Insufficient Representation Research Articles

CGPDTA: An Explainable Transfer Learning-Based Predictor With Molecule Substructure Graph for Drug-Target Binding Affinity.

Identifying interactions between drugs and targets is crucial for drug discovery and development. Nevertheless, the determination of drug-target binding affinities (DTAs) through traditional experimental methods is a time-consuming process. Conventional approaches to predicting drug-target interactions (DTIs) frequently prove inadequate due to an insufficient representation of drugs and targets, resulting in ineffective feature capture and questionable interpretability of results. To address these challenges, we introduce CGPDTA, a novel deep learning framework empowered by transfer learning, designed explicitly for the accurate prediction of DTAs. CGPDTA leverages the complementarity of drug-drug and protein-protein interaction knowledge through advanced drug and protein language models. It further enhances predictive capability and interpretability by incorporating molecular substructure graphs and protein pocket sequences to represent local features of drugs and targets effectively. Our findings demonstrate that CGPDTA not only outperforms existing methods in accuracy but also provides meaningful insights into the predictive process, marking a significant advancement in the field of drug discovery.

Algorithms for graph theory matching problems based on computer science

Existing graph-matching algorithms only use the graph’s edges to transmit information and cannot perform hierarchical reasoning and fusion. Although they have achieved good results in graph matching, problems exist such as planarization and insufficient representation of graph data. This paper aims to study graph theory matching algorithms based on computer science, solve matching problems on large-scale graphs, reduce computation time, and improve solving efficiency. This paper studied graph theory matching algorithms based on computer science, including heuristic algorithm-based matching algorithms and machine learning-based matching algorithms; the specific matching problem was mathematically analyzed and transformed into a matching problem in graph theory, which included defining the input and output of the problem, determining the structure and properties of nodes and edges in the graph, and clarifying the required matching and constraint conditions. The experimental results of this paper showed that the average optimal matching rates of the Kuhn–Munkres algorithm, Gale–Shapley (GS)-based algorithm, Genetic Algorithm (GA), Particle Swarm Optimization (PSO) algorithm and Support Vector Machine (SVM) algorithm in complex scenarios were 62.05%, 58.42%, 82.79%, 81.99% and 83.50%, respectively. Studying graph theory matching algorithms based on computer science is of great significance. It can not only solve practical application problems and improve computational efficiency, but also promote algorithm optimization, which helps to improve the processing speed and efficiency of practical problems.

Capsule Attention Network for Hyperspectral Image Classification

While many neural networks have been proposed for hyperspectral image classification, current backbones cannot achieve accurate results due to the insufficient representation by scalar features and always cause a cumbersome calculation burden. To solve the problem, we propose the capsule attention network (CAN), which combines an activity vector with an attention mechanism to improve HSI classification. In particular, we consider two attention mechanisms to improve the effectiveness of the activity vectors. First, an attention-based feature extraction (AFE) module is proposed to preprocess the spectral-spatial features of HSI data, which effectively mines useful information before the generation of the activity vectors. Second, we propose a self-weighted mechanism (SWM) to distinguish the importance of different capsule convolutions, which enhances the representation of the primary activity vectors. Experiments on four well-known HSI datasets have shown our CAN surpasses state-of-the-art (SOTA) methods on three widely used metrics with a much lower computational burden.

Machine-directed Gravitational-wave Counterpart Discovery

Joint observations in electromagnetic and gravitational waves shed light on the physics of objects and surrounding environments with extreme gravity that are otherwise unreachable via siloed observations in each messenger. However, such detections remain challenging due to the rapid and faint nature of counterparts. Protocols for discovery and inference still rely on human experts manually inspecting survey alert streams and intuiting optimal usage of limited follow-up resources. Strategizing an optimal follow-up program requires adaptive sequential decision-making given evolving light curve data that (i) maximizes a global objective despite incomplete information and (ii) is robust to stochasticity introduced by detectors/observing conditions. Reinforcement learning (RL) approaches allow agents to implicitly learn the physics or detector dynamics and the behavior policy that maximizes a designated objective through experience. To demonstrate the utility of such an approach for the kilonova follow-up problem, we train a toy RL agent with the goal of maximizing follow-up photometry for the true kilonova among several contaminant transient light curves. In a simulated environment where the agent learns online, it achieves 3× higher accuracy compared to a random strategy. However, it is surpassed by human agents by up to a factor of 2. This is likely because our hypothesis function (Q that is linear in state-action features) is an insufficient representation of the optimal behavior policy. More complex agents could perform at par or surpass human experts. Agents like these could pave the way for machine-directed software infrastructure to efficiently respond to next generation detectors, for conducting science inference and optimally planning expensive follow-up observations, scalably and with demonstrable performance guarantees.

Occurrence, Molecular Serogroups, Antimicrobial Susceptibility and Identification by MALDI-TOF MS of Listeria monocytogenes Isolated from RTE Meat Products in Southern Poland.

L. monocytogenes is considered one of the most dangerous foodborne pathogens. This study aimed to determine the occurrence of L. monocytogenes in RTE meat products from southern Poland, including serogroups and antimicrobial susceptibility, and to assess the usefulness of MALDI-TOF MS as a tool for identifying L. monocytogenes. A total of 848 production batches of RTE meat products were analyzed for L. monocytogenes. All L. monocytogenes isolates were serotyped using the multiplex PCR method, tested for antimicrobial susceptibility using the disk diffusion method and identified using the MALDI-TOF MS method. L. monocytogenes was detected in 52/848 batches of RTE meat products (6.13%). The isolates belonged to four serogroups: 17/52 (33%) isolates to IVb; 15/52 (29%) isolates to IIa; 10/52 (19%) isolates to IIc and 10/52 (19%) isolates to IIb. All isolates (52/52) showed susceptibility to the tested antimicrobials. Using MALDI-TOF MS, 10/52 isolates (19.2%) were identified at the level of secure genus identification, probable species identification; 37/52 isolates (71.2%) were identified at the level of probable genus identification; 3/52 isolates (5.8%) were incorrectly identified as L. innocua; and 2/52 isolates (3.8%) were not identified. The occurrence of L. monocytogenes in RTE meat products was low. Almost half of the analyzed isolates were L. monocytogenes of serogroups, which are most often associated with listeriosis in humans in Poland. All isolates showed susceptibility to five commonly used antimicrobials for treating listeriosis. The use of MALDI-TOF MS as a tool for the identification of L. monocytogenes indicated its limitations related to the insufficient representation of the pathogen in the reference database.

Combined effects of fine and coarse marine aerosol on vertical raindrop size distribution

Climate models commonly overestimate warm rain frequency and underestimate its intensity over the ocean, primarily due to insufficient representation of the aerosol effects. This pertains to both fine aerosols (FA) and coarse sea spray aerosols (CSA), where the latter is mostly absent in the models. Here, our observations show that adding CSA enhances vertical warm rain structure, in contrast to the effect of FA. The magnitude of the effect of CSA is larger than the opposite effect of the FA. For rain with top heights of 2–3 km, the raindrop size, concentration, and rain rate can be increased by factors of 1.03, 1.47, and 1.60, respectively. These CSA-induced changes are larger for thicker clouds, reaching a maximum by factors of 1.12, 1.85, and 2.21, respectively. Therefore, the combined FA and CSA effects should be incorporated into climate models for accurately simulated precipitation microphysical processes.

Urban hyperspectral reference data availability and reuse: State‐of‐the‐practice review

AbstractHyperspectral remote sensing is currently underutilized in urban environments due to significant barriers concerning the existence, availability, and quality of urban hyperspectral reference spectra. This paper exposes these barriers by identifying, cataloging, and characterizing the contents of 23 spectral libraries, developing metrics to assess compliance with the Principles of Findability, Accessibility, Interoperability, and Reusability (FAIR), and evaluating existing resources using these criteria. Only 2931 urban spectral records were found within the 4 Global Spectral Libraries (0.61% of 476,592 published spectra). Within a further 19 Local Urban Spectral Libraries, 3862 additional urban spectra were found, but only 1662 (43%) were accessible without restriction. Content analysis revealed insufficient representation of urban material heterogeneity, imbalanced categories, and limited library interoperability, all of which further hinder effective data utilization. In response, this paper proposes a 14‐category metadataset, with specific considerations to overcome environmentally induced and inherent, intra‐material variability. In addition, material‐based spectral groupings and data resampling to common hyperspectral equipment specifications are recommended. These measures aim to enhance the utility of urban spectral libraries by improving FAIR compliance, thereby contributing to a more cohesive and enduring framework for hyperspectral reference data.

An imbalanced learning method based on graph tran-smote for fraud detection

Fraud seriously threatens individual interests and social stability, so fraud detection has attracted much attention in recent years. In scenarios such as social media, fraudsters typically hide among numerous benign users, constituting only a small minority and often forming “small gangs”. Due to the scarcity of fraudsters, the conventional graph neural network might overlook or obscure critical fraud information, leading to insufficient representation of fraud characteristics. To address these issues, the tran-smote on graphs (GTS) method for fraud detection is proposed by this study. Structural features of each type of node are deeply mined using a subgraph neural network extractor, these features are integrated with attribute features using transformer technology, and the node’s information representation is enriched, thereby addressing the issue of inadequate feature representation. Additionally, this approach involves setting a feature embedding space to generate new nodes representing minority classes, and an edge generator is used to provide relevant connection information for these new nodes, alleviating the class imbalance problem. The results from experiments on two real datasets demonstrate that the proposed GTS, performs better than the current state-of-the-art baseline.

Optimisation of city structures with respect to high wind speeds using U-Net models

The design and placement of a new building in an urban environment is optimised so that pedestrians do not feel uncomfortable due to high wind speeds. Architects and city planners typically use Computational Fluid Dynamics (CFD) simulations to predict the effects of wind on new buildings. CFD is too time consuming to be used in generative design tools, which are necessary because they allow designers to visualise and iterate on their ideas, collaborate effectively and work more efficiently. These tools enhance the design process, facilitate communication and feedback, and save time by automating tasks. Finding a generative design model based on limited data is challenging due to issues such as insufficient representation, increased risk of overfitting, lack of statistical significance, potential bias and difficulties in validation and evaluation. In the design framework proposed in this paper, the computationally intensive CFD solver could be replaced by a fast machine learning surrogate predicting wind speed. The replacement is a U-Net convolutional neural network trained on high-precision Reynolds’ averaged Navier–Stokes (RANS) simulations (CFD simulations). The proposed workflow is demonstrated by optimising the placement of a hypothetical new building on a city square in Gothenburg, Sweden. The surrogate used in the optimisation process calculates an optimal building design within seconds instead of hours saving 11 h of simulation time. The actual area with strong wind effects is reduced by half.

Programming knowledge tracing based on heterogeneous graph representation

Existing programming knowledge tracing methods have not deeply explored the relationships between knowledge concepts and programming questions or students’ codes, which leads to insufficient representation of programming questions and students’ codes and insufficient tracing of students’ knowledge states. To address these problems, this study proposes a programming knowledge tracing method based on a heterogeneous graph representation. We constructed a heterogeneous graph, where nodes represent the knowledge concept, programming question, and student code, and edges represent the relationships among knowledge concepts, programming questions, and student code. Subsequently, we leverage a graph structure learning algorithm to exploit the potential connections among them, aiming to enhance the graph structure information. Based on the graph, we further fully integrated the knowledge concept information into the representations of programming questions and student codes through the graph convolutional representation learning algorithm. Moreover, an attention mechanism is utilized to compute the effect of programming questions and student codes on the knowledge state and update the student's knowledge state in conjunction with the corresponding answer results. Furthermore, the proposed method provides an assessment of the mastery level for each knowledge concept rather than only assessing each question using traditional methods. Experiments on two datasets, CodeWorkout and CodeNet, show that the proposed method achieves an average improvement of 4.28% in ACC and 6.48% in AUC compared with the baseline models, validating the effectiveness of the proposed method.

Global shortfalls in documented actions to conserve biodiversity

Threatened species are by definition species that are in need of assistance. In the absence of suitable conservation interventions, they are likely to disappear soon1. There is limited understanding of how and where conservation interventions are applied globally, or how well they work2,3. Here, using information from the International Union for Conservation of Nature Red List and other global databases, we find that for species at risk from three of the biggest drivers of biodiversity loss—habitat loss, overexploitation for international trade and invasive species4—many appear to lack the appropriate types of conservation interventions. Indeed, although there has been substantial recent expansion of the protected area network, we still find that 91% of threatened species have insufficient representation of their habitats within protected areas. Conservation interventions are not implemented uniformly across different taxa and regions and, even when present, have infrequently led to substantial improvements in the status of species. For 58% of the world’s threatened terrestrial species, we find conservation interventions to be notably insufficient or absent. We cannot determine whether such species are truly neglected, or whether efforts to recover them are not included in major conservation databases. If they are indeed neglected, the outlook for many of the world’s threatened species is grim without more and better targeted action.

A novel model for relation prediction in knowledge graphs exploiting semantic and structural feature integration

Relation prediction is a critical task in knowledge graph completion and associated downstream tasks that rely on knowledge representation. Previous studies indicate that both structural features and semantic information are meaningful for predicting missing relations in knowledge graphs. This has led to the development of two types of methods: structure-based methods and semantics-based methods. Since these two approaches represent two distinct learning paradigms, it is difficult to fully utilize both sets of features within a single learning model, especially deep features. As a result, existing studies usually focus on only one type of feature. This leads to an insufficient representation of knowledge in current methods and makes them prone to overlooking certain patterns when predicting missing relations. In this study, we introduce a novel model, RP-ISS, which combines deep semantic and structural features for relation prediction. The RP-ISS model utilizes a two-part architecture, with the first component being a RoBERTa module that is responsible for extracting semantic features from entity nodes. The second part of the system employs an edge-based relational message-passing network designed to capture and interpret structural information within the data. To alleviate the computational burden of the message-passing network on the RoBERTa module during the sampling process, RP-ISS introduces a node embedding memory bank, which updates asynchronously to circumvent excessive computation. The model was assessed on three publicly accessible datasets (WN18RR, WN18, and FB15k-237), and the results revealed that RP-ISS surpasses all baseline methods across all evaluation metrics. Moreover, RP-ISS showcases robust performance in graph inductive learning.

FFEDet: Fine-Grained Feature Enhancement for Small Object Detection

Small object detection poses significant challenges in the realm of general object detection, primarily due to complex backgrounds and other instances interfering with the expression of features. This research introduces an uncomplicated and efficient algorithm that addresses the limitations of small object detection. Firstly, we propose an efficient cross-scale feature fusion attention module called ECFA, which effectively utilizes attention mechanisms to emphasize relevant features across adjacent scales and suppress irrelevant noise, tackling issues of feature redundancy and insufficient representation of small objects. Secondly, we design a highly efficient convolutional module named SEConv, which reduces computational redundancy while providing a multi-scale receptive field to improve feature learning. Additionally, we develop a novel dynamic focus sample weighting function called DFSLoss, which allows the model to focus on learning from both normal and challenging samples, effectively addressing the problem of imbalanced difficulty levels among samples. Moreover, we introduce Wise-IoU to address the impact of poor-quality examples on model convergence. We extensively conduct experiments on four publicly available datasets to showcase the exceptional performance of our method in comparison to state-of-the-art object detectors.

Improving lung cancer health equity by applying deep learning to low dose CT screening of minority and disadvantaged patients.

1584 Background: In the US, disparities in lung cancer mortality exist for African American, Hispanic, and other minorities. Standard of care low dose CT screening (LDCT) detects early-stage disease and improves mortality, yet disparities are perpetuated in screening by eligibility criteria derived from cohorts underrepresenting these minorities. One such cohort is the National Lung Screening Trial (NLST) cohort which is 92% White. Consequently, guidelines for lung cancer screening may be insufficient to address the unique needs of diverse populations. We hypothesize that Artificial Intelligence prediction of future lung cancer risk from an individual’s LDCT can partially mitigate racial and ethnic disparities and improve health system practice guidelines by individualizing screening risk as compared to current general guidelines. Here, we benchmark a Resnet18 3D neural network trained on NLST LDCT images, Sybil, on the diverse patient population of the University of Illinois Health system (UIH) which is 20% White and 60% African American. Methods: A real-world cohort from UIH consisting of 1,450 CT studies was evaluated alongside 60,378 CT studies from the NLST cohort. All CT studies evaluated by the model were not used in model training. Using Youden’s J index as a probability cutoff, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were evaluated. Receiver operating characteristic (ROC) and precision-recall (PR) curves were generated to assess model performance between cohorts. NLST data were truncated to achieve equivalent incidence of lung cancer with UIH when generated PR curves. Results: Multi-year prediction performance (ROC-AUC and PR-AUC) between cohorts are summarized (Table). For prediction of lung cancer within 1-year of LDCT in the UIH cohort, the model respectively demonstrated sensitivity, specificity, positive predictive value, and negative predictive value among White (0.80, 0.77, 0.54, 0.92), African American (0.84, 0.78, 0.39, 0.97) races and Hispanic (0.75, 0.73, 0.60, 0.84) and non-Hispanic (0.87, 0.77, 0.42, 0.97) ethnicities. Conclusions: Model performance was similar between the NLST (92% White) and a diverse, real-world cohort at UIH (20% White) though decreases in ROC-AUC performance in year 1 predictions and may be due to insufficient representation of minority populations during model training. Prospective studies involving larger and more representative patient populations should be conducted to further optimize the model and evaluate its clinical utility to improve lung cancer health equity in minority populations.[Table: see text]

Under-representation of Diversity on American Urological Association and European Association of Urology Guideline Panels

ObjectiveTo assess the panel composition of the two most important guideline developers in urology as equity and acceptability, important domains in clinical guideline development, require broad stakeholder representation. MethodsFollowing a predefined protocol, we identified all current AUA and EAU guideline documents. Two authors independently abstracted data including guideline topic, number and roles of panel members, voting status, and academic rank. We determined panel member gender (woman, man, or nonbinary) and racialization (White or non-White) status based on name, internet picture, pronouns used, bios available, and gender listed on their profile. ResultsWe identified 31 AUA and 20 EAU guidelines for inclusion. Median panel size was 19 (interquartile range [IQR]: 17; 21) with 12 (IQR: 10; 14) voting members. The average composition of voting panels was predominantly male (81.8%) and White (86.8%). Eleven guideline panels (21.6%) did not include any women, and nine (17.6%) panels had no representation of individuals from non-White groups. While gender distribution was similar among guidelines of the two organizations, the AUA included more voting members from non-White groups (14.3% versus 8.0%; p=0.010). Analysis of the AUA panel composition over time revealed stable proportions of female and non-White individuals. ConclusionBoth AUA and EAU guidelines exhibit insufficient representation of females and non-White individuals, with no evident improvement observed over time. Implementing more transparent processes that advocate for diverse panel representation may enhance the incorporation of stakeholder values and preferences, thereby improving the dissemination and adoption of guidelines.

Utilization of theories in talent development: mapping the field of HRD

Purpose The process of talent development (TD) is one of the current trends in HRM and human resource development (HRD). Although scientific literature addressing the topic emphasizes that through development of talents, organizations can increase their productivity, performance and competitiveness, little is known so far concerning the development of this research field as a whole and particularly concerning theories prevailing in the area. While research into the field has been ongoing for two decades, the area has not yet been systematized based on key theories used as starting points for the research. The purpose of this paper is to focus on which theories in HRD are used in TD. Design/methodology/approach Concerning the topicality of TD, the present article provides a systematic review of literature summarizing current theories in TD based on the currently used typology of theories in HRD, adding the fourth pillar to the existing three, i.e. theories concerning adult learning and education, to increase the stability of the typology. Findings The paper argues that the area of TD prevalently uses sociological, psychological and ethical theories, which may be attributed to trends in HRD. The insufficient representation of theories of learning in TD, particularly in view of the fact that adult learning and development is the essence of TD, is an important finding. This finding is particularly important for science concerning adult learning and education. Originality/value The benefit of the presented analysis lies in a systematization of the individual theories and a comprehensive overview of the current theoretical framework of TD, as well as suggestions for future research making use of adult learning and education theories.

A self-supervised leak detection method for natural gas gathering pipelines considering unlabeled multi-class non-leak data

Detecting leaks in natural gas gathering pipelines is paramount for the safe and reliable operation of the gas and oil industry. Due to the lack of leak data and the changes in leak features, semi-supervised leak detection methods that use normal data for health model learning have attracted much attention. However, these approaches usually consider one-class normal samples as health data, which may fail to fit the reality of unlabeled multi-class non-leak data under variable operating conditions. In addition, existing semi-supervised methods often suffer from insufficient representation learning as they employ step-by-step training or rely on the low-level reconstruction of autoencoders. To address the above two key challenges, this paper proposes a novel end-to-end self-supervised leak detection method, self-supervised multi-sphere support vector data description. Specifically, it utilizes the presented multi-sphere support vector data description to model unlabeled multi-class non-leak data and the introduced self-supervised learning strategy to boost the representation learning of the end-to-end semi-supervised model. Moreover, the categories of unlabeled multi-class non-leak data are learned in an unsupervised way through alternating feature clustering and pseudo-label-based classification. A robust leak score calculation method is also designed to improve the performance of the proposed method. Finally, the experimental results on the field data collected from pipelines demonstrate the effectiveness of the proposed method.

HGCLAMIR: Hypergraph contrastive learning with attention mechanism and integrated multi-view representation for predicting miRNA-disease associations.

Existing studies have shown that the abnormal expression of microRNAs (miRNAs) usually leads to the occurrence and development of human diseases. Identifying disease-related miRNAs contributes to studying the pathogenesis of diseases at the molecular level. As traditional biological experiments are time-consuming and expensive, computational methods have been used as an effective complement to infer the potential associations between miRNAs and diseases. However, most of the existing computational methods still face three main challenges: (i) learning of high-order relations; (ii) insufficient representation learning ability; (iii) importance learning and integration of multi-view embedding representation. To this end, we developed a HyperGraph Contrastive Learning with view-aware Attention Mechanism and Integrated multi-view Representation (HGCLAMIR) model to discover potential miRNA-disease associations. First, hypergraph convolutional network (HGCN) was utilized to capture high-order complex relations from hypergraphs related to miRNAs and diseases. Then, we combined HGCN with contrastive learning to improve and enhance the embedded representation learning ability of HGCN. Moreover, we introduced view-aware attention mechanism to adaptively weight the embedded representations of different views, thereby obtaining the importance of multi-view latent representations. Next, we innovatively proposed integrated representation learning to integrate the embedded representation information of multiple views for obtaining more reasonable embedding information. Finally, the integrated representation information was fed into a neural network-based matrix completion method to perform miRNA-disease association prediction. Experimental results on the cross-validation set and independent test set indicated that HGCLAMIR can achieve better prediction performance than other baseline models. Furthermore, the results of case studies and enrichment analysis further demonstrated the accuracy of HGCLAMIR and unconfirmed potential associations had biological significance.

IGFT-MHCNN: An intelligent diagnostic model for motor compound faults based decoupling and denoising of multi-source vibration signals

In view of the insufficient representation of single source signals for multi-point compound fault and the nonlinear strong coupling of vibration signals in motor transmission system, the inverse graph Fourier transform and improved multi-head convolutional neural network (IGFT-MHCNN) diagnostic model–based decoupling and denoising of multi-source vibration signals is proposed. The MHDCNN is constructed by improved multi-head convolution network and multi-label decoupling classifier, in which they extract multi-source signal features and decouple compound fault label information, respectively. Due to strong noise in compound fault and mapping capability of graphic signal processing method for complex data, a signal reconstruction method based on IGFT is established to remove residual noise from multi-source signals and enhance the main feature components. Two experimental cases show that the constructed model can effectively reduce vibration noise and achieve multi-label decoupling and identification of motor compound faults with strong coupling.

Toward Equitable Precision Oncology: Monitoring Racial and Ethnic Inclusion in Genomics and Clinical Trials.

Ethnic diversity in cancer research is crucial as race/ethnicity influences cancer incidence, survival, drug response, molecular pathways, and epigenetic phenomena. In 2018, we began a project to examine racial/ethnic diversity in cancer research, with a commitment to review these disparities every 4 years. This report is our second assessment, detailing the present state of racial/ethnic diversity in cancer genomics and clinical trials. To study racial/ethnic inclusion in cancer genomics, we extracted ethnic records from all data sets available at cBioPortal (n = 125,128 patients) and cancer-related genome-wide association studies (n = 28,011,282 patients) between 2018 and 2022. Concerning clinical trials, we selected studies related to breast cancer (n = 125,518 patients, 181 studies), lung cancer (n = 34,329 patients, 119 studies), and colorectal cancer (n = 40,808 patients, 105 studies). In cancer genomics (N = 28,136,410), 3% of individuals lack racial/ethnic registries; tumor samples were collected predominantly from White patients (89.14%), followed by Asian (7%), African American (0.55%), and Hispanic (0.21%) patients and other populations (0.1%). In clinical trials (N = 200,655), data on race/ethnicity are missing for 60.14% of the participants; for individuals whose race/ethnicity was recorded, most were characterized as White (28.33%), followed by Asian (7.64%), African (1.79), other ethnicities (1.37), and Hispanic (0.73). Racial/ethnic representation significantly deviates from global ethnic proportions (P ≤ .001) across all data sets, with White patients outnumbering other ethnic groups by a factor of approximately 4-6. Our second update on racial/ethnic representation in cancer research highlights the persistent overrepresentation of White populations in cancer genomics and a notable absence of racial/ethnic information across clinical trials. To ensure more equitable and effective precision oncology, future efforts should address the reasons behind the insufficient representation of ethnically diverse populations in cancer research.