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.

We report the use of a deep learning model to design de novo proteins, based on the interplay of elementary building blocks via hierarchical patterns. The deep neural network model is based on translating protein sequences and structural information into a musical score that features different pitches for each of the amino acids, and variations in note length and note volume reflecting secondary structure information and information about the chain length and distinct protein molecules. We train a deep learning model whose architecture is composed of several long short-term memory units from data consisting of musical representations of proteins classified by certain features, focused here on alpha-helix rich proteins. Using the deep learning model, we then generate de novo musical scores and translate the pitch information and chain lengths into sequences of amino acids. We use a Basic Local Alignment Search Tool to compare the predicted amino acid sequences against known proteins, and estimate folded protein structures using the Optimized protein fold RecognitION method (ORION) and MODELLER. We find that the method proposed here can be used to design de novo proteins that do not exist yet, and that the designed proteins fold into specified secondary structures. We validate the newly predicted protein by molecular dynamics equilibration in explicit water and subsequent characterization using a normal mode analysis. The method provides a tool to design novel protein materials that could find useful applications as materials in biology, medicine, and engineering.

Fracture is a catastrophic and complex process that involves various time and length scales. Scientists have devoted vast efforts toward understanding the underlying mechanisms for centuries, with much work left in terms of predictability of models and fundamental understanding. To this end, we present a machine-learning approach to predict fracture processes connecting molecular simulation into a physics-based artificial intelligence (AI) multiscale model. Our model exhibits predictive power not only regarding the computed fracture patterns but also for fracture toughness—the resistance of cracks to grow. The novel AI-based fracture predictor can also deal with complex loading conditions, here examined for both mode I (tensile) and mode II (shear). These results underscore the excellent predictive power of our model. Potential applications include the design of novel types of high-performance materials, composites design, surface coatings, or innovative bio-inspired structures.

Materials-by-design is a paradigm to develop previously unknown high-performance materials. However, finding materials with superior properties is often computationally or experimentally intractable because of the astronomical number of combinations in design space. Here we report an AI-based approach, implemented in a game theory–based conditional generative adversarial neural network (cGAN), to bridge the gap between a material’s microstructure—the design space—and physical performance. Our end-to-end deep learning model predicts physical fields like stress or strain directly from the material microstructure geometry, and reaches an astonishing accuracy not only for predicted field data but also for derivative material property predictions. Furthermore, the proposed approach offers extensibility by predicting complex materials behavior regardless of component shapes, boundary conditions, and geometrical hierarchy, providing perspectives of performing physical modeling and simulations. The method vastly improves the efficiency of evaluating physical properties of hierarchical materials directly from the geometry of its structural makeup.

Understanding fracture is critical to the design of resilient nanomaterials. Molecular dynamics offers a way to study fracture at an atomistic level, but is computationally expensive with limitations of scalability. In this work, we build upon machine-learning approaches for predicting nanoscopic fracture mechanisms including crack instabilities and branching as a function of crystal orientation. We focus on a particular technologically relevant material system, graphene, and apply a deep learning method to the study of such nanomaterials and explore the parameter space necessary for calibrating machine-learning predictions to meaningful results. Our results validate the ability of deep learning methods to quantitatively capture graphene fracture behavior, including its fractal dimension as a function of crystal orientation, and provide promise toward the wider application of deep learning to materials design, opening the potential for other 2D materials., NSF (Grant 1122374), Office of Naval Research (Grants N000141612333 and N000141912375), AFOSR-MURI (Contract FA9550-15-1-0514), Army Research Office (Contract W911NF1920098), NIH (Grant U01-EB014976)