Metabolic heterogeneity in humans.

Recent advancements in technology, especially the emergence of single-cell technologies, genomic sequencing, metabolomics, and artificial intelligence, have enabled us to understand the distinct metabolic changes in different cell types, tissues, genders, disease states, ages, and populations. Six scientists whose work intersects with metabolism in various capacities tell us about their vision for human metabolic heterogeneity.

Future views on neuroscience and AI.

The relationship between neuroscience and artificial intelligence (AI) has evolved rapidly over the past decade. These two areas of study influence and stimulate each other. We invited experts to share their perspectives on this exciting intersection, focusing on current achievements, unsolved questions, and future directions.

The evolution of developmental biology through conceptual and technological revolutions.

Developmental biology-the study of the processes by which cells, tissues, and organisms develop and change over time-has entered a new golden age. After the molecular genetics revolution in the 80s and 90s and the diversification of the field in the early 21st century, we have entered a phase when powerful technologies provide new approaches and open unexplored avenues. Progress in the field has been accelerated by advances in genomics, imaging, engineering, and computational biology and by emerging model systems ranging from tardigrades to organoids. We summarize how revolutionary technologies have led to remarkable progress in understanding animal development. We describe how classic questions in gene regulation, pattern formation, morphogenesis, organogenesis, and stem cell biology are being revisited. We discuss the connections of development with evolution, self-organization, metabolism, time, and ecology. We speculate how developmental biology might evolve in an era of synthetic biology, artificial intelligence, and human engineering.

Toward a foundation model of causal cell and tissue biology with a Perturbation Cell and Tissue Atlas.

Comprehensively charting the biologically causal circuits that govern the phenotypic space of human cells has often been viewed as an insurmountable challenge. However, in the last decade, a suite of interleaved experimental and computational technologies has arisen that is making this fundamental goal increasingly tractable. Pooled CRISPR-based perturbation screens with high-content molecular and/or image-based readouts are now enabling researchers to probe, map, and decipher genetically causal circuits at increasing scale. This scale is now eminently suitable for the deployment of artificial intelligence and machine learning (AI/ML) to both direct further experiments and to predict or generate information that was not-and sometimes cannot-be gathered experimentally. By combining and iterating those through experiments that are designed for inference, we now envision a Perturbation Cell Atlas as a generative causal foundation model to unify human cell biology.

De novo protein design-From new structures to programmable functions.

Methods from artificial intelligence (AI) trained on large datasets of sequences and structures can now "write" proteins with new shapes and molecular functions de novo, without starting from proteins found in nature. In this Perspective, I will discuss the state of the field of de novo protein design at the juncture of physics-based modeling approaches and AI. New protein folds and higher-order assemblies can be designed with considerable experimental success rates, and difficult problems requiring tunable control over protein conformations and precise shape complementarity for molecular recognition are coming into reach. Emerging approaches incorporate engineering principles-tunability, controllability, and modularity-into the design process from the beginning. Exciting frontiers lie in deconstructing cellular functions with de novo proteins and, conversely, constructing synthetic cellular signaling from the ground up. As methods improve, many more challenges are unsolved.

An atlas of protein homo-oligomerization across domains of life.

Protein structures are essential to understanding cellular processes in molecular detail. While advances in artificial intelligence revealed the tertiary structure of proteins at scale, their quaternary structure remains mostly unknown. We devise a scalable strategy based on AlphaFold2 to predict homo-oligomeric assemblies across four proteomes spanning the tree of life. Our results suggest that approximately 45% of an archaeal proteome and a bacterial proteome and 20% of two eukaryotic proteomes form homomers. Our predictions accurately capture protein homo-oligomerization, recapitulate megadalton complexes, and unveil hundreds of homo-oligomer types, including three confirmed experimentally by structure determination. Integrating these datasets with omics information suggests that a majority of known protein complexes are symmetric. Finally, these datasets provide a structural context for interpreting disease mutations and reveal coiled-coil regions as major enablers of quaternary structure evolution in human. Our strategy is applicable to any organism and provides a comprehensive view of homo-oligomerization in proteomes.

Liquid-biopsy proteomics combined with AI identifies cellular drivers of eye aging and disease in vivo.

Single-cell analysis in living humans is essential for understanding disease mechanisms, but it is impractical in non-regenerative organs, such as the eye and brain, because tissue biopsies would cause serious damage. We resolve this problem by integrating proteomics of liquid biopsies with single-cell transcriptomics from all known ocular cell types to trace the cellular origin of 5,953 proteins detected in the aqueous humor. We identified hundreds of cell-specific protein markers, including for individual retinal cell types. Surprisingly, our results reveal that retinal degeneration occurs in Parkinson's disease, and the cells driving diabetic retinopathy switch with disease stage. Finally, we developed artificial intelligence (AI) models to assess individual cellular aging and found that many eye diseases not associated with chronological age undergo accelerated molecular aging of disease-specific cell types. Our approach, which can be applied to other organ systems, has the potential to transform molecular diagnostics and prognostics while uncovering new cellular disease and aging mechanisms.

Structures of sperm flagellar doublet microtubules expand the genetic spectrum of male infertility.

Sperm motility is crucial for successful fertilization. Highly decorated doublet microtubules (DMTs) form the sperm tail skeleton, which propels the movement of spermatozoa. Using cryo-electron microscopy (cryo-EM) and artificial intelligence (AI)-based modeling, we determined the structures of mouse and human sperm DMTs and built an atomic model of the 48-nm repeat of the mouse sperm DMT. Our analysis revealed 47 DMT-associated proteins, including 45 microtubule inner proteins (MIPs). We identified 10 sperm-specific MIPs, including seven classes of Tektin5 in the lumen of the A tubule and FAM166 family members that bind the intra-tubulin interfaces. Interestingly, the human sperm DMT lacks some MIPs compared with the mouse sperm DMT. We also discovered variants in 10 distinct MIPs associated with a subtype of asthenozoospermia characterized by impaired sperm motility without evident morphological abnormalities. Our study highlights the conservation and tissue/species specificity of DMTs and expands the genetic spectrum of male infertility.

The application of artificial intelligence to biology and neuroscience.

Over the last decade, the artificial intelligence (AI) has undergone a revolution that is poised to transform the economy, society, and science. The pace of progress is staggering, and problems that seemed intractable just a few years ago have now been solved. The intersection between neuroscience and AI is particularly exciting.

The impact of AI on research.

Large and complex datasets have made artificial intelligence (AI) an invaluable tool for discovery across biological research. We asked experts how AI has impacted their work. Their experiences and perspectives offer thoughtful insights into potential offered by AI for their fields.

Repurposing chemical waste: Sustainable chemistry for circularity beyond artificial intelligence.

Generating considerable amounts of industrial waste requires rethinking chemistry for circularity in a broader picture. We discuss the study by Wolos et al. (2022) showing that the critical application of artificial intelligence on chemical reactivity can help us trace an unprecedented number of syntheses to novel responsible uses of waste.

Live-cell imaging powered by computation.

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preserving cell viability. Computational methods can help to address this challenge and are now shifting the boundaries of what is possible to capture in living systems. In this Review, we discuss these computational methods focusing on artificial intelligence-based approaches that can be layered on top of commonly used existing microscopies as well as hybrid methods that integrate computation and microscope hardware. We specifically discuss how computational approaches can improve the signal-to-noise ratio, spatial resolution, temporal resolution and multi-colour capacity of live-cell imaging.

Precision medicine in 2030-seven ways to transform healthcare.

Precision medicine promises improved health by accounting for individual variability in genes, environment, and lifestyle. Precision medicine will continue to transform healthcare in the coming decade as it expands in key areas: huge cohorts, artificial intelligence (AI), routine clinical genomics, phenomics and environment, and returning value across diverse populations.

Decoding the tumor microenvironment with spatial technologies.

Visualization of the cellular heterogeneity and spatial architecture of the tumor microenvironment (TME) is becoming increasingly important to understand mechanisms of disease progression and therapeutic response. This is particularly relevant in the era of cancer immunotherapy, in which the contexture of immune cell positioning within the tumor landscape has been proven to affect efficacy. Although single-cell technologies have mostly replaced conventional approaches to analyze specific cellular subsets within tumors, those that integrate a spatial dimension are now on the rise. In this Review, we assess the strengths and limitations of emerging spatial technologies with a focus on their applications in tumor immunology, as well as forthcoming opportunities for artificial intelligence (AI) and the value of integrating multiomics datasets to achieve a holistic picture of the TME.

Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography.

Many COVID-19 patients infected by SARS-CoV-2 virus develop pneumonia (called novel coronavirus pneumonia, NCP) and rapidly progress to respiratory failure. However, rapid diagnosis and identification of high-risk patients for early intervention are challenging. Using a large computed tomography (CT) database from 3,777 patients, we developed an AI system that can diagnose NCP and differentiate it from other common pneumonia and normal controls. The AI system can assist radiologists and physicians in performing a quick diagnosis especially when the health system is overloaded. Significantly, our AI system identified important clinical markers that correlated with the NCP lesion properties. Together with the clinical data, our AI system was able to provide accurate clinical prognosis that can aid clinicians to consider appropriate early clinical management and allocate resources appropriately. We have made this AI system available globally to assist the clinicians to combat COVID-19.

AI and immunology.

AI is rapidly becoming part of many aspects of daily life, with an impact that reaches all fields of research. We asked investigators to share their thoughts on how AI is changing immunology research, what is necessary to move forward, the potential and the pitfalls, and what will remain unchanged as the field journeys into a new era.

Language in Brains, Minds, and Machines.

It has long been argued that only humans could produce and understand language. But now, for the first time, artificial language models (LMs) achieve this feat. Here we survey the new purchase LMs are providing on the question of how language is implemented in the brain. We discuss why, a priori, LMs might be expected to share similarities with the human language system. We then summarize evidence that LMs represent linguistic information similarly enough to humans to enable relatively accurate brain encoding and decoding during language processing. Finally, we examine which LM properties-their architecture, task performance, or training-are critical for capturing human neural responses to language and review studies using LMs as in silico model organisms for testing hypotheses about language. These ongoing investigations bring us closer to understanding the representations and processes that underlie our ability to comprehend sentences and express thoughts in language.

Designer genes courtesy of artificial intelligence.

The core promoter determines not only where gene transcription initiates but also the transcriptional activity in both basal and enhancer-induced conditions. Multiple short sequence elements within the core promoter have been identified in different species, but how they function together and to what extent they are truly species-specific has remained unclear. In this issue of Genes & Development, Vo ngoc and colleagues (pp. 377-382) report undertaking massively parallel measurements of synthetic core promoters to generate a large data set of their activities that informs a statistical learning model to identify the sequence differences of human and Drosophila core promoters. This machine learning model was then applied to design gene core promoters that are particularly specific for the human transcriptional machinery.

AI-assisted proofreading of RNA splicing.

RNA helicases orchestrate proofreading mechanisms that facilitate accurate intron removal from pre-mRNAs. How these activities are recruited to spliceosome/pre-mRNA complexes remains poorly understood. In this issue of Genes & Development, Zhang and colleagues (pp. 968-983) combine biochemical experiments with AI-based structure prediction methods to generate a model for the interaction between SF3B1, a core splicing factor essential for the recognition of the intron branchpoint, and SUGP1, a protein that bridges SF3B1 with the helicase DHX15. Interaction with SF3B1 exposes the G-patch domain of SUGP1, facilitating binding to and activation of DHX15. The model can explain the activation of cryptic 3' splice sites induced by mutations in SF3B1 or SUGP1 frequently found in cancer.