Cognitive effort detection for tele-robotic surgery via personalized pupil response modeling.

PURPOSE: Gaze tracking and pupillometry are established proxies for cognitive load, giving insights into a user's mental effort. In tele-robotic surgery, knowing a user's cognitive load can inspire novel human-machine interaction designs, fostering contextual surgical assistance systems and personalized training programs. While pupillometry-based methods for estimating cognitive effort have been proposed, their application in surgery is limited by the pupil's sensitivity to brightness changes, which can mask pupil's response to cognitive load. Thus, methods considering pupil and brightness conditions are essential for detecting cognitive effort in unconstrained scenarios. METHODS: To contend with this challenge, we introduce a personalized pupil response model integrating pupil and brightness-based features. Discrepancies between predicted and measured pupil diameter indicate dilations due to non-brightness-related sources, i.e., cognitive effort. Combined with gaze entropy, it can detect cognitive load using a random forest classifier. To test our model, we perform a user study with the da Vinci Research Kit, where 17 users perform pick-and-place tasks in addition to auditory tasks known to generate cognitive effort responses. RESULTS: We compare our method to two baselines (BCPD and CPD), demonstrating favorable performance in varying brightness conditions. Our method achieves an average true positive rate of 0.78, outperforming the baselines (0.57 and 0.64). CONCLUSION: We present a personalized brightness-aware model for cognitive effort detection able to operate under unconstrained brightness conditions, comparing favorably to competing approaches, contributing to the advancement of cognitive effort detection in tele-robotic surgery. Future work will consider alternative learning strategies, handling the difficult positive-unlabeled scenario in user studies, where only some positive and no negative events are reliably known.

Unlocking cellular barriers: silica nanoparticles and fullerenol conjugated cell-penetrating agents for enhanced intracellular drug delivery.

The limited delivery of cargoes at the cellular level is a significant challenge for therapeutic strategies due to the presence of numerous biological barriers. By immobilizing the Buforin II (BUF-II) peptide and the OmpA protein on magnetite nanoparticles, a new family of cell-penetrating nanobioconjugates was developed in a previous study. We propose in this study to extend this strategy to silica nanoparticles (SNPs) and silanized fullerenol (F) as nanostructured supports for conjugating these potent cell-penetrating agents. The same molecule conjugated to distinct nanomaterials may interact with subcellular compartments differently. On the obtained nanobioconjugates (OmpA-SNPs, BUF-II-PEG12-SNPs, OmpA-F, and BUF-II-PEG12-F), physicochemical characterization was performed to evaluate their properties and confirm the conjugation of these translocating agents on the nanomaterials. The biocompatibility, toxicity, and internalization capacity of nanobioconjugates in Vero cells and THP-1 cells were evaluated in vitro. Nanobioconjugates had a high internalization capacity in these cells without affecting their viability, according to the findings. In addition, the nanobioconjugates exhibited negligible hemolytic activity and a low tendency to induce platelet aggregation. In addition, the nanobioconjugates exhibited distinct intracellular trafficking and endosomal escape behavior in these cell lines, indicating their potential for addressing the challenges of cytoplasmic drug delivery and the development of therapeutics for the treatment of lysosomal storage diseases. This study presents an innovative strategy for conjugating cell-penetrating agents using silica nanoparticles and silanized fullerenol as nanostructured supports, which has the potential to enhance the efficacy of cellular drug delivery.

Multifunctional magnetoliposomes as drug delivery vehicles for the potential treatment of Parkinson's disease.

Parkinson's disease (PD) is the second most common neurodegenerative disorder after Alzheimer's disease. Therefore, development of novel technologies and strategies to treat PD is a global health priority. Current treatments include administration of Levodopa, monoamine oxidase inhibitors, catechol-O-methyltransferase inhibitors, and anticholinergic drugs. However, the effective release of these molecules, due to the limited bioavailability, is a major challenge for the treatment of PD. As a strategy to solve this challenge, in this study we developed a novel multifunctional magnetic and redox-stimuli responsive drug delivery system, based on the magnetite nanoparticles functionalized with the high-performance translocating protein OmpA and encapsulated into soy lecithin liposomes. The obtained multifunctional magnetoliposomes (MLPs) were tested in neuroblastoma, glioblastoma, primary human and rat astrocytes, blood brain barrier rat endothelial cells, primary mouse microvascular endothelial cells, and in a PD-induced cellular model. MLPs demonstrated excellent performance in biocompatibility assays, including hemocompatibility (hemolysis percentages below 1%), platelet aggregation, cytocompatibility (cell viability above 80% in all tested cell lines), mitochondrial membrane potential (non-observed alterations) and intracellular ROS production (negligible impact compared to controls). Additionally, the nanovehicles showed acceptable cell internalization (covered area close to 100% at 30 min and 4 h) and endosomal escape abilities (significant decrease in lysosomal colocalization after 4 h of exposure). Moreover, molecular dynamics simulations were employed to better understand the underlying translocating mechanism of the OmpA protein, showing key findings regarding specific interactions with phospholipids. Overall, the versatility and the notable in vitro performance of this novel nanovehicle make it a suitable and promising drug delivery technology for the potential treatment of PD.

Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence.

Antibiotic resistance is a worldwide public health problem due to the costs and mortality rates it generates. However, the large pharmaceutical industries have stopped searching for new antibiotics because of their low profitability, given the rapid replacement rates imposed by the increasingly observed resistance acquired by microorganisms. Alternatively, antimicrobial peptides (AMPs) have emerged as potent molecules with a much lower rate of resistance generation. The discovery of these peptides is carried out through extensive in vitro screenings of either rational or non-rational libraries. These processes are tedious and expensive and generate only a few AMP candidates, most of which fail to show the required activity and physicochemical properties for practical applications. This work proposes implementing an artificial intelligence algorithm to reduce the required experimentation and increase the efficiency of high-activity AMP discovery. Our deep learning (DL) model, called AMPs-Net, outperforms the state-of-the-art method by 8.8% in average precision. Furthermore, it is highly accurate to predict the antibacterial and antiviral capacity of a large number of AMPs. Our search led to identifying two unreported antimicrobial motifs and two novel antimicrobial peptides related to them. Moreover, by coupling DL with molecular dynamics (MD) simulations, we were able to find a multifunctional peptide with promising therapeutic effects. Our work validates our previously proposed pipeline for a more efficient rational discovery of novel AMPs.

Predicting target-ligand interactions with graph convolutional networks for interpretable pharmaceutical discovery.

Drug Discovery is an active research area that demands great investments and generates low returns due to its inherent complexity and great costs. To identify potential therapeutic candidates more effectively, we propose protein-ligand with adversarial augmentations network (PLA-Net), a deep learning-based approach to predict target-ligand interactions. PLA-Net consists of a two-module deep graph convolutional network that considers ligands' and targets' most relevant chemical information, successfully combining them to find their binding capability. Moreover, we generate adversarial data augmentations that preserve relevant biological backgrounds and improve the interpretability of our model, highlighting the relevant substructures of the ligands reported to interact with the protein targets. Our experiments demonstrate that the joint ligand-target information and the adversarial augmentations significantly increase the interaction prediction performance. PLA-Net achieves 86.52% in mean average precision for 102 target proteins with perfect performance for 30 of them, in a curated version of actives as decoys dataset. Lastly, we accurately predict pharmacologically-relevant molecules when screening the ligands of ChEMBL and drug repurposing Hub datasets with the perfect-scoring targets.

PharmaNet: Pharmaceutical discovery with deep recurrent neural networks.

The discovery and development of novel pharmaceuticals is an area of active research mainly due to the large investments required and long payback times. As of 2016, the development of a novel drug candidate required up to $ USD 2.6 billion in investment for only 10% rate of approval by the FDA. To help decreasing the costs associated with the process, a number of in silico approaches have been developed with relatively low success due to limited predicting performance. Here, we introduced a machine learning-based algorithm as an alternative for a more accurate search of new pharmacological candidates, which takes advantage of Recurrent Neural Networks (RNN) for active molecule prediction within large databases. Our approach, termed PharmaNet was implemented here to search for ligands against specific cell receptors within 102 targets of the DUD-E database, which contains 22886 active molecules. PharmaNet comprises three main phases. First, a SMILES representation of the molecule is converted into a raw molecular image. Second, a convolutional encoder processes the data to obtain a fingerprint molecular image that is finally analyzed by a Recurrent Neural Network (RNN). This approach enables precise predictions of the molecules' target on the basis of the feature extraction, the sequence analysis and the relevant information filtered out throughout the process. Molecule Target prediction is a highly unbalanced detection problem and therefore, we propose that an adequate evaluation metric of performance is the area under the Normalized Average Precision (NAP) curve. PharmaNet largely surpasses the previous state-of-the-art method with 97.7% in the Receiver Operating Characteristic curve (ROC-AUC) and 65.5% in the NAP curve. We obtained a perfect performance for human farnesyl pyrophosphate synthase (FPPS), which is a potential target for antimicrobial and anticancer treatments. We decided to test PharmaNet for activity prediction against FPPS by searching in the CHEMBL data set. We obtained three (3) potential inhibitors that were further validated through both molecular docking and in silico toxicity prediction. Most importantly, one of this candidates, CHEMBL2007613, was predicted as a potential antiviral due to its involvement on the PCDH17 pathway, which has been reported to be related to viral infections.

Enzyme-Based Electrochemical Biosensors for Microfluidic Platforms to Detect Pharmaceutical Residues in Wastewater.

Emerging water pollutants such as pharmaceutical contaminants are suspected to induce adverse effects to human health. These molecules became worrisome due to their increasingly high concentrations in surface waters. Despite this alarming situation, available data about actual concentrations in the environment is rather scarce, as it is not commonly monitored or regulated. This is aggravated even further by the absence of portable and reliable methods for their determination in the field. A promising way to tackle these issues is the use of enzyme-based and miniaturized biosensors for their electrochemical detection. Here, we present an overview of the latest developments in amperometric microfluidic biosensors that include, modeling and multiphysics simulation, design, manufacture, testing, and operation methods. Different types of biosensors are described, highlighting those based on oxidases/peroxidases and the integration with microfluidic platforms. Finally, issues regarding the stability of the biosensors and the enzyme molecules are discussed, as well as the most relevant approaches to address these obstacles.