Artificial Neural Networks: Applications in Biosciences
The book "Artificial Neural Networks: Applications in Biosciences," edited by Hugh Cartwright and part of the Methods in Molecular Biology series, provides detailed, expert-guided protocols and examples of ANN applications across diverse biological fields—including intracellular sorting, bacterial behavior prediction, biometric authentication, tuberculosis studies, cancer gene signatures, metabolite identification, visual navigation, and computer diagnosis—while featuring a notable chapter by Charles Fracchia on secure, scalable biomedical data collection and labeling essential for effective machine learning workflows.
Artificial Neural Networks
Editor: Hugh Cartwright
Methods in Molecular Biology | Springer Protocols
- Includes cutting-edge methods and protocols
- Provides step-by-step detail essential for reproducible results
- Contains key notes and implementation advice from the experts
“This volume presents examples of how Artificial Neural Networks (ANNs) are applied in biological sciences and related areas. Chapters cover a wide variety of topics, including the analysis of intracellular sorting information, prediction of the behavior of bacterial communities, biometric authentication, studies of Tuberculosis, gene signatures in breast cancer classification, the use of mass spectrometry in metabolite identification, visual navigation, and computer diagnosis. Written in the highly successful Methods in Molecular Biology series format, chapters include introductions to their respective topics, application details for both the expert and non-expert reader, and tips on troubleshooting and avoiding known pitfalls.
Authoritative and practical, Artificial Neural Networks: Third Edition should be of value to all scientists interested in the hands-on application of ANNs in the biosciences.”
Of note, Charles Fracchia, VP of Data at Dotmatics and CEO at BioBright, has contributed a chapter.
Charles’ chapter, Secure and Scalable Collection of Biomedical Data for Machine Learning Applications, covers data collection and labeling as prerequisites to training of any algorithm: data collection with scalability and security being key to avoiding costly, delaying bottlenecks in high-throughput workflows such as high content imaging and sequencing. Maintenance of biomedical data security is hugely important and Charles addresses best practices to achieve security, with a focus on practicality and scalability. He also covers the challenge of obtaining usable, rich metadata from the collected data, often in fragmented and proprietary formats, and how underutilized metadata plays a key role in creating labeled data for use in the training of neural networks.
Many current customers appreciate being able to discuss digital biosecurity with Charles, so it’s great to see his expertise recognized in the wider community.
Enjoy!
Related
Trends and Needs in Chemicals and Materials Innovation
Dotmatics’ VP Alister Campbell highlights that despite diverse products, Chemicals and Materials R&D teams face common challenges like regulatory pressures, tight timelines, and budgets, necessitating digitalization strategies focused on quality data management and interoperability to streamline workflows, foster collaboration, and enable AI and machine learning applications that accelerate innovation and maintain competitiveness in this evolving market.
Prioritizing Data Integrity in R&D: Challenges and Best Practices
The article emphasizes the critical importance of maintaining data integrity in R&D by implementing robust data governance, security, and management practices throughout the research lifecycle to ensure data accuracy, protect patient safety, uphold product efficacy, and comply with regulatory standards amid increasing digitization and evolving threats.
Structured Scientific Data for AI
The article argues that AI initiatives in life sciences often fail due to unstructured, fragmented scientific data that lacks consistent schemas, relationships, and context, emphasizing that true structured data—organized at the point of creation with defined formats and linked elements—is essential for producing trustworthy, verifiable AI outputs.
Maximize Efficiencies by Avoiding 9 Critical Lab Errors
The article outlines nine critical lab errors—such as redundant efforts due to siloed teams, nonrepeatable experiments from inconsistent recording, duplicate registrations from inadequate systems, data-entry errors, and unsearchable data—that hinder R&D efficiency, and recommends solutions like unified systems, standardized templates, automated data entry, and enhanced metadata use to streamline workflows, improve collaboration, and safeguard data integrity.
Life Sciences: The State of Data Integrity and Security
The Pharma IQ report, in collaboration with Dotmatics and BioBright, emphasizes the critical importance of data integrity, security, and encryption throughout the drug product lifecycle in life sciences, highlighting strategies such as automation and regulatory compliance to drive digital transformation and secure analytics in pharmaceutical research and development.
Harnessing Data and AI for Scientific R&D
The article explains that successful AI-driven life sciences R&D in 2025 hinges on trusted, well-governed, multimodal data integrated into automated, workflow-embedded AI tools, requiring collaboration between data and scientific intelligence—as exemplified by Dotmatics and Databricks’ partnership enabling low-code scientific apps and flexible workflows to overcome data silos and improve data quality, consistency, and usability for accelerated research.