Fahimeh Rahimi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fahimeh Rahimi has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Juannan Zhou
Department of Biology, University of Florida , Gainesville, FL 32611
3 shared publications Amber Singh
Department of Biology, University of Florida , Gainesville, FL 32611
2 shared publicationsBenjamin Eickwort
Department of Biology, University of Florida , Gainesville, FL 32611
2 shared publications- Charles F. Baer
Department of Biology, University of Florida , Gainesville, FL
2 shared publications - Erik C. Andersen
Department of Biology, Johns Hopkins University , Baltimore, MD 21218
2 shared publications Michael Snyder
Department of Biology, University of Florida , Gainesville, FL 32611
2 shared publications
Latest Publications
- Open Access
sorAI - a suite of machine learning models to predict plant polyploidy from target capture data
Premise: Polyploidy is a persistent feature of land plant evolution, yet it is often difficult to determine the ploidy of individual plants. The growing abundance of target capture data and other high throughput sequence datasets across plant species has generated interest in methods to infer ploidy from these data. We leverage chromosome count data and target capture data from the GoFlag probe set in ferns to train new machine learning models to infer if a sample is from a diploid or polyploid genome. Methods and Results: We trained a convolutional neural network (CNN) for each GoFlag probe locus and developed ensemble models that use two loci and a random forest model that leverages all the loci to classify fern samples as diploid or polyploid. We tested the performance of these models using held-out test datasets of GoFlag target capture data across ferns and an independent test set from the genus Lygodium . We also performed experiments to evaluate the features of loci and sequences most associated with model performance and tested the performance of the models as sequence depth decreased. Conclusions: These models, collectively named sorAI, outperform the frequency-based methods nQuire and nQuack on held-out test datasets of GoFlag target capture data across ferns. These models are capable of leveraging positional information and covariation among nucleotide sites beyond individual-site allele frequencies, and they perform well even with low sequence coverage. The random forest model, which uses all loci, appears to be robust to varying dataset features and achieves an accuracy of approximately 71–78% across test datasets and sequencing depths. sorAI is available at https://github.com/Fahimehgit/sorai , and the trained models are available at https://huggingface.co/Fahimehr140/sorai .
Open AccesssorAI - a suite of machine learning models to predict plant polyploidy from target capture data
Premise: Polyploidy is a persistent feature of land plant evolution, yet it is often difficult to determine the ploidy of individual plants. The growing abundance of target capture data and other high throughput sequence datasets across plant species has generated interest in methods to infer ploidy from these data. We leverage chromosome count data and target capture data from the GoFlag probe set in ferns to train new machine learning models to infer if a sample is from a diploid or polyploid genome. Methods and Results: We trained a convolutional neural network (CNN) for each GoFlag probe locus and developed ensemble models that use two loci and a random forest model that leverages all the loci to classify fern samples as diploid or polyploid. We tested the performance of these models using held-out test datasets of GoFlag target capture data across ferns and an independent test set from the genus Lygodium . We also performed experiments to evaluate the features of loci and sequences most associated with model performance and tested the performance of the models as sequence depth decreased. Conclusions: These models, collectively named sorAI, outperform the frequency-based methods nQuire and nQuack on held-out test datasets of GoFlag target capture data across ferns. These models are capable of leveraging positional information and covariation among nucleotide sites beyond individual-site allele frequencies, and they perform well even with low sequence coverage. The random forest model, which uses all loci, appears to be robust to varying dataset features and achieves an accuracy of approximately 71–78% across test datasets and sequencing depths. sorAI is available at https://github.com/Fahimehgit/sorai , and the trained models are available at https://huggingface.co/Fahimehr140/sorai .
- Open Access
Genetic background shapes AI-predicted variant effects
Predicting the consequences of genetic variants remains a major goal in biomedicine. Conventional approaches typically assess single-nucleotide variants in the context of a single reference genome, without accounting for genetic diversity that can modulate variant effects. Here we introduce the personalized variant effect predictor (pVEP) framework, which quantifies how genetic background across thousands of human genomes from globally diverse populations shapes computational predictions of clinical variant effects. Across deep learning models spanning protein structure, splicing, and noncoding regulation, pVEP reveals that many clinical variants exhibit heterogeneous predicted effects across haplotypes, with the same variant predicted to be pathogenic in some genetic backgrounds and benign in others. We find support for underlying molecular mechanisms, including shifts in predicted protein contacts and changes in splice-site recognition. Overall, personalized genomic context emerges as a systematically underappreciated variable in variant annotation and clinical interpretation, with particular implications for genetically diverse populations.
Open AccessGenetic background shapes AI-predicted variant effects
Predicting the consequences of genetic variants remains a major goal in biomedicine. Conventional approaches typically assess single-nucleotide variants in the context of a single reference genome, without accounting for genetic diversity that can modulate variant effects. Here we introduce the personalized variant effect predictor (pVEP) framework, which quantifies how genetic background across thousands of human genomes from globally diverse populations shapes computational predictions of clinical variant effects. Across deep learning models spanning protein structure, splicing, and noncoding regulation, pVEP reveals that many clinical variants exhibit heterogeneous predicted effects across haplotypes, with the same variant predicted to be pathogenic in some genetic backgrounds and benign in others. We find support for underlying molecular mechanisms, including shifts in predicted protein contacts and changes in splice-site recognition. Overall, personalized genomic context emerges as a systematically underappreciated variable in variant annotation and clinical interpretation, with particular implications for genetically diverse populations.
- 26 March 2026
- Published by Oxford University Press (OUP) in Genetics
- Vol. 233 (1)
Evolution of the rate, molecular spectrum, and fitness effects of mutation under minimal selection in Caenorhabditis elegans
The rate, molecular spectrum, and fitness effects of mutations vary at all levels of the biological hierarchy, from within individual genomes to among taxonomic domains. Understanding the evolutionary factors underpinning that variation is of fundamental importance to biology. Accurate quantification of the properties of mutations requires that other evolutionary forces, especially natural selection, be minimized as much as possible. To investigate the evolution of the mutational process in C. elegans, we propagated a set of 100 “first order” mutation accumulation (O1MA) lines under minimal selection for ∼150 generations, divided each O1MA line into two “second order” MA (O2MA) lines and propagated them for another ∼150 generations, at which time the genome of each O2MA line was sequenced, and a subset of 50 O1MA families was assayed for competitive fitness. Over the course of the experiment, the mean nucleotide substitution mutation rate did not change, but the variance increased. In contrast, the indel mutation rate increased significantly. The two types of mutations fulfill the predictions of different theoretical models for the evolution of mutation rate. These results reinforce previous findings that the rate of indels is more sensitive to endogenous stress than the rate of nucleotide substitutions. Several evolutionary quandaries could be resolved if deleterious mutations interact synergistically (negative epistasis). Evidence for synergistic epistasis is famously inconclusive, although there is reason to think it may be more detectable under competitive conditions. However, a model of constant mutational effects on competitive fitness explains the results significantly better than a model including epistasis.
- 26 March 2026
- Published by Oxford University Press (OUP) in Genetics
- Vol. 233 (1)
Evolution of the rate, molecular spectrum, and fitness effects of mutation under minimal selection in Caenorhabditis elegans
The rate, molecular spectrum, and fitness effects of mutations vary at all levels of the biological hierarchy, from within individual genomes to among taxonomic domains. Understanding the evolutionary factors underpinning that variation is of fundamental importance to biology. Accurate quantification of the properties of mutations requires that other evolutionary forces, especially natural selection, be minimized as much as possible. To investigate the evolution of the mutational process in C. elegans, we propagated a set of 100 “first order” mutation accumulation (O1MA) lines under minimal selection for ∼150 generations, divided each O1MA line into two “second order” MA (O2MA) lines and propagated them for another ∼150 generations, at which time the genome of each O2MA line was sequenced, and a subset of 50 O1MA families was assayed for competitive fitness. Over the course of the experiment, the mean nucleotide substitution mutation rate did not change, but the variance increased. In contrast, the indel mutation rate increased significantly. The two types of mutations fulfill the predictions of different theoretical models for the evolution of mutation rate. These results reinforce previous findings that the rate of indels is more sensitive to endogenous stress than the rate of nucleotide substitutions. Several evolutionary quandaries could be resolved if deleterious mutations interact synergistically (negative epistasis). Evidence for synergistic epistasis is famously inconclusive, although there is reason to think it may be more detectable under competitive conditions. However, a model of constant mutational effects on competitive fitness explains the results significantly better than a model including epistasis.
- Open Access
Evolution of the rate, molecular spectrum, and fitness effects of mutation under minimal selection in Caenorhabditis elegans
The rate, molecular spectrum, and fitness effects of mutations vary at all levels of the biological hierarchy, from within individual genomes to among taxonomic domains. Understanding the evolutionary factors underpinning that variation is of fundamental importance to biology. Accurate quantification of the properties of mutations requires that other evolutionary forces, especially natural selection, be minimized as much as possible. To investigate the evolution of the mutational process in C. elegans , we propagated a set of 100 “first order” mutation accumulation (O1MA) lines under minimal selection for ∼150 generations, divided each O1MA line into two “second order” MA (O2MA) lines and propagated them for another ∼150 generations, at which time the genome of each O2MA line was sequenced, and a subset of 50 O1MA families was assayed for competitive fitness. Over the course of the experiment, the mean nucleotide substitution mutation rate did not change, but the variance increased. In contrast, the indel mutation rate increased significantly. The two types of mutations fulfill the predictions of different theoretical models for the evolution of mutation rate. These results reinforce previous findings that the rate of indels is more sensitive to endogenous stress than the rate of nucleotide substitutions. Several evolutionary quandaries could be resolved if deleterious mutations interact synergistically (negative epistasis). Evidence for synergistic epistasis is famously inconclusive, although there is reason to think it may be more detectable under competitive conditions. However, a model of constant mutational effects on competitive fitness explains the results significantly better than a model including epistasis.
Open AccessEvolution of the rate, molecular spectrum, and fitness effects of mutation under minimal selection in Caenorhabditis elegans
The rate, molecular spectrum, and fitness effects of mutations vary at all levels of the biological hierarchy, from within individual genomes to among taxonomic domains. Understanding the evolutionary factors underpinning that variation is of fundamental importance to biology. Accurate quantification of the properties of mutations requires that other evolutionary forces, especially natural selection, be minimized as much as possible. To investigate the evolution of the mutational process in C. elegans , we propagated a set of 100 “first order” mutation accumulation (O1MA) lines under minimal selection for ∼150 generations, divided each O1MA line into two “second order” MA (O2MA) lines and propagated them for another ∼150 generations, at which time the genome of each O2MA line was sequenced, and a subset of 50 O1MA families was assayed for competitive fitness. Over the course of the experiment, the mean nucleotide substitution mutation rate did not change, but the variance increased. In contrast, the indel mutation rate increased significantly. The two types of mutations fulfill the predictions of different theoretical models for the evolution of mutation rate. These results reinforce previous findings that the rate of indels is more sensitive to endogenous stress than the rate of nucleotide substitutions. Several evolutionary quandaries could be resolved if deleterious mutations interact synergistically (negative epistasis). Evidence for synergistic epistasis is famously inconclusive, although there is reason to think it may be more detectable under competitive conditions. However, a model of constant mutational effects on competitive fitness explains the results significantly better than a model including epistasis.