Cell systems最新文献

Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial-intelligence-driven protein design. However, we lack a sufficient understanding of how very large-scale models and data play a role in effective protein model development. We introduce a suite of protein language models, named ProGen2, that are scaled up to 6.4B parameters and trained on different sequence datasets drawn from over a billion proteins from genomic, metagenomic, and immune repertoire databases. ProGen2 models show state-of-the-art performance in capturing the distribution of observed evolutionary sequences, generating novel viable sequences, and predicting protein fitness without additional fine-tuning. As large model sizes and raw numbers of protein sequences continue to become more widely accessible, our results suggest that a growing emphasis needs to be placed on the data distribution provided to a protein sequence model. Our models and code are open sourced for widespread adoption in protein engineering. A record of this paper's Transparent Peer Review process is included in the supplemental information.

Large language models have emerged as a new compass for navigating the complex landscapes of protein engineering. This issue of Cell Systems features ProGen2 and IgLM-two protein language models (PLMs) that use subtly different approaches to design proteins.

The generation of distinct cell types in developing tissues depends on establishing spatial patterns of gene expression. Often, this is directed by spatially graded chemical signals-known as morphogens. In the "French Flag model," morphogen concentration instructs cells to acquire specific fates. How this mechanism produces timely and organized cell-fate decisions, despite the presence of changing morphogen levels, molecular noise, and individual variability, is unclear. Moreover, feedback is present at various levels in developing tissues, breaking the link between morphogen concentration, signaling activity, and position. Here, we develop an alternative framework using optimal control theory to tackle the problem of morphogen-driven patterning: intracellular signaling is derived as the control strategy that guides cells to the correct fate while minimizing a combination of signaling levels and time. This approach recovers experimentally observed properties of patterning strategies and offers insight into design principles that produce timely, precise, and reproducible morphogen patterning.

The rapid progress in the field of deep learning has had a significant impact on protein design. Deep learning methods have recently produced a breakthrough in protein structure prediction, leading to the availability of high-quality models for millions of proteins. Along with novel architectures for generative modeling and sequence analysis, they have revolutionized the protein design field in the past few years remarkably by improving the accuracy and ability to identify novel protein sequences and structures. Deep neural networks can now learn and extract the fundamental features of protein structures, predict how they interact with other biomolecules, and have the potential to create new effective drugs for treating disease. As their applicability in protein design is rapidly growing, we review the recent developments and technology in deep learning methods and provide examples of their performance to generate novel functional proteins.

Recent experimental developments in genome-wide RNA quantification hold considerable promise for systems biology. However, rigorously probing the biology of living cells requires a unified mathematical framework that accounts for single-molecule biological stochasticity in the context of technical variation associated with genomics assays. We review models for a variety of RNA transcription processes, as well as the encapsulation and library construction steps of microfluidics-based single-cell RNA sequencing, and present a framework to integrate these phenomena by the manipulation of generating functions. Finally, we use simulated scenarios and biological data to illustrate the implications and applications of the approach.

While single-cell sequencing technologies provide unprecedented insights into genomic profiles at the cellular level, they lose the spatial context of cells. Over the past decade, diverse spatial transcriptomics and multi-omics technologies have been developed to analyze molecular profiles of tissues. In this article, we categorize current spatial genomics technologies into three classes: optical imaging, positional indexing, and mathematical cartography. We discuss trade-offs in resolution and scale, identify limitations, and highlight synergies between existing single-cell and spatial genomics methods. Further, we propose DNA-GPS (global positioning system), a theoretical framework for large-scale optics-free spatial genomics that combines ideas from mathematical cartography and positional indexing. DNA-GPS has the potential to achieve scalable spatial genomics for multiple measurement modalities, and by eliminating the need for optical measurement, it has the potential to position cells in three-dimensions (3D).

Understanding the thermal stability of the plant proteome in the context of the native cellular environment would aid the design of crops with high thermal tolerance, but only limited such data are available. Here, we applied quantitative mass spectrometry to profile the thermal stability of the Arabidopsis proteome and identify thermo-sensitive and thermo-resilient protein networks in Arabidopsis, providing a basis for understanding heat-induced damage. We also show that the similarities of the protein-melting curves can be used as a proxy to evaluate system-wide protein-protein interactions in non-engineered plants and enable the identification of transient interactions exhibited by metabolons in the context of the cellular environment. Finally, we report a systematic comparison of the thermal stability of paralogs in Arabidopsis to aid the investigation and understanding of gene duplication and protein evolution. Taken together, our results could have broad implications for the fields of plant thermal tolerance, plant protein assemblies, and evolution.

Knowledge of the thermal stability of plant proteomes within their native environments would aid in the design of climate-resilient crop plants. Identification of thermo-sensitive and -resilient proteins not only provides foundational understanding of systematic heat-induced damage but also offers insight into protein interactions and protein evolution.

Transferable plasmids play a critical role in shaping the functions of microbial communities. Previous studies suggested multiple mechanisms underlying plasmid persistence and abundance. Here, we focus on the interplay between heterogeneous community partitioning and plasmid fates. Natural microbiomes often experience partitioning that creates heterogeneous local communities with reduced population sizes and biodiversity. Little is known about how population partitioning affects the plasmid fate through the modulation of community structure. By modeling and experiments, we show that heterogeneous community partitioning can paradoxically promote the persistence of a plasmid that would otherwise not persist in a global community. Among the local communities created by partitioning, a minority will primarily consist of members able to transfer the plasmid fast enough to support its maintenance by serving as a local plasmid haven. Our results provide insights into plasmid maintenance and suggest a generalizable approach to modulate plasmid persistence for engineering and medical applications.

Our knowledge of transcriptional responses to changes in nutrient availability comes primarily from few well-studied transcription factors (TFs), often lacking an unbiased genome-wide perspective. Leveraging recent advances allowing bacterial genomic footprinting, we comprehensively mapped the genome-wide regulatory responses of Escherichia coli to exogenous leucine, methionine, alanine, and lysine. The global TF Lrp was found to individually sense three amino acids and mount three different target gene responses. Overall, 531 genes had altered RNA polymerase occupancy, and 32 TFs responded directly or indirectly to the presence of amino acids, including regulators of membrane and osmotic pressure homeostasis. About 70% of the detected TF-DNA interactions had not been reported before. We thus identified 682 previously unknown TF-binding locations, for a subset of which the involved TFs were identified by affinity purification. This comprehensive map of amino acid regulation illustrates the incompleteness of the known transcriptional regulation network, even in E. coli.