Biology subjects

Radivojac, P.

Publications and source records attributed to Radivojac, P..

At least 19 recordsLinked to original sources

bioRxiv2026

Improving splice site usage prediction with SPLAIRE

BackgroundAlternative splicing, the mechanism by which intronic sequences are excised from pre-mRNAs to produce mature mRNA, affects >95% of human protein-coding genes and is a major driver of human disease states. The spliceosome, a protein-RNA complex responsible for splicing pre-mRNA, identifies candidate splice sites partly through the recognition of characteristic sequence motifs at exon-intron junctions. Deep learning models that predict the presence of splice sites from pre-mRNA sequence have achieved breakthrough performance relative to previous machine-learning techniques, and these models have improved our ability to identify pathogenic genetic variants that alter splicing. ResultsWe show that, while overall performance measures from these models suggest near-perfect performance, substantial gaps in prediction remain, including the identification of splice sites with low usage rates and tissue-specific splice sites. We leverage one of the largest paired RNA and genotyping datasets used to date to train a novel splicing model optimized for a specific cell type, human airway epithelial cells. We trained a dilated convolutional neural network on data from cultured airway epithelial cells from 100 donors, and showed that this model outperforms current state-of-the-art models on splice site identification and splice site usage quantification, including on multiple tissues not included in the model training data. ConclusionsWe present the most comprehensive evaluation of state-of-the-art splicing models published to date, revealing reasonable performance across models for genetic variant effect prediction along with important performance gaps and insights into directions for future model development.

genomics↗

bioRxiv2026

Advances in protein function prediction from the fifth CAFA challenge

The Critical Assessment of Functional Annotation (CAFA) is a long-standing community effort to independently assess computational methods for protein function prediction, to highlight well-performing methodologies, to identify bottlenecks in the field, and to provide a forum for the dissemination of results and exchange of ideas. In its fifth round (CAFA5) of triennial challenges, a partnership with Kaggle Inc. facilitated participation from a large community of data scientists and computational biologists through a competitive prospective challenge on the crowdsourcing platform. In this work, we present an in-depth analysis of the submitted predictions and report improvements in accuracy over all methods from the previous CAFA challenges. We further introduce a new evaluation setting for proteins with pre-existing (incomplete) annotations and identify the need for methods that better leverage existing annotations to predict those that will be discovered later. Finally, we characterize the prospective evaluation framework by examining performance on a strict set of unpublished annotations and across intermediate database releases. Our results indicate that recent developments in the field, such as the availability of protein language models and accurately predicted 3D structures, as well as the growth of experimental annotations through biocuration, have all contributed to performance improvements. 1

bioinformatics↗

bioRxiv2026

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

Insertions and deletions (indels) represent a substantial source of genetic variation in humans and are associated with a diverse array of functional consequences. Despite their prevalence and clinical importance, indels, particularly short in-frame indels, remain critically understudied compared to single nucleotide variants and are challenging to interpret clinically. While many computational predictors for missense variants have been rigorously evaluated and calibrated for clinical use, the clinical utility of tools for in-frame indels remains uncertain. To address this gap, we have calibrated in-frame indel prediction tools for clinical variant classification. We constructed a high-confidence dataset of in-frame indel variants ([≤] 50bp) from clinical and population databases and estimated the prior probability of pathogenicity of a rare in-frame indel observed in a disease-associated gene, and of an insertion and deletion separately. Using a previously developed statistical framework based on local posterior probabilities, we then established score thresholds for eight computational tools, corresponding to distinct evidence levels for pathogenic and benign classification according to ACMG/AMP guidelines. All in-frame indel predictors evaluated here reached multiple evidence levels of pathogenicity and/or benignity, demonstrating measurable clinical value. However, these models consistently exhibited lower performance levels compared to missense predictors, highlighting the need for improved computational approaches for indel classification.

bioinformatics↗

bioRxiv2026

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

The utility of clinical genetic testing is limited because around 90% of missense variants in ClinVar remain of uncertain clinical significance. Variant effect predictors (VEPs) can score any missense variant, potentially empowering variant classification. Realizing this potential requires calibration to translate predictor scores into evidence. However, genome-wide calibration ignores predictor heterogeneity across genes, causing evidence misassignment. We developed an automated, data-adaptive framework that optimizes two complementary approaches: gene-specific calibration for genes with enough variants for calibration, and domain-aggregate calibration for other disease-associated genes, which groups variants from protein domains with similar predictor score distributions for calibration. Applied to three predictors across 2,769 genes, this framework assigned evidence to 10.6% more variants on average while generally improving evidence accuracy compared to genome-wide calibration. These calibrations and the resulting calibrated computational evidence are available through the PredictMD portal. Our framework substantially increases the clinical utility of VEPs for variant classification.

genetics↗

bioRxiv2026

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

Predicting the effects of genetic variants and assessing prediction performance are key computational tasks in genomic medicine. It has been shown that well-calibrated variant effect predictors can be reliably used as evidence towards establishing pathogenicity (or benignity) of missense variants, thereby rendering these variants suitable for use in (or exclusion from) the genetic diagnosis of rare Mendelian conditions. However, most predictors have been trained or calibrated on data that may not be sufficiently representative to lead to similar performance across all genetic ancestries. This raises questions about the responsible deployment of these tools to improve human health. To better understand the utility of computational predictors, we set out to assess their ancestry-specific performance in terms of accuracy and evidence strength according to the ACMG/AMP guidelines. First, we determined that the expected count of rare variants in an individuals genome and the allele frequency distribution of these variants are the key confounders when evaluating a predictors performance across different genetic ancestries. Second, we found that a predictors accuracy itself inversely correlates with the allele frequency of the rare variant. After stratifying according to allele frequency, we show that established methods for predicting the pathogenicity of missense variants have comparable performance levels across major ancestry groups. Our results therefore support the wide deployment of such models in the context of genetic diagnosis and related applications.

bioinformatics↗

bioRxiv2026

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

Obtaining a precise genetic tuberous sclerosis diagnosis is a challenge as many missense TSC2 variants are variants of uncertain significance (VUS). VUS in TSC2 have been resolved by one-at-a-time functional assays, but these assays cannot scale to the 3,634 TSC2 missense VUS observed so far. To address this challenge, we used massively parallel sequencing to measure the steady-state abundance of almost 9,000 TSC2 missense variants and developed an mTOR pathway activity assay using genome editing and cell sorting to generate activity scores for 391 missense variants. 1,288 of 8,891 (14.49%) missense variants assayed had altered TSC2 abundance, and 69 of 391 (17.65%) missense variants assayed had altered mTOR pathway activity. Calibration and integration of these data into classification of variants identified in a clinical cohort putatively reclassified 212 of 276 (76.8%) TSC2 missense VUS. These datasets will lead to improved genetic diagnosis of tuberous sclerosis with potential positive impacts on the clinical management of patients and their families.

genetics↗

bioRxiv2025

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

Disruption of protein-protein interactions (PPIs) is a major mechanism of a variants deleterious effect. Computational tools are needed to assess such variants at scale, yet existing predictors rarely consider loss of specific interactions, particularly when variants perturb binding interfaces without significantly affecting protein stability. To address this problem, we present MutPred-PPI, a graph attention network that predicts interaction-specific (edgetic) effects of missense variants by operating on AlphaFold 3-based protein complex contact graphs with protein language model embeddings imposed upon nodes. We systematically evaluated our model with stringent group cross-validation as well as benchmark data recently collected within the IGVF Consortium. MutPred-PPI outperformed all baseline methods across all evaluation criteria, achieving an AUC of 0.85 on seen proteins and 0.72 on previously unseen proteins in cross-validation, demonstrating strong generalizability despite scarce training data. To demonstrate biomedical relevance, we applied MutPred-PPI to variants from ClinVar, HGMD, COSMIC, gnomAD, and two de novo neurodevelopmental disorder-linked datasets. Disease-associated variants from Clin-Var and HGMD showed strong enrichment for both quasi-null and edgetic effects, whereas population variants from gnomAD increasingly preserved interactions with higher allele frequencies. Notably, we observed a strong edgetic disruption signature in highly recurrent cancer variants from both the full COSMIC dataset and a subset of variants from oncogenes. Recurrent tumor suppressor gene variants and autism spectrum disorder-associated variants exhibited moderate quasi-null enrichment, whilst neurodevelopmental disorder-linked variants showed a weak edgetic disruption signature. These results indicate distinct PPI perturbation mechanisms across disease types and show that MutPred-PPI captures functionally relevant molecular effects of pathogenic variants.

bioinformatics↗

bioRxiv2025

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

High-throughput assays measure a broad range of variant effects on gene function and hold promise for supporting genomic medicine. Current clinical guidelines for rare Mendelian diseases rely on establishing gene-specific score thresholds for each assay that separate pathogenic from benign variants. This introduces inconsistencies and subjectivity, ultimately lacking the rigor of calibration; i.e., mapping a variant score to a probability of pathogenicity. To address this problem, we introduce a semi-supervised framework for calibrating experimental assay data and propose Experimental score CALIBRator (ExCALIBR), a method that jointly models pathogenic, benign, synonymous, and population variants using skew normal mixtures to produce variant-specific probabilities of pathogenicity. Evaluated across 80 datasets from 39 genes, all meeting fit quality criteria, ExCALIBR substantially outperformed existing field standards and was further validated on the All of Us biobank data. Our results demonstrate that calibrated experimental assays generate indispensable evidence that will dramatically reduce variants of uncertain significance.

bioinformatics↗

bioRxiv2024

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

PurposeWe previously developed an approach to calibrate computational tools for clinical variant classification, updating recommendations for the reliable use of variant impact predictors to provide evidence strength up to Strong. A new generation of tools using distinctive approaches have since been released, and these methods must be independently calibrated for clinical application. MethodUsing our local posterior probability-based calibration and our established data set of ClinVar pathogenic and benign variants, we determined the strength of evidence provided by three new tools (AlphaMissense, ESM1b, VARITY) and calibrated scores meeting each evidence strength. Results All three tools reached the Strong level of evidence for variant pathogenicity and Moderate for benignity, though sometimes for few variants. Compared to previously recommended tools, these yielded at best only modest improvements in the tradeoffs of evidence strength and false positive predictions. ConclusionAt calibrated thresholds, three new computational predictors provided evidence for variant pathogenicity at similar strength to the four previously recommended predictors (and comparable with functional assays for some variants). This calibration broadens the scope of computational tools for application in clinical variant classification. Their new approaches offer promise for future advancement of the field.

bioinformatics↗

bioRxiv2024

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

Regular, systematic, and independent assessment of computational tools used to predict the pathogenicity of missense variants is necessary to evaluate their clinical and research utility and suggest directions for future improvement. Here, as part of the sixth edition of the Critical Assessment of Genome Interpretation (CAGI) challenge, we assess missense variant effect predictors (or variant impact predictors) on an evaluation dataset of rare missense variants from disease-relevant databases. Our assessment evaluates predictors submitted to the CAGI6 Annotate-All-Missense challenge, predictors commonly used by the clinical genetics community, and recently developed deep learning methods for variant effect prediction. To explore a variety of settings that are relevant for different clinical and research applications, we assess performance within different subsets of the evaluation data and within high-specificity and high-sensitivity regimes. We find strong performance of many predictors across multiple settings. Meta-predictors tend to outperform their constituent individual predictors; however, several individual predictors have performance similar to that of commonly used meta-predictors. The relative performance of predictors differs in high-specificity and high-sensitivity regimes, suggesting that different methods may be best suited to different use cases. We also characterize two potential sources of bias. Predictors that incorporate allele frequency as a predictive feature tend to have reduced performance when distinguishing pathogenic variants from very rare benign variants, and predictors supervised on pathogenicity labels from curated variant databases often learn label imbalances within genes. Overall, we find notable advances over the oldest and most cited missense variant effect predictors and continued improvements among the most recently developed tools, and the CAGI Annotate-All-Missense challenge (also termed the Missense Marathon) will continue to assess state-of-the-art methods as the field progresses. Together, our results help illuminate the current clinical and research utility of missense variant effect predictors and identify potential areas for future development.

genetics↗

bioRxiv2024

The landscape of regional missense mutational intolerance quantified from 125,748 exomes

Missense variants can have a range of functional impacts depending on factors such as the specific amino acid substitution and location within the gene. To interpret their deleteriousness, studies have sought to identify regions within genes that are specifically intolerant of missense variation. Here, we leverage the patterns of rare missense variation in 730,947 exome sequenced individuals in the Genome Aggregation Database (gnomAD v4.1.1) against a null mutational model to identify transcripts with regional differences in missense constraint. Missense-depleted regions are enriched for ClinVar pathogenic variants, de novo missense variants from individuals with neurodevelopmental disorders, and complex trait heritability. Following ClinGen calibration recommendations for the ACMG/AMP variant classification guidelines, we establish that variants within regions with <36% of their expected missense variation achieve moderate support for pathogenicity. We integrate this regional constraint measure into a missense deleteriousness metric (named MPC) that effectively stratifies rare and de novo missense variants in individuals with early-onset developmental conditions from controls. These results provide additional tools to aid in missense variant interpretation.

genomics↗

bioRxiv2023

Predicting the impact of rare variants on RNA splicing in CAGI6

BackgroundVariants which disrupt splicing are a frequent cause of rare disease that have been under-ascertained clinically. Accurate and efficient methods to predict a variants impact on splicing are needed to interpret the growing number of variants of unknown significance (VUS) identified by exome and genome sequencing. Here we present the results of the CAGI6 Splicing VUS challenge, which invited predictions of the splicing impact of 56 variants ascertained clinically and functionally validated to determine splicing impact. ResultsThe performance of 12 prediction methods, along with SpliceAI and CADD, was compared on the 56 functionally validated variants. The maximum overall accuracy achieved was 82% from two different approaches, one weighting SpliceAI scores by minor allele frequency, and one applying the recently published Splicing Prediction Pipeline (SPiP). SPiP performed optimally in terms of sensitivity, while an ensemble method combining multiple prediction tools and information from databases exceeded all others for specificity. ConclusionsSeveral challenge methods equalled or exceeded the performance of SpliceAI, with ultimate choice of prediction method likely to depend on experimental or clinical aims. One quarter of the variants were incorrectly predicted by at least 50% of the methods, highlighting the need for further improvements to splicing prediction methods for successful clinical application.

bioinformatics↗

bioRxiv2022

Rethinking bacterial relationships in light of their molecular abilities

Determining the repertoire of a microbes molecular functions is a central question in microbial biology. Modern techniques achieve this goal by comparing microbial genetic material against reference databases of functionally annotated genes/proteins or known taxonomic markers such as 16S rRNA. Here we describe a novel approach to exploring bacterial functional repertoires without reference databases. Our Fusion scheme establishes functional relationships between bacteria and assigns organisms to Fusion-taxa that differ from otherwise defined taxonomic clades. Three key findings of our work stand out. First, bacterial functional comparisons outperform marker genes in assigning taxonomic clades. Fusion profiles are also better for this task than other functional annotation schemes. Second, Fusion-taxa are robust to addition of novel organisms and are, arguably, able to capture the environment-driven bacterial diversity. Finally, our alignment-free nucleic acid-based Siamese Neural Network model, created using Fusion functions, enables finding shared functionality of very distant, possibly structurally different, microbial homologs. Our work can thus help annotate functional repertoires of bacterial organisms and further guide our understanding of microbial communities.

bioinformatics↗

bioRxiv2022

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

Experimental biologists, biocurators, and computational biologists all play a role in characterizing a proteins function. The discovery of protein function in the laboratory by experimental scientists is the foundation of our knowledge about proteins. Experimental findings are compiled in knowledge-bases by biocurators to provide standardized, readily accessible, and computationally amenable information. Computational biologists train their methods using these data to predict protein function and guide subsequent experiments. To understand the state of affairs in this ecosystem, centered here around protein function prediction, we surveyed scientists from these three constituent communities. Our objective was to understand their views on this research area, including the importance of the problem, the usefulness of the methods, the bottlenecks in the field, and the level of interaction between the communities. We show that the three core communities have common but also idiosyncratic perspectives on the field. Most strikingly, experimentalists rarely use modern prediction software, but when presented with predictions, report many to be surprising and useful. Ontologies appear to be highly valued by biocurators, less so by experimentalists and computational biologists, yet controlled vocabularies bridge the communities and simplify the prediction task. Additionally, many software tools are not readily accessible and the predictions presented to the users can be broad and uninformative. To meet both the social and technical challenges in the field, a more productive and meaningful interaction between members of the core communities is necessary.

bioinformatics↗

bioRxiv2022

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

Recommendations from the American College of Medical Genetics and Genomics and the Association for Molecular Pathology (ACMG/AMP) for interpreting sequence variants specify the use of computational predictors as Supporting level of evidence for pathogenicity or benignity using criteria PP3 and BP4, respectively. However, score intervals defined by tool developers, and ACMG/AMP recommendations that require the consensus of multiple predictors, lack quantitative support. Previously, we described a probabilistic framework that quantified the strengths of evidence (Supporting, Moderate, Strong, Very Strong) within ACMG/AMP recommendations. We have extended this framework to computational predictors and introduce a new standard that converts a tools scores to PP3 and BP4 evidence strengths. Our approach is based on estimating the local positive predictive value and can calibrate any computational tool or other continuous-scale evidence on any variant type. We estimate thresholds (score intervals) corresponding to each strength of evidence for pathogenicity and benignity for thirteen missense variant interpretation tools, using carefully assembled independent data sets. Most tools achieved Supporting evidence level for both pathogenic and benign classification using newly established thresholds. Multiple tools reached score thresholds justifying Moderate and several reached Strong evidence levels. One tool reached Very Strong evidence level for benign classification on some variants. Based on these findings, we provide recommendations for evidence-based revisions of the PP3 and BP4 ACMG/AMP criteria using individual tools and future assessment of computational methods for clinical interpretation.

bioinformatics↗

bioRxiv2020

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

Errors in genotype calling can have perverse effects on genetic analyses, confounding association studies and obscuring rare variants. Analyses now routinely incorporate error rates to control for spurious findings. However, reliable estimates of the error rate can be difficult to obtain because of their variance between studies. Most studies also report only a single estimate of the error rate even though genotypes can be miscalled in more than one way. Here, we report a method for estimating the rates at which different types of genotyping errors occur at biallelic loci using pedigree information. Our method identifies potential genotyping errors by exploiting instances where the haplotypic phase has not been faithfully transmitted. The expected frequency of inconsistent phase depends on the combination of genotypes in a pedigree and the probability of miscalling each genotype. We develop a model that uses the differences in these frequencies to estimate rates for different types of genotype error. Simulations show that our method accurately estimates these error rates in a variety of scenarios. We apply this method to a dataset from the whole-genome sequencing of owl monkeys (Aotus nancymaae) in three-generation pedigrees. We find significant differences between estimates for different types of genotyping error, with the most common being homozygous reference sites miscalled as heterozygous and vice versa. The approach we describe is applicable to any set of genotypes where haplotypic phase can reliably be called, and should prove useful in helping to control for false discoveries.

bioinformatics↗

bioRxiv2019

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

The computational prediction of gene function is a key step in making full use of newly sequenced genomes. Function is generally predicted by transferring annotations from homologous genes or proteins for which experimental evidence exists. The "ortholog conjecture" proposes that orthologous genes should be preferred when making such predictions, as they evolve functions more slowly than paralogous genes. Previous research has provided little support for the ortholog conjecture, though the incomplete nature of the data cast doubt on the conclusions. Here we use experimental annotations from over 40,000 proteins, drawn from over 80,000 publications, to revisit the ortholog conjecture in two pairs of species: (i) Homo sapiens and Mus musculus and (ii) Saccharomyces cerevisiae and Schizosaccharomyces pombe. By making a distinction between questions about the evolution of function versus questions about the prediction of function, we find strong evidence against the ortholog conjecture in the context of function prediction, though questions about the evolution of function remain difficult to address. In both pairs of species, we quantify the amount of data that must be ignored if paralogs are discarded, as well as the resulting loss in prediction accuracy. Taken as a whole, our results support the view that the types of homologs used for function transfer are largely irrelevant to the task of function prediction. Aiming to maximize the amount of data used for this task, regardless of whether it comes from orthologs or paralogs, is most likely to lead to higher prediction accuracy.

bioinformatics↗

bioRxiv2019

Paternal age in rhesus macaques is positively associated with germline mutation accumulation but not with measures of offspring sociability

Mutation is the ultimate source of all genetic novelty and the cause of heritable genetic disorders. Mutational burden has been linked to complex disease, including neurodevelopmental disorders such as schizophrenia and autism. The rate of mutation is a fundamental genomic parameter and direct estimates of this parameter have been enabled by accurate comparisons of whole-genome sequences between parents and offspring. Studies in humans have revealed that the paternal age at conception explains most of the variation in mutation rate: each additional year of paternal age in humans leads to approximately 1.5 additional mutations inherited by the child. Here, we present an estimate of the de novo mutation rate in the rhesus macaque (Macaca mulatta) using whole-genome sequence data from 32 individuals in four large pedigrees. We estimated an average mutation rate of 0.58 x 10-8 per base pair per generation (at an average parental age of 7.5 years), much lower than found in direct estimates from great apes (including human, chimpanzee, and gorilla). As in humans, older macaque fathers transmit more mutations to their offspring, approximately 1.5 extra mutations per year in our probands. Mutations at CpG sites accounted for 24% of all observed point mutations. We found that the rate of mutation accumulation after puberty is similar between macaques and humans, but that a smaller number of mutations accumulate before puberty in macaques. We additionally investigated the role of paternal age on offspring sociability, a proxy for normal neurodevelopment. In 203 male macaques studied in large social groups, we found no relationship between paternal age and multiple measures of social function. Our findings are consistent with the hypothesis that the increased risk of neurodevelopmental disorders with paternal age in primates is not primarily due to de novo mutations.

evolutionary biology↗