In computational neuroscience, models representing single-neuron in-vivo activity have become essential for understanding the functional identities of individual neurons. These models, such as implicit representation methods based on Transformer architectures, contrastive learning frameworks, and variational autoencoders, aim to capture the invariant and intrinsic computational features of single neurons. The learned single-neuron computational role representations should remain invariant across changing environment and are affected by their molecular expression and location. Thus, the representations allow for in vivo prediction of the molecular cell types and anatomical locations of single neurons, facilitating advanced closed-loop experimental designs. However, current models face the problem of limited generalizability. This is due to batch effects caused by differences in experimental design, animal subjects, and recording platforms. These confounding factors often lead to overfitting, reducing the robustness and practical utility of the models across various experimental scenarios. Previous studies have not rigorously evaluated how well the models generalize to new animals or stimulus conditions, creating a significant gap in the field. To solve this issue, we present a comprehensive experimental protocol that explicitly evaluates model performance on unseen animals and stimulus types. Additionally, we propose a model-agnostic adversarial training strategy. In this strategy, a discriminator network is used to eliminate batch-related information from the learned representations. The adversarial framework forces the representation model to focus on the intrinsic properties of neurons, thereby enhancing generalizability. Our approach is compatible with all major single-neuron representation models and significantly improves model robustness. This work emphasizes the importance of generalization in single-neuron representation models and offers an effective solution, paving the way for the practical application of computational models in vivo. It also shows potential for building unified atlases based on single-neuron in vivo activity.

Methylated RNA m6A immunoprecipitation sequencing (m6A-Seq) is a powerful technique for investigating transcriptome-wide m6A modification. However, most of the existing m6A-Seq protocols rely on reference genomes, limiting their use in species lacking sequenced genomes. Here, we introduce mlPEA, a user-friendly, multi-functional platform specifically tailored to the streamlined processing of m6A-Seq data in a reference genome-free manner. mlPEA provides a comprehensive collection of functions required for performing transcriptome-wide m6A identification and analysis, where the reference-de novo assembled transcriptome-is built solely using m6A-Seq data. By taking advantage of machine learning (ML) algorithms, mlPEA enhances m6A-Seq data analysis by constructing robust computational models for identifying high-quality transcripts and high-confidence m6A-modified regions. These functions and ML models have been integrated into a web-based Galaxy framework. This ensures that mlPEA has powerful data interaction and visualization capabilities, with flexibility, traceability, and reproducibility throughout the analytical process. mlPEA also has high compatibility and portability as it employs advanced packaging technology, dramatically simplifying its large-scale application in various species. Validated through case studies of Arabidopsis, maize, and wheat, mlPEA has demonstrated its utility and robustness regarding reference genome-free m6A-Seq data analysis for plants of various genomic complexities. mlPEA is freely available via GitHub: https://github.com/cma2015/mlPEA.

Code smells are structures in the source code that suggest the possibility of refactorings. Consequently, developers may identify refactoring opportunities by detecting code smells. However, manual identification of code smells is challenging and tedious. To this end, a number of approaches have been proposed to identify code smells automatically or semi-automatically. Most of such approaches rely on manually designed heuristics to map manually selected source code metrics into predictions. However, it is challenging to manually select the best features. It is also difficult to manually construct the optimal heuristics. To this end, in this paper we propose a deep learning based novel approach to detecting code smells. The key insight is that deep neural networks and advanced deep learning techniques could automatically select features of source code for code smell detection, and could automatically build the complex mapping between such features and predictions. A big challenge for deep learning based smell detection is that deep learning often requires a large number of labeled training data (to tune a large number of parameters within the employed deep neural network) whereas existing datasets for code smell detection are rather small. To this end, we propose an automatic approach to generating labeled training data for the neural network based classifier, which does not require any human intervention. As an initial try, we apply the proposed approach to four common and well-known code smells, i.e., feature envy, long method, large class, and misplaced class. Evaluation results on open-source applications suggest that the proposed approach significantly improves the state-of-the-art.