Skip to content

Dr. Saman Farahmand

Dr. Saman Farahmand

Current Position: Research Senior Scientist, Takeda

Education:

  • Ph.D. in Computational Science, UMass Boston, 2021
  • Master's degree, Health Information Technology, University of Tehran, 2015

Research at MathBioLab: Development of machine learning models for regulatory mechanisms and morphological variations in cancer

Links: LinkedIn | Google Scholar

Biography

Dr. Saman Farahmand was a Ph.D. student and Graduate Research Assistant in the MathBioLab from 2017 to 2021. His research focused on developing innovative machine learning approaches for analyzing high-throughput molecular data in oncology research. His dissertation, titled "Machine Learning Models for Deciphering Regulatory Mechanisms and Morphological Variations in Cancer," combined deep learning techniques with computational biology to address complex biological questions.

After completing his Ph.D., Dr. Farahmand joined Takeda as a Research Scientist and has advanced to Research Senior Scientist, where he continues his work in computational biology, bioinformatics, and machine learning applications.

Publications from MathBioLab

  1. Noorbakhsh J, Farahmand S, Namburi S, Caruana D, Rimm D, et al. (2020). "Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images." Nature Communications, 11(6367).

  2. Farahmand S, Riley T, Zarringhalam K (2020). "ModEx: A text mining system for extracting mode of regulation of Transcription Factor-gene regulatory interaction." Journal of Biomedical Informatics, 102, 103353.

  3. Farahmand S, Fernandez AI, Ahmed FS, Rimm DL, Chuang JH, Zarringhalam K (2022). "Deep learning trained on hematoxylin and eosin tumor region of Interest predicts HER2 status and trastuzumab treatment response in HER2+ breast cancer." Modern Pathology.

  4. Noorbakhsh J, Farahmand S, Foroughi pour A, Namburi S, Caruana D, et al. (2021). "Deep learning identifies conserved pan-cancer tumor features." Clinical Cancer Research, 27(5_Supplement), PO-003-PO-003.

  5. Farahmand S, O'Connor C, Macoska JA, Zarringhalam K (2019). "Causal Inference Engine: a platform for directional gene set enrichment analysis and inference of active transcriptional regulators." Nucleic acids research, 47(22), 11563-11573.

Research Expertise

Dr. Farahmand's research expertise includes:

  • Deep learning for medical image analysis
  • Machine learning applications in cancer research
  • Systems biology and network analysis
  • Computational approaches for multi-omics data integration
  • Development of text mining tools for biomedical literature
  • Predictive modeling for drug response and adverse reactions

Patents

  1. Chuang JHM, Noorbakhsh J, Zarringhalam K, Farahmand S (2022). "Convolutional neural networks for classification of cancer histological images." US Patent App. 17/628,144.

Honors and Awards

  • Dean's Fellowship for Doctoral Studies
  • GSA-Research Funding Grant
  • CSM Doctoral Fellowship

Collaborative Projects

During his time at the MathBioLab, Dr. Farahmand worked on several high-impact collaborative projects:

  1. Deep Learning for Cancer Histopathology Analysis: Collaboration with Yale University School of Medicine, Jackson Laboratory, and Boston University to develop deep learning models for analyzing H&E stained tissue images to predict HER2 status and treatment response in breast cancer patients.

  2. Causal Inference Engine (CIE) for Gene Regulatory Networks: Development of a proprietary R package and web-based tool for detecting active transcription factors, competing with commercial products like Ingenuity Pathway.

  3. Single-Cell RNA-seq Analysis Methods: Development of network-based smoothing and regularized clustering methods for analyzing single-cell RNA-seq data.

  4. Text Mining Pipeline (ModEx): Design and development of an innovative text mining pipeline to extract regulatory activities from biomedical literature, processing citations from 24 million PubMed abstracts.

Dr. Farahmand continues to maintain collaborative relationships with the MathBioLab while advancing his research in computational biology and machine learning at Takeda.