Assistant Professor of Biomedical Informatics
Harvard Medical School
Dr. Farhat is an Assistant Professor of of
Biomedical Informatics atHarvard Medical School and a a practicing physician at
the Massachusetts General Hospital Division of Pulmonary and Critical Care
Medicine.
Dr. Farhat's research focuses on the development and application of methods for associating genotype and phenotype in infectious disease pathogens, with a strong emphasis on translation to better diagnostics and surveillance in resource-poor settings. Farhat's work has focused on bacterial and viral pathoges and spans the spectrum from computational analysis to field studies. She is PI and Co-Investigator on several large projects funded by NIH including the NIAID and the BD2K initiative.
Maha Farhat holds an MD from the McGill University Faculty of Medicine and a MSc in biostatistics from the Harvard Chan School of Public Health.
Assistant Professor of Biomedical Informatics
Harvard Medical School
Dr. Farhat is an Assistant Professor of of
Biomedical Informatics atHarvard Medical School and a a practicing physician at
the Massachusetts General Hospital Division of Pulmonary and Critical Care
Medicine.
Dr. Farhat's research focuses on the development and application of methods for associating genotype and phenotype in infectious disease pathogens, with a strong emphasis on translation to better diagnostics and surveillance in resource-poor settings. Farhat's work has focused on bacterial and viral pathoges and spans the spectrum from computational analysis to field studies. She is PI and Co-Investigator on several large projects funded by NIH including the NIAID and the BD2K initiative.
Maha Farhat holds an MD from the McGill University Faculty of Medicine and a MSc in biostatistics from the Harvard Chan School of Public Health.
Journal article
There is considerable interest in training machine learning (ML) models on genomic data that achieve clinical grade diagnostic accuracy. Many successful ML models have been trained and validated on binary tasks because predicting biomedically relevant continuous variables is difficult to optimize. In this work, we present convolutional neural networks (CNNs) that predict minimum inhibitory concentrations (MICs) for eight antibiotics from Mycobacterium tuberculosis complex (MTBC) gene sequences....
Journal article
No abstract