Annotation Method Research Articles

Knowledge-based inductive bias and domain adaptation for cell type annotation.

Measurement techniques often result in domain gaps among batches of cellular data from a specific modality. The effectiveness of cross-batch annotation methods is influenced by inductive bias, which refers to a set of assumptions that describe the behavior of model predictions. Different annotation methods possess distinct inductive biases, leading to varying degrees of generalizability and interpretability. Given that certain cell types exhibit unique functional patterns, we hypothesize that the inductive biases of cell annotation methods should align with these biological patterns to produce meaningful predictions. In this study, we propose KIDA, Knowledge-based Inductive bias and Domain Adaptation. The knowledge-based inductive bias constrains the prediction rules learned from the reference dataset, composed of multiple batches, to functional patterns relevant to biology, thereby enhancing the generalization of the model to unseen batches. Since the query dataset also contains gaps from multiple batches, KIDA's domain adaptation employs pseudo labels for self-knowledge distillation, effectively narrowing the distribution gap between model predictions and the query dataset. Benchmark experiments demonstrate that KIDA is capable of achieving accurate cross-batch cell type annotation.

Structure-aware annotation of leucine-rich repeat domains.

Protein domain annotation is typically done by predictive models such as HMMs trained on sequence motifs. However, sequence-based annotation methods are prone to error, particularly in calling domain boundaries and motifs within them. These methods are limited by a lack of structural information accessible to the model. With the advent of deep learning-based protein structure prediction, existing sequenced-based domain annotation methods can be improved by taking into account the geometry of protein structures. We develop dimensionality reduction methods to annotate repeat units of the Leucine Rich Repeat solenoid domain. The methods are able to correct mistakes made by existing machine learning-based annotation tools and enable the automated detection of hairpin loops and structural anomalies in the solenoid. The methods are applied to 127 predicted structures of LRR-containing intracellular innate immune proteins in the model plant Arabidopsis thaliana and validated against a benchmark dataset of 172 manually-annotated LRR domains.

Superpixel-based principal feature clustering annotation method for dual-phase microstructure segmentation

Metallographic analysis is one of the most commonly used techniques by materials scientists for studying metal materials. The deep learning methods, which have been widely applied in metallographic images analysis, demonstrate excellent performance in this task. However, the optimization of deep learning models often relies on a substantial amount of accurately labeled samples for effective supervision. To address this issue, this paper proposes a novel automatic annotation method based on brightness and spatial distribution which is suitable for deep learning-based segmentation of optical dual-phase metallographic microstructure. The proposed automatic annotated method includes the superpixel segmentation, principal feature extraction, and clustering algorithm therefore it is referred as the superpixel-based principal feature clustering annotation (SPFCA) method. SPFCA employs discriminative criteria similar to those used by metallurgists to differentiate between metallographic structures. Furthermore, it can mitigate the occasional errors inherent in manual annotation, leading to improved performance compared to models trained with expert annotations. Experimental validation was conducted using four self-built datasets with different image qualities to test the performance of models from different perspective. Initially, hyperparameter optimization for the SPFCA method tailored to our dataset was performed. Subsequently, SPFCA was utilized to guide the optimization of the convolutional neural network employed for segmentation. The results demonstrate that the segmentation model optimized with SPFCA guidance achieved an F1 score of 0.9226 in the single dataset without the need for manual labeling, surpassing the segmentation models optimized with expert annotations.

Machine learning methods for compound annotation in non-targeted mass spectrometry-A brief overview of fingerprinting, in silico fragmentation and de novo methods.

Non-targeted screenings (NTS) are essential tools in different fields, such as forensics, health and environmental sciences. NTSs often employ mass spectrometry (MS) methods due to their high throughput and sensitivity in comparison to, for example, nuclear magnetic resonance-based methods. As the identification of mass spectral signals, called annotation, is labour intensive, it has been used for developing supporting tools based on machine learning (ML). However, both the diversity of mass spectral signals and the sheer quantity of different ML tools developed for compound annotation present a challenge for researchers in maintaining a comprehensive overview of the field. In this work, we illustrate which ML-based methods are available for compound annotation in non-targeted MS experiments and provide a nuanced comparison of the ML models used in MS data analysis, unravelling their unique features and performance metrics. Through this overview we support researchers to judiciously apply these tools in their daily research. This review also offers a detailed exploration of methods and datasets to show gaps in current methods, and promising target areas, offering a starting point for developers intending to improve existing methodologies.

Study of Contactless Computer Vision-Based Road Condition Estimation Methods Within the Framework of an Operational Design Domain Monitoring System

Deployment of Level 3 and Level 4 autonomous vehicles (AVs) in urban environments is significantly constrained by adverse weather conditions, limiting their operation to clear weather due to safety concerns. Ensuring that AVs remain within their designated Operational Design Domain (ODD) is a formidable challenge, making boundary monitoring strategies essential for safe navigation. This study explores the critical role of an ODD monitoring system (OMS) in addressing these challenges. It reviews various methodologies for designing an OMS and presents a comprehensive visualization framework incorporating trigger points for ODD exits. These trigger points serve as essential references for effective OMS design. The study also delves into a specific use case concerning ODD exits: the reduction in road friction due to adverse weather conditions. It emphasizes the importance of contactless computer vision-based methods for road condition estimation (RCE), particularly using vision sensors such as cameras. The study details a timeline of methods involving classical machine learning and deep learning feature extraction techniques, identifying contemporary challenges such as class imbalance, lack of comprehensive datasets, annotation methods, and the scarcity of generalization techniques. Furthermore, it provides a factual comparison of two state-of-the-art RCE datasets. In essence, the study aims to address and explore ODD exits due to weather-induced road conditions, decoding the practical solutions and directions for future research in the realm of AVs.

Clinical relevance of protein-truncating variants of germline DNA repair genes in prostate cancer

BackgroundInterpreting genetic variants remains a challenge in prostate cancer (PCa). Although many annotation tools are available for prioritizing causal variants, the clinical relevance of these variants is rarely studied.MethodsWe collected a cohort study that included 274 PCa patients from June 2017 to December 2020 and sequenced 19 DNA damage repair (DDR) genes in these patients and explored the clinical consequence of these different approaches. We also examined all-cause and PCa-specific survival in DDR gene mutation carriers compared to non-carriers after androgen receptor (AR)-directed therapy.ResultsWe identified 13 variants from 19 DDR genes in a total of 14 (5.1%) patients who had at least one presumed pathogenic mutation using different annotation methods. Four variants were annotated as pathogenic, 11 variants were predicted as protein-truncating variants (PTVs), four variants received proxy-deleterious (Combined Annotation-Dependent Depletion scores of > 30), and only one variant was identified as a pathogenic variant or as having a functional effect by all three methods. PCa patients with PTVs were significantly associated with early onset, high cancer stage, and a worse response to AR-directed treatment. However, patients carrying a proxy-deleterious variant were only associated with a higher T (tumor) stage and N (node) stage than those without such a variant, but not associated with other clinical characteristics. In patients treated with AR-directed therapy, patients with a PTV showed an increased risk of all-cause death (adjusted hazard ratio (aHR) = 3.51, 95% confidence interval (CI): 1.06 ~ 11.56) and PCa-specific death (aHR = 4.49, 95% CI: 1.87 ~ 10.77) compared to non-PTV carriers after adjustment. We were unable to examine gene-specific risks due to the small number of patients.ConclusionsPTVs may assist in guiding treatment and early screening in PCa, while population-specific data for pathogenic variants are still being amassed.

Structural elucidation of 14-membered ring macrolide antibiotics using electrospray ionization tandem mass spectrometry and density functional theory calculations.

Macrolides are critical antibiotics featuring a macrocyclic lactone core with deoxy sugars. Understanding their gas-phase fragmentation is challenging but essential for improving structural elucidation in mass spectrometry, which has implications for drug discovery and development. We used electrospray ionization collision-induced dissociation tandem mass spectrometry (ESI-CID-MS) combined with quantum chemical calculations to investigate the fragmentation pathways of erythromycin A and roxithromycin. This approach helps elucidate the preferred fragmentation routes influenced by protonation sites. Macrolides showed similar fragmentation patterns, including sequential losses of saccharide or amino sugar units and dehydration from the macrocycle core. Multiple competitive pathways were observed, influenced by protonation sites. Computational studies confirmed the most favorable protonation sites and their impact on fragmentation, providing insights into key diagnostic product ions. Subsequent fragments involved rearrangement pathways such as alkene formation and cleavages via remote hydrogen transfers and pericyclic reactions. Our integrated approach offers a comprehensive understanding of macrolide fragmentation, enhancing structural elucidation and potential applications in drug development. This study advances mass spectrometry analysis of macrolides, contributing to pharmaceutical research by integrating orthogonal annotation methods and fragmentation studies.

SDFSD-v1.0: A Sub-Meter SAR Dataset for Fine-Grained Ship Detection

In the field of target detection, a prominent area is represented by ship detection in SAR imagery based on deep learning, particularly for fine-grained ship detection, with dataset quality as a crucial factor influencing detection accuracy. Datasets constructed with commonly used slice-based annotation methods suffer from a lack of scalability and low efficiency in repeated editing and reuse. Existing SAR ship datasets mostly consist of medium to low resolution imagery, leading to coarse ship categories and limited background scenarios. We developed the “annotate entire image, then slice” workflow (AEISW) and constructed a sub-meter SAR fine-grained ship detection dataset (SDFSD) by using 846 sub-meter SAR images that include 96,921 ship instances of 15 ship types across 35,787 slices. The data cover major ports and shipping routes globally, with varied and complex backgrounds, offering diverse annotation information. Several State-of-the-Art rotational detection models were used to evaluate the dataset, providing a baseline for ship detection and fine-grained ship detection. The SDFSD is a high spatial resolution ship detection dataset that could drive advancements in research on ship detection and fine-grained detection in SAR imagery.

Quest for Orthologs in the Era of Biodiversity Genomics.

The era of biodiversity genomics is characterised by large-scale genome sequencing efforts that aim to represent each living taxon with an assembled genome. Generating knowledge from this wealth of data has not kept up with this pace. We here discuss major challenges to integrating these novel genomes into a comprehensive functional and evolutionary network spanning the tree of life. In summary, the expanding datasets create a need for scalable gene annotation methods. To trace gene function across species, new methods must seek to increase the resolution of ortholog analyses, e.g., by extending analyses to the protein domain level and by accounting for alternative splicing. Additionally, the scope of orthology prediction should be pushed beyond well-investigated proteomes. This demands the development of specialised methods for the identification of orthologs to short proteins and non-coding RNAs, and for the functional characterization of novel gene families. Furthermore, protein structures predicted by machine learning are now readily available, but this new information is yet to be integrated with orthology-based analyses. Finally, an increasing focus should be placed on making orthology assignments adhere to the FAIR principles. This fosters green bioinformatics by avoiding redundant computations and helps integrating diverse scientific communities sharing the need for comparative genetics and genomics information. It should also help with communicating orthology-related concepts in a format that is accessible to the public, to counteract existing misinformation about evolution.

Evaluation of segmentation and semi‐supervised learning for spotted spurge recognition in bermudagrass turf

AbstractDiverse datasets are crucial for training machine learning‐based weed recognition models. However, annotating (i.e., labeling) images can be laborious and time‐consuming. Choice of annotation method and training approach not only affects the overall model effectiveness but also its minimum training data requirements and development pace. Segmentation and semi‐supervised learning (SSL) may offer performance or training enhancements. This study evaluated (1) segmentation against object detection in spotted spurge [Chamaesyce maculata (L.) Small] recognition in Latitude 36 hybrid bermudagrass [Cynodon dactylon (L.) Pers. × C. transvaalensis Burtt‐Davy] maintained as a golf course fairway and (2) the potential of two‐step SSL‐based training procedure using data labeled both manually and automatically with a pre‐trained model to expedite the model development. The architecture used across this research was You Only Look Once version 8 (YOLOv8) employing nano, small, and medium variants. All models were trained with a dataset restricted to 1200 training and 300 validation images. Both annotation methods resulted in adequate spotted spurge identification, as evidenced with >0.60 (>0.50 acceptability threshold) medium average precision at intersection over union threshold of 0.50 (mAP@50). Although the difference was minimal, object detection performed superior to segmentation. The two‐step training effectively accelerated image annotation while preserving or improving (with 8:4 and 6:6 splits between manually and auto‐labeled data) object detection performance. Segmentation tolerated only 10:2 split and exhibited increased sensitivity to declining dataset quality proportionally to the increase in auto‐labeled images in the final training dataset. Findings show a two‐step SSL‐based training procedure expedites annotation, enhancing model development efficiency.

Real-time robust liver and gallbladder segmentation during laparoscopic cholecystectomy using convolutional neural networks: an analysis

Aim: Images in different laparoscopic cholecystectomy datasets are acquired using various camera models, parameters, and settings, with the annotation methods varying by institution. These factors result in inconsistent inference performance of the network model. This study aims to identify the optimal network model architecture for liver and gallbladder segmentation from several options. Then, the performance and robustness of the optimal network model are evaluated using an independent dataset that is not included in the training. Methods: The public dataset, CholecSeg8k, was utilized as the input for the network model training, validation, and testing. A local private dataset from KPJ Damansara Hospital, Selangor, Malaysia, was used for testing purposes only. For the implementation of liver and gallbladder segmentation, segmentation models, a public Python library was employed. Results: Among the experiments, highly accurate liver and gallbladder segmentation results were achieved using the feature pyramid network (FPN) architecture as the network model, with the Inception-ResNet-v2 architecture as the network backbone. The best-trained network model resulted in a loss of 0.070955, a mean intersection over union (IoU) score of 0.95896, and a mean F1-score of 0.9773 on the test set. However, visualized results for the private dataset contained considerable false-negative areas. Conclusion: The proposed automated technique has the potential to serve as an alternative to the conventional indocyanine green injection along with near-infrared fluorescence imaging (ICG-NIRF)-based method for liver and gallbladder segmentation during laparoscopic cholecystectomy. Future work will focus on enhancing the results of the private dataset. Additionally, a surgeon-assistant robotic arm that will use the liver and gallbladder segmentation results for camera steering will be analyzed.

Enhancing Large Language Model Comprehension of Material Phase Diagrams through Prompt Engineering and Benchmark Datasets

Large Language Models (LLMs) excel in fields such as natural language understanding, generation, complex reasoning, and biomedicine. With advancements in materials science, traditional manual annotation methods for phase diagrams have become inadequate due to their time-consuming nature and limitations in updating thermodynamic databases. To overcome these challenges, we propose a framework based on instruction tuning, utilizing LLMs for automated end-to-end annotation of phase diagrams. High-quality phase diagram images and expert descriptions are collected from handbooks and then preprocessed to correct errors, remove redundancies, and enhance information. These preprocessed data form a golden dataset, from which a subset are used to train LLMs through hierarchical sampling. The fine-tuned LLM is then tested for automated phase diagram annotation. Results show that the fine-tuned model achieves a cosine similarity of 0.8737, improving phase diagram comprehension accuracy by 7% compared to untuned LLMs. To the best of our knowledge, this is the first paper to propose using LLMs for the automated annotation of phase diagrams, replacing traditional manual annotation methods and significantly enhancing efficiency and accuracy.

High-throughput protein characterization by complementation using DNA barcoded fragment libraries

Our ability to predict, control, or design biological function is fundamentally limited by poorly annotated gene function. This can be particularly challenging in non-model systems. Accordingly, there is motivation for new high-throughput methods for accurate functional annotation. Here, we used complementation of auxotrophs and DNA barcode sequencing (Coaux-Seq) to enable high-throughput characterization of protein function. Fragment libraries from eleven genetically diverse bacteria were tested in twenty different auxotrophic strains of Escherichia coli to identify genes that complement missing biochemical activity. We recovered 41% of expected hits, with effectiveness ranging per source genome, and observed success even with distant E. coli relatives like Bacillus subtilis and Bacteroides thetaiotaomicron. Coaux-Seq provided the first experimental validation for 53 proteins, of which 11 are less than 40% identical to an experimentally characterized protein. Among the unexpected function identified was a sulfate uptake transporter, an O-succinylhomoserine sulfhydrylase for methionine synthesis, and an aminotransferase. We also identified instances of cross-feeding wherein protein overexpression and nearby non-auxotrophic strains enabled growth. Altogether, Coaux-Seq’s utility is demonstrated, with future applications in ecology, health, and engineering.

Towards an open digital catalogue of sound signatures from the underwater soundscape

Passive acoustic monitoring plays a crucial role to study the underwater soundscape. Identifying the sound signatures of specific marine species and anthropogenic contributions is a key step in assessing the impact of human activities on the acoustic environment. The project COSS (Catalogue of Sound Signatures) aims to build an open library of sound signatures from the coastal seascape of European waters. In this framework, a data management workflow is developed within FAIR principles from the storage of the metadata, ensuring integrity and traceability of the recorded datasets, to the analysis and the annotation method, providing interoperability classification of sound signatures. An interactive map provides an overview of the database. Sound events are analyzed using a home-made annotation software. Labeling is based on a tree-structure ontology with respect to the biological species, human activities and geophony. This labels standardization makes it possible to extract information at several levels of precision. In particular, this library will serve as a learning and testing base for open source AI algorithms for the automatic classification of signals of anthropogenic origin. A long-term objective is to provide a means of determining the acoustic impact of human activities on the marine environment.

One point is all you need for weakly supervised object detection

Object detection with weak annotations has attracted much attention recently. Weakly supervised object detection(WSOD) methods which only use image-level labels to train a detector encounter some severe problems that it cannot cover the whole object and the region proposal methods waste a large amount of time. Meanwhile, point supervised object detection(PSOD) leverages point annotations that remarkably improves the performance. However, point annotation is still complex and increase the costs of annotation. To overcome these issues, we propose a novel method which only requires one point per category for a training image. Compared to point annotation, our method significantly reduces the annotation cost as the number of point annotations is largely reduced. We design a framework to train a detector with one point per category annotation. Firstly, a pseudo box generation module is introduced to generate the corresponding pseudo boxes of the annotated points. Then, inspired by the observation that the features of objects with the same class in an image are very similar, a dense instances mining module is proposed to make use of the similarity between the features of objects with the same class to discover unlabeled instances and generate pseudo category heatmaps. Finally, the pseudo boxes and pseudo category heatmaps are leveraged to train a detector. Experiments conducted on popular open-source datasets verify the effectiveness of our annotation method and framework. Our proposed method outperforms previous WSOD methods and achieves comparable performance with some PSOD methods in a more efficient way.

Prompt-guided and multimodal landscape scenicness assessments with vision-language models.

Recent advances in deep learning and Vision-Language Models (VLM) have enabled efficient transfer to downstream tasks even when limited labelled training data is available, as well as for text to be directly compared to image content. These properties of VLMs enable new opportunities for the annotation and analysis of images. We test the potential of VLMs for landscape scenicness prediction, i.e., the aesthetic quality of a landscape, using zero- and few-shot methods. We experiment with few-shot learning by fine-tuning a single linear layer on a pre-trained VLM representation. We find that a model fitted to just a few hundred samples performs favourably compared to a model trained on hundreds of thousands of examples in a fully supervised way. We also explore the zero-shot prediction potential of contrastive prompting using positive and negative landscape aesthetic concepts. Our results show that this method outperforms a linear probe with few-shot learning when using a small number of samples to tune the prompt configuration. We introduce Landscape Prompt Ensembling (LPE), which is an annotation method for acquiring landscape scenicness ratings through rated text descriptions without needing an image dataset during annotation. We demonstrate that LPE can provide landscape scenicness assessments that are concordant with a dataset of image ratings. The success of zero- and few-shot methods combined with their ability to use text-based annotations highlights the potential for VLMs to provide efficient landscape scenicness assessments with greater flexibility.

Identification of kidney cell types in scRNA-seq and snRNA-seq data using machine learning algorithms

IntroductionSingle-cell RNA sequencing (scRNA-seq) and single-nucleus RNA sequencing (snRNA-seq) provide valuable insights into the cellular states of kidney cells. However, the annotation of cell types often requires extensive domain expertise and time-consuming manual curation, limiting scalability and generalizability. To facilitate this process, we tested the performance of five supervised classification methods for automatic cell type annotation. ResultsWe analyzed publicly available sc/snRNA-seq datasets from five expert-annotated studies, comprising 62,120 cells from 79 kidney biopsy samples. Datasets were integrated by harmonizing cell type annotations across studies. Five different supervised machine learning algorithms (support vector machines, random forests, multilayer perceptrons, k-nearest neighbors, and extreme gradient boosting) were applied to automatically annotate cell types using four training datasets and one testing dataset. Performance metrics, including accuracy (F1 score) and rejection rates, were evaluated. All five machine learning algorithms demonstrated high accuracies, with a median F1 score of 0.94 and a median rejection rate of 1.8 %. The algorithms performed equally well across different datasets and successfully rejected cell types that were not present in the training data. However, F1 scores were lower when models trained primarily on scRNA-seq data were tested on snRNA-seq data. ConclusionsDespite limitations including the number of biopsy samples, our findings demonstrate that machine learning algorithms can accurately annotate a wide range of adult kidney cell types in scRNA-seq/snRNA-seq data. This approach has the potential to standardize cell type annotation and facilitate further research on cellular mechanisms underlying kidney disease.

GGN-GO: geometric graph networks for predicting protein function by multi-scale structure features.

Recent advances in high-throughput sequencing have led to an explosion of genomic and transcriptomic data, offering a wealth of protein sequence information. However, the functions of most proteins remain unannotated. Traditional experimental methods for annotation of protein functions are costly and time-consuming. Current deep learning methods typically rely on Graph Convolutional Networks to propagate features between protein residues. However, these methods fail to capture fine atomic-level geometric structural features and cannot directly compute or propagate structural features (such as distances, directions, and angles) when transmitting features, often simplifying them to scalars. Additionally, difficulties in capturing long-range dependencies limit the model's ability to identify key nodes (residues). To address these challenges, we propose a geometric graph network (GGN-GO) for predicting protein function that enriches feature extraction by capturing multi-scale geometric structural features at the atomic and residue levels. We use a geometric vector perceptron to convert these features into vector representations and aggregate them with node features for better understanding and propagation in the network. Moreover, we introduce a graph attention pooling layer captures key node information by adaptively aggregating local functional motifs, while contrastive learning enhances graph representation discriminability through random noise and different views. The experimental results show that GGN-GO outperforms six comparative methods in tasks with the most labels for both experimentally validated and predicted protein structures. Furthermore, GGN-GO identifies functional residues corresponding to those experimentally confirmed, showcasing its interpretability and the ability to pinpoint key protein regions. The code and data are available at: https://github.com/MiJia-ID/GGN-GO.

Navigating the archaeal frontier: insights and projections from bioinformatic pipelines.

Archaea continues to be one of the least investigated domains of life, and in recent years, the advent of metagenomics has led to the discovery of many new lineages at the phylum level. For the majority, only automatic genomic annotations can provide information regarding their metabolic potential and role in the environment. Here, genomic data from 2,978 archaeal genomes was used to perform automatic annotations using bioinformatics tools, alongside synteny analysis. These automatic classifications were done to assess how good these different tools perform in relation to archaeal data. Our study revealed that even with lowered cutoffs, several functional models do not capture the recently discovered archaeal diversity. Moreover, our investigation revealed that a significant portion of archaeal genomes, approximately 42%, remain uncharacterized. In comparison, within 3,235 bacterial genomes, a diverse range of unclassified proteins is obtained, with well-studied organisms like Escherichia coli having a substantially lower proportion of uncharacterized regions, ranging from <5 to 25%, and less studied lineages being comparable to archaea with the range of 35-40% of unclassified regions. Leveraging this analysis, we were able to identify metabolic protein markers, thereby providing insights into the metabolism of the archaea in our dataset. Our findings underscore a substantial gap between automatic classification tools and the comprehensive mapping of archaeal metabolism. Despite advances in computational approaches, a significant portion of archaeal genomes remains unexplored, highlighting the need for extensive experimental validation in this domain, as well as more refined annotation methods. This study contributes to a better understanding of archaeal metabolism and underscores the importance of further research in elucidating the functional potential of archaeal genomes.

Flexible and robust cell type annotation for highly multiplexed tissue images.

Identifying cell types in highly multiplexed images is essential for understanding tissue spatial organization. Current cell type annotation methods often rely on extensive reference images and manual adjustments. In this work, we present a tool, Robust Image-Based Cell Annotator (RIBCA), that enables accurate, automated, unbiased, and fine-grained cell type annotation for images with a wide range of antibody panels, without requiring additional model training or human intervention. Our tool has successfully annotated over 1 million cells, revealing the spatial organization of various cell types across more than 40 different human tissues. It is open-source and features a modular design, allowing for easy extension to additional cell types.