Skip to content
View sajfb's full-sized avatar

Block or report sajfb

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sajfb/README.md

CRAN stats Python PyTorch LinkedIn Google Scholar

I'm an award-winning data scientist bridging cheminformatics and metabolomics with a focus on small molecule discovery and mass spectrometry data sciences.

For more details about my work and recognition:

  • Read my award news from the Metabolomics Association of North America (MANA).
  • View my presentation details here.

I've developed multiple computational pipelines for untargeted mass spectrometry data processing across domains such as metabolomics, lipidomics, exposomics, and environmental studies. My development philosophy emphasizes maximal automation, high precision, multi-platform compatibility, and user-friendly interfaces to minimize extensive lab-based experiments. I’m also driven to advance next-generation AI for chemistry and biological applications.

Developing AI-Powered Digital Twin Replicas for Bioreactors at Aropha

At Aropha, I lead the development of digital twins for bioreactors—high-fidelity virtual replicas that enable accurate performance prediction, real-time process monitoring, and data-driven decision-making in dynamic bioproduction workflows. By integrating state-of-the-art AI with bioprocess engineering, our approach enhances process control, reduces experimental costs, and accelerates optimization.

Explore our digital twin platform for batch processing simulations.

Completed Projects

Mass Spectrometry Data Processing Workflows

At the Integrated Data Science Laboratory for Metabolomics and Exposomics, I developed an end-to-end untargeted metabolomics workflow to efficiently process and annotate large-scale mass spectrometry data. This workflow minimizes reliance on purely data-driven methods by leveraging stable isotopic principles that underpin biochemistry and organic chemistry.

Comprehensive Untargeted Metabolomics Workflow

Environmental Cheminformatics and PhD Research Projects

During my doctoral research, I developed computational mass spectrometry pipelines for environmental cheminformatics projects.

  • Isotopic Profile Deconvoluted Chromatogram (IPDC):
    An algorithm designed to screen complex environmental matrices for unknown contaminants using chemometric methods. The IPDC algorithm was successfully applied in five projects during my PhD.
    Explore the project

Pinned Loading

  1. idslme/IDSL_MINT idslme/IDSL_MINT Public

    A Deep Learning Framework to Interpret Raw Mass Spectrometry (m/z) Data

    Python 19 1

  2. idslme/IDSL.IPA idslme/IDSL.IPA Public

    Intrinsic Peak Analysis (IPA) pipeline for peak-picking in large-scale untargeted small molecule analysis including metabolomics, lipidomics, exposomics, and environmental studies.

    R 13 1

  3. idslme/IDSL.UFA idslme/IDSL.UFA Public

    United Formula Annotation (UFA) for LC-HRMS data

    R 8 1

  4. idslme/IDSL.CSA idslme/IDSL.CSA Public

    Composite Spectra Analysis

    R 5