Dataset Information

HydrogelFinder: A Foundation Model for Efficient Self-Assembling Peptide Discovery Guided by Non-Peptidal Small Molecules.

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 rational design of self-assembling peptides from scratch. This model explores the self-assembly properties by molecular structure, leveraging 1,377 self-assembling non-peptidal small molecules to navigate chemical space and improve structural diversity. Utilizing HydrogelFinder, 111 peptide candidates are generated and synthesized 17 peptides, subsequently experimentally validating the self-assembly and biophysical characteristics of nine peptides ranging from 1-10 amino acids-all achieved within a 19-day workflow. Notably, the two de novo-designed self-assembling peptides demonstrated low cytotoxicity and biocompatibility, as confirmed by live/dead assays. This work highlights the capacity of HydrogelFinder to diversify the design of self-assembling peptides through non-peptidal small molecules, offering a powerful toolkit and paradigm for future peptide discovery endeavors.

SUBMITTER: Ren X

PROVIDER: S-EPMC11234452 | biostudies-literature | 2024 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

HydrogelFinder: A Foundation Model for Efficient Self-Assembling Peptide Discovery Guided by Non-Peptidal Small Molecules.

Ren Xuanbai X Wei Jiaying J Luo Xiaoli X Liu Yuansheng Y Li Kenli K Zhang Qiang Q Gao Xin X Yan Sizhe S Wu Xia X Jiang Xingyue X Liu Mingquan M Cao Dongsheng D Wei Leyi L Zeng Xiangxiang X Shi Junfeng J

Advanced science (Weinheim, Baden-Wurttemberg, Germany) 20240505 26

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 rational design of self-assembling peptides from scratch. This model explores the self-assembly properties by molecular structure, leveraging 1,377 self-assembling non-peptidal small molecules to navigate chemical space and improve stru ...[more]

PMID: 38704695

Similar Datasets

Project description:Multidomain peptides (MDPs) are a class of self-assembling peptides that are organized in a β-sheet motif, resulting in a nanofibrous architecture. This structure is stabilized by hydrophobic packing in the fiber core and a hydrogen-bonding network down the fiber long axis. Under easily controllable conditions, regulated by electrostatic interactions between the peptides and the pH and salt composition of the solvent, the nanofiber length can be dramatically extended, resulting in fiber entanglement and hydrogel formation. One of the chief strengths of this supramolecular material is that the design criteria governing its structure and assembly are robust and permit a wide range of modifications without disruption. This allows the MDPs to be tailored to suit a wide range of applications, particularly in biomedical engineering. For example, delivery of small molecules, proteins, and cells is easily achievable. These materials can be trapped within the matrices of the hydrogel or trapped within the hydrophobic core of the nanofiber, depending on the cargo and the design of the MDP. Interactions between the nanofibers and their cargo can be tailored to alter the release profile, and in the most sophisticated cases, different cargos can be released in a cascading time-dependent fashion. The MDP hydrogel and its cargo can be targeted to specific locations, as the thixotropic nature of the hydrogel allows it to be easily aspirated into a syringe and then delivered from a narrow-bore needle. The sequence of amino acids making up the MDP can also be modified to permit cross-linking or enzymatic degradation. Selection of sequences with or without these modifications allows one to control the rate of degradation in vivo from as rapidly as 1 week to well over 6 weeks as the MDP nanofibers are degraded to their amino acid components. MDP sequences can also be modified to add biomimetic sequences derived from growth factors and other signaling proteins. These chemical signals are displayed at a very high density on the fibers' surface, where they contribute to the modification of cellular behavior. We have used this approach to drive blood vessel formation, which is critical for tissue regeneration generally and more specifically for the treatment of diseases related to poor blood flow. MDPs represent an ideal case of bottom-up design where control of chemical structure leads to control of self-assembly and nanostructure and thereby control of material properties that collectively can control biological function.

Dataset Information

HydrogelFinder: A Foundation Model for Efficient Self-Assembling Peptide Discovery Guided by Non-Peptidal Small Molecules.

Publications

HydrogelFinder: A Foundation Model for Efficient Self-Assembling Peptide Discovery Guided by Non-Peptidal Small Molecules.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets