5 shared publications - Michael Rera
Université Paris Cité, CNRS, Functional and Adaptive Biology, UMR8251, Paris, France
4 shared publications - Arnaud Liehrmann
Sorbonne Université, CNRS, IBPS, Department of Computational, Quantitative and Synthetic Biology (CQSB, UMR7238), 75005 Paris, France
2 shared publications - Burkhard Rost
School of Computation, Information, and Technology (CIT), Department of Informatics, Bioinformatics & Computational Biology, TUM (Technical University of Munich), 85748 Garching/Munich, Germany
2 shared publications - Céline Marquet
Technical University of Munich
2 shared publications - Maria Inés Freiberger
Sorbonne Université, CNRS, IBPS, Department of Computational, Quantitative and Synthetic Biology (CQSB, UMR7238), 75005 Paris, France
2 shared publications
Latest Publications
- Open Access
- 27 April 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Proteome-wide prediction of the functional impact of missense variants with ProteoCast
Dissecting the functional impact of genetic mutations is essential to advancing our understanding of genotype-phenotype relationships and identifying therapeutic targets. Despite progress in sequencing and genome editing technologies, proteome-wide mutation effect prediction remains challenging. Here we show that evolutionary information alone enables accurate prediction of mutation effects across entire proteomes. ProteoCast is a scalable and interpretable computational method that leverages protein sequence conservation to classify genetic variants and identify functionally important protein sites. We apply ProteoCast to the complete Drosophila melanogaster proteome (22,000 isoforms, 300 million mutations) and validate it against nearly 400,000 natural and experimental variants. It correctly classifies 85% of known lethal mutations as functionally impactful versus 13-18% of population variants. ProteoCast-guided genome editing experiments confirm these predictions. Moreover, ProteoCast successfully identifies functionally important protein modification sites and binding motifs. ProteoCast provides a publicly available resource and deployable pipeline for studying gene function and mutations in any organism.
- 27 April 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessProteome-wide prediction of the functional impact of missense variants with ProteoCast
Dissecting the functional impact of genetic mutations is essential to advancing our understanding of genotype-phenotype relationships and identifying therapeutic targets. Despite progress in sequencing and genome editing technologies, proteome-wide mutation effect prediction remains challenging. Here we show that evolutionary information alone enables accurate prediction of mutation effects across entire proteomes. ProteoCast is a scalable and interpretable computational method that leverages protein sequence conservation to classify genetic variants and identify functionally important protein sites. We apply ProteoCast to the complete Drosophila melanogaster proteome (22,000 isoforms, 300 million mutations) and validate it against nearly 400,000 natural and experimental variants. It correctly classifies 85% of known lethal mutations as functionally impactful versus 13-18% of population variants. ProteoCast-guided genome editing experiments confirm these predictions. Moreover, ProteoCast successfully identifies functionally important protein modification sites and binding motifs. ProteoCast provides a publicly available resource and deployable pipeline for studying gene function and mutations in any organism.
- 9 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Large-scale assessment of the impact of protein sequence variations on ageing using Drosophila melanogaster
Évaluation à grande échelle de l'impact de la variation des séquences protéiques sur le vieillissement chez Drosophila melanogaster: Comprendre comment la variation génétique modifie la fonction des protéines et contribue à la diversité phénotypique demeure un défi central en génomique. Cette thèse explore comment la modélisation computationnelle de la variation protéique peut améliorer notre compréhension des traits complexes, tels que la viabilité et la longévité des organismes, en prédisant l'impact des mutations faux-sens sur la fonction des protéines. Nous nous concentrons ici sur Drosophila melanogaster, un organisme modèle puissant pour l'étude des relations génotype-phénotype à grande échelle. Cette thèse présente trois contributions principales qui font progresser la prédiction des effets des variants à grande échelle et de manière interprétable : (1) nous avons établi un pipeline à l'échelle du protéome combinant GEMME, un modèle fondé sur l'évolution, avec des alignements multiples de séquences (MSAs) générés par ColabFold, permettant une prédiction précise et efficace des paysages mutationnels sur des milliers de protéines de Drosophila ; (2) nous avons développé ProteoCast, une méthode à haut débit qui prédit systématiquement l'impact de toutes les mutations faux-sens possibles dans le protéome de Drosophila, validée par une évaluation multi-niveaux incluant des annotations fonctionnelles, des données de population et cinq expériences CRISPR ciblant des mutants faux-sens ; et (3) nous avons introduit VespaG, un modèle de langage protéique guidé par une expertise évolutive, qui exploite des embeddings préentraînés pour prédire des paysages mutationnels complets. VespaG allie scalabilité et interprétabilité, permettant une exploration rapide des effets des variants sans nécessiter d'alignements. Ensemble, ces méthodes permettent une exploration exhaustive des paysages mutationnels et soutiennent l'identification de sites fonctionnellement importants à l'échelle du protéome. Les résultats contribuent à rapprocher les prédictions computationnelles de la génétique expérimentale et fournissent des outils précieux pour la communauté de recherche sur Drosophila et au-delà.
- 9 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Large-scale assessment of the impact of protein sequence variations on ageing using Drosophila melanogaster
Évaluation à grande échelle de l'impact de la variation des séquences protéiques sur le vieillissement chez Drosophila melanogaster: Comprendre comment la variation génétique modifie la fonction des protéines et contribue à la diversité phénotypique demeure un défi central en génomique. Cette thèse explore comment la modélisation computationnelle de la variation protéique peut améliorer notre compréhension des traits complexes, tels que la viabilité et la longévité des organismes, en prédisant l'impact des mutations faux-sens sur la fonction des protéines. Nous nous concentrons ici sur Drosophila melanogaster, un organisme modèle puissant pour l'étude des relations génotype-phénotype à grande échelle. Cette thèse présente trois contributions principales qui font progresser la prédiction des effets des variants à grande échelle et de manière interprétable : (1) nous avons établi un pipeline à l'échelle du protéome combinant GEMME, un modèle fondé sur l'évolution, avec des alignements multiples de séquences (MSAs) générés par ColabFold, permettant une prédiction précise et efficace des paysages mutationnels sur des milliers de protéines de Drosophila ; (2) nous avons développé ProteoCast, une méthode à haut débit qui prédit systématiquement l'impact de toutes les mutations faux-sens possibles dans le protéome de Drosophila, validée par une évaluation multi-niveaux incluant des annotations fonctionnelles, des données de population et cinq expériences CRISPR ciblant des mutants faux-sens ; et (3) nous avons introduit VespaG, un modèle de langage protéique guidé par une expertise évolutive, qui exploite des embeddings préentraînés pour prédire des paysages mutationnels complets. VespaG allie scalabilité et interprétabilité, permettant une exploration rapide des effets des variants sans nécessiter d'alignements. Ensemble, ces méthodes permettent une exploration exhaustive des paysages mutationnels et soutiennent l'identification de sites fonctionnellement importants à l'échelle du protéome. Les résultats contribuent à rapprocher les prédictions computationnelles de la génétique expérimentale et fournissent des outils précieux pour la communauté de recherche sur Drosophila et au-delà.
- Open Access
ProteoCast: a web server to predict, validate, and interpret missense variant effects
Understanding how mutations affect protein function remains critical yet challenging, particularly for variants in clinical databases lacking experimental characterisation and for intrinsically disordered regions. Current computational approaches often operate as black boxes, providing predictions without sufficient transparency or quality assessment of the underlying data. Here we present ProteoCast, a user-friendly web server that predicts variant effects through evolutionary constraint analysis and structural context integration. ProteoCast provides a three-tier variant classification (impactful, mild, neutral) to help prioritise mutations for clinical interpretation and experimental validation. It incorporates multiple sequence alignment quality controls to ensure prediction reliability and flag positions with insufficient evolutionary information. Beyond single-variant classification, ProteoCast employs a novel segmentation approach based on mutational sensitivity to identify functional linear peptides in disordered regions. Interactive visualisations guide users through results interpretation, from variant-level predictions to protein-wide functional landscapes. Evaluation on 63,000 ClinVar variants demonstrates 77% sensitivity and 87% specificity for pathogenicity prediction, with performance maintained across species (85% accuracy on Drosophila lethal mutations). ProteoCast successfully identifies twice as many functional motifs in intrinsically disordered regions compared to conservation-based phylogenetic methods. Predictions can be tuned to specific conformations, such as bound forms in protein complexes, for improved accuracy and interpretability. With its transparent, unsupervised methodology and computational efficiency (minutes per protein), ProteoCast democratises access to variant effect prediction and functional site discovery for the broader research community. The web server is freely available at: https://proteocast.ijm.fr/ . Highlights: ProteoCast web server democratises variant effect prediction through a fast, transparent platform combining evolutionary analysis and structural context Three-tier variant classification enables prioritisation for clinical interpretation and genome editing experiments Novel mutational sensitivity segmentation approach identifies functional peptides in disordered regions Interactive visualisations and input alignment quality controls guide interpretation
Open AccessProteoCast: a web server to predict, validate, and interpret missense variant effects
Understanding how mutations affect protein function remains critical yet challenging, particularly for variants in clinical databases lacking experimental characterisation and for intrinsically disordered regions. Current computational approaches often operate as black boxes, providing predictions without sufficient transparency or quality assessment of the underlying data. Here we present ProteoCast, a user-friendly web server that predicts variant effects through evolutionary constraint analysis and structural context integration. ProteoCast provides a three-tier variant classification (impactful, mild, neutral) to help prioritise mutations for clinical interpretation and experimental validation. It incorporates multiple sequence alignment quality controls to ensure prediction reliability and flag positions with insufficient evolutionary information. Beyond single-variant classification, ProteoCast employs a novel segmentation approach based on mutational sensitivity to identify functional linear peptides in disordered regions. Interactive visualisations guide users through results interpretation, from variant-level predictions to protein-wide functional landscapes. Evaluation on 63,000 ClinVar variants demonstrates 77% sensitivity and 87% specificity for pathogenicity prediction, with performance maintained across species (85% accuracy on Drosophila lethal mutations). ProteoCast successfully identifies twice as many functional motifs in intrinsically disordered regions compared to conservation-based phylogenetic methods. Predictions can be tuned to specific conformations, such as bound forms in protein complexes, for improved accuracy and interpretability. With its transparent, unsupervised methodology and computational efficiency (minutes per protein), ProteoCast democratises access to variant effect prediction and functional site discovery for the broader research community. The web server is freely available at: https://proteocast.ijm.fr/ . Highlights: ProteoCast web server democratises variant effect prediction through a fast, transparent platform combining evolutionary analysis and structural context Three-tier variant classification enables prioritisation for clinical interpretation and genome editing experiments Novel mutational sensitivity segmentation approach identifies functional peptides in disordered regions Interactive visualisations and input alignment quality controls guide interpretation
- Open Access
Proteome-wide Prediction of the Functional Impact of Missense Variants with ProteoCast
Dissecting the functional impact of genetic mutations is essential to advancing our understanding of genotype-phenotype relationships and identifying therapeutic targets. Despite progress in sequencing and genome editing technologies, proteome-wide mutation effect prediction remains challenging. Here we show that evolutionary information alone enables accurate prediction of mutation effects across entire proteomes. ProteoCast is a scalable and interpretable computational method that leverages protein sequence conservation to classify genetic variants and identify functionally important protein sites. We apply ProteoCast to the complete Drosophila melanogaster proteome (22,000 isoforms, 300 million mutations) and validate it against nearly 400,000 natural and experimental variants. It correctly classifies 85% of known lethal mutations as functionally impactful versus 13-18% of population variants. ProteoCast-guided genome editing experiments confirm these predictions. Moreover, ProteoCast successfully identifies functionally important protein modification sites and binding motifs. ProteoCast provides a publicly available resource and deployable pipeline for studying gene function and mutations in any organism.
Open AccessProteome-wide Prediction of the Functional Impact of Missense Variants with ProteoCast
Dissecting the functional impact of genetic mutations is essential to advancing our understanding of genotype-phenotype relationships and identifying therapeutic targets. Despite progress in sequencing and genome editing technologies, proteome-wide mutation effect prediction remains challenging. Here we show that evolutionary information alone enables accurate prediction of mutation effects across entire proteomes. ProteoCast is a scalable and interpretable computational method that leverages protein sequence conservation to classify genetic variants and identify functionally important protein sites. We apply ProteoCast to the complete Drosophila melanogaster proteome (22,000 isoforms, 300 million mutations) and validate it against nearly 400,000 natural and experimental variants. It correctly classifies 85% of known lethal mutations as functionally impactful versus 13-18% of population variants. ProteoCast-guided genome editing experiments confirm these predictions. Moreover, ProteoCast successfully identifies functionally important protein modification sites and binding motifs. ProteoCast provides a publicly available resource and deployable pipeline for studying gene function and mutations in any organism.
- Open Access
Expert-guided protein Language Models enable accurate and blazingly fast fitness prediction
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). Availability VespaG is available freely at https://github.com/JSchlensok/VespaG
Open AccessExpert-guided protein Language Models enable accurate and blazingly fast fitness prediction
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). Availability VespaG is available freely at https://github.com/JSchlensok/VespaG
- Open Access
Alignment-based protein mutational landscape prediction: doing more with less
The wealth of genomic data has boosted the development of computational methods predicting the phenotypic outcomes of missense variants. The most accurate ones exploit multiple sequence alignments, which can be costly to generate. Recent efforts for democratizing protein structure prediction have overcome this bottleneck by leveraging the fast homology search of MMseqs2. Here, we show the usefulness of this strategy for mutational outcome prediction through a large-scale assessment of 1.5M missense variants across 72 protein families. Our study demonstrates the feasibility of producing alignment-based mutational landscape predictions that are both high-quality and compute-efficient for entire proteomes. We provide the community with the whole human proteome mutational landscape and simplified access to our predictive pipeline. Significant statement: Understanding the implications of DNA alterations, particularly missense variants, on our health is paramount. This study introduces a faster and more efficient approach to predict these effects, harnessing vast genomic data resources. The speed-up is possible by establishing that resource-saving multiple sequence alignments suffice even as input to a method fitting few parameters given the alignment. Our results opens the door to discovering how tiny changes in our genes can impact our health. They provide valuable insights into the genotype-phenotype relationship that could lead to new treatments for genetic diseases.
Open AccessAlignment-based protein mutational landscape prediction: doing more with less
The wealth of genomic data has boosted the development of computational methods predicting the phenotypic outcomes of missense variants. The most accurate ones exploit multiple sequence alignments, which can be costly to generate. Recent efforts for democratizing protein structure prediction have overcome this bottleneck by leveraging the fast homology search of MMseqs2. Here, we show the usefulness of this strategy for mutational outcome prediction through a large-scale assessment of 1.5M missense variants across 72 protein families. Our study demonstrates the feasibility of producing alignment-based mutational landscape predictions that are both high-quality and compute-efficient for entire proteomes. We provide the community with the whole human proteome mutational landscape and simplified access to our predictive pipeline. Significant statement: Understanding the implications of DNA alterations, particularly missense variants, on our health is paramount. This study introduces a faster and more efficient approach to predict these effects, harnessing vast genomic data resources. The speed-up is possible by establishing that resource-saving multiple sequence alignments suffice even as input to a method fitting few parameters given the alignment. Our results opens the door to discovering how tiny changes in our genes can impact our health. They provide valuable insights into the genotype-phenotype relationship that could lead to new treatments for genetic diseases.