The recent interest in peptides incorporating non-canonical amino acids has surged within the scientific community, driven by their enhanced stability and resistance to proteolytic degradation. These so-called non-canonical peptides offer significant potential for modifying biological, pharmacological, and physiochemical characteristics in both native and synthetic contexts. Despite their advantages, there remains a notable gap in the availability of an efficient pre-trained model capable of effectively capturing feature representations from such intricate peptide sequences. This study herein introduces PepLand, a novel pre-training framework designed for the comprehensive representation and analysis of peptides, encompassing both canonical and non-canonical amino acids. PepLand leverages a general-purpose multi-view heterogeneous graph neural network to unveil the subtle structural representations of peptides. Our empirical evaluations demonstrate PepLand's proficiency in a range of peptide property prediction tasks, including cell penetrability, solubility, and protein-peptide binding affinity. These rigorous assessments affirm PepLand's superior capability in discerning critical representations of peptides with both canonical and non-canonical amino acids, and provide a robust foundation for transformative advances in peptide-focused pharmaceutical research. We have made the entire source code and datasets available at http://www.healthinformaticslab.org/supp/resources.php or https://github.com/zhangruochi/PepLand.

MOTIVATION: Molecular pre-training has emerged as a foundational approach in computational drug discovery, enabling the extraction of expressive molecular representations from large-scale unlabeled datasets. However, existing methods largely focus on topological or structural features, often neglecting critical physicochemical attributes embedded in molecular systems. RESULT: We present MolPrompt, a knowledge-enhanced multimodal pre-training framework that integrates molecular graphs and textual descriptions via contrastive learning. MolPrompt employs a dual-encoder architecture consisting of Graphormer for graph encoding and BERT for textual encoding, and introduces knowledge prompts, semantic embeddings constructed by converting molecular descriptors into natural language, into the graph encoder to guide structure-aware representation learning. Across tasks including molecular property prediction, toxicity estimation, cross-modal retrieval, and anticancer inhibitor identification, MolPrompt consistently surpasses state-of-the-art baselines. These results highlight the value of embedding domain knowledge into structural learning to improve the depth, interpretability, and transferability of molecular representations. AVAILABILITY AND IMPLEMENTATION: The source code of MolPrompt is available at: https://github.com/catly/MolPrompt.

Center-based 3D object detection has underperformed recently compared to advanced techniques. We experimentally find that the root lies in two weaknesses of the basic sample mechanism: (1) Unreasonable assignment that close-range and high-frequency objects dominate the network optimization since samples are equally assigned to each object. (2) Ambiguous encoding that samples exhibit suboptimal object discrimination ability, as the encoding process is restricted to a limited receptive field. To realize a reasonable assignment, Dynamic Multi-Quality Assignment (DMQA) is proposed, which dynamically assigns and supervises samples through fine-grained control. Concretely, initial samples are defined based on prior attributes (category and distance) per object, and dynamically adjusted upon the learning effect (classification and localization confidence). Besides, multi-scale auxiliary losses are introduced, ensuring precise sample learning. As for ambiguous encoding, Interactive Enhancement (IE) is introduced to improve sample representation through cross-task and cross-sample interaction. Cross-task interaction first aggregates neighborhood context from another task map. Parallel attention further performs cross-sample interaction on both local and global levels. Based on DMQA and IE, we propose a novel 3D detector named Sample Enhanced 3D Object Detection (SampleDet3D). Comprehensive experiments demonstrate that SampleDet3D effectively enhances center-based detection and achieves state-of-the-art performance on both Waymo and ONCE datasets.

MOTIVATION: Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem is often hindered by the lack of annotated data and imbalanced class distributions, which pose significant challenges in developing accurate and robust predictive models. RESULTS: This study tackles these issues by employing pretrained molecular models within a few-shot learning framework. A novel dynamic contrastive loss function is utilized to further improve model performance in the situation of class imbalance. The proposed MolFeSCue framework not only facilitates rapid generalization from minimal samples, but also employs a contrastive loss function to extract meaningful molecular representations from imbalanced datasets. Extensive evaluations and comparisons of MolFeSCue and state-of-the-art algorithms have been conducted on multiple benchmark datasets, and the experimental data demonstrate our algorithm's effectiveness in molecular representations and its broad applicability across various pretrained models. Our findings underscore MolFeSCues potential to accelerate advancements in drug discovery. AVAILABILITY AND IMPLEMENTATION: We have made all the source code utilized in this study publicly accessible via GitHub at http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue. The code (MolFeSCue-v1-00) is also available as the supplementary file of this paper.

Early identification of safe and efficacious disease targets is crucial to alleviating the tremendous cost of drug discovery projects. However, existing experimental methods for identifying new targets are generally labor-intensive and failure-prone. On the other hand, computational approaches, especially machine learning-based frameworks, have shown remarkable application potential in drug discovery. In this work, we propose Progeni, a novel machine learning-based framework for target identification. In addition to fully exploiting the known heterogeneous biological networks from various sources, Progeni integrates literature evidence about the relations between biological entities to construct a probabilistic knowledge graph. Graph neural networks are then employed in Progeni to learn the feature embeddings of biological entities to facilitate the identification of biologically relevant target candidates. A comprehensive evaluation of Progeni demonstrated its superior predictive power over the baseline methods on the target identification task. In addition, our extensive tests showed that Progeni exhibited high robustness to the negative effect of exposure bias, a common phenomenon in recommendation systems, and effectively identified new targets that can be strongly supported by the literature. Moreover, our wet lab experiments successfully validated the biological significance of the top target candidates predicted by Progeni for melanoma and colorectal cancer. All these results suggested that Progeni can identify biologically effective targets and thus provide a powerful and useful tool for advancing the drug discovery process.

One-stage 3D object detection, known for its simplicity and high-speed inference, is attracting increasing attention in autonomous driving scenarios. However, current one-stage detectors tend to perform sub-optimally compared to two-stage competitors. Our experimental findings suggest that one-stage detectors underperform due to the underutilization of spatial information in feature embedding and classification. Concretely, the spatial context is severely lost during feature propagation, inducing distorted spatial awareness. On the other hand, category recognition relies on the full utilization of spatial information, which is neglected by current detectors. This inadequate spatial awareness of the classification branch can exacerbate misclassification. To address these issues, we propose Spatial-aware Learning in Feature Embedding and Classification for One-stage 3D Object Detection (SLDet). Specifically, to restore the distorted spatial awareness, Category-wise Spatial Augmentation (CSA) is proposed to adaptively bring the network with pre-encoding multi-scale spatial contexts. As for misclassification, Spatial Guiding Classification (SGC) is introduced to guide the classification using explicit scale information. It employs the natural scale divergences among categories to rectify misclassification. Comprehensive experiments demonstrate that SLDet efficiently utilizes spatial information and achieves newly state-of-the-art performance on both the Waymo Open Dataset and the ONCE Dataset. Furthermore, additional experiments demonstrate the excellent generalization capacity of SLDet.

Modern detectors commonly employ classification scores to reflect the localization quality of detection results. However, there exists an inconsistency between them, misguiding the selection of high-quality predictions and providing unreliable results for downstream applications. In this paper, we find that the root of this confidence inconsistency lies in the inaccurate IoU estimation and the spatial misalignment of the learned features between the classification and localization tasks. Therefore, a Confidence-Consistent Detector (CCDet) which includes the Distribution-based IoU Prediction (DIP) and Consistency-aware label assignment (CLA), is proposed. DIP provides more stable and accurate IoU estimation by learning the probability distribution over the IoU range and employing the expectation as the predicted IoU. CLA adopts both the prediction performance and consistency degree of samples as assignment metrics to select positives, which guides the classification and localization tasks to promote similar feature distribution. Comprehensive experiments demonstrate that CCDet can effectively mitigate the confidence inconsistency between classification and localization, and achieve stable improvement across different baselines. On the test-dev set of MS COCO, CCDet acquires a single-model single-scale AP of 50.1%, surpassing most of the existing object detectors.

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection ambiguity that selected pseudo labels are less accurate, since classification scores cannot properly represent the localization quality. (2) Assignment ambiguity that samples are matched with improper labels in pseudo-label assignment, as the strategy is misguided by missed objects and inaccurate pseudo boxes. To tackle these problems, we propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Specifically, to alleviate the selection ambiguity, Joint-Confidence Estimation (JCE) is proposed to jointly quantifies the classification and localization quality of pseudo labels. As for the assignment ambiguity, Task-Separation Assignment (TSA) is introduced to assign labels based on pixel-level predictions rather than unreliable pseudo boxes. It employs a ‘divide-and-conquer’ strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity. Comprehensive experiments demonstrate that ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC. Codes can be found at https://github.com/PaddlePaddle/PaddleDetection.

Accurately detecting multi-class objects in a single pass is critical but challenging for real-world autonomous driving scenarios. Several single-class anchor-based methods have recently achieved the state-of-the-art performance in the car category, but when extending to multi-class detection tasks, their performance on small objects (i.e., pedestrians and cyclists) is limited. We find that the core problem that causes this phenomenon lies in the unbalanced sample quality and the classification objective. To address this problem, we proposed a single-model multi-class 3D object detector with balanced sample assignment and objective, named BSAODet. Specifically, the quality-balanced sample assignment (QBSA) is introduced to dynamically collect stable high-quality samples for each class according to the predicted sample performance and geometric constraints. In conjunction with the QBSA, the class-balanced classification objective (CBCO) performs instance-wise label normalization and weighting on positive samples, preventing the model from biasing toward objects with more samples. Extensive experiments on the popular KITTI dataset, the latest large-scale ONCE dataset, and the challenging Waymo Open Dataset show that our method steadily improves the performance of current state-of-the-art detectors by 2–7 mAP in pedestrians and cyclists while maintaining competitiveness in cars. Moreover, our best model achieves 66.31 mAP on three classes, outperforming all published LiDAR-only detectors on the KITTI benchmark.