MDNNSyn: A Multi-Modal Deep Learning Framework for Drug Synergy Prediction.

Synergistic drug combination prediction tasks based on the computational models have been widely studied and applied in the cancer field. However, most of models only consider the interactions between drug pairs and specific cell lines, without taking into account the multiple biological relationships of drug-drug and cell line-cell line that also largely affect synergistic mechanisms. To this end, here we propose a multi-modal deep learning framework, termed MDNNSyn, which adequately applies multi-source information and trains multi-modal features to infer potential synergistic drug combinations. MDNNSyn extracts topology modality features by implementing the multi-layer hypergraph neural network on drug synergy hypergraph and constructs semantic modality features through similarity strategy. A multi-modal fusion network layer with gated neural network is then employed for synergy score prediction. MDNNSyn is compared to five classic and state-of-the-art prediction methods on DrugCombDB and Oncology-Screen datasets. The model achieves area under the curve (AUC) scores of 0.8682 and 0.9013 on two datasets, an improvement of 3.70% and 2.71% over the second-best model. Case study indicates that MDNNSyn is capable of detecting potential synergistic drug combinations.

Dual-clamped one-pot SERS-based biosensors for rapid and sensitive detection of SARS-CoV-2 using portable Raman spectrometer.

Rapid and sensitive diagnostics of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is of utmost importance to control the widespread coronavirus disease 2019 (COVID-19) upsurge. This study demonstrated a novel one-pot surface-enhanced Raman scattering (SERS) based immunoassay to detect SARS-CoV-2, without any washing process using a portable Raman spectrometer. The SERS-immune assay was designed using a regular digital versatile disk (DVD) substrate integrated with Raman reporter labeled silver nanoparticles for double clamping effects. The disks were molded to form nanopillar arrays and coated with silver film to enhance the sensitivity of immunoassay. The SERS platform demonstrated a limit of detection (LoD) up to 50 pg mL-1 for SARS-CoV-2 spike protein and virus-like-particle (VLP) protein in phosphate buffer saline within a turnaround time of 20 mins. Moreover, VLP protein spiked in untreated saliva achieved an LoD of 400 pg mL-1, providing a cycle threshold (Ct) value range of 30-32, closer to reverse transcription-polymerase chain reaction (RT-PCR) results (35-40) and higher than the commercial rapid antigen tests, ranging from 25 to 28. Therefore, the developed one-pot SERS based biosensor exhibited highly sensitive and rapid detection of SARS-CoV-2, which could be a potential point-of-care platform for early and cost-effective diagnosis of the COVID-19 virus.

A 3D-ACEK/SERS system for highly efficient and selectable electrokinetic bacteria concentration/detection/ antibiotic-susceptibility-test on whole blood.

This study demonstrates a novel multi-functional microfluidic system, designated three dimensional Alternative Current Electrokinetic/Surface Enhanced Raman Scattering (3D-ACEK/SERS), which can concentrate bacteria from whole blood, identify bacterial species, and determine antibiotic susceptibilities of the bacteria rapidly. The system consists of a hybrid electrokinetic mechanism, integrating AC-electroosmosis (AC-EO) and dielectrophoresis (DEP) that allows thousand-fold concentration of bacteria, including S. aureus, Escherichia coli, and Chryseobacterium indologenes, in the center of an electrode with a wide range of working distance (hundreds to thousands of µm), while exclusion of blood cells through negative DEP forces. This microchip employs SERS assay to determine the identity of the concentrated bacteria in approximately 2 min with a limit of detection of 3 CFU/ml, 5 orders of magnitude lower than that using standard centrifugation-purification process. Finally, label-free antibiotic susceptibility testing has been successfully demonstrated on the platform using both antibiotic-sensitive and multidrug-resistant bacterial strains illustrating a potential utility of the system to clinical applications.

Development of Surface-Enhanced Raman Scattering (SERS)-Based Surface-Corrugated Nanopillars for Biomolecular Detection of Colorectal Cancer.

In this paper, a nanobiosensor with surface-enhanced Raman scattering (SERS) capability is introduced for highly sensitive miRNA detection in colorectal cancer. This sensor was designed and fabricated by employing a nanoshielding mechanism from nanopolystyrene beads to resist reactive ion etching and allow anisotropic electrochemical etching, producing high-aspect-ratio, surface-corrugated nanopillars (SiNPs) on a silicon wafer to create extensive hot spots along the nanopillars for improved SERS signals. SERS enhancements were correlated with nanorange roughness, indicating that hot spots along the pillars were the crucial factor to improve the SERS effect. We achieved the detection capability of a trace amount of R6G (10-8 M), and the SERS signal enhancement factor (EF) was close to 1.0 × 107 on surface-corrugated gold SiNPs. miRNA samples were also demonstrated on this sensor with good sensitivity and specificity. The target molecule miR-21-Cy5 was easily monitored through Raman spectrum variation with a PCR-comparable concentration at around 100 pM with clear nucleotide-specific Raman signals, which is also suitable for biomolecule sensing.