APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics

Proceedings of the National Academy of Sciences, Год журнала: 2024, Номер 121(27)

Опубликована: Июнь 24, 2024

The prediction of protein 3D structure from amino acid sequence is a computational grand challenge in biophysics and plays key role robust algorithms, drug discovery to genome interpretation. advent AI models, such as AlphaFold, revolutionizing applications that depend on algorithms. To maximize the impact, ease usability, these tools we introduce APACE, AlphaFold2 advanced computing service, framework effectively handles this model its TB-size database conduct accelerated analyses modern supercomputing environments. We deployed APACE Delta Polaris supercomputers quantified performance for accurate predictions using four exemplar proteins: 6AWO, 6OAN, 7MEZ, 6D6U. Using up 300 ensembles, distributed across 200 NVIDIA A100 GPUs, found two orders magnitude faster than off-the-self implementations, reducing time-to-solution weeks minutes. This approach may be readily linked with robotics laboratories automate accelerate scientific discovery.

Язык: Английский

---

Predictive Modeling of Proteins Encoded by a Plant Virus Sheds a New Light on Their Structure and Inherent Multifunctionality

Biomolecules, Год журнала: 2024, Номер 14(1), С. 62 - 62

Опубликована: Янв. 2, 2024

Plant virus genomes encode proteins that are involved in replication, encapsidation, cell-to-cell, and long-distance movement, avoidance of host detection, counter-defense, transmission from to host, among other functions. Even though the multifunctionality plant viral is well documented, contemporary functional repertoires individual incomplete. However, these can be enhanced by modeling tools. Here, predictive encoded two genomic RNAs, i.e., RNA1 RNA2, grapevine fanleaf (GFLV) their satellite RNAs a suite protein prediction software confirmed not only previously validated functions (suppressor RNA silencing [VSR], genome-linked [VPg], protease [Pro], symptom determinant [Sd], homing [HP], movement [MP], coat [CP], [Td]) identified putative (helicase [Hel] RNA-dependent polymerase [Pol]), but also predicted novel with varying levels confidence. These include T3/T7-like domain for 1A

Язык: Английский

---

Computational Approaches to Drug Repurposing: Methods, Challenges, and Opportunities

Annual Review of Biomedical Data Science, Год журнала: 2024, Номер 7(1), С. 15 - 29

Опубликована: Апрель 10, 2024

Drug repurposing refers to the inference of therapeutic relationships between a clinical indication and existing compounds. As an emerging paradigm in drug development, enables more efficient treatment rare diseases, stratified patient populations, urgent threats public health. However, prioritizing well-suited candidates from among nearly infinite number options continues represent significant challenge development. Over past decade, advances genomic profiling, database curation, machine learning techniques have enabled accurate identification for subsequent evaluation. This review outlines major methodologic classes that these approaches comprise, which rely on (a) protein structure, (b) signatures, (c) biological networks, (d) real-world data. We propose realizing full impact methodologies requires multidisciplinary understanding each method's advantages limitations with respect practice.

Язык: Английский

---

Integration of AlphaFold with Molecular Dynamics for Efficient Conformational Sampling of Transporter Protein NarK

The Journal of Physical Chemistry B, Год журнала: 2024, Номер 128(31), С. 7530 - 7537

Опубликована: Июль 27, 2024

Transporter proteins carry their substrate across the cell membrane by changing conformation. Thus, conformational dynamics are crucial for transport function. However, clarifying complete cycle is challenging even with current structural biology approach. Molecular (MD) simulation a computational approach that can provide time-resolved of transporter in atomic details but suffers from high cost. Here, we integrate state-of-the-art protein structure prediction AI, AlphaFold2 (AF2), MD to reduce Focusing on NarK, first show AF2 sampled broad conformations including inward-open, occluded, and outward-open states. We also applied coevolution-informed mutation AF2, identifying state-shifting mutations. Then, simulations AF2-generated conformation, which experimentally unresolved, captured essence state. found intermediates showed transient like transition state connecting two This study paves way efficient sampling proteins.

Язык: Английский

---

Innovative Mamba and graph transformer framework for superior protein-ligand affinity prediction

Microchemical Journal, Год журнала: 2024, Номер 206, С. 111444 - 111444

Опубликована: Авг. 15, 2024

Язык: Английский

---