Search

Molecule inverse folding has been a long-standing challenge in chemistry and biology, with the potential to revolutionize drug discovery and material science. Despite specified models have been proposed for different small- or macro-molecules, few have attempted to unify the learning process, resulting in redundant efforts. Complementary to recent advancements in molecular structure prediction, such as RoseTTAFold All-Atom and AlphaFold3, we propose the unified model UniIF for the inverse folding of all molecules. We do such unification in two levels: 1) Data-Level: We propose a unified block graph data form for all molecules, including the local frame building and geometric feature initialization. 2) Model-Level: We introduce a geometric block attention network, comprising a geometric interaction, interactive attention and virtual long-term dependency modules, to capture the 3D interactions of all molecules. Through comprehensive evaluations across various tasks such as protein design, RNA design, and material design, we demonstrate that our proposed method surpasses state-of-the-art methods on all tasks. UniIF offers a versatile and effective solution for general molecule inverse folding.

Redundancy-based automated program repair (APR), which generates patches by referencing existing source code, has gained much attention since they are effective in repairing real-world bugs with good interpretability. However, since existing approaches either demand the existence of multi-line similar code or randomly reference existing code, they can only repair a small number of bugs with many incorrect patches, hindering their wide application in practice. In this work, we aim to improve the effectiveness of redundancy-based APR by exploring more effective source code reuse methods for improving the number of correct patches and reducing incorrect patches. Specifically, we have proposed a new repair technique named Repatt, which incorporates a two-level pattern mining process for guiding effective patch generation (i.e., token and expression levels). We have conducted an extensive experiment on the widely-used Defects4J benchmark and compared Repatt with eight state-of-the-art APR approaches. The results show that our approach complements existing approaches by repairing {15} unique bugs compared with the latest deep learning-based methods and {19} unique bugs compared with traditional repair methods when providing the perfect fault localization. In addition, when the perfect fault localization is unknown in real practice, Repatt significantly outperforms the baseline approaches by achieving much higher patch precision, i.e., {83.8\%}. Moreover, we further proposed an effective patch ranking strategy for combining the strength of Repatt and the baseline methods. The result shows that it repairs 124 bugs when only considering the Top-1 patches and improves the best-performing repair method by repairing 39 more bugs. The results demonstrate the effectiveness of our approach for practical use.

Recent advances in bottleneck studies have highlighted that different architectural adjustments at the exit may reduce the probability of clogging at the exit thereby enhancing the outflow of the individuals. However, those studies are mostly limited to the controlled experiments with non-human organisms or predictions models. Complementary data with human subjects to test the model's limited in literature. This study aims to examine the effect of different geometrical layouts at the exit towards the pedestrian flow via controlled laboratory experiments with human participants. The experimental setups involve pedestrian flow through 14 different geometrical configurations that include different exit locations and obstacles near exit under normal and slow running conditions. It was found that corner exit performed better than middle exit under same obstacle condition. Further, it was observed that the effectiveness of obstacle is sensitive to its size and distance from the exit. Thus, with careful architectural adjustment within a standard escape area, a substantial increase in outflow under normal and slow running conditions could be achieved. However, it was also observed that placing the obstacle too close to the exit can reduce outflow under both normal and slow running conditions. Moreover, we could not observe "faster-is-slower" effect under slow running condition and instead noticed "faster-is-faster" effect. In addition, the power law fitted headway distribution demonstrated that any architectural configurations that enhanced the outflow have higher exponent value compared to the other configuration that negates the outflow., Comment: 26 pages, 5 figures, 3 tables. Submitted to Physica A in 2016, now its under 3rd round review but lasted more than 1 year