Albert M.

Bioinformatics Expert Specializing in Genome Annotation and ML

I am a highly skilled bioinformatician with extensive experience in genome annotation, machine learning, and data analysis. My goal is to leverage my expertise to help you decode complex biological data, uncovering insights that drive your research and development projects forward. Whether you need assistance with genome assembly, gene prediction, or developing predictive models for early-stage cancer detection, I am here to deliver high-quality, data-driven solutions. Services Offered: Genome Assembly and Annotation: Assembling genomes from raw sequencing data Annotating genes and predicting gene functions Utilizing tools like SPAdes, Prodigal, Glimmer, and Barrnap Bioinformatics Data Analysis: Analyzing RNA-Seq data to determine gene expression levels Conducting metagenomics studies to explore microbial communities Implementing quality control measures to ensure data integrity Machine Learning for Genomics: Developing predictive models for early-stage cancer detection using ctDNA datasets Applying supervised learning algorithms such as logistic regression, random forests, and support vector machines Performing feature engineering and variant annotation to enhance model performance Custom Bioinformatics Pipelines: Creating and optimizing bioinformatics pipelines for seamless data processing Automating data analysis workflows to increase efficiency and reproducibility Scripting in Python, R, and bash for robust and scalable solutions Experience Highlights: Genome Annotation Project: Led a comprehensive project to annotate the genome of Bacillus thuringiensis. Utilized a combination of Prodigal, Glimmer, and Barrnap to predict genes and ribosomal RNA. Applied homology searches to validate predicted genes, resulting in a detailed and accurate genome annotation. Predictive Modeling for Cancer Detection: Developed an artificial neural network (ANN) to predict the efficacy of cancer drugs based on tumor genomic profiles. This model achieved over 85% accuracy, demonstrating its potential for personalized medicine applications. Transcriptomics Analysis: Conducted RNA-Seq analysis to compare gene expression levels at different time points. Utilized tools like minimap2 and bam-readcount to map reads to the reference genome and quantify gene expression, providing valuable insights into gene regulation. Key Projects: Targeted Membrane Disruption by Parasporin-2 in Cancer Cells: Conducted research on the cytotoxic effects of Parasporin-2, a Bacillus thuringiensis crystal protein, on human liver and colon cancer cells using computational biology. Investigated the toxin's cell membrane interaction, focusing on N-terminal cleavage and C-terminal damage induction. Utilized molecular dynamics simulations, protein-protein interaction analyses, and mutational studies to enhance toxin efficacy and specificity. Employed machine learning to improve predictive models for Parasporin-2's binding affinity and cytotoxic effects, contributing to targeted cancer therapy development. Neural Network for Ideal Cancer Drug Prediction Based on Tumor Profile: Designed and implemented an artificial neural network (ANN) to predict optimal cancer drug efficacy based on genomic information of tumor cell lines, achieving an accuracy of 85% or higher. Utilized comprehensive data from public databases on cancer drug responses and preclinical research trials. Project executed in collaboration with the University of Maryland, Global Campus. Skills and Tools: Programming Languages: Python, R, SQL, bash Machine Learning Frameworks: TensorFlow, Keras, Scikit-learn, PyTorch Bioinformatics Tools: SPAdes, Prodigal, Glimmer, Barrnap, BLAST, Clustal Omega, GATK, BEDTools, BioPython Protein Analysis Tools: PSI-BLAST, Pymol, Swiss-Model, Protein Data Bank Data Analysis Tools: ArcGIS, QGIS, Geostatistics, Map Algebra, Shell Scripting Data Quality Control: Experienced in data cleaning, normalization, and quality control processes Education: PhD in Bioinformatics & Computational Biology, George Mason University: Currently ABD (All But Dissertation) Masters in Biotechnology with Bioinformatics, University of Maryland Global Campus: GPA: 3.66 Bachelors in Anthropology with Geospatial Technologies, Southern New Hampshire University: Graduated Summa Cum Laude, GPA: 3.87 Why Choose Me: I am committed to delivering precise, reliable, and actionable bioinformatics solutions. My approach combines rigorous scientific methodologies with innovative machine learning techniques to address complex biological questions. Let’s collaborate to transform your raw data into meaningful insights that propel your projects forward. Contact Me: Ready to get started? Contact me today to discuss your project requirements and how I can help you achieve your goals.


  • Machine Learning
  • Machine Learning Model
  • Linux
  • Java
  • Information Analysis
  • Unix
  • Geospatial Data