Unveiling New Druggable Pockets in Influenza Non-Structural Protein 1: NS1-Host Interactions as Antiviral Targets for Flu.

Influenza viruses are responsible for significant morbidity and mortality worldwide in winter seasonal outbreaks and in flu pandemics. Influenza viruses have a high rate of evolution, requiring annual vaccine updates and severely diminishing the effectiveness of the available antivirals. Identifying novel viral targets and developing new effective antivirals is an urgent need. One of the most promising new targets for influenza antiviral therapy is non-structural protein 1 (NS1), a highly conserved protein exclusively expressed in virus-infected cells that mediates essential functions in virus replication and pathogenesis. Interaction of NS1 with the host proteins PI3K and TRIM25 is paramount for NS1's role in infection and pathogenesis by promoting viral replication through the inhibition of apoptosis and suppressing interferon production, respectively. We, therefore, conducted an analysis of the druggability of this viral protein by performing molecular dynamics simulations on full-length NS1 coupled with ligand pocket detection. We identified several druggable pockets that are partially conserved throughout most of the simulation time. Moreover, we found out that some of these druggable pockets co-localize with the most stable binding regions of the protein-protein interaction (PPI) sites of NS1 with PI3K and TRIM25, which suggests that these NS1 druggable pockets are promising new targets for antiviral development.

Doomed for carcinomatosis? An unusual presentation of abdominal tuberculosis.

A 35-year old male from Brazil presented with intermittent abdominal pain. Abdominal computed tomography revealed a nodule adjacent to splenic hilum and multiple abdominal nodules, suspicious of carcinomatosis. The patient underwent gastroscopy and endoscopic ultrasound (EUS), that revealed an ill-defined hypoechogenic lesion adjacent to the spleen and two hypoechogenic subepithelial lesions located in the 4th layer of the stomach and duodenal bulb. Biopsies revealed non-necrotizing granulomatous inflammation with multinucleated giant cells. Soon after, a 18cm palpable mass within the rectus abdominis muscle was identified, and the biopsy was positive for Mycobacterium tuberculosis DNA, confirming the diagnosis of disseminated abdominal tuberculosis.

Factors Influencing Performance of Cholangioscopy-Guided Lithotripsy Including Available Different Technologies: A Prospective Multicenter Study with 94 Patients.

BACKGROUND: Peroral cholangioscopy (POC)-guided lithotripsy is an effective treatment for difficult biliary stones. A clear definition of factors associated with the efficacy of POC-guided lithotripsy in one session and the performance of electrohydraulic lithotripsy (EHL) and laser lithotripsy (LL) have not clearly emerged. METHODS: This was a non-randomized prospective multicenter study of all consecutive patients who underwent POC lithotripsy (using EHL and/or LL) for difficult biliary stones. The primary endpoint of the study was the number of sessions needed to achieve complete ductal clearance and the factors associated with this outcome. Secondary endpoints included the evaluated efficacies of LL and EHL. RESULTS: Ninety-four patients underwent 113 procedures of EHL or LL. Complete ductal clearance was obtained in 93/94 patients (98.94%). In total, 80/94 patients (85.11%) achieved stone clearance in a single session. In the multivariate analysis, stone size was independently associated with the need for multiple sessions to achieve complete ductal clearance (odds ratio = 1.146, 95% confidence interval: 1.055-1.244; p = 0.001). Using ROC curves and the Youden index, 22 mm was found to be the optimal cutoff for stone size (95% confidence interval: 15.71-28.28; p < 0.001). The majority of the patients (62.8%) underwent LL in the first session. Six patients failed the first session with EHL after using two probes and therefore were crossed over to LL, obtaining ductal clearance in a single additional session with a single LL fiber. EHL was significantly associated with a larger number of probes (2.0 vs. 1.02) to achieve ductal clearance (p < 0.01). The mean procedural time was significantly longer for EHL than for LL [72.1 (SD 16.3 min) versus 51.1 (SD 10.5 min)] (p < 0.01). CONCLUSIONS: POC is highly effective for difficult biliary stones. Most patients achieved complete ductal clearance in one session, which was significantly more likely for stones < 22 mm. EHL was significantly associated with the need for more probes and a longer procedural time to achieve ductal clearance.

Augmenting Adaptive Machine Learning with Kinetic Modeling for Reaction Optimization.

We combine random sampling and active machine learning (ML) to optimize the synthesis of isomacroin, executing only 3% of all possible Friedländer reactions. Employing kinetic modeling, we augment machine intuition by extracting mechanistic knowledge and verify that a global optimum was obtained with ML. Our study contributes evidence on the potential of multiscale approaches to expedite the access to chemical matter, further democratizing organic chemistry in a data-motivated fashion.

Use of the margin of stability to quantify stability in pathologic gait - a qualitative systematic review.

BACKGROUND: The Margin of Stability (MoS) is a widely used objective measure of dynamic stability during gait. Increasingly, researchers are using the MoS to assess the stability of pathological populations to gauge their stability capabilities and coping strategies, or as an objective marker of outcome, response to treatment or disease progression. The objectives are; to describe the types of pathological gait that are assessed using the MoS, to examine the methods used to assess MoS and to examine the way the MoS data is presented and interpreted. METHODS: A systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Guidelines (PRISMA) in the following databases: Web of Science, PubMed, UCL Library Explore, Cochrane Library, Scopus. All articles measured the MoS of a pathologically affected adult human population whilst walking in a straight line. Extracted data were collected per a prospectively defined list, which included: population type, method of data analysis and model building, walking tasks undertaken, and interpretation of the MoS. RESULTS: Thirty-one studies were included in the final review. More than 15 different clinical populations were studied, most commonly post-stroke and unilateral transtibial amputee populations. Most participants were assessed in a gait laboratory using motion capture technology, whilst 2 studies used instrumented shoes. A variety of centre of mass, base of support and MoS definitions and calculations were described. CONCLUSIONS: This is the first systematic review to assess use of the MoS and the first to consider its clinical application. Findings suggest the MoS has potential to be a helpful, objective measurement in a variety of clinically affected populations. Unfortunately, the methodology and interpretation varies, which hinders subsequent study comparisons. A lack of baseline results from large studies mean direct comparison between studies is difficult and strong conclusions are hard to make. Further work from the biomechanics community to develop reporting guidelines for MoS calculation methodology and a commitment to larger baseline studies for each pathology is welcomed.

Eslicarbazepine acetate in post-stroke epilepsy: Clinical practice evidence from Euro-Esli.

OBJECTIVES: To assess the effectiveness and safety/tolerability of eslicarbazepine acetate (ESL) in patients included in the Euro-Esli study who had focal seizures associated with post-stroke epilepsy (PSE). MATERIALS AND METHODS: Euro-Esli was a pooled analysis of 14 European clinical practice studies. Effectiveness assessments (evaluated after 3, 6 and 12 months of ESL treatment and at final follow-up ["last visit"]) included rates of response (≥50% seizure frequency reduction), seizure freedom (no seizures since at least the prior visit) and retention. Safety/tolerability was assessed throughout ESL treatment by evaluating adverse events (AEs) and discontinuation due to AEs. A post hoc analysis was conducted of patients with PSE versus patients without PSE ("non-PSE"). RESULTS: Of 1656 patients included in the analysis, 76 (4.6%) had PSE and 1580 (95.4%) had non-PSE. Compared with non-PSE patients, PSE patients were significantly older, had significantly shorter epilepsy duration, significantly lower total baseline seizure frequency, and were treated with significantly fewer prior and concomitant antiepileptic drugs (P < .001 for all). At the last visit, the responder rate was significantly higher in PSE versus non-PSE patients (72.9% vs 60.6%; P = .040), as was the seizure freedom rate (48.6% vs 31.7%; P = .003). After 12 months, retention was significantly higher in PSE versus non-PSE patients (87.8% vs 77.4%; P = .035). The incidence of AEs was similar for PSE versus non-PSE patients (36.0% vs 35.8%; P = .966). CONCLUSIONS: These findings suggest that ESL may be an effective and well-tolerated treatment option for patients with focal seizures due to PSE.

Prostate Cancer Risk Calculator Apps in a Taiwanese Population Cohort: Validation Study.

BACKGROUND: Mobile health apps have emerged as useful tools for patients and clinicians alike, sharing health information or assisting in clinical decision-making. Prostate cancer (PCa) risk calculator mobile apps have been introduced to assess risks of PCa and high-grade PCa (Gleason score ≥7). The Rotterdam Prostate Cancer Risk Calculator and Coral-Prostate Cancer Nomogram Calculator apps were developed from the 2 most-studied PCa risk calculators, the European Randomized Study of Screening for Prostate Cancer (ERSPC) and the North American Prostate Cancer Prevention Trial (PCPT) risk calculators, respectively. A systematic review has indicated that the Rotterdam and Coral apps perform best during the prebiopsy stage. However, the epidemiology of PCa varies among different populations, and therefore, the applicability of these apps in a Taiwanese population needs to be evaluated. This study is the first to validate the PCa risk calculator apps with both biopsy and prostatectomy cohorts in Taiwan. OBJECTIVE: The study's objective is to validate the PCa risk calculator apps using a Taiwanese cohort of patients. Additionally, we aim to utilize postprostatectomy pathology outcomes to assess the accuracy of both apps with regard to high-grade PCa. METHODS: All male patients who had undergone transrectal ultrasound prostate biopsies in a single Taiwanese tertiary medical center from 2012 to 2018 were identified retrospectively. The probabilities of PCa and high-grade PCa were calculated utilizing the Rotterdam and Coral apps, and compared with biopsy and prostatectomy results. Calibration was graphically evaluated with the Hosmer-Lemeshow goodness-of-fit test. Discrimination was analyzed utilizing the area under the receiver operating characteristic curve (AUC). Decision curve analysis was performed for clinical utility. RESULTS: Of 1134 patients, 246 (21.7%) were diagnosed with PCa; of these 246 patients, 155 (63%) had high-grade PCa, according to the biopsy results. After confirmation with prostatectomy pathological outcomes, 47.2% (25/53) of patients were upgraded to high-grade PCa, and 1.2% (1/84) of patients were downgraded to low-grade PCa. Only the Rotterdam app demonstrated good calibration for detecting high-grade PCa in the biopsy cohort. The discriminative ability for both PCa (AUC: 0.779 vs 0.687; DeLong's method: P<.001) and high-grade PCa (AUC: 0.862 vs 0.758; P<.001) was significantly better for the Rotterdam app. In the prostatectomy cohort, there was no significant difference between both apps (AUC: 0.857 vs 0.777; P=.128). CONCLUSIONS: The Rotterdam and Coral apps can be applied to the Taiwanese cohort with accuracy. The Rotterdam app outperformed the Coral app in the prediction of PCa and high-grade PCa. Despite the small size of the prostatectomy cohort, both apps, to some extent, demonstrated the predictive capacity for true high-grade PCa, confirmed by the whole prostate specimen. Following our external validation, the Rotterdam app might be a good alternative to help detect PCa and high-grade PCa for Taiwanese men.

A tale of two tails: The importance of unstructured termini in the aggregation pathway of ß2-microglobulin.

The identification of intermediate states for folding and aggregation is important from a fundamental standpoint and for the design of novel therapeutic strategies targeted at conformational disorders. Protein human ß2-microglobulin (HB2m) is classically associated with dialysis-related amyloidosis, but the single point mutant D76N was recently identified as the causative agent of a hereditary systemic amyloidosis affecting visceral organs. Here, we use D76N as a model system to explore the early stage of the aggregation mechanism of HB2m by means of an integrative approach framed on molecular simulations. Discrete molecular dynamics simulations of a structured-based model predict the existence of two intermediate states populating the folding landscape. The intermediate I1 features an unstructured C-terminus, while I2 , which is exclusively populated by the mutant, exhibits two unstructured termini. Docking simulations indicate that I2 is the key species for aggregation at acidic and physiological pH contributing to rationalize the higher amyloidogenic potential of D76N relative to the wild-type protein and the ΔN6 variant. The analysis carried out here recapitulates the importance of the DE-loop in HB2m self-association at a neutral pH and predicts a leading role of the C-terminus and the adjacent G-strand in the dimerization process under acidic conditions. The identification of aggregation hot-spots is in line with experimental results that support the importance of Phe56, Asp59, Trp60, Phe62, Tyr63, and Tyr66 in HB2m amyloidogenesis. We further predict the involvement of new residues such as Lys94 and Trp95 in the aggregation process.

An Ultralow-Power Real-Time Machine Learning Based fNIRS Motion Artifacts Detection.

Due to iterative matrix multiplications or gradient computations, machine learning modules often require a large amount of processing power and memory. As a result, they are often not feasible for use in wearable devices, which have limited processing power and memory. In this study, we propose an ultralow-power and real-time machine learning-based motion artifact detection module for functional near-infrared spectroscopy (fNIRS) systems. We achieved a high classification accuracy of 97.42%, low field-programmable gate array (FPGA) resource utilization of 38354 lookup tables and 6024 flip-flops, as well as low power consumption of 0.021 W in dynamic power. These results outperform conventional CPU support vector machine (SVM) methods and other state-of-the-art SVM implementations. This study has demonstrated that an FPGA-based fNIRS motion artifact classifier can be exploited while meeting low power and resource constraints, which are crucial in embedded hardware systems while keeping high classification accuracy.

Interaction between a water-soluble anionic porphyrin and human serum albumin unexpectedly stimulates the aggregation of the photosensitizer at the surface of the albumin.

The 5,10,15,20-tetrakis(2,6-difluoro-3-sulfophenyl)porphyrin (TDFPPS4) was reported as a potential photosensitizer for photodynamic therapy. The capacity of the photosensitizers to be carried in the human bloodstream is predominantly determined by its extension of binding, binding location, and binding mechanism to human serum albumin (HSA), influencing its biodistribution and ultimately its photodynamic therapy efficacy in vivo. Thus, the present work reports a biophysical characterization on the interaction between the anionic porphyrin TDFPPS4 and HSA by UV-visible absorption, circular dichroism, steady-state, time-resolved, and synchronous fluorescence techniques under physiological conditions, combined with molecular docking calculations and molecular dynamics simulations. The interaction HSA:TDFPPS4 is spontaneous (ΔG° < 0), strong, and enthalpically driven (ΔH° = -70.1 ± 3.3 kJ mol-1) into subdomain IIA (site I). Curiously, despite the porphyrin binding into an internal pocket, about 50 % of TDFPPS4 structure is still accessible to the solvent, making aggregation in the bloodstream possible. In silico calculations were reinforced by spectroscopic data indicating porphyrin aggregation between bound and unbound porphyrins. This results in an adverse scenario for anionic porphyrins to achieve their therapeutical potential as photosensitizers and control of effective dosages. Finally, a trend of anionic porphyrins to have a combination of quenching mechanisms (static and dynamic) was noticed.

Folding Kinetics and Volume Variation of the ß-Hairpin Peptide Chignolin upon Ultrafast pH-Jumps.

In-depth characterization of fundamental folding steps of small model peptides is crucial for a better understanding of the folding mechanisms of more complex biomacromolecules. We have previously reported on the folding/unfolding kinetics of a model α-helix. Here, we study folding transitions in chignolin (GYDPETGTWG), a short ß-hairpin peptide previously used as a model to study conformational changes in ß-sheet proteins. Although previously suggested, until now, the role of the Tyr2-Trp9 interaction in the folding mechanism of chignolin was not clear. In the present work, pH-dependent conformational changes of chignolin were characterized by circular dichroism (CD), nuclear magnetic resonance (NMR), ultrafast pH-jump coupled with time-resolved photoacoustic calorimetry (TR-PAC), and molecular dynamics (MD) simulations. Taken together, our results present a comprehensive view of chignolin's folding kinetics upon local pH changes and the role of the Tyr2-Trp9 interaction in the folding process. CD data show that chignolin's ß-hairpin formation displays a pH-dependent skew bell-shaped curve, with a maximum close to pH 6, and a large decrease in ß-sheet content at alkaline pH. The ß-hairpin structure is mainly stabilized by aromatic interactions between Tyr2 and Trp9 and CH-π interactions between Tyr2 and Pro4. Unfolding of chignolin at high pH demonstrates that protonation of Tyr2 is essential for the stability of the ß-hairpin. Refolding studies were triggered by laser-induced pH-jumps and detected by TR-PAC. The refolding of chignolin from high pH, mainly due to the protonation of Tyr2, is characterized by a volume expansion (10.4 mL mol-1), independent of peptide concentration, in the microsecond time range (lifetime of 1.15 µs). At high pH, the presence of the deprotonated hydroxyl (tyrosinate) hinders the formation of the aromatic interaction between Tyr2 and Trp9 resulting in a more disorganized and dynamic tridimensional structure of the peptide. This was also confirmed by comparing MD simulations of chignolin under conditions mimicking neutral and high pH.

Increasing the polarity of ß-lapachone does not affect its binding capacity with bovine plasma protein.

Despite ortho-quinones showing several biological and pharmacological activities, there is still a lack of biophysical characterization of their interaction with albumin - the main carrier of different endogenous and exogenous compounds in the bloodstream. Thus, the interactive profile between bovine serum albumin (BSA) with ß-lapachone (1) and its corresponding synthetic 3-sulfonic acid (2, under physiological pH in the sulphonate form) was performed. There is one main binding site of albumin for both ß-lapachones (n ≈ 1) and a static fluorescence quenching mechanism was proposed. The Stern-Volmer constant (KSV) values are 104 M-1, indicating a moderate binding affinity. The enthalpy (-3.41 ± 0.45 and - 8.47 ± 0.37 kJ mol-1, for BSA:1 and BSA:2, respectively) and the corresponding entropy (0.0707 ± 0.0015 and 0.0542 ± 0.0012 kJ mol-1 K-1) values indicate an enthalpically and entropically binding driven. Hydrophobic interactions and hydrogen bonding are the main binding forces. The differences in the polarity of 1 and 2 did not change significantly the affinity to albumin. In addition, the 1,2-naphthoquinones showed a similar binding trend compared with 1,4-naphthoquinones.

AI enhanced collaborative human-machine interactions for home-based telerehabilitation.

The use of robots in a telerehabilitation paradigm could facilitate the delivery of rehabilitation on demand while reducing transportation time and cost. As a result, it helps to motivate patients to exercise frequently in a more comfortable home environment. However, for such a paradigm to work, it is essential that the robustness of the system is not compromised due to network latency, jitter, and delay of the internet. This paper proposes a solution to data loss compensation to maintain the quality of the interaction between the user and the system. Data collected from a well-defined collaborative task using a virtual reality (VR) environment was used to train a robotic system to adapt to the users' behaviour. The proposed approach uses nonlinear autoregressive models with exogenous input (NARX) and long-short term memory (LSTM) neural networks to smooth out the interaction between the user and the predicted movements generated from the system. LSTM neural networks are shown to learn to act like an actual human. The results from this paper have shown that, with an appropriate training method, the artificial predictor can perform very well by allowing the predictor to complete the task within 25 s versus 23 s when executed by the human.

Learning based motion artifacts processing in fNIRS: a mini review.

This paper provides a concise review of learning-based motion artifacts (MA) processing methods in functional near-infrared spectroscopy (fNIRS), highlighting the challenges of maintaining optimal contact during subject movement, which can lead to MA and compromise data integrity. Traditional strategies often result in reduced reliability of the hemodynamic response and statistical power. Recognizing the limited number of studies focusing on learning-based MA removal, we examine 315 studies, identifying seven pertinent to our focus area. We discuss the current landscape of learning-based MA correction methods and highlight research gaps. Noting the absence of standard evaluation metrics for quality assessment of MA correction, we suggest a novel framework, integrating signal and model quality considerations and employing metrics like ΔSignal-to-Noise Ratio (ΔSNR), confusion matrix, and Mean Squared Error. This work aims to facilitate the application of learning-based methodologies to fNIRS and improve the accuracy and reliability of neurovascular studies.

Review of recent advances in frequency-domain near-infrared spectroscopy technologies [Invited].

Over the past several decades, near-infrared spectroscopy (NIRS) has become a popular research and clinical tool for non-invasively measuring the oxygenation of biological tissues, with particular emphasis on applications to the human brain. In most cases, NIRS studies are performed using continuous-wave NIRS (CW-NIRS), which can only provide information on relative changes in chromophore concentrations, such as oxygenated and deoxygenated hemoglobin, as well as estimates of tissue oxygen saturation. Another type of NIRS known as frequency-domain NIRS (FD-NIRS) has significant advantages: it can directly measure optical pathlength and thus quantify the scattering and absorption coefficients of sampled tissues and provide direct measurements of absolute chromophore concentrations. This review describes the current status of FD-NIRS technologies, their performance, their advantages, and their limitations as compared to other NIRS methods. Significant landmarks of technological progress include the development of both benchtop and portable/wearable FD-NIRS technologies, sensitive front-end photonic components, and high-frequency phase measurements. Clinical applications of FD-NIRS technologies are discussed to provide context on current applications and needed areas of improvement. The review concludes by providing a roadmap toward the next generation of fully wearable, low-cost FD-NIRS systems.

fNIRS-EEG BCIs for Motor Rehabilitation: A Review.

Motor impairment has a profound impact on a significant number of individuals, leading to a substantial demand for rehabilitation services. Through brain-computer interfaces (BCIs), people with severe motor disabilities could have improved communication with others and control appropriately designed robotic prosthetics, so as to (at least partially) restore their motor abilities. BCI plays a pivotal role in promoting smoother communication and interactions between individuals with motor impairments and others. Moreover, they enable the direct control of assistive devices through brain signals. In particular, their most significant potential lies in the realm of motor rehabilitation, where BCIs can offer real-time feedback to assist users in their training and continuously monitor the brain's state throughout the entire rehabilitation process. Hybridization of different brain-sensing modalities, especially functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG), has shown great potential in the creation of BCIs for rehabilitating the motor-impaired populations. EEG, as a well-established methodology, can be combined with fNIRS to compensate for the inherent disadvantages and achieve higher temporal and spatial resolution. This paper reviews the recent works in hybrid fNIRS-EEG BCIs for motor rehabilitation, emphasizing the methodologies that utilized motor imagery. An overview of the BCI system and its key components was introduced, followed by an introduction to various devices, strengths and weaknesses of different signal processing techniques, and applications in neuroscience and clinical contexts. The review concludes by discussing the possible challenges and opportunities for future development.

Congenital cystic lesions of the biliary tree.

OBJECTIVE: The purpose of this essay is to illustrate the imaging findings of congenital cystic lesions of the biliary tract. CONCLUSION: Congenital cystic lesions of the biliary tract include ductal plate malformations and choledochal cysts and can be recognized with characteristic imaging findings and basic knowledge of the embryologic development of the biliary tree.

Virtual Reality combined with Robotic facilitated movements for pain management and sensory stimulation of the upper limb following a Brachial Plexus injury: A case study.

Brachial Plexus injuries are complex in nature caused in large by high impact traffic accidents which can lead to additional complications such as Complex Regional Pain Syndrome and even lead to amputation or the need for further surgical intervention. Treatment options to help repair the brachial plexus initially involve surgical intervention and post-surgery rehabilitation with medication to help with ongoing pain. Pain treatments used for these types of injuries are limited and differ in effectiveness. Paradigms utilising multimodal systems such as the one described in this paper based on virtual reality and robotics could yield results that are non-invasive and provide better rehabilitation outcomes for the sufferers. In this paper we present a single case study exploring whether Virtual Reality plus Haptic feedback have any practical potential for reducing upper limb pain and improving function in patients with brachial plexus injuries. The case study is presented with long standing complex combination of phantom limb and neuropathic pain. A decrease in perceived levels of pain was reported which amounts to a 50% reduction in pain from baseline and an improved range of motion. An examination of the sensory phantom map on the stump seems to indicate an early establishment of the thumb representation on the stump close to the area being stimulated with potential implications for prosthesis use.

Correlating Vibration Patterns to Perception of Tactile Information for Long-Term Prosthetic Limb Use and Continued Rehabilitation of Neuropathic Pain.

Prosthetic limbs (and orthotic devices) have been used as a paradigm for the treatment and rehabilitation of neuropathic pain, such as phantom limb pain. Long-term adoption of the devices for the continued use in rehabilitation remains low in part due to reduced embodiment and the high cognitive load associated with controlling the device. Previous research has shown that incorporating sensory feedback in prostheses can provide proprioceptive information, increase control and manipulation of objects, and improve embodiment. However, feedback experienced by the user varies daily and requires constant parameter adjustments to maintain accurate and intuitive sensory perception, further preventing long term adoption. Work therefore needs to be explored that correlate feedback modalities to perception of tactile information, such as texture and pressure. The work presented in this paper begins to explore this by utilizing a deep-learning algorithm to classify the dissipation of vibration artefacts found in the EMG signals of able-bodied individuals to specific texture patterns. Four texture patterns were applied to 7 participants using two vibration motors and repeated 3 times. In post processing, a RNN network identified the artefact features along equidistantly spaced EMG electrodes and correctly classified unseen data from each participant.