Predrag Radivojac A

An integrated, scaled approach to resolve TSC2 variants of uncertain significance

Abundance scores for 8,891 TSC2 missense variants, plus mTOR pathway activity scores for 391, were calibrated to ACMG/AMP evidence. They putatively reclassify 212 of 276 clinical-cohort missense VUS.

Saturation Genome Editing reveals the functional impact of RAD51D and XRCC2 variants

The paper uses saturation genome editing to assess the functional impact of RAD51D and XRCC2 variants, showing high accuracy in distinguishing pathogenic from benign variants.

Improving splice site usage prediction with SPLAIRE

The paper evaluates splicing models, identifies performance gaps, and introduces a cell-type-specific model for improved splice site prediction in human airway epithelial cells.

Advances in protein function prediction from the fifth CAFA challenge

This work analyzes CAFA5 submissions, showing improved accuracy in protein function prediction and highlights the role of protein language models and 3D structures in performance gains.

Structure-aware protein function prediction at isoform resolution

This study develops a framework for predicting protein function and domain annotation at isoform resolution using structural and sequence data, showing strong performance in benchmark tests and capturing domain changes across isoforms.

Calibration of in-frame indel variant effect predictors for clinical variant classification

This study calibrates in-frame indel variant effect predictors for clinical classification, showing they reach multiple evidence levels but perform worse than missense predictors.

Gene- and domain-aware calibration increases the clinical utility of variant effect predictors

This paper improves variant effect predictors by calibrating them gene- and domain-aware, increasing evidence assignment and accuracy for variant classification.

A scalable approach to resolving variants of uncertain significance

The paper develops a scalable workflow to reclassify variants of uncertain significance using experimental and predictive evidence, resolving 75% of VUS in 40 genes.

Ancestry-specific performance of variant effect predictors in clinical variant classification

The paper evaluates how well variant effect predictors perform across different genetic ancestries, finding comparable performance across major groups after accounting for allele frequency.

Predicting interaction-specific protein-protein interaction perturbations by missense variants with MutPred-PPI

MutPred-PPI predicts interaction-specific effects of missense variants using graph attention networks, showing strong performance on both seen and unseen proteins.

Gene-based calibration of high-throughput functional assays for clinical variant classification

This paper introduces ExCALIBR, a method to calibrate variant scores from functional assays, improving pathogenicity prediction and reducing variants of uncertain significance.

Calibration of additional computational tools expands ClinGen recommendation options for variant classification with PP3/BP4 criteria

The paper calibrates three new computational tools for clinical variant classification, finding they provide evidence strength comparable to previously recommended tools.

Evaluation of enzyme activity predictions for variants of unknown significance in Arylsulfatase A

The paper evaluates variant effect predictions for ARSA gene variants, finding that a bootcamp-trained model outperformed others and that deep learning slightly improved performance over simpler methods.

Critical assessment of missense variant effect predictors on disease-relevant variant data

The paper evaluates missense variant effect predictors using CAGI6 data, finding strong performance across settings and highlighting biases in some predictors.

Assessment of the evidence yield for the calibrated PP3/BP4 computational recommendations

The paper assesses rare missense variants in genome sequences using PP3/BP4 evidence strength classifications and finds few variants meet strong or moderate criteria.

Critical assessment of variant prioritization methods for rare disease diagnosis within the Rare Genomes Project

The paper evaluates variant prioritization methods for rare disease diagnosis using data from the Rare Genomes Project, finding that top models identify causal variants in most solved families and uncover potential candidates in unsolved ones.

The landscape of regional missense mutational intolerance quantified from 730,947 exomes

The paper quantifies regional missense mutational intolerance using 730,947 exomes to identify constrained gene regions and improve variant interpretation.

Predicting the impact of rare variants on RNA splicing in CAGI6

The paper evaluates splicing prediction methods on 56 clinically validated variants, finding some methods match or exceed SpliceAI's performance but highlighting ongoing challenges in accuracy.

Learning from the unknown: exploring the range of bacterial functionality

This paper introduces a novel method to explore bacterial functional repertoires without reference databases, showing it outperforms existing approaches in taxonomic assignment and captures environment-driven diversity.

Evidence-based calibration of computational tools for missense variant pathogenicity classification and ClinGen recommendations for clinical use of PP3/BP4 criteria

The paper calibrates computational tools for missense variant pathogenicity classification and provides evidence-based revisions to PP3/BP4 ACMG/AMP criteria.

The field of protein function prediction as viewed by different domain scientists

The paper surveys perspectives of experimental biologists, biocurators, and computational biologists on protein function prediction, highlighting differences in their views and challenges in collaboration.

Distinct error rates for reference and non-reference genotypes estimated by pedigree analysis

The paper estimates distinct error rates for reference and non-reference genotypes using pedigree analysis in owl monkeys, finding significant differences in error types.

MutPred2: inferring the molecular and phenotypic impact of amino acid variants

MutPred2 identifies pathogenic amino acid variants, predicts their molecular mechanisms, and validates their functional impact in neurodevelopmental disorders.

The Ortholog Conjecture Revisited: the Value of Orthologs and Paralogs in Function Prediction

This study revisits the ortholog conjecture by analyzing function prediction accuracy using orthologs and paralogs across two species pairs, finding strong evidence against the conjecture.

New Drosophila long-term memory genes revealed by assessing computational function prediction methods.

The paper identifies 11 novel Drosophila genes involved in long-term memory formation using computational methods and behavioral assays.