6 papers
Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
Xiang Zhang, Jiaqi Wei, Yuejin Yang +8
Chain-of-Thought (CoT) prompting has significantly advanced task-solving capabilities in natural language processing with large language models. Unlike standard prompting, CoT enco…
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Wanghan Xu, Yuhao Zhou, Yifan Zhou +104
Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific do…
Accurate de novo sequencing of the modified proteome with OmniNovo
Yuhan Chen, Shang Qu, Zhiqiang Gao +13
Post-translational modifications (PTMs) serve as a dynamic chemical language regulating protein function, yet current proteomic methods remain blind to a vast portion of the modifi…
Bidirectional Representations Augmented Autoregressive Biological Sequence Generation
Xiang Zhang, Jiaqi Wei, Zijie Qiu +5
Autoregressive (AR) models, common in sequence generation, are limited in many biological tasks such as de novo peptide sequencing and protein modeling by their unidirectional natu…
Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing
Xiang Zhang, Jiaqi Wei, Zijie Qiu +4
Peptide sequencing-the process of identifying amino acid sequences from mass spectrometry data-is a fundamental task in proteomics. Non-Autoregressive Transformers (NATs) have prov…
Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing
Zijie Qiu, Jiaqi Wei, Xiang Zhang +6
De novo peptide sequencing is a critical task in proteomics. However, the performance of current deep learning-based methods is limited by the inherent complexity of mass spectrome…