MohammadReza KarimiNejad

MohammadReza KarimiNejad

Auto-generated profile, based on publicly available information

MohammadReza KarimiNejad

Department of Computer Engineering, Sharif University of Technology, Tehran, Iran

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 September 2024 in bioRxiv
Verified
Preprint
Open access
PDF file
AAAli Akbari
Ali Akbari
ABAlison R. Barton
Alison R. Barton
SGSteven Gazal
Steven Gazal
ZLZheng Li
Zheng Li
MKMohammadreza Kariminejad
Mohammadreza Kariminejad
DRDavid Reich
David Reich
We present a method for detecting evidence of natural selection in ancient DNA time-series data that leverages an opportunity not utilized in previous scans: testing for a consistent trend in allele frequency change over time. By applying this to 8433 West Eurasians who lived over the past 14000 years and 6510 contemporary people, we find an order of magnitude more genome-wide significant signals than previous studies: 347 independent loci with >99% probability of selection. Previous work showed that classic hard sweeps driving advantageous mutations to fixation have been rare over the broad span of human evolution, but in the last ten millennia, many hundreds of alleles have been affected by strong directional selection. Discoveries include an increase from ∼0% to ∼20% in 4000 years for the major risk factor for celiac disease at HLA-DQB1 ; a rise from ∼0% to ∼8% in 6000 years of blood type B; and fluctuating selection at the TYK2 tuberculosis risk allele rising from ∼2% to ∼9% from ∼5500 to ∼3000 years ago before dropping to ∼3%. We identify instances of coordinated selection on alleles affecting the same trait, with the polygenic score today predictive of body fat percentage decreasing by around a standard deviation over ten millennia, consistent with the “Thrifty Gene” hypothesis that a genetic predisposition to store energy during food scarcity became disadvantageous after farming. We also identify selection for combinations of alleles that are today associated with lighter skin color, lower risk for schizophrenia and bipolar disease, slower health decline, and increased measures related to cognitive performance (scores on intelligence tests, household income, and years of schooling). These traits are measured in modern industrialized societies, so what phenotypes were adaptive in the past is unclear. We estimate selection coefficients at 9.9 million variants, enabling study of how Darwinian forces couple to allelic effects and shape the genetic architecture of complex traits.

30 June 2025 in medRxiv
Verified
Preprint
Open access
PDF file
MKMohammadReza KarimiNejad
MohammadReza KarimiNejad
NSNarges SangaraniPour
Narges SangaraniPour
YNYasmin Naji
Yasmin Naji
MSMohammad Shafiezadeh
Mohammad Shafiezadeh
RTReza Tavakoli
Reza Tavakoli
MRMohammad Hossein Rohban
Mohammad Hossein Rohban
Predicting variant-drug interactions is essential for advancing precision medicine across therapeutic areas. The Pharmacogenomics Knowledge Base (PharmGKB) dataset, with ~11,000 samples, is underutilized in machine learning (ML) due to its limited size. After filtering for variant mappings and excluding metabolizer-related conditions, we obtain ~4,000 samples for a six-class prediction task (increasing or decreasing toxicity, efficacy, and dosage). We introduce VarDrug, the first ML framework for variant-drug interaction prediction using PharmGKB, designed to model interactions between genetic variants and drugs. VarDrug integrates a self-supervised VariantEncoder pre-trained on 100,000 GRCh38 variants, Fingerprint method for drug encoding, and gene co-expression profiles for enhanced variant representation. Using SMOTE for class balancing and 5-fold cross-validation, we evaluate five ML models (CatBoost, RandomForest, ExtraTree, DecisionTree, SVC) against label encoding and rule-based baselines. RandomForest achieves a weighted F1 score of 90%, significantly outperforming baselines (best weighted F1: 68%). Ablation studies confirm the VariantEncoder’s critical role, while a case study on psychiatric disorders, focusing on borderline personality disorder (BPD), demonstrates biological plausibility with alignment to known pharmacogenetic annotations for genes like ABCB1 and CYP2D6. VarDrug’s approach, mapping drug-gene and mechanism-of-action-gene interactions, offers a scalable framework for optimizing treatment strategies and reducing adverse drug reactions across pharmacogenomic applications.