Andreas Dengel: Artificial Intelligence for Molecular Biology, Gebunden

Klappentext

The integration of artificial intelligence (AI) into molecular biology has brought about a paradigm shift, enabling researchers to tackle some of the most challenging problems in life sciences. This second volume builds upon the foundational principles explored in Volume I, delving into advanced AI methodologies and their applications in understanding biological sequences at a granular level. From word embeddings to language models, this volume examines the state-of-the-art techniques driving progress in molecular biology.

The chapters in this volume are structured to provide an in-depth exploration of AI methods and their transformative impact on DNA, RNA, protein, and peptide analysis:

Word Embedding Methods: This chapter explores the evolution of word embedding techniques, including foundational models like Word2Vec, FastText, and GloVe, as well as advanced graph-based embeddings such as DeepWalk, Node2Vec, and Struc2Vec.
Large Language Models: This chapter examines models like ULMFiT, BERT, and cutting-edge tools like AlphaFold and RNAFormer, which have set new benchmarks in structure prediction and sequence analysis.

AI-Driven Insights into DNA Sequence Analysis Landscape: This chapter reviews methodologies, datasets, and predictive pipelines, offering insights into the performance and distribution of research across various benchmarks.
AI-Driven Insights into RNA Sequence Analysis Landscape: This chapter investigates datasets, predictive pipelines, and performance metrics specific to RNA analysis.
AI-Driven Insights into Protein Sequence Analysis Landscape: This chapter discusses embedding-based and language model-based methods, as well as the resources and benchmarks available for protein analysis.
AI-Driven Revolution in Peptide Classification Landscape: This chapter provides a thorough examination of peptide classification, exploring AI methodologies, datasets, evaluation strategies, and the state-of-the-art performance of predictive models.

Volume II provides a detailed narrative of how advanced AI methodologies are transforming the study of molecular biology. Each chapter bridges the gap between theoretical advancements and practical applications, equipping researchers and practitioners with the knowledge needed to drive innovation in this interdisciplinary field.