Labeling Tool Research Articles

Mark3D - A semi-automated open-source toolbox for 3D head- surface reconstruction and electrode position registration using a smartphone camera video.

Source localization in EEG necessitates co-registering the EEG sensor locations with the subject's MRI, where EEG sensor locations are typically captured using electromagnetic tracking or 3D scanning of the subject's head with EEG cap, using commercially available 3D scanners. Both methods have drawbacks, where, electromagnetic tracking is slow and immobile, while 3D scanners are expensive. Photogrammetry offers a cost-effective alternative but requires multiple photos to sample the head, with good spatial sampling to adequately reconstruct the head surface. Post-reconstruction, the existing tools for electrode position labelling on the 3D head-surface have limited visual feedback and do not easily accommodate customized montages, which are typical in multi-modal measurements. We introduce Mark3D, an open-source, integrated tool for 3D head-surface reconstruction from phone camera video. It eliminates the need for keeping track of spatial sampling during image capture for video-based photogrammetry reconstruction. It also includes blur detection algorithms, a user-friendly interface for electrode and tracking, and integrates with popular toolboxes such as FieldTrip and MNE Python. The accuracy of the proposed method was benchmarked with the head-surface derived from a commercially available handheld 3D scanner Einscan-Pro + (Shining 3D Inc.,) which we treat as the "ground truth". We used reconstructed head-surfaces of ground truth (G1) and phone camera video (M1080) to mark the EEG electrode locations in 3D space using a dedicated UI provided in the tool. The electrode locations were then used to form pseudo-specific MRI templates for individual subjects to reconstruct source information. Somatosensory source activations in response to vibrotactile stimuli were estimated and compared between G1 and M1080. The mean positional errors of the EEG electrodes between G1 and M1080 in 3D space were found to be 0.09 ± 0.01mm across different cortical areas, with temporal and occipital areas registering a relatively higher error than other regions such as frontal, central or parietal areas. The error in source reconstruction was found to be 0.033 ± 0.016mm and 0.037 ± 0.017mm in the left and right cortical hemispheres respectively.

Clickable HaloTag ligands for live cell labeling and imaging

Self-labeling protein (SLP) tags, such as HaloTag, have gained considerable interest as advanced tools for live cell labeling. However, the chloroalkane-based substrates that can be directly used for protein labeling are limited. Here, we report two bioorthogonal small molecule linkers, chloroalkane-tetrazine (CA-Tz) and chloroalkane-azide (CA-N3), which can penetrate cell membranes and facilitate click chemistry-based labeling in live cells. We compare their labeling capability using two clickable silicon rhodamine dyes (SiR-PEG3-TCO and SiR-PEG4-DBCO). Confocal imaging results demonstrate that using CA-Tz and SiR-PEG3-TCO dye exhibits superior intracellular labeling with low nonspecific signals. We subsequently compared the photostability of SiR dyes with that of green fluorescent proteins (mEmerald). Total internal reflection fluorescence (TIRF) imaging indicates that SiR dyes exhibit superior photostability under identical excitation conditions, making them suitable for long-term cell imaging. Furthermore, SiR dyes labeling also shows high structure retention for the fourth-order super-resolution optical fluctuation imaging (SOFI) compared to fluorescent proteins. This study presents clickable HaloTag linkers as effective tools for live cell labeling and imaging, highlighting the high-quality labeling of chloroalkane linkers and clickable dyes for live cell imaging.

INTELLIGENT VIDEO ANALYSIS TECHNOLOGY FOR AUTOMATIC FIRE CONTROL TARGET RECOGNITION BASED ON MACHINE LEARNING

Context. Target recognition is a priority in military affairs. This task is complicated by the fact that it is necessary to recognize moving objects, different terrain and landscape create obstacles for recognition. Combat actions can take place at different times of the day, accordingly, it is necessary to take into account the perspective of lighting and general lighting. It is necessary to detect the object in the video by segmenting the video frames, recognize and classify. Objective of the study is to develop a technology for the analysis of the development of a technology for recognizing targets in real time as a component of the fire control system, due to the use of artificial intelligence, YOLO and machine learning. Method. The article develops a video stream analysis technology for automatic target recognition of the fire control system based on machine learning. The paper proposes the development of a target recognition module as a component of the fire control system within the framework of the proposed information technology using artificial intelligence. The YOLOv8 pattern recognition model family was used to develop the target recognition module. The methods used during the study of the formed dataset. – Bounding Box: Noise – Up to 15% of pixels (limiting frame: adding salt and pepper noise to the image – up to 15% of pixels). – Bounding Box: Blur – Up to 2.5px (bounding box: adding Gaussian blur to the image – up to 2.5 pixels). – Cutout – 3 boxes with 10% size each (cut out a part of the image – 3 boxes of 10% size each). – Brightness Between –25% and +25% (changing the brightness of the image to increase the resistance of the model to changes in lighting and camera settings – from –25% to +25%). – Rotation – Between –15 and +15 (rotation of the image object – clockwise or counterclockwise by degrees from –15 to +15). – Flip – Horizontal (flip the image object horizontally). Results. The data is collected from open sources, in particular, from videos posted in open sources on the YouTube platform. The main task of data preprocessing is the classification of three classes of objects on video or in real time – APC, BMP and TANK. The dataset is formed using the Roboflow platform based on the labeling tools and subsequently the augmentation tools. The dataset consists of 1193 unique images – approximately equally for each class. The training was conducted using Google Colab resources. It took 100 epochs to train the model. Conclusions. Analysis is performed according to mAP50 (average precision as 0.85), mAP50-95 (0.6), precision (0.89) and recall (0.75). Big losses are due to the fact that the background was not taken into account during the research – training the module on the basis of confirmed data (images) of the background without technology

An immersive labeling method for large point clouds

3D point clouds, such as those produced by 3D scanners, often require labeling – the accurate classification of each point into structural or semantic categories – before they can be used in their intended application. However, in the absence of fully automated methods, such labeling must be performed manually, which can prove extremely time and labor intensive. To address this we present a virtual reality tool for accelerating and improving the manual labeling of very large 3D point clouds. The labeling tool provides a variety of 3D interactions for efficient viewing, selection and labeling of points using the controllers of consumer VR-kits. The main contribution of our work is a mixed CPU/GPU-based data structure that supports rendering, selection and labeling with immediate visual feedback at high frame rates necessary for a convenient VR experience. Our mixed CPU/GPU data structure supports fluid interaction with very large point clouds in VR, what is not possible with existing continuous level-of-detail rendering algorithms. We evaluate our method with 25 users on tasks involving point clouds of up to 50 million points and find convincing results that support the case for VR-based point cloud labeling.

Evaluating the Performance and Bias of Natural Language Processing Tools in Labeling Chest Radiograph Reports.

Background Natural language processing (NLP) is commonly used to annotate radiology datasets for training deep learning (DL) models. However, the accuracy and potential biases of these NLP methods have not been thoroughly investigated, particularly across different demographic groups. Purpose To evaluate the accuracy and demographic bias of four NLP radiology report labeling tools on two chest radiograph datasets. Materials and Methods This retrospective study, performed between April 2022 and April 2024, evaluated chest radiograph report labeling using four NLP tools (CheXpert [rule-based], RadReportAnnotator [RRA; DL-based], OpenAI's GPT-4 [DL-based], cTAKES [hybrid]) on a subset of the Medical Information Mart for Intensive Care (MIMIC) chest radiograph dataset balanced for representation of age, sex, and race and ethnicity (n = 692) and the entire Indiana University (IU) chest radiograph dataset (n = 3665). Three board-certified radiologists annotated the chest radiograph reports for 14 thoracic disease labels. NLP tool performance was evaluated using several metrics, including accuracy and error rate. Bias was evaluated by comparing performance between demographic subgroups using the Pearson χ2 test. Results The IU dataset included 3665 patients (mean age, 49.7 years ± 17 [SD]; 1963 female), while the MIMIC dataset included 692 patients (mean age, 54.1 years ± 23.1; 357 female). All four NLP tools demonstrated high accuracy across findings in the IU and MIMIC datasets, as follows: CheXpert (92.6% [47 516 of 51 310], 90.2% [8742 of 9688]), RRA (82.9% [19 746 of 23 829], 92.2% [2870 of 3114]), GPT-4 (94.3% [45 586 of 48 342], 91.6% [6721 of 7336]), and cTAKES (84.7% [43 436 of 51 310], 88.7% [8597 of 9688]). RRA and cTAKES had higher accuracy (P < .001) on the MIMIC dataset, while CheXpert and GPT-4 had higher accuracy on the IU dataset. Differences (P < .001) in error rates were observed across age groups for all NLP tools except RRA on the MIMIC dataset, with the highest error rates for CheXpert, RRA, and cTAKES in patients older than 80 years (mean, 15.8% ± 5.0) and the highest error rate for GPT-4 in patients 60-80 years of age (8.3%). Conclusion Although commonly used NLP tools for chest radiograph report annotation are accurate when evaluating reports in aggregate, demographic subanalyses showed significant bias, with poorer performance in older patients. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Cai in this issue.

Presenting the framework of the whole slide image file Babel fish: An OCR-based file labeling tool

IntroductionMetadata extraction from digitized slides or whole slide image files is a frequent, laborious, and tedious task. In this work, we present a tool to automatically extract all relevant slide information, such as case number, year, slide number, block number, and staining from the macro-images of the scanned slide.We named the tool Babel fish as it helps translate relevant information printed on the slide. It is written to contain certain basic assumptions regarding, for example, the location of certain information. This can be adapted to the respective location. The extracted metadata can then be used to sort digital slides into databases or to link them with associated case IDs from laboratory information systems. Material and methodsThe tool is based on optical character recognition (OCR). For most information, the easyOCR tool is used. For the block number and cases with insufficient results in the first OCR round, a second OCR with pytesseract is applied.Two datasets are used: one for tool development has 342 slides; and another for one for testing has 110 slides. ResultsFor the testing set, the overall accuracy for retrieving all relevant information per slide is 0.982. Of note, the accuracy for most information parts is 1.000, whereas the accuracy for the block number detection is 0.982. ConclusionThe Babel fish tool can be used to rename vast amounts of whole slide image files in an image analysis pipeline. Furthermore, it could be an essential part of DICOM conversion pipelines, as it extracts relevant metadata like case number, year, block ID, and staining.

SaLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset

Deep learning’s reliance on abundant data with accurate annotations presents a significant drawback, as developing datasets is often time-consuming and costly for specific problems. To address this drawback, we propose a semi-automatic live-feed image annotation tool called saLFIA. Our case study utilized CCTV data from Indonesia’s toll roads as one of the sources for live-feed images. The primary contribution of saLFIA is a labeling tool designed to generate new datasets from public source images, focusing on vehicle classification using YOLOv3 and SSD algorithms. The evaluation results indicated that SSD achieved higher accuracy with fewer initial images, while YOLOv3 reached maximum accuracy with larger initial datasets, resulting in 8 misdetections out of 380 objects. The saLFIA tool simplifies the annotation process, presenting a labeling tool for creating annotated datasets in a single operation. saLFIA is available at URL https://github.com/gilangmantara/salfia.

Automatic Method for Extracting Tree Branching Structures from a Single RGB Image

Creating automated methods for detecting branches in images is crucial for applications like harvesting robots and forest monitoring. However, the tree images encountered in real-world scenarios present significant challenges for branch detection techniques due to issues such as background interference, occlusion, and varying environmental lighting. While there has been notable progress in extracting tree trunks for specific species, research on identifying lateral branches remains limited. The primary challenges include establishing a unified mathematical representation for multi-level branch structures, conducting quantitative analyses, and the absence of suitable datasets to facilitate the development of effective models. This study addresses these challenges by creating a dataset encompassing various tree species, developing annotation tools for multi-level branch structure labeling, designing branch vector representations and quantitative metrics. Building on this foundation, the study introduces an automatic extraction model for multi-level branch structures that utilizes ResNet and a self-attention mechanism, along with a tailored loss function for branch extraction tasks. The study evaluated several model variants through both qualitative and quantitative experiments. Results from different tree images demonstrate that the final model can accurately identify the trunk structure and effectively extract detailed lateral branch structures, offering a valuable tool for applications in this area.

Thg1 family 3'-5' RNA polymerases as tools for targeted RNA synthesis.

Members of the 3'-5' RNA polymerase family, comprised of tRNAHis guanylyltransferase (Thg1) and Thg1-like proteins (TLPs), catalyze templated synthesis of RNA in the reverse direction to all other known 5'-3' RNA and DNA polymerases. The discovery of enzymes capable of this reaction raised the possibility of exploiting 3'-5' polymerases for posttranscriptional incorporation of nucleotides to the 5'-end of nucleic acids without ligation, and instead by templated polymerase addition. To date, studies of these enzymes have focused on nucleotide addition to highly structured RNAs, such as tRNA and other noncoding RNAs. Consequently, general principles of RNA substrate recognition and nucleotide preferences that might enable broader application of 3'-5' polymerases have not been elucidated. Here, we investigated the feasibility of using Thg1 or TLPs for multiple nucleotide incorporation to the 5'-end of a short duplex RNA substrate, using a templating RNA oligonucleotide provided in trans to guide 5'-end addition of specific sequences. Using optimized assay conditions, we demonstrated a remarkable capacity of certain TLPs to accommodate short RNA substrate-template duplexes of varying lengths with significantly high affinity, resulting in the ability to incorporate a desired nucleotide sequence of up to eight bases to 5'-ends of the model RNA substrates in a template-dependent manner. This work has further advanced our goals to develop this atypical enzyme family as a versatile nucleic acid 5'-end labeling tool.

Mapping subcellular RNA localization with proximity labeling.

The subcellular localization of RNA is critical to a variety of physiological and pathological processes. Dissecting the spatiotemporal regulation of the transcriptome is key to understanding cell function and fate. However, it remains challenging to effectively enrich and catalogue RNAs from various subcellular structures using traditional approaches. In recent years, proximity labeling has emerged as an alternative strategy for efficient isolation and purification of RNA from these intricate subcellular compartments. This review focuses on examining RNA-related proximity labeling tools and exploring their application in elucidating the spatiotemporal regulation of RNA at the subcellular level.

Expanding the genetic toolbox for Neisseria meningitidis with efficient tools for unmarked gene editing, complementation, and labeling.

The efficient natural transformation of Neisseria meningitidis allows the rapid construction of bacterial mutants in which the genes of interest are interrupted or replaced by antibiotic-resistance cassettes. However, this proved to be a double-edged sword, i.e., although facilitating the genetic characterization of this important human pathogen, it has limited the development of strategies for constructing markerless mutants without antibiotic-resistance markers. In addition, efficient tools for complementation or labeling are also lacking in N. meningitidis. In this study, we significantly expand the meningococcal genetic toolbox by developing new and efficient tools for the construction of markerless mutants (using a dual counterselection strategy), genetic complementation (using integrative vectors), and cell labeling (using a self-labeling protein tag). This expanded toolbox paves the way for more in-depth genetic characterization of N. meningitidis and might also be useful in other Neisseria species.IMPORTANCENeisseria meningitidis and Neisseria gonorrhoeae are two important human pathogens. Research focusing on these bacteria requires genetic engineering, which is facilitated by their natural ability to undergo transformation. However, the ease of mutant engineering has led the Neisseria community to neglect the development of more sophisticated tools for gene editing, particularly for N. meningitidis. In this study, we have significantly expanded the meningococcal genetic toolbox by developing novel and efficient tools for markerless mutant construction, genetic complementation, and cell tagging. This expanded toolbox paves the way for more in-depth genetic characterization of N. meningitidis and might also be useful in other Neisseria species.

The potential of ALFA-tag and tyramide-based fluorescence signal amplification to expand the CRISPR-based DNA imaging toolkit.

Understanding the spatial organization of genomes within chromatin is crucial for deciphering gene regulation. A recently developed CRISPR-dCas9-based genome labeling tool, known as CRISPR-FISH, allows efficient labelling of repetitive sequences. Unlike standard fluorescence in situ hybridization (FISH), CRISPR-FISH eliminates the need for global DNA denaturation, allowing for superior preservation of chromatin structure. Here, we report on the further development of the CRISPR-FISH method, which has been enhanced for increased efficiency through the engineering of a recombinant dCas9 protein containing an ALFA-tag. Using an ALFA-tagged dCas9 protein assembled with an A. thaliana centromere-specific gRNA, we demonstrate target-specific labelling with a fluorescence-labeled NbALFA nanobody. The dCas9 protein possessing multiple copies of the ALFA-tag, in combination with a minibody and fluorescence-labelled anti-rabbit secondary antibody, resulted in enhanced target-specific signals. The dCas9-ALFA-tag system was also instrumental in live cell imaging of telomeres in N. benthamiana. This method will further expand the CRISPR imaging toolkit, facilitating a better understanding of genome organization. Furthermore, we report the successful integration of the highly sensitive Tyramide Signal Amplification (TSA) method with CRISPR-FISH, demonstrating effective labeling of A. thaliana centromeres.

Quantum dots as a fluorescent labeling tool for live-cell imaging of Leptospira.

Leptospirosis is a global public health problem caused by Gram-negative pathogenic bacteria belonging to the genus Leptospira. The disease is transmitted through the urine of infected animals, which contaminates water and soil, leading to the infection of other animals and humans. Currently, several approaches exist to detect these bacteria; however, a new sensitive method for the live-cell imaging of Leptospira is required. In this study, we report the green synthesis of cadmium telluride quantum dots (CdTe QDs) which are unique fluorescent nanocrystals with a high fluorescence quantum yield capable of modifying cell surfaces and are biocompatible with cells. The fabrication of QDs with concanavalin A (ConA), a carbohydrate-binding lectin and known biological probe for Gram-negative bacteria, produced ConA-QDs which can effectively bind on Leptospira and exhibit strong fluorescence under simple fluorescence microscopy, allowing the live-cell imaging of the bacteria. Overall, we performed the simple synthesis of ConA-QDs and demonstrated their potential use as versatile fluorescent probes for the live-cell imaging of Leptospira. This technique could be further applied to track leptospiral cells and study the infection mechanism, contributing to a more thorough understanding of leptospirosis and how to control it in the future.

Biocatalytic Nucleobase Diversification of 4'-Thionucleosides and Application of Derived 5-Ethynyl-4'-thiouridine for RNA Synthesis Detection.

Nucleoside and nucleotide analogues have proven to be transformative in the treatment of viral infections and cancer. One branch of structural modification to deliver new nucleoside analogue classes explores replacement of canonical ribose oxygen with a sulfur atom. Whilst biological activity of such analogues has been shown in some cases, widespread exploration of this compound class is hitherto hampered by the lack of a straightforward and universal nucleobase diversification strategy. Herein, we present a synergistic platform enabling both biocatalytic nucleobase diversification from 4'-thiouridine in a one-pot process, and chemical functionalization to access new entities. This methodology delivers entry across pyrimidine and purine 4'-thionucleosides, paving a way for wider synthetic and biological exploration. We exemplify our approach by enzymatic synthesis of 5-iodo-4'-thiouridine on multi-milligram scale and from here switch to complete chemical synthesis of a novel nucleoside analogue probe, 5-ethynyl-4'-thiouridine. Finally, we demonstrate the utility of this probe to monitor RNA synthesis in proliferating HeLa cells, validating its capability as a new metabolic RNA labelling tool.

Biocatalytic Nucleobase Diversification of 4′‐Thionucleosides and Application of Derived 5‐Ethynyl‐4′‐thiouridine for RNA Synthesis Detection

AbstractNucleoside and nucleotide analogues have proven to be transformative in the treatment of viral infections and cancer. One branch of structural modification to deliver new nucleoside analogue classes explores replacement of canonical ribose oxygen with a sulfur atom. Whilst biological activity of such analogues has been shown in some cases, widespread exploration of this compound class is hitherto hampered by the lack of a straightforward and universal nucleobase diversification strategy. Herein, we present a synergistic platform enabling both biocatalytic nucleobase diversification from 4′‐thiouridine in a one‐pot process, and chemical functionalization to access new entities. This methodology delivers entry across pyrimidine and purine 4′‐thionucleosides, paving a way for wider synthetic and biological exploration. We exemplify our approach by enzymatic synthesis of 5‐iodo‐4′‐thiouridine on multi‐milligram scale and from here switch to complete chemical synthesis of a novel nucleoside analogue probe, 5‐ethynyl‐4′‐thiouridine. Finally, we demonstrate the utility of this probe to monitor RNA synthesis in proliferating HeLa cells, validating its capability as a new metabolic RNA labelling tool.

PatchSorter: a high throughput deep learning digital pathology tool for object labeling

The discovery of patterns associated with diagnosis, prognosis, and therapy response in digital pathology images often requires intractable labeling of large quantities of histological objects. Here we release an open-source labeling tool, PatchSorter, which integrates deep learning with an intuitive web interface. Using >100,000 objects, we demonstrate a >7x improvement in labels per second over unaided labeling, with minimal impact on labeling accuracy, thus enabling high-throughput labeling of large datasets.

Probing Glycerolipid Metabolism using a Caged Clickable Glycerol-3-Phosphate Probe.

In this study, we present the probe SATE-G3P-N3 as a novel tool for metabolic labeling of glycerolipids (GLs) to investigate lipid metabolism in yeast cells. By introducing a clickable azide handle onto the glycerol backbone, this probe enables general labeling of glycerolipids. Additionally, this probe contains a caged phosphate moiety at the glycerol sn-3 position to not only facilitate probe uptake by masking negative charge but also to bypass the phosphorylation step crucial for initiating phospholipid synthesis, thereby enhancing phospholipid labeling. The metabolic labeling activity of the probe was thoroughly assessed through cellular fluorescence microscopy, mass spectrometry (MS), and thin-layer chromatography (TLC) experiments. Fluorescence microscopy analysis demonstrated successful incorporation of the probe into yeast cells, with labeling predominantly localized at the plasma membrane. LCMS analysis confirmed metabolic labeling of various phospholipid species (PC, PS, PA, PI, and PG) and neutral lipids (MAG, DAG, and TAG), and GL labeling was corroborated by TLC. These results showcased the potential of the SATE-G3P-N3 probe in studying GL metabolism, offering a versatile and valuable approach to explore the intricate dynamics of lipids in yeast cells.

Retrograde tracing of breast cancer-associated sensory neurons.

Breast cancer is one of the leading causes of mortality among women. The tumour microenvironment, consisting of host cells and extracellular matrix, has been increasingly studied for its interplay with cancer cells, and the resulting effect on tumour progression. While the breast is one of the most innervated organs in the body, the role of neurons, and specifically sensory neurons, has been understudied, mostly for technical reasons. One of the reasons is the anatomy of sensory neurons: sensory neuron somas are located in the spine, and their axons can extend longer than a meter across the body to provide innervation in the breast. Next, neurons are challenging to culture, and there are no cell lines adequately representing the diversity of sensory neurons. Finally, sensory neurons are responsible for transporting several different types of signals to the brain, and there are many different subtypes of sensory neurons. The subtypes of sensory neurons, which innervate and interact with breast tumours, are unknown. To establish the tools for labelling and subtyping neurons that interact with breast cancer cells, we utilised two retrograde tracer's standards in neuroscience, wheat-germ agglutinin (WGA) and cholera toxin subunit B (CTB). In vitro, we employed primary sensory neurons isolated from mouse dorsal root ganglia, cultured in a custom-built microfluidic device DACIT, that mimics the anatomical compartmentalisation of the sensory neuron's soma and axons. In vivo, we utilised both syngeneic and transgenic mouse models of mammary carcinoma. We show that CTB and WGA trace different but overlapping sensory neuronal subpopulations: while WGA is more efficient in labelling CGRP+ neurons, CTB is superior in labelling the NF200+ neurons. Surprisingly, both tracers are also taken up by a significant population of breast cancer cells, both in vitro and in vivo. In summary, we have established methodologies for retrograde tracing of sensory neurons interacting with breast cancer cells. Our tools will be useful for future studies of breast tumour innervation, and development of therapies targeting breast cancer-associated neuron subpopulations of sensory neurons. Lay description: Breast cancer is an aggressive disease that affects both women and men throughout the world. While it has been reported that the increasing size of nerves in breast cancer correlates to bad prognosis in patients, the role of nerves, especially sensory nerves, in breast cancer progression, has remained largely understudied. Sensory nerves are responsible for delivering signals such as pain, mechanical forces (pressure, tension, stretch, touch) and temperature to the brain. The human body is densely innervated, and nerves extending into peripheral organs can be as long as a few meters. Nerve classification and function can be very complex, as they contain bundles of extensions (axons) originating in different neuronal bodies (soma). Maintaining neurons and growing axons in cell culture conditions in order to mimic innervation is technically challenging, as it involves multiple organs of the human body. Here, we focus on tracing sensory axons from the breast tumours back to the neuronal soma, located in the dorsal root ganglia, inside the spine. To do so, we are using two different 'retrograde' tracers, WGA and CTB, which are proteins with a natural ability to enter axons and travel in a retrograde fashion, arriving at the soma, even if it means to travel distances longer than a meter. Both tracers are fluorescently labelled, making them visible using high-resolution fluorescent microscopy. We show that both WGA and CTB can label sensory neurons in tumours, or in cell culture conditions. The two tracers differ in efficiency of tracing different sensory neurons subpopulations: while WGA is more efficient in tracing small C-fibres (CGRP-positive), CTB is more efficient in tracing A-fibres (NF200+) of sensory neurons. In summary, we have successfully established retrograde tracing techniques for sensory neurons towards studying and targeting breast cancer innervation.

Multicolor, Cell-Impermeable, and High Affinity BACE1 Inhibitor Probes Enable Superior Endogenous Staining and Imaging of Single Molecules.

The prevailing but not undisputed amyloid cascade hypothesis places the β-site of APP cleaving enzyme 1 (BACE1) center stage in Alzheimer's Disease pathogenesis. Here, we investigated functional properties of BACE1 with novel tag- and antibody-free labeling tools, which are conjugates of the BACE1-inhibitor IV (also referred to as C3) linked to different impermeable Alexa Fluor dyes. We show that these fluorescent small molecules bind specifically to BACE1, with a 1:1 labeling stoichiometry at their orthosteric site. This is a crucial property especially for single-molecule and super-resolution microscopy approaches, allowing characterization of the dyes' labeling capabilities in overexpressing cell systems and in native neuronal tissue. With multiple colors at hand, we evaluated BACE1-multimerization by Förster resonance energy transfer (FRET) acceptor-photobleaching and single-particle imaging of native BACE1. In summary, our novel fluorescent inhibitors, termed Alexa-C3, offer unprecedented insights into protein-protein interactions and diffusion behavior of BACE1 down to the single molecule level.

Novel approach to implementing natural language processing for clinical staging of non-small-cell lung cancer.

e13624 Background: Cancer staging is instrumental in driving clinical management and trial enrollment, but staging data are generally unreliable and unstructured in the electronic health record (EHR). Advances in natural language processing (NLP) may facilitate clinical staging and documentation [1], but challenges to real-world implementation include (1) automatically identifying appropriate patients and reports from the EHR and (2) developing an unbiased dataset for training and validation [2]. We describe our institution’s novel approach to overcome these barriers while building an in-house NLP pipeline for clinical tumor staging of non-small-cell lung cancer (NSCLC). Methods: We identified patients by searching our EHR (Epic) for a molecular analysis test ordered specifically for pathological diagnoses of NSCLC at our institution. We used the test order date as the diagnosis proxy date (DPD). For each patient, we extracted imaging reports up to 16 weeks before and 6 weeks after the DPD. To derive primary tumor size, we analyzed the CT Chest or PET/CT report closest to the DPD using an oncology-trained NLP text extraction and labeling tool (John Snow Labs). We cleaned all extracted tumor size entities and identified the largest measurement linked to the lungs. We compared primary tumor measurements from the NLP pipeline to those in a preexisting, manually compiled cancer registry (CNEXT). We manually analyzed discrepancies through chart review. Results: 542 patients with a DPD between 11/2016 - 9/2023 were processed through the NLP pipeline. Of 443 patients with valid values in both the pipeline and CNEXT, 53% (234) were exact matches, and 20% (90) had a close match (within 0-5mm), yielding a 73% accuracy rate for values within 5mm. When mismatched values were manually reviewed, several cases in CNEXT were found to have a DPD differing by more than 3 months and tumor sizes derived from external reports. When these cases were excluded, 320 of the remaining 349 patients had valid values in both the pipeline and the updated manual review. In this refined population, 66% (213) were exact matches, and 15% (48) had a close match, yielding an 82% accuracy rate for values within 5mm. Conclusions: To our knowledge, this is the first report of a pathology-based method to automatically and reliably identify patients with NSCLC and their relevant imaging reports directly from the EHR. We used a prebuilt NLP tool to derive primary tumor sizes with relatively high accuracy and found that adding flags for timeline discrepancies and external reports can further improve validity. As we near completion of analogous pipelines for node and metastasis staging, we will develop methodology to identify subgroups of patients that can be clinically staged with near-perfect accuracy, ultimately aiming to substantially limit manual staging of uncomplicated cases. 1. Puts 2023. 2. Wang 2022.