In this paper, we introduce a deep learning model to classify children as either healthy or potentially having autism with 94.6% accuracy using Deep Learning. Patients with autism struggle with social skills, repetitive behaviors, and communication, both verbal and non-verbal. Although the disease is considered to be genetic, the highest rates of accurate diagnosis occur when the child is tested on behavioral characteristics and facial features. Patients have a common pattern of distinct facial deformities, allowing researchers to analyze only an image of the child to determine if the child has the disease. While there are other techniques and models used for facial analysis and autism classification on their own, our proposal bridges these two ideas allowing classification in a cheaper, more efficient method. Our deep learning model uses MobileNet and two dense layers to perform feature extraction and image classification. The model is trained and tested using 3,014 images, evenly split between children with autism and children without it; 90% of the data is used for training and 10% is used for testing. Based on our accuracy, we propose that the diagnosis of autism can be done effectively using only a picture. Additionally, there may be other diseases that are similarly diagnosable.

Microinjection is an essential process in genetic engineering that is used to deliver genetic materials into various biological specimens. Considering the high-throughput requirement for microinjection applications ranging from gene editing to cell therapies, there is a need for an automated, highly parallelized, reproducible, and easy-to-use microinjection strategy. Here we report an on-chip, microfluidic microinjection module designed for compatibility with microfluidic large-scale integration (mLSI) technology and that can be fabricated via standard, multilayer soft lithography techniques. The needle-on-chip (NOC) module consists of a two-layer PDMS-based microfluidic module whose puncture and injection operations are reliant solely on Quake valve actuation. We designed a NOC module to conduct the microinjection of a common genetics model organism, Caenorhabditis elegans (C. elegans). The NOC design was analyzed using finite element method simulations for a large range of practically viable geometrical parameters. The computational results suggested that a slight lateral offset (>10 μm) of the control channel is sufficient for a successful NOC operation with a large fabrication tolerance (50 μm, 50% channel width). To demonstrate proof-of-concept, the microinjection platform was fabricated and utilized to perform a successful injection of a tracer dye into C. elegans.

Nanoporous dialysis membranes made of regenerated cellulose are used as molecular weight cutoff standards in bioseparations. In this study, mesoporous standards with Stokes’ radii (50 kDa/2.7 nm, 100 kDa/3.4 nm and 1000 kDa/7.3 nm) and overlapping skewed distributions were characterized using AFM, with the specific aim of generating pore size classifiers for biomimetic membranes using supervised learning. Gamma transformation was used prior to conducting discriminant analysis in terms of the area under the receiver operating curve (AUC) and classification accuracy (Acc). Monte Carlo simulations were run to generate datasets (n = 10) on which logistic regression was conducted using a constant ratio of 80:20 (measurement:algorithm training), followed by algorithm validation by WEKA. The proposed algorithm can classify the 1000 kDa vs. 100 kDa (AUC > 0.8) correctly, but discrimination is weak for the 100 kDa vs. 50 kDa (AUC < 0.7), the latter being attributed to the instrument accuracy errors below 5 nm. As indicated by the results of the cross-validation study, a test size equivalent to 70% (AUCtapping = 0.8341 ± 0.0519, Acctapping = 76.8% ± 5.9%) and 80% (AUCfluid = 0.7614 ± 0.0314, Acctfluid = 76.2% ± 1.0%) of the training sets for the tapping and fluid modes are needed for correct classification, resulting in predicted reduction of scan times.