Data-driven approaches for foams can be a time- and data-efficient alternative method to experimental and conventional modeling techniques.

MXenes belong to a new class of two dimensional (2D) functional nanomaterials, mainly encompassing transition‐metal carbides, nitrides and carbonitrides, with unique physical, chemical, electronic and mechanical properties for various emerging applications across different fields. To date, the potentials of MXenes for biomedical application such as drug delivery have not been thoroughly explored due to the lack of information on their biocompatibility, cytotoxicity and biomolecule‐surface interaction. In this study, we developed novel drug delivery system from MXene for the controlled release of a model therapeutic protein. First, the structural, chemical and morphological properties of as synthesized MXenes were probed with electron microscopy and X‐ray diffraction. Second, the potential cytotoxicity of MXene toward the proliferation and cell morphology of murine macrophages (RAW 264.7) were evaluated with MTT assays and electron microscopy, respectively. Moreover, the drug loading capacities and sustained release capabilities of MXene were assessed in conjunction with machine learning approaches. Our results demonstrated that MXene did not significantly induce cellular toxicity at any concentration below 1 mg/ml which is within the range for effective dose of drug delivery vehicle. Most importantly, MXene was efficiently loaded with FITC‐catalase for subsequently achieving controlled release under different pHs. The release profiles of catalase from MXene showed higher initial rate under basic buffer (pH 9) compared to that in physiological (pH 7.4) and acidic buffers (pH 2). Taken together, the results of this study lead to a fundamental advancement toward the use of MXene as a nanocarrier for therapeutic proteins in drug delivery applications.

Conventional foam modelling techniques require tuning of too many parameters and long computational time in order to provide accurate predictions. Therefore, there is a need for alternative methodologies for the efficient and reliable prediction of the foams’ performance. Foams are susceptible to various operational conditions and reservoir parameters. This research aims to apply machine learning (ML) algorithms to experimental data in order to correlate important affecting parameters to foam rheology. In this way, optimum operational conditions for CO2 foam enhanced oil recovery (EOR) can be determined. In order to achieve that, five different ML algorithms were applied to experimental rheology data from various experimental studies. It was concluded that the Gradient Boosting (GB) algorithm could successfully fit the training data and give the most accurate predictions for unknown cases.

No abstract