A computational approach to predicting cell growth on polymeric biomaterials

Machine learning guided structure function predictions enable in silico nanoparticle screening for polymeric gene delivery

Developing highly efficient non-viral gene delivery reagents is still difficult for many hard-to-transfect cell types and, to date, has mostly been conducted via brute force screening routines. High throughput in silico methods of evaluating biomaterials can enable accelerated optimization and development of devices or therapeutics by exploring large chemical design spaces quickly and at low cost. This work reports application of state-of-the-art machine learning algorithms to a dataset of synthetic biodegradable polymers, poly(beta-amino ester)s (PBAEs), which have shown exciting promise for therapeutic gene delivery in vitro and in vivo. The data set includes polymer properties as inputs as well as polymeric nanoparticle transfection performance and nanoparticle toxicity in a range of cells as outputs. This data was used to train and evaluate several state-of-the-art machine learning algorithms for their ability to predict transfection and understand structure-function relationships. By developing an encoding scheme for vectorizing the structure of a PBAE polymer in a machine-readable format, we demonstrate that a random forest model can satisfactorily predict DNA transfection in vitro based on the chemical structure of the constituent PBAE polymer in a cell line dependent manner. Based on the model, we synthesized PBAE polymers and used them to form polymeric gene delivery nanoparticles that were predicted in silico to be successful. We validated the computational predictions in two cell lines in vitro, RAW 264.7 macrophages and Hep3B liver cancer cells, and found that the Spearman's R correlation between predicted and experimental transfection was 0.57 and 0.66 respectively. Thus, a computational approach that encoded chemical descriptors of polymers was able to demonstrate that in silico computational screening of polymeric nanomedicine compositions had utility in predicting de novo biological experiments. STATEMENT OF SIGNIFICANCE: Developing highly efficient non-viral gene delivery reagents is difficult for many hard-to-transfect cell types and, to date, has mostly been explored via brute force screening routines. High throughput in silico methods of evaluating biomaterials can enable accelerated optimization and development for therapeutic or biomanufacturing purposes by exploring large chemical design spaces quickly and at low cost. This work reports application of state-of-the-art machine learning algorithms to a large compiled PBAE DNA gene delivery nanoparticle dataset across many cell types to develop predictive models for transfection and nanoparticle cytotoxicity. We develop a novel computational pipeline to encode PBAE nanoparticles with chemical descriptors and demonstrate utility in a de novo experimental context.

Materiomics: an -omics approach to biomaterials research

The past fifty years have seen a surge in the use of materials for clinical application, but in order to understand and exploit their full potential, the scientific complexity at both sides of the interface--the material on the one hand and the living organism on the other hand--needs to be considered. Technologies such as combinatorial chemistry, recombinant DNA as well as computational multi-scale methods can generate libraries with a very large number of material properties whereas on the other side, the body will respond to them depending on the biological context. Typically, biological systems are investigated using both holistic and reductionist approaches such as whole genome expression profiling, systems biology and high throughput genetic or compound screening, as already seen, for example, in pharmacology and genetics. The field of biomaterials research is only beginning to develop and adopt these approaches, an effort which we refer to as "materiomics". In this review, we describe the current status of the field, and its past and future impact on the biomedical sciences. We outline how materiomics sets the stage for a transformative change in the approach to biomaterials research to enable the design of tailored and functional materials for a variety of properties in fields as diverse as tissue engineering, disease diagnosis and de novo materials design, by combining powerful computational modelling and screening with advanced experimental techniques.

Logical Analysis of Data in Structure-Activity Investigation of Polymeric Gene Delivery

To date semi-empirical or surrogate modeling has demonstrated great success in the prediction of the biologically relevant properties of polymeric materials. For the first time, a correlation between the chemical structures of poly(β-amino esters) and their efficiency in transfecting DNA was established using the novel technique of logical analysis of data (LAD). Linear combination and explicit representation models were introduced and compared in the framework of the present study. The most successful regression model yielded satisfactory agreement between the predicted and experimentally measured values of transfection efficiency (Pearson correlation coefficient, 0.77; mean absolute error, 3.83). It was shown that detailed analysis of the rules provided by the LAD algorithm offered practical utility to a polymer chemist in the design of new biomaterials.

Identification of osteoconductive and biodegradable polymers from a combinatorial polymer library

Combinatorial polymer syntheses are now being utilized to create libraries of materials with potential utility for a wide variety of biomedical applications. We recently developed a library of photopolymerizable and biodegradable poly(beta-amino ester)s (PBAEs) that possess a range of tunable properties. In this study, the PBAE library was assessed for candidate materials that met design criteria (e.g., physical properties such as degradation and mechanical strength and in vitro cell viability and osteoconductive behavior) for scaffolding in mineralized tissue repair. The most promising candidate, A6, was then processed into three-dimensional porous scaffolds and implanted subcutaneously and only presented a mild inflammatory response. The scaffolds were then implanted intramuscularly and into a critical-sized cranial defect either alone or loaded with bone morphogenetic protein-2 (BMP-2). The samples in both locations displayed mineralized tissue formation in the presence of BMP-2, as evident through radiographs, micro-computed tomography, and histology, whereas samples without BMP-2 showed minimal or no mineralized tissue. These results illustrate a process to identify a candidate scaffolding material from a combinatorial polymer library, and specifically for the identification of an osteoconductive scaffold with osteoinductive properties via the inclusion of a growth factor.

Neural network analysis identifies scaffold properties necessary for in vitro chondrogenesis in elastin-like polypeptide biopolymer scaffolds

The successful design of biomaterial scaffolds for articular cartilage tissue engineering requires an understanding of the impact of combinations of material formulation parameters on diverse and competing functional outcomes of biomaterial performance. This study sought to explore the use of a type of unsupervised artificial network, a self-organizing map, to identify relationships between scaffold formulation parameters (crosslink density, molecular weight, and concentration) and 11 such outcomes (including mechanical properties, matrix accumulation, metabolite usage and production, and histological appearance) for scaffolds formed from crosslinked elastin-like polypeptide (ELP) hydrogels. The artificial neural network recognized patterns in functional outcomes and provided a set of relationships between ELP formulation parameters and measured outcomes. Mapping resulted in the best mean separation amongst neurons for mechanical properties and pointed to crosslink density as the strongest predictor of most outcomes, followed by ELP concentration. The map also grouped formulations together that simultaneously resulted in the highest values for matrix production, greatest changes in metabolite consumption or production, and highest histological scores, indicating that the network was able to recognize patterns amongst diverse measurement outcomes. These results demonstrated the utility of artificial neural network tools for recognizing relationships in systems with competing parameters, toward the goal of optimizing and accelerating the design of biomaterial scaffolds for articular cartilage tissue engineering.

Logical Analysis of Data (LAD) model for the early diagnosis of acute ischemic stroke

Background

Strokes are a leading cause of morbidity and the first cause of adult disability in the United States. Currently, no biomarkers are being used clinically to diagnose acute ischemic stroke. A diagnostic test using a blood sample from a patient would potentially be beneficial in treating the disease.

Results

A classification approach is described for differentiating between proteomic samples of stroke patients and controls, and a second novel predictive model is developed for predicting the severity of stroke as measured by the National Institutes of Health Stroke Scale (NIHSS). The models were constructed by applying the Logical Analysis of Data (LAD) methodology to the mass peak profiles of 48 stroke patients and 32 controls. The classification model was shown to have an accuracy of 75% when tested on an independent validation set of 35 stroke patients and 25 controls, while the predictive model exhibited superior performance when compared to alternative algorithms. In spite of their high accuracy, both models are extremely simple and were developed using a common set consisting of only 3 peaks.

Conclusion

We have successfully identified 3 biomarkers that can detect ischemic stroke with an accuracy of 75%. The performance of the classification model on the validation set and on cross-validation does not deteriorate significantly when compared to that on the training set, indicating the robustness of the model. As in the case of the LAD classification model, the results of the predictive model validate the function constructed on our support-set for approximating the severity scores of stroke patients. The correlation and root mean absolute error of the LAD predictive model are consistently superior to those of the other algorithms used (Support vector machines, C4.5 decision trees, Logistic regression and Multilayer perceptron).

Profiling cell-biomaterial interactions via cell-based fluororeporter imaging

Cell-based, high-throughput screening has revolutionized the development of small-molecule pharmaceuticals. A similar paradigm for the accelerated development of biomaterials for cell and tissue engineering involves the iterative use of combinatorial biomaterial synthesis, rapid cellular response screens, and computational modeling methods. However assays to probe cell responses to biomaterials are frequently subjective, lack dynamic responsiveness, and are limited to low-throughput experimentation. In this report, we highlight the use of high-resolution imaging of cell-based fluororeporters to establish and correlate quantifiable metrics of cell functional endpoints (e.g., cell growth, cell adhesion, cell attachment strength), as well as of intracellular cytoskeletalfeatures (e.g., descriptors of actin organization) on a set of model biomaterial substrates synthesized by combinatorial variations. Selected mammalian cell lines were genetically engineered with a series of green fluorescent protein (GFP)fusion genes to allow for live cell imaging on biomaterials. We demonstrate that high-content imaging yields a large number of quantifiable morphometric descriptors of ultrastructural cell features (e.g., cell cytoskeleton) in conjunction with densitometric descriptors of cell behaviors (e.g., cell apoptosis). We illustrate how such descriptors can be used to discern combinatorial variations in substrate composition, and how living GFP reporters are uniquely suited to generate such descriptors unlike fixed tissue preparations. This quantitative approach of live fluororeporter cell imaging could be valuable for metrology of cell-material interactions.

Interface Interactions of Osteoblasts with Structured Titanium and the Correlation between Physicochemical Characteristics and Cell Biological Parameters

Cellular behavior at the interface of an implant is influenced by the material's topography. However, little is known about the correlation between the biological parameters and the physicochemical characteristics of the biomaterial. We therefore modified pure titanium surfaces by polishing, machining, blasting with glass spheres, blasting with corundum particles, and vacuum plasma spraying to give progressively higher surface roughness. The material surface was characterized by SEM, surface profiling, and electrochemical methods. We revealed a correlation for integrin expression and formation, adhesion, spreading, proliferation, and bone sialo protein expression with the physicochemical parameters of the titanium surfaces.

Mini-review: combinatorial approaches for the design of novel coating systems

Combinatorial and high throughput experimental methods are being applied to the design and development of novel polymers and coatings used in a number of application areas. Methods have been developed for polymer synthesis and screening and for the development of polymer thin film and coating libraries and the screening of these libraries for key properties such as surface energy and modulus. Combinatorial and high throughput methods enable the efficient exploration of a large number of compositional variables over a wide range. In the development of coatings for use in the marine environment, the key challenge is in the development of screening methods that can predict good performance. A number of assays are under development that will permit the rapid screening of the interaction of coatings with representative marine organisms.

Minute changes in composition of polymer substrates produce amplified differences in cell adhesion and motility via optimal ligand conditioning

We explored the interplay between substratum chemistry of polymeric materials and surface-adsorbed ligand concentration (human plasma fibronectin) in the control of cell adhesion and cell motility. We found that small changes in the chemical composition of a polymeric substratum had different effects on cellular motility--depending on the concentration of preadsorbed fibronectin. We used two tyrosine-derived polyarylates, poly(DTD diglycolate) and poly(DTD glutarate), as substrata for the seeding of NIH-3T3 fibroblasts. The only compositional difference between the two test polymers was that one single oxygen atom in the polymer backbone of poly(DTD diglycolate) had been substituted by a methylene group in the backbone of poly(DTD glutarate), The two polymers had closely matched hydrophobicity and physical properties. Flat, spin-coated surfaces of these polymers were pretreated with different concentrations of human plasma fibronectin (0-20 microg/ml). After seeding with NIH-3T3 fibroblasts, we examined the adhesion and motility behavior of these cells. We found that NIH-3T3 fibroblasts migrated significantly faster on poly(DTD diglycolate), but only when the polymer surfaces were pretreated with intermediate concentrations of fibronectin. Only at these intermediate levels of ligand conditioning, did the presence of an extra oxygen atom in the backbone of poly(DTD diglycolate) relative to poly(DTD glutarate) (i) alter the overall organization/concentration of the fibronectin; (ii) weaken cell attachment strength and inhibited excessive cell spreading; and (iii) promote cell motility kinetics. These findings indicate that the biological effect of minute changes in substratum chemistry is critically dependent on the level of surface-adsorbed cell-binding ligands.

Selected successful approaches in combinatorial materials research

Combinatorial materials research (CMR) is still a relatively young field of research. Nevertheless, it already provides successful strategies for a fast and accurate evaluation of a large variety of different research problems. Some of these approaches in CMR considering polymeric materials will be discussed and highlighted within this contribution by focussing on three prominent literature examples: structure-property relationships in biomaterials research, material properties evaluation utilizing thin film polymer libraries as well as the parallel and automated study of polymer based reversed unimolecular micelles and their application possibilities. These examples are meant to demonstrate the almost unlimited possibilities of combinatorial approaches in polymer science rather than to provide an extended overview of the field.

Breast cancer prognosis by combinatorial analysis of gene expression data

INTRODUCTION

The potential of applying data analysis tools to microarray data for diagnosis and prognosis is illustrated on the recent breast cancer dataset of van 't Veer and coworkers. We re-examine that dataset using the novel technique of logical analysis of data (LAD), with the double objective of discovering patterns characteristic for cases with good or poor outcome, using them for accurate and justifiable predictions; and deriving novel information about the role of genes, the existence of special classes of cases, and other factors.

METHOD

Data were analyzed using the combinatorics and optimization-based method of LAD, recently shown to provide highly accurate diagnostic and prognostic systems in cardiology, cancer proteomics, hematology, pulmonology, and other disciplines.

RESULTS

LAD identified a subset of 17 of the 25,000 genes, capable of fully distinguishing between patients with poor, respectively good prognoses. An extensive list of 'patterns' or 'combinatorial biomarkers' (that is, combinations of genes and limitations on their expression levels) was generated, and 40 patterns were used to create a prognostic system, shown to have 100% and 92.9% weighted accuracy on the training and test sets, respectively. The prognostic system uses fewer genes than other methods, and has similar or better accuracy than those reported in other studies. Out of the 17 genes identified by LAD, three (respectively, five) were shown to play a significant role in determining poor (respectively, good) prognosis. Two new classes of patients (described by similar sets of covering patterns, gene expression ranges, and clinical features) were discovered. As a by-product of the study, it is shown that the training and the test sets of van 't Veer have differing characteristics.

CONCLUSION

The study shows that LAD provides an accurate and fully explanatory prognostic system for breast cancer using genomic data (that is, a system that, in addition to predicting good or poor prognosis, provides an individualized explanation of the reasons for that prognosis for each patient). Moreover, the LAD model provides valuable insights into the roles of individual and combinatorial biomarkers, allows the discovery of new classes of patients, and generates a vast library of biomedical research hypotheses.