Combinatorial CRISPR screening enables large-scale identification of synergistic gene pairs for combination therapies, but exhaustive experimentation is infeasible. We introduce NAIAD, an active learning framework that efficiently discovers optimal gene pairs by leveraging single-gene perturbation effects and adaptive gene embeddings that scale with the training data size, mitigating overfitting in small-sample learning while capturing complex gene interactions as more data is collected. Evaluated on four CRISPR datasets with over 350,000 interactions, NAIAD trained on small datasets outperforms existing models by up to 40%. Its recommendation system prioritizes gene pairs with maximum predicted effects, accelerating discovery with fewer experiments. We also extend NAIAD to optimal drug combination identification among 2,000 candidates. Overall, NAIAD enhances combinatorial perturbation design and drives advances in genomics research and therapeutic development in combination therapy. Our code is publicly available at: https://github.com/NeptuneBio/NAIAD

Extrinsic calibration between LiDAR and camera has become an indispensable task across diverse domains, including autonomous vehicles, robotics, and surveillance systems. However, existing methods suffer from limited precision due to the inaccurate and insufficient detected features caused by the sparsity of point-clouds and the inherent ranging errors of LiDAR. In this paper, we propose a multi-dimensional geometric feature-based calibration method between LiDAR and camera. First, a 3D structured calibration target is proposed with multi-normal surfaces, edges in different directions, and distinctive corner features. Secondly, a point-plane and angle error-based point-cloud feature detection method is designed to establish 3D-2D feature point pairs with image features. Finally, a Perspective-n-Point (PnP) problem is solved to estimate the extrinsic parameters. The experimental results show that the proposed method reduces Mean Reprojection Error (MRE) by 0.05 pixels and achieves a 70% reduction in Normalized Reprojection Error (NRE) compared with state-of-the-art (SOTA) methods under the conditions of smaller training size, larger test size, and more repeat times.

The fast charging problem of lithium-ion batteries with minimum charging time while limiting battery degradation is receiving increasing attention and is a critical challenge to battery community. Difficulties in this optimization lie in that: 1) the parameter space of charging strategies is high dimensional, while the budget of the experimental cost is often limited; 2) the evaluation of charging strategies' performance is expensive; and 3) the degradation process of the battery is strongly nonlinear, and multiple degradation mechanisms occur simultaneously leading to difficulties for establishing accurate first-principle models. Current methods to address these difficulties are mainly electrochemical-model-based optimization and grid search, which are rarely adaptive to battery degradation and/or are of low sample efficiency. In this article, we propose an adaptive model-based reinforcement learning (RL) approach for fast-charging optimization while limiting battery degradation, in which a probabilistic surrogate model of differential Gaussian process (GP) is adopted to adaptively describe the degradation of cells. The effectiveness of the proposed approach is demonstrated on PETLION, a high-performance porous-electrode-theory-based battery simulator. The results show that 1) compared with the model-free RL method, the proposed adaptive GP-based RL approach possesses superior charging performance and high sample efficiency and 2) the proposed method performs well in the handling of degradation constraints on voltage and temperature for dynamically aging batteries with its adaptability to the variations of environment.

Motivation: Shotgun DNA sequencing provides sensitive detection of all 182 HPV types in tissue and body fluid. However, existing computational methods either produce false positives misidentifying HPV types due to shared sequences among HPV, human and prokaryotes, or produce false negative since they identify HPV by assembled contigs requiring large abundant of HPV reads. Results: We designed HPViewer with two custom HPV reference databases masking simple repeats and homology sequences respectively and one homology distance matrix to hybridize these two databases. It directly identified HPV from short DNA reads rather than assembled contigs. Using 100 100 simulated samples, we revealed that HPViewer was robust for samples containing either high or low number of HPV reads. Using 12 shotgun sequencing samples from respiratory papillomatosis, HPViewer was equal to VirusTAP, and Vipie and better than HPVDetector with the respect to specificity and was the most sensitive method in the detection of HPV types 6 and 11. We demonstrated that contigs-based approaches had disadvantages of detection of HPV. In 1573 sets of metagenomic data from 18 human body sites, HPViewer identified 104 types of HPV in a body-site associated pattern and 89 types of HPV co-occurring in one sample with other types of HPV. We demonstrated HPViewer was sensitive and specific for HPV detection in metagenomic data. Availability and implementation: HPViewer can be accessed at https://github.com/yuhanH/HPViewer/. Supplementary information: Supplementary data are available at Bioinformatics online.