Manual Steps Research Articles

PreAlgPro: Prediction of allergenic proteins with pre-trained protein language model and efficient neutral network

Allergy is a prevalent phenomenon, involving allergens such as nuts and milk. Avoiding exposure to allergens is the most effective preventive measure against allergic reactions. However, current homology-based methods for identifying allergenic proteins encounter challenges when dealing with non-homologous data. Traditional machine learning approaches rely on manually extracted features, which lack important protein functional characteristics, including evolutionary information. Consequently, there is still considerable room for improvement in existing methods. In this study, we present PreAlgPro, a method for identifying allergenic proteins based on pre-trained protein language models and deep learning techniques. Specifically, we employed the ProtT5 model to extract protein embedding features, replacing the manual feature extraction step. Furthermore, we devised an Attention-CNN neural network architecture to identify potential features that contribute to the classification of allergenic proteins. The performance of our model was evaluated on four independent test sets, and the experimental results demonstrate that PreAlgPro surpasses existing state-of-the-art methods. Additionally, we collected allergenic protein samples to validate the robustness of the model and conducted an analysis of model interpretability.

AI-Enhanced Allergy Diagnostics: Streamlining Healthcare and Reducing Costs

Abstract Issue/Problem WHO projects a shortfall of 10 million health workers by 2030. One area particularly lacking technological support is allergy diagnostics. The World Allergy Organization recognizes skin tests as the gold standard for allergy diagnostics, yet these tests are still manually assessed. General practitioners lack the time and tools, leading them to focus on treating the symptoms without addressing the causes. Description of the problem Symptomatic treatment of allergy can lead to the development of asthma in 30-40% of patients, increasing healthcare costs and causing lost productivity. The shortage of allergists further exacerbates this issue in many countries. Results Research conducted by the Military Institute of Medicine in Warsaw, in collaboration with a company producing automated allergy testing systems, explored a solution for allergy diagnostics, analyzing the entire process from the patient’s initial visit to desensitization therapy. The solution uses AI algorithms to reusable existing patient data and analyze patient history, correlate symptoms, medications, and allergen exposure, streamlining diagnostics and treatment. Patients at high risk undergo a computer-assisted interview to determine allergen panels. The only manual step is applying allergens to the skin, after which AI performs the reading and diagnosis. Clinical trials involving around 300 patients demonstrated high sensitivity and specificity, along with significant time savings for allergists and other medical staff, averaging 40 minutes per patient. The HTA evidence base will be ready by the end of this year. Lessons The integration of this AI-supported diagnostic method can eliminate bottlenecks in allergy diagnostics, improving health outcomes and reducing healthcare costs. However, its effectiveness depends on having at least few years of patient treatment data available. Without access to patient data, the method can be used in part to objectify PRICK test readings. Key messages • AI-supported diagnostics streamline allergy testing, reducing time and costs in the healthcare system. • The most accurate technique currently available for the automated reading of test results is that which evaluates the response to an allergen in the dermis in two spectra.

Bolus tracking from pulsed x-ray projections: A feasibility study using a five-dimensional cardiac CT contrast dynamics model.

Cardiac computed tomography (CT) exams are some of the most complex CT exams due to the need to carefully time the scan when the heart chambers are near the peak contrast concentration. With current "bolus tracking" and "timing bolus" techniques, after contrast medium is injected, a target vessel or chamber is scanned periodically, and images are reconstructed to monitor the opacification. Both techniques have opportunities for improvement, such as reducing the contrast medium volume, the exam time, the number of manual steps, and improving the robustness of correctly timing the peak opacification. The objective of our study is to (1) develop a novel autonomous cardiac CT clinical workflow to track contrast bolus dynamics directly from pulsed x-ray projections, (2) develop a new five-dimensional virtual cardiac CT data generation tool with programmable cardiac profiles and bolus dynamics, and (3) demonstrate the feasibility of projection-domain prospective bolus tracking using a neural network trained and tested with the virtual data to find the contrast peak. In our proposed workflow, pulsed mode projections (PMPs) are acquired with a wide-open collimator under sparse view conditions (monitoring phase). Each time a new PMP is acquired, the neural network is used to estimate the contrast enhancement inside the target chambers. To train such a network, we introduce a new approach to generate clinically realistic virtual scan data based on a five-dimensional cardiac model, by synthesizing user-defined contrast bolus dynamics and patient electrocardiogram profiles. In this study, we investigated a scenario with one single PMP per rotation. To find the optimal PMP view angle, 20 angles were explored. For each angle, 300 virtual exams were generated from 115 human subject datasets and divided into training, validation, and testing groups. Twenty neural networks were trained and evaluated in total to find the optimal network. Finally, a simple bolus peak time estimation algorithm was developed and evaluated by comparing to the ground truth bolus peak time. To evaluate the accuracy of a bolus time-intensity curve estimated by the network, the cosine similarity between the estimation and the ground truth was computed. The cosine similarity was larger than 0.97 for all projection angles. A view angle corresponding to the x-ray tube at 30 degrees from vertical (left-anterior of subject) showed the lowest errors. The amplitude of the estimated bolus curves (in Hounsfield Units) was not always correctly predicted, but the shape was accurately predicted. This resulted in an RMSE of 1.23s for the left chambers and 0.78s for the right chambers in the contrast peak time estimation. In this study, we proposed an innovative real-time way to predict the contrast bolus peak in cardiac CT as well as an innovative approach to train a neural network using virtual but clinically realistic data. Our trained network successfully estimated the shape of the time-intensity curve for the target chambers, which led to accurate bolus peak time estimation. This technique could be used for autonomous diagnostic cardiac CT to trigger a diagnostic scan for optimal contrast enhancement.

A deployable film method to enable replicable sampling of low-abundance environmental microbiomes

Urbanizing global populations spend over 90% of their time indoors where microbiome abundance and diversity are low. Chronic exposure to microbiomes with low abundance and diversity have demonstrated negative long-term impacts on human health. Sequencing-based analyses of environmental nucleic acids are critical to understanding the impact of the indoor microbiome on human health, however low DNA yields indoors, alongside sample collection and processing inconsistencies, currently challenge study replicability. This study presents a comparative assessment of a novel, passive, easily replicable sampling strategy using polydimethylsiloxane (PDMS) sheets alongside a representative swab-based collection protocol. Deployable, customizable PDMS films designed for whole-sample insertion into standardized extraction kits demonstrated 43% higher DNA yields per sample, and 76% higher yields per cm2 of sampler over swab-based protocols. These results indicate that this accessible, scalable method enables sufficient DNA collection to comprehensively evaluate indoor microbiome exposures and potential human health impacts using smaller, more space efficient samplers, representing an attractive alternative to swab-based collection. In addition, this process reduces the manual steps required for microbiome sampling which could address inter-study variability, transform the current microbiome sampling paradigm, and ultimately benefit the replicability and accessibility of microbiome exposure studies.

A-245 Evaluation of an Automated MALDI-TOF Target and Antimicrobial Susceptibility Suspension Preparation Instrument

Abstract Background Several studies have shown that the implementation of automation in microbiology laboratories may allow for increased volume growth without the need for additional staffing. One of the more recently available pieces of microbiology automation, the COPAN Colibri, automates the manual steps of colony spotting and preparation of targets for use on MALDI-TOF instruments for bacterial identification. This same instrument can also prepare a diluted bacterial inoculum for immediate use on automated susceptibility testing platforms. We wanted to evaluate the performance of both of these functions in real-time with clinical cultures, to determine if implementation would be beneficial over current workflows. Methods The COPAN Colibri was operated following the manufacturer’s recommendations with the exception of the identification of gram-positive organisms. The Colibri is FDA cleared for MALDI-TOF target spotting, however not with the use of formic acid, nor is it FDA cleared for susceptibility suspension preparation. Preliminary data suggested that addition of formic acid was necessary for accurate identification. A subset of cultures were digitally read in real-time as part of clinical workflows, selected for Colibri MALDI-TOF target spotting and Vitek2 suspension preparation using the COPAN WebApp software. Targets were run on the MALDI Bioptyper Sirius (Bruker) and suspensions were run on Vitek2 (BioMerieux) using the pre-dilution mode using GN-99 and GN-801 cards for appropriate organisms. All results were compared to standard manual workflows. Results A total of 145 gram-negative and 60 gram-positive organisms were picked for MALDI-target spotting on Colibri. Compared to standard testing, 144 (99%) gram-negative and 57 (95%) gram-positive Colibri spotted isolates matched expected species-level identifications. 97 Gram negative bacilli were run on Vitek 2 generating 95.52% categorical agreement across all drugs but with 13 major errors (MEs) and 2 very major errors (VMEs), which exceeded the acceptable percentage for certain drugs. The total number of failed runs was 13 (13.34% of total GNB isolates run), and all required complete resetting of MALDI-spotting and suspension preparation. Conclusions The Colibri performed well for MALDI-TOF target spotting with the addition of formic acid for gram-positive organisms. It did not perform within the acceptable range for susceptibility suspension preparation as it exceeded the recommended cutoffs for MEs and VMEs for certain drugs. The proportion of failed runs due to instrument errors may offset any advantages in labor savings due to the need for repeat set up.

Hierarchical robot learning method for industrial fluorescent penetrant inspection

Fluorescent Penetrant Inspection (FPI) is a Non-Destructive Testing (NDT) method, extensively used to evaluate components for identifying defects across a broad range of industries. FPI process remains a manual visual inspection, where the operator by means of fluorescent dye, that penetrates discontinuities on the component, aims to distinguish between indications that are relevant (i.e., can be associated with surface defects) and non-relevant (i.e., can be associated to insufficient wash-off, dust or other non-relevant factors). The FPI process can be decomposed into the following steps: (a) thorough visual examination of the component, (b) executing manual wiping-off of the fluorescent dye with a brush, of all areas that require interrogation for potential indications, and (c) disposition of the inspected components. The number of those areas on the component that require interrogation and hence to be wiped-off is unknown a priori of the inspection and varies depending on the condition of the part. As a result, replacing this manual wipe-off step by a robot requires tedious manual programming of an excessive number of robot paths to assure reach of the robot to the entire surface of the part as well as safe robot motion. In addition, these robot motions are part specific and thus not transferrable to other geometries of components, making scaling of this technology across manufacturing industry not possible. In this paper, we propose a hierarchical robot learning method to address the challenge of reducing manual robot programming and enable the scaling of this automated NDT technology. The proposed method integrates and fuses Deep Reinforcement Learning (DRL), Screw Linear Interpolation (ScLERP) and Learning from Demonstration (LfD), enabling an autonomous generation of brushing strokes with a six-degrees of freedom (DoF) industrial manipulator, and automating the wipe-off step of the FPI process. Using this approach, a robot learning policy is generated for the wipe-off motion in a simulated industrial robotic cell at first and then the policy is transferred to the real system for validation.

Can input reconstruction be used to directly estimate uncertainty of a dose prediction U-Net model?

The reliable and efficient estimation of uncertainty in artificial intelligence (AI) models poses an ongoing challenge in many fields such as radiation therapy. AI models are intended to automate manual steps involved in the treatment planning workflow. We focus in this study on dose prediction models that predict an optimal dose trade-off for each new patient for a specific treatment modality. They can guide physicians in the optimization, be part of automatic treatment plan generation or support decision in treatmentindication. Most common uncertainty estimation methods are based on Bayesian approximations, like Monte Carlo dropout (MCDO) or Deep ensembling (DE). These two techniques, however, have a high inference time (i.e., require multiple inference passes) and might not work for detecting out-of-distribution (OOD) data (i.e., overlapping uncertainty estimate for in-distribution (ID) and OOD). In this study, we present a direct uncertainty estimation method and apply it for a dose prediction U-Net architecture. It can be used to flag OOD data and give information on the quality of the doseprediction. Our method consists in the addition of a branch decoding from the bottleneck which reconstructs the CT scan given as input. The input reconstruction error can be used as a surrogate of the model uncertainty. For the proof-of-concept, our method is applied to proton therapy dose prediction in head and neck cancer patients. A dataset of 60 oropharyngeal patients was used to train the network using a nested cross-validation approach with 11 folds (training: 50 patients, validation: 5 patients, test: 5 patients). For the OOD experiment, we used 10 extra patients with a different head and neck sub-location. Accuracy, time-gain, and OOD detection are analyzed for our method in this particular application and compared with the popular MCDO andDE. The additional branch did not reduce the accuracy of the dose prediction model. The median absolute error is close to zero for the target volumes and less than 1% of the dose prescription for organs at risk. Our input reconstruction method showed a higher Pearson correlation coefficient with the prediction error (0.620) than DE (0.447) and MCDO (between 0.599 and 0.612). Moreover, our method allows an easier identification of OOD (no overlap for ID and OOD data and a Z-score of 34.05). The uncertainty is estimated simultaneously to the regression task, therefore requires less time and computationalresources. This study shows that the error in the CT scan reconstruction can be used as a surrogate of the uncertainty of the model. The Pearson correlation coefficient with the dose prediction error is slightly higher than state-of-the-art techniques. OOD data can be more easily detected and the uncertainty metric is computed simultaneously to the regression task, therefore faster than MCDO or DE. The code and pretrained model are available on the gitlab repository: https://gitlab.com/ai4miro/ct-reconstruction-for-uncertainty-quatification-of-hdunet.

A novel nucleic acid extraction system integrating a switching valve-assisted microfluidic cartridge and a constant pressure pump

BackgroundNucleic acid extraction (NAE) is essential in molecular diagnostics, genetic engineering, and DNA sequencing. While advances in switching valve-assisted, self-contained microfluidic (S2M) cartridges have improved the NAE processes, challenges persist in streamlining workflows, reducing processing times, and enhancing multi-target detection. Achieving these objectives requires precise control of on-chip fluid dynamics and efficient transfer of nucleic acid solutions (NAS) to detection areas. However, research on novel S2M cartridge designs and compatible fluid control systems is still limited. ResultThis study presented an innovative NAE system that integrated an S2M cartridge, a constant pressure (CP) pump, a metal heating bath, a rotating lever, and a magnet. The S2M cartridge contained the reagents for both NAE and detection, while the CP pump provided stable, precise, and rapid fluid delivery, outperforming traditional peristaltic and injection pumps, especially for handling small volumes and reducing pulsation. A custom rotating lever connects reagent chambers, facilitating mixing, cleaning, elution, and NAS transfer. This system showed advantages over manual methods, achieving all processes in 20 min. The CP pump-assisted S2M cartridge enabled rapid MBs re-suspension with a recovery rate of 80 %. The system's sensitivity, repeatability, and ease of use were also confirmed. The NAE system can extract Escherichia coli DNA (50 CFU mL^-1) from food and serum samples and viral DNA (HBV, HCV, HIV) at 200 copies mL^-1 from serum samples. SignificanceThis study highlighted the need for an efficient fluid system in the S2M cartridge for stable NAE. By streamlining NAE and facilitating on-chip reagent preparation, the system enhanced point-of-care diagnostics. Although manual steps remain, the CP pump effectively managed fluid processes, paving the way for automated pathogen detection. Moreover, when combined with visual detection reagents, the NAE system showed promise as a direct molecular diagnostic tool.

Multianalyte Approach-Including Automated Preparation of Calibrators-for Validated Quantification of 82 Drugs in Whole Blood by Liquid Chromatography-Tandem Mass Spectrometry.

Bioanalysis, such as the quantification of drugs in different matrices, is of great importance in forensic toxicology. Nowadays, mainly so-called multianalyte approaches are used given their increased speed and effectiveness. However, such multianalyte procedures can be difficult to develop and maintain with sufficient robustness in the laboratory. One aspect of this is the tedious, manual preparation of spiking solutions containing such a great number of analytes. Therefore, the current study aimed to develop and validate a fast, simple, and robust liquid chromatography-tandem mass spectrometry (LC-MS/MS) method for the quantification of 82 classic drugs and to evaluate an alternative autosampler-assisted automated approach for the preparation of spiking solutions. Simple protein precipitation of 200-μL whole blood was used followed by analysis by reversed-phase LC-MS/MS in advanced scheduled multiple reaction monitoring (MRM) mode. The method was fully validated according to international guidelines, including selectivity, recovery, matrix effects, linearity, bias/imprecision, processed-sample stability, and limits. Validation criteria were fulfilled for all analytes except for buprenorphine and five benzodiazepines. In the context of a multianalyte procedure, a (multipurpose) autosampler-assisted automatic preparation of calibrator spiking solutions proved comparable to manual preparation. Thus, automated preparation can overcome the frequently performed manual, time-consuming, and error-prone steps of multianalyte approaches and still allow for customized calibration ranges. Since its introduction, more than 8000 cases have been measured with the presented method, and 35 proficiency tests have been passed.

Automated echocardiography view classification and quality assessment with recognition of unknown views.

Interpreting echocardiographic exams requires substantial manual interaction as videos lack scan-plane information and have inconsistent image quality, ranging from clinically relevant to unrecognizable. Thus, a manual prerequisite step for analysis is to select the appropriate views that showcase both the target anatomy and optimal image quality. To automate this selection process, we present a method for automatic classification of routine views, recognition of unknown views, and quality assessment of detected views. We train a neural network for view classification and employ the logit activations from the neural network for unknown view recognition. Subsequently, we train a linear regression algorithm that uses feature embeddings from the neural network to predict view quality scores. We evaluate the method on a clinical test set of 2466 echocardiography videos with expert-annotated view labels and a subset of 438 videos with expert-rated view quality scores. A second observer annotated a subset of 894 videos, including all quality-rated videos. The proposed method achieved an accuracy of for the joint objective of routine view classification and unknown view recognition, whereas a second observer reached an accuracy of 87.6%. For view quality assessment, the method achieved a Spearman's rank correlation coefficient of 0.71, whereas a second observer reached a correlation coefficient of 0.62. The proposed method approaches expert-level performance, enabling fully automatic selection of the most appropriate views for manual or automatic downstream analysis.

High-Throughput Bioprinting Method for Modeling Vascular Permeability in Standard Six-well Plates with Size and Pattern Flexibility.

Vascular permeability is a key factor in developing therapies for disorders associated with compromised endothelium, such as endothelial dysfunction in coronary arteries and impaired function of the blood-brain barrier. Existing fabrication techniques do not adequately replicate the geometrical variation in vascular networks in the human body, which substantially influences disease progression; moreover, these techniques often involve multi-step fabrication procedures that hinder the high-throughput production necessary for pharmacological testing. This paper presents a bioprinting protocol for creating multiple vascular tissues with desired patterns and sizes directly on standard six-well plates, overcoming existing resolution and productivity challenges in bioprinting technology. A simplified fabrication approach was established to construct six hollow, perfusable channels within a hydrogel, which were subsequently lined with human umbilical vein endothelial cells to form a functional and mature endothelium. The computer-controlled nature of 3D bioprinting ensures high reproducibility and requires fewer manual fabrication steps than traditional methods. This highlights VOP's potential as an efficient high-throughput platform for modeling vascular permeability and advancing drug discovery.

Point-of-care CRISPR-based Diagnostics with Premixed and Freeze-dried Reagents.

Molecular diagnostics by Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-based detection have high diagnostic accuracy and attributes that are suitable for use at point-of-care settings such as fast turnaround times for results, convenient simple readouts, and no requirement of complicated instruments. However, the reactions can be cumbersome to perform at the point of care due to their many components and manual handling steps. Herein, we provide a step-by-step, optimized protocol for the robust detection of disease pathogens and genetic markers with recombinase-based isothermal amplification and CRISPR-based reagents, which are premixed and then freeze-dried in easily stored and ready-to-use formats. Premixed, freeze-dried reagents can be rehydrated for immediate use and retain high amplification and detection efficiencies. We also provide a troubleshooting guide for commonly found problems upon preparing and using premixed, freeze-dried reagents for CRISPR-based diagnostics, to make the detection platform more accessible to the wider diagnostic/genetic testing communities.

Automation and standardisation of a quantitative multiplex PCR assay using PCR.Ai

BackgroundWe previously undertook a prospective clinical study to evaluate PCR.Ai’s (www.pcr.ai) accuracy and impact when automating the manual data-analysis and quality control steps associated with routine clinical pathogen testing using a non-quantitative multiplex quantitative real-time PCR (qPCR). In this study we demonstrated 100 % concurrence between our manual routine analysis method and PCR.Ai. This paper expands the evaluation of PCR.Ai’s (www.pcr.ai) accuracy and impact using a multiplex quantitative real-time PCR (qPCR). ObjectivesWe evaluated the impact of PCR.Ai when used as the final interpretation/verification step for routine in-house multiplex quantitative qPCR tests for CMV, EBV and adenovirus from blood samples for a total of 1350 interpretations. Study DesignWe compared PCR.Ai to our existing manual interpretation, to determine accuracy and hands on time savings. Results and ConclusionsThere was 100 % concurrence between validated CMV, EBV and adenovirus detection and quantitation by our manual routine analysis method and PCR.Ai. Furthermore, there were significant routine savings with PCR.Ai of 63 minutes/ run. Our conclusion is that for quantitative tests PCR.Ai is a highly accurate time-saving tool that reduces complexity of qPCR analysis and hence the need for specialists and hands-on time. It demonstrated capabilities to enable us to get results out more quickly with lower costs and less risk of errors.

Advancements in differentiation between sperm cells and epithelial cells for efficient forensic DNA analysis in sexual assault cases.

Most of the sexual assault casework samples are of mixed sources. Forensic DNA laboratories are always in the requirement of a precise technique for the efficient separation of sperm and non-sperm DNA from mixed samples. Since the introduction of the differential extraction technique in 1985, it has seen significant advancements in the form of either chemicals used or modification of incubation times. Several automated and semi-automated techniques have also adopted the fundamentals of conventional differential extraction techniques. However, lengthy incubation, several manual steps, and carryover over non-sperm material in sperm fraction are some of the major limitations of this technique. Advanced cell separation techniques have shown huge promise in separating sperm cells from a mixture based on their size, shape, composition, and membrane structure and antigens present on sperm membranes. Such advanced techniques such as DEParray, ADE, FACS, LCM, HOT and their respective pros and cons have been discussed in this article. As current-day forensic techniques should be as per the line of Olympic slogan i.e., faster, higher, stronger, the advanced cell separation techniques show a huge potential to be implemented in the casework samples.

Automating shareable cyber threat intelligence production for closed source software vulnerabilities: a deep learning based detection system

Software can be vulnerable to various types of interference. The production of cyber threat intelligence for closed source software requires significant effort, experience, and many manual steps. The objective of this study is to automate the process of producing cyber threat intelligence, focusing on closed source software vulnerabilities. To achieve our goal, we have developed a system called cti-for-css. Deep learning algorithms were used for detection. To simplify data representation and reduce pre-processing workload, the study proposes the function-as-sentence approach. The MLP, OneDNN, LSTM, and Bi-LSTM algorithms were trained using this approach with the SOSP and NDSS18 binary datasets, and their results were compared. The aforementioned datasets contain buffer error vulnerabilities (CWE-119) and resource management error vulnerabilities (CWE-399). Our results are as successful as the studies in the literature. The system achieved the best performance using Bi-LSTM, with F1 score of 82.4%. Additionally, AUC score of 93.0% was acquired, which is the best in the literature. The study concluded by producing cyber threat intelligence using closed source software. Shareable intelligence was produced in an average of 0.1 s, excluding the detection process. Each record, which was represented using our approach, was classified in under 0.32 s on average.

A robust CETSA data analysis automation workflow for routine screening

The Cellular Thermal Shift Assay (CETSA) enables the study of protein-ligand interactions in a cellular context. It provides valuable information on the binding affinity and specificity of both small and large molecule ligands in a relevant physiological context, hence forming a unique tool in drug discovery. Though high-throughput lab protocols exist for scaling up CETSA, subsequent data analysis and quality control remain laborious and limit experimental throughput. Here, we introduce a scalable and robust data analysis workflow which allows integration of CETSA into routine high throughput screening (HT-CETSA). This new workflow automates data analysis and incorporates quality control (QC), including outlier detection, sample and plate QC, and result triage. We describe the workflow and show its robustness against typical experimental artifacts, show scaling effects, and discuss the impact of data analysis automation by eliminating manual data processing steps.

Self-supervised denoising at low signal-to-noise ratios: A seismic-while-drilling application

Self-supervised blind-mask denoising networks overcome the challenge of requiring clean training targets by employing a mask on raw noisy data to form the input for training while using the unmasked version as the network's target. The application of such networks has shown considerable strength in suppressing both random and coherent noise in seismic data. However, because such networks need to figure out the target (clean signal) on their own, they struggle at low signal-to-noise ratios. Seismic-while-drilling acquisitions result in seismic data of very low quality because the drilling operation introduces significant noise propagating from the rig site. Due to its consistent and low-frequency nature, it is hard to design a noise mask to hide the rig noise from the network without also hiding useful information required for predicting the signal. However, by reframing the task from a noise suppression to a noise prediction task and utilizing a mask to hide the signal from the network, the rig noise can be predicted accurately. Therefore, the difference between the network's prediction and the raw data results in common bit (equivalent to shot, but continuous) gathers with a significantly higher signal-to-noise ratio due to the removal of rig noise. Illustrated on six common bit gathers, this reversed methodology is shown to separate the rig noise and signal, even in their shared bandwidth. The additional use of explainable artificial intelligence is investigated as a means of avoiding the manual step of creating the signal mask, providing promising results. This study lays the ground work for suppression of high-amplitude, consistent noises, such as those arising from well site operations like fluid injection procedures for carbon sequestration or geothermal energy production purposes.

An automated workflow based on data independent acquisition for practical and high-throughput personalized assay development and minimal residual disease monitoring in multiple myeloma patients.

Minimal residual disease (MRD) status in multiple myeloma (MM) is an important prognostic biomarker. Personalized blood-based targeted mass spectrometry detecting M-proteins (MS-MRD) was shown to provide a sensitive and minimally invasive alternative to MRD-assessment in bone marrow. However, MS-MRD still comprises of manual steps that hamper upscaling of MS-MRD testing. Here, we introduce a proof-of-concept for a novel workflow using data independent acquisition-parallel accumulation and serial fragmentation (dia-PASEF) and automated data processing. Using automated data processing of dia-PASEF measurements, we developed a workflow that identified unique targets from MM patient sera and personalized protein sequence databases. We generated patient-specific libraries linked to dia-PASEF methods and subsequently quantitated and reported M-protein concentrations in MM patient follow-up samples. Assay performance of parallel reaction monitoring (prm)-PASEF and dia-PASEF workflows were compared and we tested mixing patient intake sera for multiplexed target selection. No significant differences were observed in lowest detectable concentration, linearity, and slope coefficient when comparing prm-PASEF and dia-PASEF measurements of serial dilutions of patient sera. To improve assay development times, we tested multiplexing patient intake sera for target selection which resulted in the selection of identical clonotypic peptides for both simplex and multiplex dia-PASEF. Furthermore, assay development times improved up to 25× when measuring multiplexed samples for peptide selection compared to simplex. Dia-PASEF technology combined with automated data processing and multiplexed target selection facilitated the development of a faster MS-MRD workflow which benefits upscaling and is an important step towards the clinical implementation of MS-MRD.

MT36 Assessment and Comparison of the Manual Steps Required to Perform Whole Blood Processing Using a Semi-Automated Method Versus a Fully Automated Method

MT36 Assessment and Comparison of the Manual Steps Required to Perform Whole Blood Processing Using a Semi-Automated Method Versus a Fully Automated Method

A Closed Formalism for Anatomy-Independent Projection and Optimization of Magnetic Stimulation Coils on Arbitrarily Shaped Surfaces.

Transcranial magnetic stimulation (TMS) is a popular method for the noninvasive stimulation of neurons in the brain. It has become a standard instrument in experimental brain research and has been approved for a range of diagnostic and therapeutic applications. These applications require appropriately shaped coils. Various applications have been established or approved for specific coil designs with their corresponding spatial electric field distributions. However, the specific coil implementation may no longer be appropriate from the perspective of available material and manufacturing opportunities or considering the latest understanding of how to achieve induced electric fields in the head most efficiently. Furthermore, in some cases, field measurements of coils with unknown winding or a user-defined field are available and require an actual implementation. Similar applications exist for magnetic resonance imaging coils. This work aims at introducing a complete formalism free from heuristics, iterative optimization, and ad-hoc or manual steps to form practical stimulation coils with individual turns to either equivalently match an existing coil or produce a given field. The target coil can reside on practically any sufficiently large or closed surface adjacent to or around the head. The method derives an equivalent field through vector projection exploiting the well-known Huygens' and Love's equivalence principle. In contrast to other coil design or optimization approaches recently presented, the procedure is an explicit forward Hilbert-space vector projection or basis change. For demonstration, we map a commercial figure-of-eight coil as one of the most widely used devices and a more intricate coil recently approved clinically for addiction treatment (H4) onto a bent surface close to the head for highest efficiency and lowest field energy. The resulting projections are within ≤4% of the target field and reduce the necessary pulse energy by more than 40%.