With the exponential growth of digital data, there is a pressing need for innovative storage media and techniques. DNA molecules, due to their stability, storage capacity, and density, offer a promising solution for information storage. However, DNA storage also faces numerous challenges, such as complex biochemical constraints and encoding efficiency. This paper presents Explorer, a high-efficiency DNA coding algorithm based on the De Bruijn graph, which leverages its capability to characterize local sequences. Explorer enables coding under various biochemical constraints, such as homopolymers, GC content, and undesired motifs. This paper also introduces Codeformer, a fast decoding algorithm based on the transformer architecture, to further enhance decoding efficiency. Numerical experiments indicate that, compared with other advanced algorithms, Explorer not only achieves stable encoding and decoding under various biochemical constraints but also increases the encoding efficiency and bit rate by ¿10%. Additionally, Codeformer demonstrates the ability to efficiently decode large quantities of DNA sequences. Under different parameter settings, its decoding efficiency exceeds that of traditional algorithms by more than two-fold. When Codeformer is combined with Reed-Solomon code, its decoding accuracy exceeds 99%, making it a good choice for high-speed decoding applications. These advancements are expected to contribute to the development of DNA-based data storage systems and the broader exploration of DNA as a novel information storage medium.

The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions.Existing benchmarks often focus on lexical generalization, the interpretation of novel lexical items in syntactic structures familiar from training.Structural generalization tasks, where a model needs to interpret syntactic structures that are themselves unfamiliar from training, are often underrepresented, resulting in overly optimistic perceptions of how well models can generalize.We introduce SLOG, a semantic parsing dataset that extends COGS (Kim and Linzen, 2020) with 17 structural generalization cases.In our experiments, the generalization accuracy of Transformer models, including pretrained ones, only reaches 40.6%, while a structure-aware parser only achieves 70.8%.These results are far from the near-perfect accuracy existing models achieve on COGS, demonstrating the role of SLOG in foregrounding the large discrepancy between models' lexical and structural generalization capacities.

Abstract Many studies have shown that transformers are able to predict subject-verb agreement, demonstrating their ability to uncover an abstract representation of the sentence in an unsupervised way. Recently, Li et al. (2021) found that transformers were also able to predict the object-past participle agreement in French, the modeling of which in formal grammar is fundamentally different from that of subject-verb agreement and relies on a movement and an anaphora resolution. To better understand transformers’ internal working, we propose to contrast how they handle these two kinds of agreement. Using probing and counterfactual analysis methods, our experiments on French agreements show that (i) the agreement task suffers from several confounders that partially question the conclusions drawn so far and (ii) transformers handle subject-verb and object-past participle agreements in a way that is consistent with their modeling in theoretical linguistics.

Recently, metabolic pathway design has attracted considerable attention and become an increasingly important area in metabolic engineering. Manual or computational methods have been introduced to retrieve the metabolic pathway. These methods model metabolic pathway design as a single-objective optimization problem with the weighted sum of a variety of criteria as the final score. While these methods have demonstrated promising results, the majority of current methods do not account for comparisons and competition among criteria. Here, we propose MooSeeker, a metabolic pathway design tool based on the multi-objective optimization algorithm that aims to trade off all the criteria optimally. The metabolic pathway design problem is characterized as a multi-objective optimization problem with three objectives including pathway length, thermodynamic feasibility and theoretical yield. In order to digitize the continuous metabolic pathway, MooSeeker develops the encoding strategy, BioCrossover and BioMutation operators to search for the candidate pathways. Finally, MooSeeker outputs the Pareto optimal solutions of the candidate metabolic pathways with three criterion values. The experiment results show that MooSeeker is capable of constructing the experimentally validated pathways and finding the higher-performance pathway than the single-objective-based methods.

We evaluate the ability of Bert embeddings to represent tense information, taking French and Chinese as a case study.In French, the tense information is expressed by verb morphology and can be captured by simple surface information.On the contrary, tense interpretation in Chinese is driven by abstract, lexical, syntactic and even pragmatic information.We show that while French tenses can easily be predicted from sentence representations, results drop sharply for Chinese, which suggests that Bert is more likely to memorize shallow patterns from the training data rather than uncover abstract properties.

Many recent works have demonstrated that unsupervised sentence representations of neural networks encode syntactic information by observing that neural language models are able to predict the agreement between a verb and its subject.We take a critical look at this line of research by showing that it is possible to achieve high accuracy on this agreement task with simple surface heuristics, indicating a possible flaw in our assessment of neural networks' syntactic ability.Our fine-grained analyses of results on the long-range French objectverb agreement show that contrary to LSTMs, Transformers are able to capture a non-trivial amount of grammatical structure.