Luca Annecchino joined BioPharmaSpec earlier this year as an R&D Scientist to lead our Bioinformatics and Software Development Programme, developing methods and algorithms to aid data interpretation during our structural and physicochemical characterization studies of biopharmaceuticals.
Luca’s background is in Computer Engineering, Micro and Nano Technology, Neural Interfaces and Electrophysiology, with a Ph.D. in Bioengineering and Neuroscience from Imperial College (2017). Luca also has an industrial background in health applications with Bios Health and Boston Scientific.
We took this opportunity to ask Luca a few questions to help us understand this evolving scientific area.
Bioinformatics is a multidisciplinary field at the interface between biology and information technology that plays a crucial role in modern life sciences. It has been defined as “the science of collecting and analyzing complex biological data”.
The integration of Artificial Intelligence (AI) has further enhanced bioinformatic capabilities, transforming experimental data into actionable insights that drive research, development, and innovation. AI refers to computer algorithms programmed to learn and perform complex tasks that typically require specialized human intelligence. Machine learning (ML), a subset of AI, involves the development of algorithms and statistical models that learn from data and make predictions without explicitly requiring programing.
As the volume of biological data expands exponentially, the synergy between bioinformatics and AI/ML is becoming essential in managing and interpreting the vast volumes of biological and clinical data with applications spanning genomics, proteomics, drug discovery, and personalized medicine. This is especially true for the analytics and characterization work we focus on at BioPharmaSpec, where the complexity and volume of the mass spectrometric data generated can be overwhelming.
To address this burgeoning complexity, we have been developing several bioinformatic and AI tools to optimize the management, annotation, analysis and interpretation of vast datasets starting with Host Cell Protein (HCP) analytics.
HCPs are a major concern in biopharmaceutical production and these contaminants must be minimized to ensure the purity and safety of therapeutic products. It's crucial to check HCPs early in product development to demonstrate the effectiveness of purification processes.
HCP identification and quantitation are achieved by combining information dependent acquisition (IDA) and sequential window acquisition of all theoretical mass spectra (SWATH MS) acquisitions of proteolytic digests of product material.
The workflow involves steps for noise filtering, signal calibration and normalization, and several algorithms can be used for matching any significant mass spectrometric signal with protein databases to identify and quantify HCPs present in the sample. All these steps are crucial to perform quantitative analysis and so determine the abundance of each HCP across different production batches or purification steps. AI and ML techniques can then be deployed to detect patterns and predict potential HCPs that might co-purify with the therapeutic protein, facilitating proactive measures to mitigate contamination.
Integrating automation and AI into our characterization studies offers several benefits to our clients:
In essence, Bioinformatics plays a key role in helping BioPharmaSpec expert scientists organize, analyze and interpret the complex data obtained from their analyses to enable our clients to make fully informed decisions regarding their product’s development journey.
Unlock deeper insights and accelerate your biopharmaceutical development with BioPharmaSpec’s advanced bioinformatics solutions.
