Integrating biophysical modeling, quantum computing, and AI to discover plastic-binding peptides that combat microplastic pollution DOI Creative Commons

Jeet Dhoriyani,

Michael T. Bergman, Carol K. Hall

et al.

PNAS Nexus, Journal Year: 2024, Volume and Issue: 4(1)

Published: Dec. 23, 2024

Abstract Methods are needed to mitigate microplastic (MP) pollution minimize their harm the environment and human health. Given ability of polypeptides adsorb strongly materials micro- or nanometer size, plastic-binding peptides (PBPs) could help create bio-based tools for detecting, filtering, degrading MNP pollution. However, development such is prevented by lack PBPs. In this work, we discover evaluate PBPs several common plastics combining biophysical modeling, molecular dynamics (MD), quantum computing, reinforcement learning. We frame peptide affinity a given plastic through Potts model that function amino acid sequence then search sequences with greatest predicted using annealing. also use proximal policy optimization find broader range physicochemical properties, as isoelectric point solubility. Evaluation discovered in MD simulations demonstrates have high two plastics: polyethylene polypropylene. conclude describing how our computational approach be paired experimental approaches nexus designing optimizing peptide-based aid detection, capture, biodegradation MPs. thus hope study will fight against MP

Language: Английский

HydrogelFinder: A Foundation Model for Efficient Self‐Assembling Peptide Discovery Guided by Non‐Peptidal Small Molecules DOI Creative Commons

Xuanbai Ren,

Jiaying Wei,

Xiaoli Luo

et al.

Advanced Science, Journal Year: 2024, Volume and Issue: 11(26)

Published: May 5, 2024

Abstract Self‐assembling peptides have numerous applications in medicine, food chemistry, and nanotechnology. However, their discovery has traditionally been serendipitous rather than driven by rational design. Here, HydrogelFinder, a foundation model is developed for the design of self‐assembling from scratch. This explores self‐assembly properties molecular structure, leveraging 1,377 non‐peptidal small molecules to navigate chemical space improve structural diversity. Utilizing 111 peptide candidates are generated synthesized 17 peptides, subsequently experimentally validating biophysical characteristics nine ranging 1–10 amino acids—all achieved within 19‐day workflow. Notably, two de novo‐designed demonstrated low cytotoxicity biocompatibility, as confirmed live/dead assays. work highlights capacity HydrogelFinder diversify through molecules, offering powerful toolkit paradigm future endeavors.

Language: Английский

Citations

13
Deep Learning Empowers the Discovery of Self‐Assembling Peptides with Over 10 Trillion Sequences DOI Creative Commons
Jiaqi Wang, Zihan Liu, Shuang Zhao

et al.

Advanced Science, Journal Year: 2023, Volume and Issue: 10(31)

Published: Sept. 25, 2023

Self-assembling of peptides is essential for a variety biological and medical applications. However, it challenging to investigate the self-assembling properties within complete sequence space due enormous quantities. Here, demonstrated that transformer-based deep learning model effective in predicting aggregation propensity (AP) peptide systems, even decapeptide mixed-pentapeptide systems with over 10 trillion Based on predicted AP values, not only laws designing are derived, but transferability relation among APs pentapeptides, decapeptides, mixed pentapeptides also revealed, leading discoveries by concatenating or mixing, as consolidated experiments. This approach enables speedy, accurate, thorough search design oligopeptides, advancing science inspiring new

Language: Английский

Citations

18
Transient and elusive intermediate states in self‐assembly processes: An overview DOI Creative Commons
Ziyi Zhang,

Ze Bo Hu,

Junfei Xing

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: 2(2)

Published: May 1, 2024

Abstract The transient and elusive intermediate states are the keys in self‐assembly processes, which common phenomena shaping structure, properties, functionalities of assembled materials across many scientific domains. However, understanding about process is always challenging limited. In this review, we focus on these by combining theoretical experimental approaches. By examining a wide variety systems that span from biological to metal–organic nanostructures, review uncovers wealth self‐assembled materials. addition current knowledge, it will identify challenges provide new insight into opportunities for future research.

Language: Английский

Citations

4
Peptide-IR820 Conjugate: A Promising Strategy for Efficient Vascular Disruption and Hypoxia Induction in Melanoma DOI

Hongxia Zhang,

Mengmeng Jiang,

Weiyu Xing

et al.

ACS Applied Materials & Interfaces, Journal Year: 2024, Volume and Issue: 16(31), P. 40641 - 40652

Published: July 25, 2024

Photothermal therapy (PTT) has emerged as a noninvasive and precise cancer treatment modality known for its high selectivity lack of drug resistance. However, the clinical translation many PTT agents is hindered by limited biodegradability inorganic nanoparticles instability organic dyes. In this study, peptide conjugate, IR820-Cys-Trp-Glu-Trp-Thr-Trp-Tyr (IR820-C), was designed to self-assemble into both potent vascular disruption in melanoma treatment. When co-assembled with poorly soluble disrupting agent (VDA) combretastatin A4 (CA4), resulting (IR820-C@CA4 NPs) accumulate efficiently tumors, activate systemic antitumor immune responses, effectively ablate single near-infrared irradiation, confirmed our vivo experiments. Furthermore, exploiting tumor hypoxia, we subsequently administered hypoxia-activated prodrug tirapazamine (TPZ) capitalize on created microenvironment, thereby boosting therapeutic efficacy antimetastatic potential. This study showcases potential short-peptide-based nanocarriers design development stable efficient photothermal platforms. The multifaceted strategy, which merges ablation chemotherapy, holds great promise advancing scope modalities.

Language: Английский

Citations

4
How Does Sampling Affect the AI Prediction Accuracy of Peptides' Physicochemical Properties? DOI Open Access
Min Yan,

Ankeer Abuduhebaier,

Hao Zhou

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 2, 2025

Abstract Accurate AI prediction of peptide physicochemical properties is essential for advancing peptide-based biomedicine, biotechnology, and bioengineering. However, the performance predictive models significantly affected by representativeness training data, which depends on sample size sampling methods employed. This study addresses challenge determining optimal to enhance accuracy generalization capacity estimating aggregation propensity, hydrophilicity, isoelectric point tetrapeptides. Four were evaluated: Latin Hypercube Sampling (LHS), Uniform Design (UDS), Simple Random (SRS), Probability-Proportional-to-Size (PPS), across sizes ranging from 100 20,000. A approximately 12,000 (7.5% total tetrapeptide dataset) marks a key threshold stable consistent model performance. provides valuable insights into interplay between size, strategies, performance, offering foundational framework optimizing data collection peptides’ properties, especially in complete sequence space longer peptides with more than four amino acids.

Language: Английский

Citations

0
Integrating sequence and chemical insights: a co-modeling AI prediction framework for peptides DOI Open Access
Zihan Liu, Min Yan, Zhihui Zhu

et al.

Journal of Materials Informatics, Journal Year: 2025, Volume and Issue: 5(2)

Published: Feb. 27, 2025

Understanding the impact of primary structure peptides on a range physicochemical properties is crucial for development various applications. Peptides can be conceptualized as sequences amino acids in their biological representation and molecular architectures composed atoms chemical bonds representation. This study examines influence different representations local interpretability accuracy respective prediction models has developed “feature attribution” methodologies based these representations. The effectiveness validated through analyses, specifically within context peptide aggregation propensity (AP) prediction, with training datasets derived from high-throughput dynamics (MD) simulations. Our findings reveal significant discrepancies attribution extracted sequence-based structure-based representations, which led to proposal co-modeling framework that integrates insights both perspectives. Empirical comparisons have demonstrated contrastive learning-based excels terms efficiency. research not only extends applicability method but also lays groundwork elucidating intrinsic mechanisms governing activities functions aid domain-specific knowledge. Moreover, strategy poised enhance precision downstream applications facilitate future endeavors drug discovery protein engineering.

Language: Английский

Citations

0
Context dependence in assembly code for supramolecular peptide materials and systems DOI
Kübra Kaygisiz, Deborah Sementa, Vignesh Athiyarath

et al.

Nature Reviews Materials, Journal Year: 2025, Volume and Issue: unknown

Published: March 13, 2025

Language: Английский

Citations

0
Learning the rules of peptide self-assembly through data mining with large language models DOI
Zhenze Yang, Sarah K. Yorke, Tuomas P. J. Knowles

et al.

Science Advances, Journal Year: 2025, Volume and Issue: 11(13)

Published: March 26, 2025

Peptides are ubiquitous and important biomolecules that self-assemble into diverse structures. Although extensive research has explored the effects of chemical composition exterior conditions on self-assembly, a systematic study consolidating these data to uncover global rules is lacking. In this work, we curate peptide assembly database through combination manual processing by human experts large language model–assisted literature mining. As result, collect over 1000 experimental entries with information about sequence, conditions, corresponding self-assembly phases. Using data, machine learning models developed, demonstrating excellent accuracy (>80%) in phase classification. Moreover, fine-tune GPT model for mining developed dataset, which markedly outperforms pretrained extracting from academic publications. This workflow can improve efficiency when exploring potential self-assembling candidates, guiding while also deepening our understanding governing mechanisms.

Language: Английский

Citations

0
Interplay of Hydrophobicity, Charge, and Sequence Length in Oligopeptide Coassembly DOI

Subhadra Thapa,

Anshul Gahlawat,

Severin T. Schneebeli

et al.

The Journal of Physical Chemistry B, Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Peptide coassembly offers novel opportunities for designing advanced nanomaterials. This study used coarse-grained molecular dynamics simulations to examine the of charge-complementary peptides, assessing various ratios and role charge hydrophobicity in their aggregation. We discovered that peptide length, charge, significantly influence behavior, with more hydrophobic peptides exhibiting greater aggregation despite electrostatic repulsion. Beyond two we also observed than will likely lead new assembly structures properties. Our findings underscore importance composition length tuning resulting properties, thus facilitating design complex nanoparticles biomedical biotechnological applications.

Language: Английский

Citations

0
Engineering Peptide Self-Assembly: Modulating Noncovalent Interactions for Biomedical Applications DOI Creative Commons
Yaoting Li,

Huanfen Lu,

Liheng Lu

et al.

Accounts of Materials Research, Journal Year: 2025, Volume and Issue: unknown

Published: March 16, 2025

Language: Английский

Citations

0