Search

Collagen is the most abundant structural protein in humans, with dozens of sequence variants accounting for over 30% of the protein in an animal body. The fibrillar and hierarchical arrangements of collagen are critical in providing mechanical properties with high strength and toughness. Due to this ubiquitous role in human tissues, collagen-based biomaterials are commonly used for tissue repairs and regeneration, requiring chemical and thermal stability over a range of temperatures during materials preparation ex vivo and subsequent utility in vivo. Collagen unfolds from a triple helix to a random coil structure during a temperature interval in which the midpoint or Tm is used as a measure to evaluate the thermal stability of the molecules. However, finding a robust framework to facilitate the design of a specific collagen sequence to yield a specific Tm remains a challenge, including using conventional molecular dynamics modeling. Here we propose a de novo framework to provide a model that outputs the Tm values of input collagen sequences by incorporating deep learning trained on a large data set of collagen sequences and corresponding Tm values. By using this framework, we are able to quickly evaluate how mutations and order in the primary sequence affect the stability of collagen triple helices. Specifically, we confirm that mutations to glycines, mutations in the middle of a sequence, and short sequence lengths cause the greatest drop in Tm values.

Collagen is the most abundant structural protein in humans, providing crucial mechanical properties, including high strength and toughness, in tissues. Collagen-based biomaterials are, therefore, used for tissue repair and regeneration. Utilizing collagen effectively during materials processing ex vivo and subsequent function in vivo requires stability over wide temperature ranges to avoid denaturation and loss of structure, measured as melting temperature (T m ). Although significant research has been conducted on understanding how collagen primary amino acid sequences correspond to T m values, a robust framework to facilitate the design of collagen sequences with specific T m remains a challenge. Here, we develop a general model using a genetic algorithm within a deep learning framework to design collagen sequences with specific T m values. We report 1,000 de novo collagen sequences, and we show that we can efficiently use this model to generate collagen sequences and verify their T m values using both experimental and computational methods. We find that the model accurately predicts T m values within a few degrees centigrade. Further, using this model, we conduct a high-throughput study to identify the most frequently occurring collagen triplets that can be directly incorporated into collagen. We further discovered that the number of hydrogen bonds within collagen calculated with molecular dynamics (MD) is directly correlated to the experimental measurement of triple-helical quality. Ultimately, we see this work as a critical step to helping researchers develop collagen sequences with specific T m values for intended materials manufacturing methods and biomedical applications, realizing a mechanistic materials by design paradigm.

A framework for inverse design of tuning mechanical properties of polycrystalline brittle materials is presented using artificial intelligence (AI). Crystalline solids, which often exhibit distinct mechanical properties at different orientations, can be used as building blocks for polycrystalline composites. However, the design space of geometry and crystal misorientations is typically intractable, and all possible solutions cannot be discovered using experiment or numerical simulation. Herein, a framework using deep learning (DL) alongside a genetic algorithm (GA) is adopted to generate composite polycrystalline materials, whereas the raw material is brittle and sensitive to crystalline orientation, to achieve distinct mechanical properties in various combinatorial designs. The DL model, trained by full-atomistic simulations of crystals with different orientations, evolves autonomously to yield a desirable range of target toughness values, exemplified in maximizing and minimizing toughness, which are validated by molecular dynamics (MD) simulations. It is found that higher crystal misorientations are preferred for high toughness, as opposed to lower overall misorientations for low-toughness designs. Notably, this shows that a mechanism can be extracted from the AI algorithm. This materiomics method may ultimately change the way nanomaterials are designed, and can be applied to de novo biomaterial design, architected materials, and bioinspired structural materials.

This review revisits the state of the art of research efforts on the design of mechanical materials using machine learning.