Expanding the genetic code: In vivo approaches for incorporating non-proteinogenic monomers

The Journal of Microbiology, Год журнала: 2025, Номер 63(3), С. e2501005 - e2501005

Опубликована: Март 28, 2025

Язык: Английский

---

Structural Dynamics and Algorithmic Suitability of Gut-Derived Amps: A Comparative Study of Computational Modeling Approaches

Опубликована: Янв. 1, 2025

Язык: Английский

---

Enhancing Enzyme Commission Number Prediction With Contrastive Learning and Agent Attention

Proteins Structure Function and Bioinformatics, Год журнала: 2025, Номер unknown

Опубликована: Апрель 2, 2025

The accurate prediction of enzyme function is crucial for elucidating disease mechanisms and identifying drug targets. Nevertheless, existing commission (EC) number methods are limited by database coverage the depth sequence information mining, hindering efficiency precision annotation. Therefore, this study introduces ProteEC-CLA (Protein EC model with Contrastive Learning Agent Attention). utilizes contrastive learning to construct positive negative sample pairs, which not only enhances feature extraction but also improves utilization unlabeled data. This process helps learn differences in features, thereby enhancing its ability predict function. Integrating pre-trained protein language ESM2, generates informative embeddings deep functional correlation analysis, significantly accuracy. With incorporation Attention mechanism, ProteEC-CLA's comprehensively capture local details global features enhanced, ensuring high-accuracy predictions on complex sequences. results demonstrate that performs exceptionally well two independent representative datasets. In standard dataset, it achieves 98.92% accuracy at EC4 level. more challenging clustered split 93.34% an F1-score 94.72%. sequences as input, can accurately numbers up fourth level, annotation accuracy, makes a highly efficient precise tool enzymology research applications.

Язык: Английский

---

Quantum Mechanics Paradox in Protein Structure Prediction: Intrinsically Linked to Sequence yet Independent of it

Deleted Journal, Год журнала: 2025, Номер unknown, С. 100039 - 100039

Опубликована: Апрель 1, 2025

Язык: Английский

---

Unveiling the influence of fastest nobel prize winner discovery: alphafold’s algorithmic intelligence in medical sciences

Journal of Molecular Modeling, Год журнала: 2025, Номер 31(6)

Опубликована: Май 19, 2025

Язык: Английский

---

Analysing protein complexes in plant science: insights and limitation with AlphaFold 3

Botanical studies, Год журнала: 2025, Номер 66(1)

Опубликована: Май 22, 2025

Abstract AlphaFold 3 (AF3), an artificial intelligence (AI)-based software for protein complex structure prediction, represents a significant advancement in structural biology. Its flexibility and enhanced scalability have unlocked new applications various fields, specifically plant science, including improving crop resilience predicting the structures of plant-specific proteins involved stress responses, signalling pathways, immune responses. Comparisons with existing tools, such as ClusPro AlphaPulldown, highlight AF3’s unique strengths sequence-based interaction predictions its greater adaptability to biomolecular structures. However, limitations persist, challenges modelling large complexes, dynamics, from underrepresented limited evolutionary data. Additionally, AF3 encounters difficulties mutation effects on interactions DNA binding, which can be improved molecular dynamics experimental validation. This review presents overview advancements, using examples fungal research, comparisons tools. It also discusses current offers perspectives integrating validation enhance capabilities.

Язык: Английский

---

Integrating Computational Design and Experimental Approaches for Next-Generation Biologics

Biomolecules, Год журнала: 2024, Номер 14(9), С. 1073 - 1073

Опубликована: Авг. 27, 2024

Therapeutic protein engineering has revolutionized medicine by enabling the development of highly specific and potent treatments for a wide range diseases. This review examines recent advances in computational experimental approaches improved therapeutics. Key areas focus include antibody engineering, enzyme replacement therapies, cytokine-based drugs. Computational methods like structure-based design, machine learning integration, language models have dramatically enhanced our ability to predict properties guide efforts. Experimental techniques such as directed evolution rational design continue evolve, with high-throughput accelerating discovery process. Applications these led breakthroughs affinity maturation, bispecific antibodies, stability enhancement, conditionally active cytokines. Emerging intracellular delivery, stimulus-responsive proteins, de novo designed therapeutic proteins offer exciting new possibilities. However, challenges remain predicting vivo behavior, scalable manufacturing, immunogenicity mitigation, targeted delivery. Addressing will require continued integration methods, well deeper understanding behavior complex physiological environments. As field advances, we can anticipate increasingly sophisticated effective therapeutics treating human

Язык: Английский

---

Special Issue: “Molecular Dynamics Simulations and Structural Analysis of Protein Domains”

International Journal of Molecular Sciences, Год журнала: 2024, Номер 25(19), С. 10793 - 10793

Опубликована: Окт. 8, 2024

The 3D protein structure is the basis for all their biological functions [...]

Язык: Английский

---

Deciphering bacterial protein functions with innovative computational methods

Trends in Microbiology, Год журнала: 2024, Номер unknown

Опубликована: Дек. 1, 2024

Язык: Английский

---