Saleh Sereshki
​
Home
Bio? You mean Bioinformatics?
I am Saleh and I'm a fifth year Ph.D. student in Computer Science at the University of California Riverside under the supervision of an esteemed computer scientist, Stefano Lonardi. My Ph.D. focuses on using Machine Learning methods on genetic datasets. I completed my undergrad at Sharif University of Technology. Besides that, I was an Android developer and developed several innovative applications. I enjoy a variety of hobbies: I am an adept soccer player, I play the Sitar and the Piano, and I have a passion for photography and cinema. I am quite certain that in the future, I will make a movie, at least a short one.
Research
On the prediction of Non-CG DNA methylation using machine learning (2022)
We introduced AMPS a convolutional neural network-based model to predict DNA methylation from sequence context. We tested our model on 6 plants and compared our results with the state-of-the-art methods. This paper is published on NAR genomics and bioinformatics.
A Drug Repurposing Approach Reveals Targetable Epigenetic Pathways in Plasmodium vivax Hypnozoites (2021)
We've found that certain DNA-modifying drugs could offer a new way to tackle this stage of the infection.
Prediction of TET and DNMT3 activity using transformer-based models (2023)
We introduced L-MAP a tool that utilizes DNABERT a transformer-based model to predict the activity domains of TET and DNMT3 two most important enzymes working together on cytosine methylation in the mammalian genome.
Studying the effect of epigenomics on SNP rate of Arabidopsis Thaliana (2023)
We studied the correlation and predictability of SNP rate and SNP biases in the Arabidopsis genome by a set of epigenomic features. We checked this hypothesis on different accessions of Arabidopsis as well as SNPs from 1001 genomics.
Copy number variation detectoin in Tyroid Cancer RNA-seq single cell data (2020)
For thyroid normal and cancer single cells, we applied batch effect removal tools before cell annotation, followed by analyzing the copy number variation of the samples.
MotorCycle detection in highway from traffic cameras (2014)
Utilizing traffic camera footage and opencv to accurately detect motorcycles on highways, aiming to improve road safety and traffic flow
University of California, Riverside, 169 Aberdeen Dr, Riverside, CA 92507