Graph-pMHC: graph neural network approach to MHC class II peptide presentation and antibody immunogenicity.

Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been made in pMHCII presentation modeling due to the collection of large-scale pMHC mass spectrometry datasets (ligandomes) and advances in machine learning. Here, we develop graph-pMHC, a graph neural network approach to predict pMHCII presentation. We derive adjacency matrices for pMHCII using Alphafold2-multimer and address the peptide-MHC binding groove alignment problem with a simple graph enumeration strategy. We demonstrate that graph-pMHC dramatically outperforms methods with suboptimal inductive biases, such as the multilayer-perceptron-based NetMHCIIpan-4.0 (+20.17% absolute average precision). Finally, we create an antibody drug immunogenicity dataset from clinical trial data and develop a method for measuring anti-antibody immunogenicity risk using pMHCII presentation models. Our model increases receiver operating characteristic curve (ROC)-area under the ROC curve (AUC) by 2.57% compared to just filtering peptides by hits in OASis alone for predicting antibody drug immunogenicity.

Sensing Antibiotics in Wastewater Using Surface-Enhanced Raman Scattering.

Rapid and cost-effective detection of antibiotics in wastewater and through wastewater treatment processes is an important first step in developing effective strategies for their removal. Surface-enhanced Raman scattering (SERS) has the potential for label-free, real-time sensing of antibiotic contamination in the environment. This study reports the testing of two gold nanostructures as SERS substrates for the label-free detection of quinoline, a small-molecular-weight antibiotic that is commonly found in wastewater. The results showed that the self-assembled SERS substrate was able to quantify quinoline spiked in wastewater with a lower limit of detection (LoD) of 5.01 ppb. The SERStrate (commercially available SERS substrate with gold nanopillars) had a similar sensitivity for quinoline quantification in pure water (LoD of 1.15 ppb) but did not perform well for quinoline quantification in wastewater (LoD of 97.5 ppm) due to interferences from non-target molecules in the wastewater. Models constructed based on machine learning algorithms could improve the separation and identification of quinoline Raman spectra from those of interference molecules to some degree, but the selectivity of SERS intensification was more critical to achieve the identification and quantification of the target analyte. The results of this study are a proof-of-concept for SERS applications in label-free sensing of environmental contaminants. Further research is warranted to transform the concept into a practical technology for environmental monitoring.

Deep Learning Analysis of Vibrational Spectra of Bacterial Lysate for Rapid Antimicrobial Susceptibility Testing.

Rapid antimicrobial susceptibility testing (AST) is an integral tool to mitigate the unnecessary use of powerful and broad-spectrum antibiotics that leads to the proliferation of multi-drug-resistant bacteria. Using a sensor platform composed of surface-enhanced Raman scattering (SERS) sensors with control of nanogap chemistry and machine learning algorithms for analysis of complex spectral data, bacteria metabolic profiles post antibiotic exposure are correlated with susceptibility. Deep neural network models are able to discriminate the responses of Escherichia coli and Pseudomonas aeruginosa to antibiotics from untreated cells in SERS data in 10 min after antibiotic exposure with greater than 99% accuracy. Deep learning analysis is also able to differentiate responses from untreated cells with antibiotic dosages up to 10-fold lower than the minimum inhibitory concentration observed in conventional growth assays. In addition, analysis of SERS data using a generative model, a variational autoencoder, identifies spectral features in the P. aeruginosa lysate data associated with antibiotic efficacy. From this insight, a combinatorial dataset of metabolites is selected to extend the latent space of the variational autoencoder. This culture-free dataset dramatically improves classification accuracy to select effective antibiotic treatment in 30 min. Unsupervised Bayesian Gaussian mixture analysis achieves 99.3% accuracy in discriminating between susceptible versus resistant to antibiotic cultures in SERS using the extended latent space. Discriminative and generative models rapidly provide high classification accuracy with small sets of labeled data, which enormously reduces the amount of time needed to validate phenotypic AST with conventional growth assays. Thus, this work outlines a promising approach toward practical rapid AST.

Quantification of Analyte Concentration in the Single Molecule Regime Using Convolutional Neural Networks.

Single molecule (SM) detection represents the ultimate limit of chemical detection. Over the years, many experimental techniques have emerged with this capacity. Yet, SM detection and imaging methods produce large spectral data sets that benefit from chemometric methods. In particular, surface enhanced Raman scattering spectroscopy (SERS), with extensive applications in biosensing, is demonstrated to be particularly promising because Raman active molecules can be identified without recognition elements and is capable of SM detection. Yet quantification at ultralow analyte concentrations requiring detection of SM events remains an ongoing challenge, with the few existing methods requiring carefully developed calibration curves that must be redeveloped for each analyte molecule. In this work, we demonstrate that a convolutional neural network (CNN) model when applied to bundles of SERS spectra yields a robust, facile method for concentration quantification down to 10 fM using SM detection events. We further demonstrate that transfer learning, the process of reusing the weights of a trained CNN model, greatly reduces the amount of data required to train CNN models on new analyte molecules. These results point the way for unambiguous analysis of large spectral data sets and the use of SERS in important ultra low concentration chemical detection applications such as metabolomic profiling, water quality evaluation, and fundamental research.

Surface-Enhanced Raman Scattering-Based Odor Compass: Locating Multiple Chemical Sources and Pathogens.

Olfaction is important for identifying and avoiding toxic substances in living systems. Many efforts have been made to realize artificial olfaction systems that reflect the capacity of biological systems. A sophisticated example of an artificial olfaction device is the odor compass which uses chemical sensor data to identify odor source direction. Successful odor compass designs often rely on plume-based detection and mobile robots, where active, mechanical motion of the sensor platform is employed. Passive, diffusion-based odor compasses remain elusive as detection of low analyte concentrations and quantification of small concentration gradients from within the sensor platform are necessary. Further, simultaneously identifying multiple odor sources using an odor compass remains an ongoing challenge, especially for similar analytes. Here, we show that surface-enhanced Raman scattering (SERS) sensors overcome these challenges, and we present the first SERS odor compass. Using a grid array of SERS sensors, machine learning analysis enables reliable identification of multiple odor sources arising from diffusion of analytes from one or two localized sources. Specifically, convolutional neural network and support vector machine classifier models achieve over 90% accuracy for a multiple odor source problem. This system is then used to identify the location of an Escherichia coli biofilm via its complex signature of volatile organic compounds. Thus, the fabricated SERS chemical sensors have the needed limit of detection and quantification for diffusion-based odor compasses. Solving the multiple odor source problem with a passive platform opens a path toward an Internet of things approach to monitor toxic gases and indoor pathogens.

Longitudinal Monitoring of Biofilm Formation via Robust Surface-Enhanced Raman Scattering Quantification of Pseudomonas aeruginosa-Produced Metabolites.

Detection of bacterial metabolites at low concentrations in fluids with complex background allows for applications ranging from detecting biomarkers of respiratory infections to identifying contaminated medical instruments. Surface-enhanced Raman scattering (SERS) spectroscopy, when utilizing plasmonic nanogaps, has the relatively unique capacity to reach trace molecular detection limits in a label-free format, yet large-area device fabrication incorporating nanogaps with this level of performance has proven difficult. Here, we demonstrate the advantages of using chemical assembly to fabricate SERS surfaces with controlled nanometer gap spacings between plasmonic nanospheres. Control of nanogap spacings via the length of the chemical crosslinker provides uniform SERS signals, exhibiting detection of pyocyanin, a secondary metabolite of Pseudomonas aeruginosa, in aqueous media at concentration of 100 pg·mL-1. When using machine learning algorithms to analyze the SERS data of the conditioned medium from a bacterial culture, having a more complex background, we achieve 1 ng·mL-1 limit of detection of pyocyanin and robust quantification of concentration spanning 5 orders of magnitude. Nanogaps are also incorporated in an in-line microfluidic device, enabling longitudinal monitoring of P. aeruginosa biofilm formation via rapid pyocyanin detection in a medium effluent as early as 3 h after inoculation and quantification in under 9 h. Surface-attached bacteria exposed to a bactericidal antibiotic were differentially less susceptible after 10 h of growth, indicating that these devices may be useful for early intervention of bacterial infections.