Target selection is crucial in pharmaceutical drug discovery, directly influencing clinical trial success. Despite its importance, drug development remains resource-intensive, often taking over a decade with significant financial costs. High failure rates highlight the need for better early-stage target selection. We present GATher, a graph attention network designed to predict therapeutic gene-disease links by integrating data from diverse biomedical sources into a graph with over 4.4 million edges. GATher incorporates GATv3, a novel graph attention convolution layer, and GATv3HeteroConv, which aggregates transformations for each edge type, enhancing its ability to manage complex interactions within this extensive dataset. Utilizing hard negative sampling and multi-task pre-training, GATher addresses topological imbalances and improves specificity. Trained on data up to 2018 and evaluated through 2024, our results show GATher predicts clinical trial outcomes with a ROC AUC of 0.69 for unmet efficacy failures and 0.79 for positive efficacy. Feature attribution methods, using Captum, highlight key nodes and relationships, enhancing model interpretability. By 2024, GATher improved precision in prioritizing the top 200 clinical trial targets to 14.1%, an absolute increase of over 3.5% compared to other methods. GATher outperforms existing models like GAT, GATv2, and HGT in predicting clinical trial outcomes, demonstrating its potential in enhancing target validation and predicting clinical efficacy and safety.
Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide, highlighting the urgent need for advanced therapeutic strategies. Nanoparticle-based drug delivery systems have emerged as a promising approach to improve the specificity and efficacy of anticancer treatments. This review examines three cutting-edge mesoporous silica nanoparticle (MSN)-based drug delivery to introduce novel CRC therapy, each utilizing unique functionalization strategies for targeted drug release. The first system, hyaluronidase-responsive MSN-HA/DOX, employs biotin-modified hyaluronic acid to facilitate dual-stimulus drug release in the tumor microenvironment, exhibiting enhanced in vivo tumor inhibition. The DOX/SLN-PEG-Biotin utilizes polyethylene glycol and biotin to improve drug stability and target biotin-overexpressing CRC cells, demonstrating superior anti-cancer efficacy in vitro and in vivo. Lastly, galactosylated chitosan-functionalized MSNs enable targeted delivery through asialoglycoprotein receptors, providing controlled drug release and strong therapeutic potential. Collectively, these systems highlight the advancements in nanoparticle functionalization for CRC treatment, offering a pathway to overcome the limitations of conventional chemotherapy. Further research is required to translate these innovations into clinical practice, ensuring safety and scalability.
Study Objectives: To evaluate the agreement between the millimeter-wave radar-based device and polysomnography (PSG) in diagnosis of obstructive sleep apnea (OSA) and classification of sleep stage in children. Methods: 281 children, aged 1 to 18 years, who underwent sleep monitoring between September and November 2023 at the Sleep Center of Beijing Children's Hospital, Capital Medical University, were recruited in the study. All enrolled children underwent sleep monitoring by PSG and the millimeter-wave radar-based device, QSA600, simultaneously. QSA600 recordings were automatically analyzed using a deep learning model meanwhile the PSG data was manually scored. Results: The Obstructive Apnea-Hypopnea Index (OAHI) obtained from QSA600 and PSG demonstrates a high level of agreement with an intraclass correlation coefficient of 0.945 (95% CI: 0.93 to 0.96). Bland-Altman analysis indicates that the mean difference of OAHI between QSA600 and PSG is -0.10 events/h (95% CI: -11.15 to 10.96). The deep learning model evaluated through cross-validation showed good sensitivity (81.8%, 84.3% and 89.7%) and specificity (90.5%, 95.3% and 97.1%) values for diagnosing children with OAHI>1, OAHI>5 and OAHI>10. The area under the receiver operating characteristic curve is 0.923, 0.955 and 0.988, respectively. For sleep stage classification, the model achieved Kappa coefficients of 0.854, 0.781, and 0.734, with corresponding overall accuracies of 95.0%, 84.8%, and 79.7% for Wake-sleep classification, Wake-REM-Light-Deep classification, and Wake-REM-N1-N2 N3 classification, respectively. Conclusions: QSA600 has demonstrated high agreement with PSG in diagnosing OSA and performing sleep staging in children. The device is portable, low-load and suitable for follow up and long-term pediatric sleep assessment.
Antibody-drug conjugates (ADCs) have emerged as a promising class of targeted cancer therapeutics, but the design and optimization of their cytotoxic payloads remain challenging. This study introduces DumplingGNN, a novel hybrid Graph Neural Network architecture specifically designed for predicting ADC payload activity based on chemical structure. By integrating Message Passing Neural Networks (MPNN), Graph Attention Networks (GAT), and GraphSAGE layers, DumplingGNN effectively captures multi-scale molecular features and leverages both 2D topological and 3D structural information. We evaluate DumplingGNN on a comprehensive ADC payload dataset focusing on DNA Topoisomerase I inhibitors, as well as on multiple public benchmarks from MoleculeNet. DumplingGNN achieves state-of-the-art performance across several datasets, including BBBP (96.4\% ROC-AUC), ToxCast (78.2\% ROC-AUC), and PCBA (88.87\% ROC-AUC). On our specialized ADC payload dataset, it demonstrates exceptional accuracy (91.48\%), sensitivity (95.08\%), and specificity (97.54\%). Ablation studies confirm the synergistic effects of the hybrid architecture and the critical role of 3D structural information in enhancing predictive accuracy. The model's strong interpretability, enabled by attention mechanisms, provides valuable insights into structure-activity relationships. DumplingGNN represents a significant advancement in molecular property prediction, with particular promise for accelerating the design and optimization of ADC payloads in targeted cancer therapy development.
Deep Neural Network (DNN) based classifiers have recently been used for the modulation classification of RF signals. These classifiers have shown impressive performance gains relative to conventional methods, however, they are vulnerable to imperceptible (low-power) adversarial attacks. Some of the prominent defense approaches include adversarial training (AT) and randomized smoothing (RS). While AT increases robustness in general, it fails to provide resilience against previously unseen adaptive attacks. Other approaches, such as Randomized Smoothing (RS), which injects noise into the input, address this shortcoming by providing provable certified guarantees against arbitrary attacks, however, they tend to sacrifice accuracy. In this paper, we study the problem of designing robust DNN-based modulation classifiers that can provide provable defense against arbitrary attacks without significantly sacrificing accuracy. To this end, we first analyze the spectral content of commonly studied attacks on modulation classifiers for the benchmark RadioML dataset. We observe that spectral signatures of un-perturbed RF signals are highly localized, whereas attack signals tend to be spread out in frequency. To exploit this spectral heterogeneity, we propose Filtered Randomized Smoothing (FRS), a novel defense which combines spectral filtering together with randomized smoothing. FRS can be viewed as a strengthening of RS by leveraging the specificity (spectral Heterogeneity) inherent to the modulation classification problem. In addition to providing an approach to compute the certified accuracy of FRS, we also provide a comprehensive set of simulations on the RadioML dataset to show the effectiveness of FRS and show that it significantly outperforms existing defenses including AT and RS in terms of accuracy on both attacked and benign signals.
In this work, we present MedImageInsight, an open-source medical imaging embedding model. MedImageInsight is trained on medical images with associated text and labels across a diverse collection of domains, including X-Ray, CT, MRI, dermoscopy, OCT, fundus photography, ultrasound, histopathology, and mammography. Rigorous evaluations demonstrate MedImageInsight's ability to achieve state-of-the-art (SOTA) or human expert level performance across classification, image-image search, and fine-tuning tasks. Specifically, on public datasets, MedImageInsight achieves SOTA in CT 3D medical image retrieval, as well as SOTA in disease classification and search for chest X-ray, dermatology, and OCT imaging. Furthermore, MedImageInsight achieves human expert performance in bone age estimation (on both public and partner data), as well as AUC above 0.9 in most other domains. When paired with a text decoder, MedImageInsight achieves near SOTA level single image report findings generation with less than 10\% the parameters of other models. Compared to fine-tuning GPT-4o with only MIMIC-CXR data for the same task, MedImageInsight outperforms in clinical metrics, but underperforms on lexical metrics where GPT-4o sets a new SOTA. Importantly for regulatory purposes, MedImageInsight can generate ROC curves, adjust sensitivity and specificity based on clinical need, and provide evidence-based decision support through image-image search (which can also enable retrieval augmented generation). In an independent clinical evaluation of image-image search in chest X-ray, MedImageInsight outperformed every other publicly available foundation model evaluated by large margins (over 6 points AUC), and significantly outperformed other models in terms of AI fairness (across age and gender). We hope releasing MedImageInsight will help enhance collective progress in medical imaging AI research and development.
Diabetic macular edema (DME) is a severe complication of diabetes, characterized by thickening of the central portion of the retina due to accumulation of fluid. DME is a significant and common cause of visual impairment in diabetic patients. Center-involved DME (ci-DME) is the highest risk form of disease because fluid extends close to the fovea which is responsible for sharp central vision. Earlier diagnosis or prediction of ci-DME may improve treatment outcomes. Here, we propose an ensemble method to predict ci-DME onset within a year, after using synthetic ultra-wide field color fundus photography (UWF-CFP) images provided by the DIAMOND Challenge during development. We adopted a variety of baseline state-of-the-art classification networks including ResNet, DenseNet, EfficientNet, and VGG with the aim of enhancing model robustness. The best performing models were Densenet-121, Resnet-152 and EfficientNet-b7, and these were assembled into a definitive predictive model. The final ensemble model demonstrates a strong performance with an Area Under Curve (AUC) of 0.7017, an F1 score of 0.6512, and an Expected Calibration Error (ECE) of 0.2057 when deployed on the synthetic test dataset. Results from our ensemble model were superior/comparable to previous recorded results in highly curated settings using conventional fundus photography/ultra-wide field fundus photography. Optimal sensitivity in previous studies (using humans or computers to diagnose) ranges from 67.3%-98%, specificity from 47.8%-80%. Therefore, our method can be used safely and effectively in a range of settings may facilitate earlier diagnosis, better treatment decisions, and improved prognostication in ci-DME.
Evaluating the creativity of large language models (LLMs) in story writing is difficult because LLM-generated stories could seemingly look creative but be very similar to some existing stories in their huge and proprietary training corpus. To overcome this challenge, we introduce a novel benchmark dataset with varying levels of prompt specificity: CS4 ($\mathbf{C}$omparing the $\mathbf{S}$kill of $\mathbf{C}$reating $\mathbf{S}$tories by $\mathbf{C}$ontrolling the $\mathbf{S}$ynthesized $\mathbf{C}$onstraint $\mathbf{S}$pecificity). By increasing the number of requirements/constraints in the prompt, we can increase the prompt specificity and hinder LLMs from retelling high-quality narratives in their training data. Consequently, CS4 empowers us to indirectly measure the LLMs' creativity without human annotations. Our experiments on LLaMA, Gemma, and Mistral not only highlight the creativity challenges LLMs face when dealing with highly specific prompts but also reveal that different LLMs perform very differently under different numbers of constraints and achieve different balances between the model's instruction-following ability and narrative coherence. Additionally, our experiments on OLMo suggest that Learning from Human Feedback (LHF) can help LLMs select better stories from their training data but has limited influence in boosting LLMs' ability to produce creative stories that are unseen in the training corpora. The benchmark is released at https://github.com/anirudhlakkaraju/cs4_benchmark.
With the rapid advancement of Natural Language Processing in recent years, numerous studies have shown that generic summaries generated by Large Language Models (LLMs) can sometimes surpass those annotated by experts, such as journalists, according to human evaluations. However, there is limited research on whether these generic summaries meet the individual needs of ordinary people. The biggest obstacle is the lack of human-annotated datasets from the general public. Existing work on personalized summarization often relies on pseudo datasets created from generic summarization datasets or controllable tasks that focus on specific named entities or other aspects, such as the length and specificity of generated summaries, collected from hypothetical tasks without the annotators' initiative. To bridge this gap, we propose a high-quality, personalized, manually annotated abstractive summarization dataset called PersonalSum. This dataset is the first to investigate whether the focus of public readers differs from the generic summaries generated by LLMs. It includes user profiles, personalized summaries accompanied by source sentences from given articles, and machine-generated generic summaries along with their sources. We investigate several personal signals - entities/topics, plot, and structure of articles - that may affect the generation of personalized summaries using LLMs in a few-shot in-context learning scenario. Our preliminary results and analysis indicate that entities/topics are merely one of the key factors that impact the diverse preferences of users, and personalized summarization remains a significant challenge for existing LLMs.
Query-by-example spoken term detection (QbE-STD) is typically constrained by transcribed data scarcity and language specificity. This paper introduces a novel, language-agnostic QbE-STD model leveraging image processing techniques and transformer architecture. By employing a pre-trained XLSR-53 network for feature extraction and a Hough transform for detection, our model effectively searches for user-defined spoken terms within any audio file. Experimental results across four languages demonstrate significant performance gains (19-54%) over a CNN-based baseline. While processing time is improved compared to DTW, accuracy remains inferior. Notably, our model offers the advantage of accurately counting query term repetitions within the target audio.
Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious features learned from noisy data hinder their generalizability. Supervised finetuning can introduce task specificity, but introduce data inefficiency. Prior studies indicate that (i) noisy neural circuitries coexist with generalizable ones within LLMs, and (ii) finetuning typically enhances (or suppresses) existing abilities without introducing newer ones. Building upon these, we propose TaRot, a novel method for task adaptation. TaRot intervenes in the neural circuitries using learnable rotation matrices that are optimized using Bayesian Optimization, on labelled samples in the order of standard few-shot prompting examples. Experiments on multiple classification and generation tasks using LLMs of varying sizes reveal the efficacy of TaRot, improving upon both zero- as well as few-shot performance, with average improvements (across models and tasks) of 23.81% and 11.15%, respectively. The source code is available at https://github.com/joykirat18/TaRot
Liquid biopsies (eg., blood draws) offer a less invasive and non-localized alternative to tissue biopsies for monitoring the progression of metastatic breast cancer (mBCa). Immunofluoresence (IF) microscopy is a tool to image and analyze millions of blood cells in a patient sample. By detecting and genetically sequencing circulating tumor cells (CTCs) in the blood, personalized treatment plans are achievable for various cancer subtypes. However, CTCs are rare (about 1 in 2M), making manual CTC detection very difficult. In addition, clinicians rely on quantitative cellular biomarkers to manually classify CTCs. This requires prior tasks of cell detection, segmentation and feature extraction. To assist clinicians, we have developed a fully automated machine learning-based production-level pipeline to efficiently detect, segment and classify CTCs in multi-channel IF images. We achieve over 99% sensitivity and 97% specificity on 9,533 cells from 15 mBCa patients. Our pipeline has been successfully deployed on real mBCa patients, reducing a patient average of 14M detected cells to only 335 CTC candidates for manual review.
People with disabilities (PwD) regularly encounter ableist hate and microaggressions online. These spaces are generally moderated by machine learning models, but little is known about how effectively AI models identify ableist speech and how well their judgments align with PwD. To investigate this, we curated a first-of-its-kind dataset of 200 social media comments targeted towards PwD, and prompted state-of-the art AI models (i.e., Toxicity Classifiers, LLMs) to score toxicity and ableism for each comment, and explain their reasoning. Then, we recruited 190 participants to similarly rate and explain the harm, and evaluate LLM explanations. Our mixed-methods analysis highlighted a major disconnect: AI underestimated toxicity compared to PwD ratings, while its ableism assessments were sporadic and varied. Although LLMs identified some biases, its explanations were flawed--they lacked nuance, made incorrect assumptions, and appeared judgmental instead of educational. Going forward, we discuss challenges and opportunities in designing moderation systems for ableism, and advocate for the involvement of intersectional disabled perspectives in AI.
In this work, we propose Erasure of Language Memory (ELM), an approach for concept-level unlearning built on the principle of matching the distribution defined by an introspective classifier. Our key insight is that effective unlearning should leverage the model's ability to evaluate its own knowledge, using the model itself as a classifier to identify and reduce the likelihood of generating content related to undesired concepts. ELM applies this framework to create targeted low-rank updates that reduce generation probabilities for concept-specific content while preserving the model's broader capabilities. We demonstrate ELM's efficacy on biosecurity, cybersecurity, and literary domain erasure tasks. Comparative analysis shows that ELM achieves superior performance across key metrics, including near-random scores on erased topic assessments, maintained coherence in text generation, preserved accuracy on unrelated benchmarks, and robustness under adversarial attacks. Our code, data, and trained models are available at https://elm.baulab.info
Bone marrow lesions (BMLs) are critical indicators of knee osteoarthritis (OA). Since they often appear as small, irregular structures with indistinguishable edges in knee magnetic resonance images (MRIs), effective detection of BMLs in MRI is vital for OA diagnosis and treatment. This paper proposes a semi-supervised local anomaly detection method using mask inpainting models for identification of BMLs in high-resolution knee MRI, effectively integrating a 3D femur bone segmentation model, a large mask inpainting model, and a series of post-processing techniques. The method was evaluated using MRIs at various resolutions from a subset of the public Osteoarthritis Initiative database. Dice score, Intersection over Union (IoU), and pixel-level sensitivity, specificity, and accuracy showed an advantage over the multiresolution knowledge distillation method-a state-of-the-art global anomaly detection method. Especially, segmentation performance is enhanced on higher-resolution images, achieving an over two times performance increase on the Dice score and the IoU score at a 448x448 resolution level. We also demonstrate that with increasing size of the BML region, both the Dice and IoU scores improve as the proportion of distinguishable boundary decreases. The identified BML masks can serve as markers for downstream tasks such as segmentation and classification. The proposed method has shown a potential in improving BML detection, laying a foundation for further advances in imaging-based OA research.
As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we propose an ID-induced prompt synthesis framework for evaluating LLMs to ensure the evaluation set can continually update and refine according to model abilities. Our data synthesis framework prioritizes both breadth and specificity. It can generate prompts that comprehensively evaluate the capabilities of LLMs while revealing meaningful performance differences between models, allowing for effective discrimination of their relative strengths and weaknesses across various tasks and domains. To produce high-quality data, we incorporate a self-correct mechanism into our generalization framework, and develop two models to predict prompt discrimination and difficulty score to facilitate our data synthesis framework, contributing valuable tools to evaluation data synthesis research. We apply our generated data to evaluate five SOTA models. Our data achieves an average score of 51.92, accompanied by a variance of 10.06. By contrast, previous works (i.e., SELF-INSTRUCT and WizardLM) obtain an average score exceeding 67, with a variance below 3.2. The results demonstrate that the data generated by our framework is more challenging and discriminative compared to previous works. We will release a dataset of over 3,000 carefully crafted prompts to facilitate evaluation research of LLMs.
Domain dependence and annotation subjectivity pose challenges for supervised keyword extraction. Based on the premises that second-order keyness patterns are existent at the community level and learnable from annotated keyword extraction datasets, this paper proposes a supervised ranking approach to keyword extraction that ranks keywords with keyness patterns consisting of independent features (such as sublanguage domain and term length) and three categories of dependent features -- heuristic features, specificity features, and representavity features. The approach uses two convolutional-neural-network based models to learn keyness patterns from keyword datasets and overcomes annotation subjectivity by training the two models with bootstrap sampling strategy. Experiments demonstrate that the approach not only achieves state-of-the-art performance on ten keyword datasets in general supervised keyword extraction with an average top-10-F-measure of 0.316 , but also robust cross-domain performance with an average top-10-F-measure of 0.346 on four datasets that are excluded in the training process. Such cross-domain robustness is attributed to the fact that community-level keyness patterns are limited in number and temperately independent of language domains, the distinction between independent features and dependent features, and the sampling training strategy that balances excess risk and lack of negative training data.
The precision of contouring target structures and organs-at-risk (OAR) in radiotherapy planning is crucial for ensuring treatment efficacy and patient safety. Recent advancements in deep learning (DL) have significantly improved OAR contouring performance, yet the reliability of these models, especially in the presence of out-of-distribution (OOD) scenarios, remains a concern in clinical settings. This application study explores the integration of epistemic uncertainty estimation within the OAR contouring workflow to enable OOD detection in clinically relevant scenarios, using specifically compiled data. Furthermore, we introduce an advanced statistical method for OOD detection to enhance the methodological framework of uncertainty estimation. Our empirical evaluation demonstrates that epistemic uncertainty estimation is effective in identifying instances where model predictions are unreliable and may require an expert review. Notably, our approach achieves an AUC-ROC of 0.95 for OOD detection, with a specificity of 0.95 and a sensitivity of 0.92 for implant cases, underscoring its efficacy. This study addresses significant gaps in the current research landscape, such as the lack of ground truth for uncertainty estimation and limited empirical evaluations. Additionally, it provides a clinically relevant application of epistemic uncertainty estimation in an FDA-approved and widely used clinical solution for OAR segmentation from Varian, a Siemens Healthineers company, highlighting its practical benefits.
The significant portion of diabetic patients was affected due to major blindness caused by Diabetic retinopathy (DR). For diabetic retinopathy, lesion segmentation, and detection the comprehensive examination is delved into the deep learning techniques application. The study conducted a systematic literature review using the PRISMA analysis and 62 articles has been investigated in the research. By including CNN-based models for DR grading, and feature fusion several deep-learning methodologies are explored during the study. For enhancing effectiveness in classification accuracy and robustness the data augmentation and ensemble learning strategies are scrutinized. By demonstrating the superior performance compared to individual models the efficacy of ensemble learning methods is investigated. The potential ensemble approaches in DR diagnosis are shown by the integration of multiple pre-trained networks with custom classifiers that yield high specificity. The diverse deep-learning techniques that are employed for detecting DR lesions are discussed within the diabetic retinopathy lesions segmentation and detection section. By emphasizing the requirement for continued research and integration into clinical practice deep learning shows promise for personalized healthcare and early detection of diabetics.
Current image retrieval systems often face domain specificity and generalization issues. This study aims to overcome these limitations by developing a computationally efficient training framework for a universal feature extractor that provides strong semantic image representations across various domains. To this end, we curated a multi-domain training dataset, called M4D-35k, which allows for resource-efficient training. Additionally, we conduct an extensive evaluation and comparison of various state-of-the-art visual-semantic foundation models and margin-based metric learning loss functions regarding their suitability for efficient universal feature extraction. Despite constrained computational resources, we achieve near state-of-the-art results on the Google Universal Image Embedding Challenge, with a mMP@5 of 0.721. This places our method at the second rank on the leaderboard, just 0.7 percentage points behind the best performing method. However, our model has 32% fewer overall parameters and 289 times fewer trainable parameters. Compared to methods with similar computational requirements, we outperform the previous state of the art by 3.3 percentage points. We release our code and M4D-35k training set annotations at https://github.com/morrisfl/UniFEx.