Proteins, which are one of the fundamental building blocks of life and govern major biochemical reactions, typically adhere to the sequence-to-structure rule. This rule posits that a protein's sequence dictates its 3D shape, which in turn influences its function. However, this principle does not universally apply to intrinsically disordered proteins (IDPs) and intrinsically disordered regions (IDRs) within proteins. These IDPs can execute specific functions without assuming a fixed 3D structure, and they constitute a significant fraction of the proteome.
Research into these disordered proteins has revealed their critical role in various cellular processes, including signal propagation, molecular recognition and assembly, cell cycle regulation, transcription, translation, and phase separation. Despite this, due to the flexible and diverse nature of these proteins, a complete understanding of their behavior remains a consistent challenge in the field of computational biology. However, a growing understanding is emerging, largely due to the advancement of various data-driven tools, particularly those based on machine learning and deep learning. As the key issue is to determine all possible conformational spaces—which still pose a barrier for advanced molecular dynamics (MD) techniques—various sophisticated deep learning tools are becoming leading solutions for this problem. Since these AI models are not hindered by kinetic barriers, they can easily overcome this main bottleneck of MD.
We are extending an invitation to researchers to submit original research papers and thorough, in-depth reviews within the realm of using deep learning in IDP research. We are open to a wide range of topics, which may include but are certainly not limited to the following:
• Utilizing deep learning techniques to predict the conformations of intrinsically disordered proteins (IDPs).
• Investigating the conformations of intrinsically disordered regions (IDRs) when interacting with small molecules.
• Developing novel deep learning algorithms that combine with molecular dynamics (MD) techniques to predict IDP conformations.
• Using deep learning tools to link between conformations of IDPs/IDRs and liquid-liquid phase separation (LLPS) behaviors.
Keywords:
deep learning, intrinsically disordered proteins, Intrinsically Disordered Regions, Protein structure prediction, Liquid-liquid phase separation
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Proteins, which are one of the fundamental building blocks of life and govern major biochemical reactions, typically adhere to the sequence-to-structure rule. This rule posits that a protein's sequence dictates its 3D shape, which in turn influences its function. However, this principle does not universally apply to intrinsically disordered proteins (IDPs) and intrinsically disordered regions (IDRs) within proteins. These IDPs can execute specific functions without assuming a fixed 3D structure, and they constitute a significant fraction of the proteome.
Research into these disordered proteins has revealed their critical role in various cellular processes, including signal propagation, molecular recognition and assembly, cell cycle regulation, transcription, translation, and phase separation. Despite this, due to the flexible and diverse nature of these proteins, a complete understanding of their behavior remains a consistent challenge in the field of computational biology. However, a growing understanding is emerging, largely due to the advancement of various data-driven tools, particularly those based on machine learning and deep learning. As the key issue is to determine all possible conformational spaces—which still pose a barrier for advanced molecular dynamics (MD) techniques—various sophisticated deep learning tools are becoming leading solutions for this problem. Since these AI models are not hindered by kinetic barriers, they can easily overcome this main bottleneck of MD.
We are extending an invitation to researchers to submit original research papers and thorough, in-depth reviews within the realm of using deep learning in IDP research. We are open to a wide range of topics, which may include but are certainly not limited to the following:
• Utilizing deep learning techniques to predict the conformations of intrinsically disordered proteins (IDPs).
• Investigating the conformations of intrinsically disordered regions (IDRs) when interacting with small molecules.
• Developing novel deep learning algorithms that combine with molecular dynamics (MD) techniques to predict IDP conformations.
• Using deep learning tools to link between conformations of IDPs/IDRs and liquid-liquid phase separation (LLPS) behaviors.
Keywords:
deep learning, intrinsically disordered proteins, Intrinsically Disordered Regions, Protein structure prediction, Liquid-liquid phase separation
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.