More Like this

1. Acceleration in Low-Rank Tensor Completion

   https://doi.org/10.1137/1.9781611978520.4  

   Kang, Yifan; Zhang, Mengyuan; Liu, Kai (January 2025, Society for Industrial and Applied Mathematics)

   Generative AI is generating much enthusiasm on potentially advancing biological design in computational biology. In this paper we take a somewhat contrarian view, arguing that a broader and deeper understanding of existing biological sequences is essential before undertaking the design of novel ones. We draw attention, for instance, to current protein function prediction methods which currently face significant limitations due to incomplete data and inherent challenges in defining and measuring function. We propose a “blue sky” vision centered on both comprehensive and precise annotation of existing protein and DNA sequences, aiming to develop a more complete and precise understanding of biological function. By contrasting recent studies that leverage generative AI for biological design with the pressing need for enhanced data annotation, we underscore the importance of prioritizing robust predictive models over premature generative efforts. We advocate for a strategic shift toward thorough sequence annotation and predictive understanding, laying a solid foundation for future advances in biological design. 

   more » « less
2. Mapping Data to Deep Understanding: Making the Most of the Deluge of SARS-CoV-2 Genome Sequences

   https://doi.org/10.1128/msystems.00035-22  

   Sokhansanj, Bahrad A.; Rosen, Gail L. (April 2022, mSystems)

   Gaglia, Marta M. (Ed.)

   ABSTRACT Next-generation sequencing has been essential to the global response to the COVID-19 pandemic. As of January 2022, nearly 7 million severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) sequences are available to researchers in public databases. Sequence databases are an abundant resource from which to extract biologically relevant and clinically actionable information. As the pandemic has gone on, SARS-CoV-2 has rapidly evolved, involving complex genomic changes that challenge current approaches to classifying SARS-CoV-2 variants. Deep sequence learning could be a potentially powerful way to build complex sequence-to-phenotype models. Unfortunately, while they can be predictive, deep learning typically produces “black box” models that cannot directly provide biological and clinical insight. Researchers should therefore consider implementing emerging methods for visualizing and interpreting deep sequence models. Finally, researchers should address important data limitations, including (i) global sequencing disparities, (ii) insufficient sequence metadata, and (iii) screening artifacts due to poor sequence quality control. 

   more » « less
3. Deep Reinforcement Learning for Sequence-to-Sequence Models

   https://doi.org/10.1109/TNNLS.2019.2929141  

   Keneshloo, Yaser; Shi, Tian; Ramakrishnan, Naren; Reddy, Chandan K. (July 2020, IEEE Transactions on Neural Networks and Learning Systems)

   In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide stateof-the-art performance in a wide variety of tasks, such as machine translation, headline generation, text summarization, speech-to-text conversion, and image caption generation. The underlying framework for all these models is usually a deep neural network comprising an encoder and a decoder. Although simple encoder–decoder models produce competitive results, many researchers have proposed additional improvements over these seq2seq models, e.g., using an attention-based model over the input, pointer-generation models, and self-attention models. However, such seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently, a completely novel point of view has emerged in addressing these two problems in seq2seq models, leveraging methods from reinforcement learning (RL). In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with seq2seq models that enable remembering long-term memories. We present some of the most recent frameworks that combine the concepts from RL and deep neural networks. Our work aims to provide insights into some of the problems that inherently arise with current approaches and how we can address them with better RL models. We also provide the source code for implementing most of the RL models discussed in this paper to support the complex task of abstractive text summarization and provide some targeted experiments for these RL models, both in terms of performance and training time. 

   more » « less
4. Preference-grounded Token-level Guidance for Language Model Fine-tuning

   Yang, Shentao; Zhang, Shujian; Xia, Congying; Feng, Yihao; Xiong, Caiming; Zhou, Mingyuan (December 2023, Neural Information Processing Systems)

   Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the token level. There is, therefore, a granularity mismatch between the preference and the LM training losses, which may complicate the learning problem. In this paper, we address this issue by developing an alternate training process, where we iterate between grounding the sequence-level preference into token-level training guidance, and improving the LM with the learned guidance. For guidance learning, we design a framework that extends the pairwise-preference learning in imitation learning to both variable-length LM generation and the utilization of the preference among multiple generations. For LM training, based on the amount of supervised data, we present two minimalist learning objectives that utilize the learned guidance. In experiments, our method performs competitively on two distinct representative LM tasks — discrete-prompt generation and text summarization. Source codes are released at https://github.com/Shentao-YANG/Preference_Grounded_Guidance. 

   more » « less
5. Crystal Composition Transformer: Self‐Learning Neural Language Model for Generative and Tinkering Design of Materials

   https://doi.org/10.1002/advs.202304305  

   Wei, Lai; Li, Qinyang; Song, Yuqi; Stefanov, Stanislav; Dong, Rongzhi; Fu, Nihang; Siriwardane, Edirisuriya_M_D; Chen, Fanglin; Hu, Jianjun (August 2024, Advanced Science)

   Abstract Self‐supervised neural language models have recently achieved unprecedented success from natural language processing to learning the languages of biological sequences and organic molecules. These models have demonstrated superior performance in the generation, structure classification, and functional predictions for proteins and molecules with learned representations. However, most of the masking‐based pre‐trained language models are not designed for generative design, and their black‐box nature makes it difficult to interpret their design logic. Here a Blank‐filling Language Model for Materials (BLMM) Crystal Transformer is proposed, a neural network‐based probabilistic generative model for generative and tinkering design of inorganic materials. The model is built on the blank‐filling language model for text generation and has demonstrated unique advantages in learning the “materials grammars” together with high‐quality generation, interpretability, and data efficiency. It can generate chemically valid materials compositions with as high as 89.7% charge neutrality and 84.8% balanced electronegativity, which are more than four and eight times higher compared to a pseudo‐random sampling baseline. The probabilistic generation process of BLMM allows it to recommend materials tinkering operations based on learned materials chemistry, which makes it useful for materials doping. The model is applied to discover a set of new materials as validated using the Density Functional Theory (DFT) calculations. This work thus brings the unsupervised transformer language models based generative artificial intelligence to inorganic materials. A user‐friendly web app for tinkering materials design has been developed and can be accessed freely atwww.materialsatlas.org/blmtinker. 

   more » « less