Maha Reda Farhat

The paper predicts antibiotic resistance mutations in Mycobacterium tuberculosis by integrating structural context with mutation data, finding that structural clustering improves prediction accuracy.

Complete genomes from 151 clinical M. tuberculosis isolates show gene conversion between paralogs creating diversity hotspots in PE/PPE/ESX genes and T cell antigens, including PPE18.

The paper identifies SSR INDELs in Mycobacterium tuberculosis that alter antibiotic susceptibility through phylogenomic analysis and experimental validation.

This paper evaluates active learning strategies for whole-cell antibiotic discovery, finding an optimal approach that significantly improves hit rates and generalizability across bacterial species.

This study benchmarks seven variant callers for detecting low-frequency variants in M. tuberculosis using simulated short-read data, finding FreeBayes performs best and introducing an error model to filter false positives.

BIG-TB evaluates sequence-based machine learning models for predicting antibiotic resistance and variant attribution using *Mycobacterium tuberculosis* genomes, showing DNA-based models outperform protein-based ones.

This study identifies factors affecting the success of direct sputum whole genome sequencing for Mycobacterium tuberculosis, highlighting optimal pre-processing steps and the negative impact of sodium hydroxide decontamination.

The paper evaluates pan-genome analysis methods using M. tuberculosis isolates, finding that annotation discrepancies and assembly quality affect results, and introduces panqc to address these issues.

Fleming is an AI agent that identifies lead compounds for Mycobacterium tuberculosis by combining discriminative and generative models, achieving higher discrimination and hit rates than alternative approaches.

This paper shows that standard protein language models do not support evolutionary reasoning, but a new model trained with phylogenetic supervision performs better on tree reconstruction and clustering.

This paper evaluates how well deep learning models generalize to new molecular sequences using a new framework called SPECTRA across 18 datasets and 19 models.

The paper quantifies the MTBC pangenome, revealing a small, closed genome with lineage-specific regions of difference and implications for virulence and drug resistance.

The paper evaluates DNA decontamination methods and a new target enrichment protocol to improve Mycobacterium tuberculosis whole-genome sequencing from direct patient samples.

The paper identifies conserved regions in ESX-1 related proteins by mapping SNVs from MTB isolates onto protein structures, highlighting potential therapeutic targets.

The paper shows that phylogenetic clustering in Mycobacterium abscessus is linked to reduced mutation rates and DNA repair gene variation, suggesting adaptation rather than transmission as the cause.

This paper presents a deep convolutional neural network to predict antibiotic resistance in M. tuberculosis isolates, achieving state-of-the-art accuracy and enabling interpretable feature analysis.

The paper identifies genome-wide mutational dependencies in Mycobacterium tuberculosis evolution, showing how mutations interact to confer antibiotic resistance and detect environmental pressures.

GenTB predicts tuberculosis drug resistance from genomic data using machine learning, achieving higher sensitivity than existing tools with slightly lower specificity.

The paper demonstrates epistatic interactions in Mycobacterium tuberculosis complex that can reverse antibiotic resistance, specifically showing that eis promoter mutations cannot confer resistance if paired with LoF mutations in the eis coding region.

The paper evaluates short-read variant calling accuracy in Mycobacterium tuberculosis using Illumina and PacBio data, finding high precision with optimized mapping thresholds and identifying 68% of excluded repetitive regions as accurately called.

This study analyzes global M. tuberculosis whole genome sequences to trace the temporal and geographic patterns of drug resistance acquisition and its correlation with country wealth.

The paper analyzes global S. maltophilia strains to show genetic diversity and intra-hospital transmission.

The paper analyzes M. tuberculosis population dynamics during treatment failure using whole-genome sequencing data from clinical isolates to identify resistance mutations and in-host evolutionary patterns.

GenomegaMap estimates genome-wide dN/dS ratios across 10,209 tuberculosis genomes to identify selection pressures shaping the pathogen's evolution.

This study uses a multitask deep learning model to predict tuberculosis drug resistance from genomic data, achieving high accuracy in both first-line and second-line drug resistance prediction.

This study identifies 38 loci and 250 epistatic pairs affecting antibiotic resistance in Neisseria gonorrhoeae using evolutionary couplings.