What is Bioinformatics?

Bioinformatics is the interdisciplinary field that combines biology, computer science, mathematics, and statistics to analyze and interpret biological data. It’s essential for handling huge datasets such as DNA/RNA sequences, protein structures, gene expression data, and medical images — helping researchers discover new genes, understand diseases, and develop new treatments.

Biological Data Analysis

focuses on interpreting genomic, proteomic, and other molecular datasets to extract meaningful biological insights.

Statistics & Probability

provide methods to quantify variation, test significance, and validate experimental results.

Algorithms & Computational Methods

deliver efficient ways to search, align, and analyze large biological sequences and networks.

Programming & Software Development

enables building custom tools, pipelines, and platforms to process and visualize data.

Machine Learning & Deep Learning

uncover hidden patterns and make predictive models from complex biological data.

Data Management & Big Data Infrastructure

handle the storage, organization, and accessibility of massive biological datasets.

From Molecules to Machines

Driving Innovation in Bioinformatics

With a foundation in bioinformatics and data science, and now as Head of Technology and Innovation at MOLEQLAR Analytics, I bridge life sciences and advanced computing to turn complex biological data into actionable insights. My experience spans mass spectrometry-based proteomics, epigenetics, and deep learning, complemented by expertise in cloud infrastructure, algorithm design, and innovation strategy. Combining scientific curiosity with technological leadership, I develop data-driven solutions that accelerate discovery and push the boundaries of biotech innovation.

Molecular Data Science

I develop computational methods to analyze complex biological datasets from genomics, proteomics, and epigenetics. This includes high-resolution mass spectrometry data processing, feature extraction, and integration of multi-omics datasets to uncover molecular signatures and pathways that shape health outcomes.

Artificial Intelligence & Algorithms

I design and apply machine learning and deep learning models to recognize patterns in high-dimensional biological data. From neural network architectures for MS1 sample classification to algorithmic optimization of data pipelines, my work transforms raw data into predictive and interpretable models

Data Infrastructure & Innovation

I create robust big data infrastructures and cloud-based analysis environments that enable reproducible research. This includes designing secure data pipelines on AWS, integrating automation tools, and aligning cutting-edge technology with scientific goals to accelerate discovery and innovation.

Example: Prediction of the charge state of peptides in LC-MS experiments

This work stems from a project I conducted during my studies, where I explored predicting the precursor charge states of peptides in LC-MS experiments using the PROSPECT dataset. To tackle this task, I developed various deep learning models and architectures from scratch, primarily as multi-class classification models based on embedding layers with dense networks, and also experimented with multi-head and multilabel approaches. The following figures illustrate example prediction performances of these models.