Mohammadali Serajian

Mohammadali Serajian

Auto-generated profile, based on publicly available information

Mohammadali Serajian

University of Florida

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
28 June 2024 in Bioinformatics
Verified
Journal Article
Open access
PDF file
MSMohammadali Serajian
Mohammadali Serajian
SMSimone Marini
Simone Marini
JAJarno N Alanko
Jarno N Alanko
NNNoelle Noyes
Noelle Noyes
MPMattia Prosperi
Mattia Prosperi
CBChristina Boucher
Christina Boucher
World Health Organization estimates that there were over 10 million cases of tuberculosis (TB) worldwide in 2019, resulting in over 1.4 million deaths, with a worrisome increasing trend yearly. The disease is caused by Mycobacterium tuberculosis (MTB) through airborne transmission. Treatment of TB is estimated to be 85% successful, however, this drops to 57% if MTB exhibits multiple antimicrobial resistance (AMR), for which fewer treatment options are available. We develop a robust machine-learning classifier using both linear and nonlinear models (i.e. LASSO logistic regression (LR) and random forests (RF)) to predict the phenotypic resistance of Mycobacterium tuberculosis (MTB) for a broad range of antibiotic drugs. We use data from the CRyPTIC consortium to train our classifier, which consists of whole genome sequencing and antibiotic susceptibility testing (AST) phenotypic data for 13 different antibiotics. To train our model, we assemble the sequence data into genomic contigs, identify all unique 31-mers in the set of contigs, and build a feature matrix M, where M[i, j] is equal to the number of times the ith 31-mer occurs in the jth genome. Due to the size of this feature matrix (over 350 million unique 31-mers), we build and use a sparse matrix representation. Our method, which we refer to as MTB++, leverages compact data structures and iterative methods to allow for the screening of all the 31-mers in the development of both LASSO LR and RF. MTB++ is able to achieve high discrimination (F-1 >80%) for the first-line antibiotics. Moreover, MTB++ had the highest F-1 score in all but three classes and was the most comprehensive since it had an F-1 score >75% in all but four (rare) antibiotic drugs. We use our feature selection to contextualize the 31-mers that are used for the prediction of phenotypic resistance, leading to some insights about sequence similarity to genes in MEGARes. Lastly, we give an estimate of the amount of data that is needed in order to provide accurate predictions. The models and source code are publicly available on Github at https://github.com/M-Serajian/MTB-Pipeline.

29 April 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
MSMohammadali Serajian
Mohammadali Serajian
MLMahsa Lotfollahi
Mahsa Lotfollahi
OGOded Green
Oded Green
KSKaleb Smith
Kaleb Smith
SMSimone Marini
Simone Marini
CBChristina Boucher
Christina Boucher
Multidrug-resistant and extensively drug-resistant Mycobacterium tuberculosis (MTB) represents a growing global health crisis, characterized by limited treatment options and high mortality rates. Rapid and accurate prediction of resistance profiles is critical to guide effective therapy and curb transmission. Whole-genome sequencing (WGS) offers promise for individualized resistance profiling, yet existing computational tools remain constrained by predefined mutation catalogs and prohibitive resource requirements for large-scale analyses. Here, we present AURA, a GPU-accelerated, pangenome-scale machine learning framework for de novo resistance prediction. Trained on 12,185 globally diverse MTB isolates, AURA predicts resistance to 13 first-line, second-line, and repurposed antibiotics with high precision and identifies 59 novel resistance-associated loci, including variants in katG, pncA, rpoC , and members of the PE/PGRS gene family. By enabling model training on an unprecedented genomic scale, AURA provides new insights into the genetic architecture of resistance and establishes a scalable platform for precision-guided therapy and global surveillance of MTB.

25 May 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
MSMohammadali Serajian
Mohammadali Serajian
YHYunheng Han
Yunheng Han
CBChristina Boucher
Christina Boucher
Tuberculosis remains a leading cause of infectious disease mortality, and the continued emergence of drug-resistant Mycobacterium tuberculosis strains threatens the effectiveness of standard treatment regimens. Culture-based antibiotic susceptibility testing remains the clinical reference standard for resistance determination but typically requires six to eight weeks, delaying initiation of optimized therapy for patients with drug-resistant disease. Whole-genome sequencing–based approaches provide a rapid alternative for predicting antimicrobial resistance directly from genomic data and are increasingly being incorporated into diagnostic workflows. This survey reviews computational approaches for genomic resistance prediction in Mycobacterium tuberculosis, focusing on two major classes of methods: catalog-based tools that identify established resistance-conferring variants, and de novo machine learning approaches that infer resistance from genome-wide sequence features. We examine the strengths and limitations of these approaches with respect to interpretability, scalability, computational requirements, and concordance with phenotypic testing. We further discuss emerging directions in quantitative minimum inhibitory concentration prediction, challenges in pyrazinamide susceptibility testing, and the limited availability of resistant isolates for newer and repurposed drugs used in multidrug-resistant tuberculosis and extensively drug-resistant tuberculosis treatment regimens. Continued expansion of paired phenotypic and genomic datasets, standardized minimum inhibitory concentration testing protocols, and rigorous lineage-aware evaluation frameworks will be essential for improving the clinical reliability and global deployment of genomic resistance prediction for tuberculosis diagnostics.

21 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
RVRahul Varki
Rahul Varki
MSMohammadali Serajian
Mohammadali Serajian
CSCannon Spencer
Cannon Spencer
AHAaron Hong
Aaron Hong
OGOded Green
Oded Green
CBChristina Boucher
Christina Boucher
The factorization is a core primitive in lossless data compression and serves as a building block for many compressed data structures used in practice, particularly on large and highly repetitive datasets. While a substantial literature has developed linear-time and space-efficient algorithms for computing the LZ77 factorization, these methods are almost exclusively designed for sequential execution on CPUs and do not readily exploit modern parallel hardware. In this work, we present GZLZ, the first algorithm for computing the LZ77 factorization that is explicitly designed for execution on GPUs. To address GPU memory constraints, the algorithm uses shared-memory optimizations and a hybrid execution model that enables processing of inputs that exceed device memory capacity, with limited coordination on the CPU. We evaluate GZLZ on large and highly repetitive datasets and compare it against state-of-the-art CPU-based implementations. Our results show that GZLZ reduces construction time while remaining robust across a range of input sizes and hardware configurations. Beyond these performance gains, this work highlights several open challenges in adapting classical string algorithms to GPU architectures, including the need for fully GPU-resident suffix array construction and more scalable parallel approaches to longest common extension computation.