Novel machine learning approaches revolutionize protein knowledge.

Breakthrough methods in machine learning (ML), protein structure prediction, and novel ultrafast structural aligners are revolutionizing structural biology. Obtaining accurate models of proteins and annotating their functions on a large scale is no longer limited by time and resources. The most recent method to be top ranked by the Critical Assessment of Structure Prediction (CASP) assessment, AlphaFold 2 (AF2), is capable of building structural models with an accuracy comparable to that of experimental structures. Annotations of 3D models are keeping pace with the deposition of the structures due to advancements in protein language models (pLMs) and structural aligners that help validate these transferred annotations. In this review we describe how recent developments in ML for protein science are making large-scale structural bioinformatics available to the general scientific community.

Recent advances in predicting and modeling protein-protein interactions.

Protein-protein interactions (PPIs) drive biological processes, and disruption of PPIs can cause disease. With recent breakthroughs in structure prediction and a deluge of genomic sequence data, computational methods to predict PPIs and model spatial structures of protein complexes are now approaching the accuracy of experimental approaches for permanent interactions and show promise for elucidating transient interactions. As we describe here, the key to this success is rich evolutionary information deciphered from thousands of homologous sequences that coevolve in interacting partners. This covariation signal, revealed by sophisticated statistical and machine learning (ML) algorithms, predicts physiological interactions. Accurate artificial intelligence (AI)-based modeling of protein structures promises to provide accurate 3D models of PPIs at a proteome-wide scale.

Deception abilities emerged in large language models.

Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady increase in reasoning abilities, future LLMs are under suspicion of becoming able to deceive human operators and utilizing this ability to bypass monitoring efforts. As a prerequisite to this, LLMs need to possess a conceptual understanding of deception strategies. This study reveals that such strategies emerged in state-of-the-art LLMs, but were nonexistent in earlier LLMs. We conduct a series of experiments showing that state-of-the-art LLMs are able to understand and induce false beliefs in other agents, that their performance in complex deception scenarios can be amplified utilizing chain-of-thought reasoning, and that eliciting Machiavellianism in LLMs can trigger misaligned deceptive behavior. GPT-4, for instance, exhibits deceptive behavior in simple test scenarios 99.16% of the time (P < 0.001). In complex second-order deception test scenarios where the aim is to mislead someone who expects to be deceived, GPT-4 resorts to deceptive behavior 71.46% of the time (P < 0.001) when augmented with chain-of-thought reasoning. In sum, revealing hitherto unknown machine behavior in LLMs, our study contributes to the nascent field of machine psychology.

Interface-confined intermediate phase in TiO2 enables efficient photocatalysis.

As a prototypical photocatalyst, TiO[Formula: see text] has been extensively studied. An interesting yet puzzling experimental fact was that P25-a mixture of anatase and rutile TiO[Formula: see text]-outperforms the individual phases; the origin of this mysterious fact, however, remains elusive. Employing rigorous first-principles calculations, here we uncover a metastable intermediate structure (MIS), which is formed due to confinement at the anatase/rutile interface. The MIS has a high conduction-band minimum level and thus substantially enhances the overpotential of the hydrogen evolution reaction. Also, the corresponding band alignment at the interface leads to efficient separation of electrons and holes. The interfacial confinement additionally creates a wide distribution of the band gap in the vicinity of the interface, which in turn improves optical absorption. These factors all contribute to the enhanced photocatalytic efficiency in P25. Our insights provide a rationale to the puzzling superior photocatalytic performance of P25 and enable a strategy to achieve highly efficient photocatalysis via interface engineering.

Principled and interpretable alignability testing and integration of single-cell data.

Single-cell data integration can provide a comprehensive molecular view of cells, and many algorithms have been developed to remove unwanted technical or biological variations and integrate heterogeneous single-cell datasets. Despite their wide usage, existing methods suffer from several fundamental limitations. In particular, we lack a rigorous statistical test for whether two high-dimensional single-cell datasets are alignable (and therefore should even be aligned). Moreover, popular methods can substantially distort the data during alignment, making the aligned data and downstream analysis difficult to interpret. To overcome these limitations, we present a spectral manifold alignment and inference (SMAI) framework, which enables principled and interpretable alignability testing and structure-preserving integration of single-cell data with the same type of features. SMAI provides a statistical test to robustly assess the alignability between datasets to avoid misleading inference and is justified by high-dimensional statistical theory. On a diverse range of real and simulated benchmark datasets, it outperforms commonly used alignment methods. Moreover, we show that SMAI improves various downstream analyses such as identification of differentially expressed genes and imputation of single-cell spatial transcriptomics, providing further biological insights. SMAI's interpretability also enables quantification and a deeper understanding of the sources of technical confounders in single-cell data.

Predicting protein conformational motions using energetic frustration analysis and AlphaFold2.

Proteins perform their biological functions through motion. Although high throughput prediction of the three-dimensional static structures of proteins has proved feasible using deep-learning-based methods, predicting the conformational motions remains a challenge. Purely data-driven machine learning methods encounter difficulty for addressing such motions because available laboratory data on conformational motions are still limited. In this work, we develop a method for generating protein allosteric motions by integrating physical energy landscape information into deep-learning-based methods. We show that local energetic frustration, which represents a quantification of the local features of the energy landscape governing protein allosteric dynamics, can be utilized to empower AlphaFold2 (AF2) to predict protein conformational motions. Starting from ground state static structures, this integrative method generates alternative structures as well as pathways of protein conformational motions, using a progressive enhancement of the energetic frustration features in the input multiple sequence alignment sequences. For a model protein adenylate kinase, we show that the generated conformational motions are consistent with available experimental and molecular dynamics simulation data. Applying the method to another two proteins KaiB and ribose-binding protein, which involve large-amplitude conformational changes, can also successfully generate the alternative conformations. We also show how to extract overall features of the AF2 energy landscape topography, which has been considered by many to be black box. Incorporating physical knowledge into deep-learning-based structure prediction algorithms provides a useful strategy to address the challenges of dynamic structure prediction of allosteric proteins.

Non-canonical role for the BAF complex subunit DPF3 in mitosis and ciliogenesis.

DPF3, along with other subunits, is a well-known component of the BAF chromatin remodeling complex, which plays a key role in regulating chromatin remodeling activity and gene expression. Here, we elucidated a non-canonical localization and role for DPF3. We showed that DPF3 dynamically localizes to the centriolar satellites in interphase and to the centrosome, spindle midzone and bridging fiber area, and midbodies during mitosis. Loss of DPF3 causes kinetochore fiber instability, unstable kinetochore-microtubule attachment and defects in chromosome alignment, resulting in altered mitotic progression, cell death and genomic instability. In addition, we also demonstrated that DPF3 localizes to centriolar satellites at the base of primary cilia and is required for ciliogenesis by regulating axoneme extension. Taken together, these findings uncover a moonlighting dual function for DPF3 during mitosis and ciliogenesis.

Scoring alignments by embedding vector similarity.

Sequence similarity is of paramount importance in biology, as similar sequences tend to have similar function and share common ancestry. Scoring matrices, such as PAM or BLOSUM, play a crucial role in all bioinformatics algorithms for identifying similarities, but have the drawback that they are fixed, independent of context. We propose a new scoring method for amino acid similarity that remedies this weakness, being contextually dependent. It relies on recent advances in deep learning architectures that employ self-supervised learning in order to leverage the power of enormous amounts of unlabelled data to generate contextual embeddings, which are vector representations for words. These ideas have been applied to protein sequences, producing embedding vectors for protein residues. We propose the E-score between two residues as the cosine similarity between their embedding vector representations. Thorough testing on a wide variety of reference multiple sequence alignments indicate that the alignments produced using the new $E$-score method, especially ProtT5-score, are significantly better than those obtained using BLOSUM matrices. The new method proposes to change the way alignments are computed, with far-reaching implications in all areas of textual data that use sequence similarity. The program to compute alignments based on various $E$-scores is available as a web server at e-score.csd.uwo.ca. The source code is freely available for download from github.com/lucian-ilie/E-score.

scBOL: a universal cell type identification framework for single-cell and spatial transcriptomics data.

MOTIVATION: Over the past decade, single-cell transcriptomic technologies have experienced remarkable advancements, enabling the simultaneous profiling of gene expressions across thousands of individual cells. Cell type identification plays an essential role in exploring tissue heterogeneity and characterizing cell state differences. With more and more well-annotated reference data becoming available, massive automatic identification methods have sprung up to simplify the annotation process on unlabeled target data by transferring the cell type knowledge. However, in practice, the target data often include some novel cell types that are not in the reference data. Most existing works usually classify these private cells as one generic 'unassigned' group and learn the features of known and novel cell types in a coupled way. They are susceptible to the potential batch effects and fail to explore the fine-grained semantic knowledge of novel cell types, thus hurting the model's discrimination ability. Additionally, emerging spatial transcriptomic technologies, such as in situ hybridization, sequencing and multiplexed imaging, present a novel challenge to current cell type identification strategies that predominantly neglect spatial organization. Consequently, it is imperative to develop a versatile method that can proficiently annotate single-cell transcriptomics data, encompassing both spatial and non-spatial dimensions. RESULTS: To address these issues, we propose a new, challenging yet realistic task called universal cell type identification for single-cell and spatial transcriptomics data. In this task, we aim to give semantic labels to target cells from known cell types and cluster labels to those from novel ones. To tackle this problem, instead of designing a suboptimal two-stage approach, we propose an end-to-end algorithm called scBOL from the perspective of Bipartite prototype alignment. Firstly, we identify the mutual nearest clusters in reference and target data as their potential common cell types. On this basis, we mine the cycle-consistent semantic anchor cells to build the intrinsic structure association between two data. Secondly, we design a neighbor-aware prototypical learning paradigm to strengthen the inter-cluster separability and intra-cluster compactness within each data, thereby inspiring the discriminative feature representations. Thirdly, driven by the semantic-aware prototypical learning framework, we can align the known cell types and separate the private cell types from them among reference and target data. Such an algorithm can be seamlessly applied to various data types modeled by different foundation models that can generate the embedding features for cells. Specifically, for non-spatial single-cell transcriptomics data, we use the autoencoder neural network to learn latent low-dimensional cell representations, and for spatial single-cell transcriptomics data, we apply the graph convolution network to capture molecular and spatial similarities of cells jointly. Extensive results on our carefully designed evaluation benchmarks demonstrate the superiority of scBOL over various state-of-the-art cell type identification methods. To our knowledge, we are the pioneers in presenting this pragmatic annotation task, as well as in devising a comprehensive algorithmic framework aimed at resolving this challenge across varied types of single-cell data. Finally, scBOL is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/aimeeyaoyao/scBOL.

pathMap: a path-based mapping tool for long noisy reads with high sensitivity.

With the rapid development of single-molecule sequencing (SMS) technologies, the output read length is continuously increasing. Mapping such reads onto a reference genome is one of the most fundamental tasks in sequence analysis. Mapping sensitivity is becoming a major concern since high sensitivity can detect more aligned regions on the reference and obtain more aligned bases, which are useful for downstream analysis. In this study, we present pathMap, a novel k-mer graph-based mapper that is specifically designed for mapping SMS reads with high sensitivity. By viewing the alignment chain as a path containing as many anchors as possible in the matched k-mer graph, pathMap treats chaining as a path selection problem in the directed graph. pathMap iteratively searches the longest path in the remaining nodes; more candidate chains with high quality can be effectively detected and aligned. Compared to other state-of-the-art mapping methods such as minimap2 and Winnowmap2, experiment results on simulated and real-life datasets demonstrate that pathMap obtains the number of mapped chains at least 11.50% more than its closest competitor and increases the mapping sensitivity by 17.28% and 13.84% of bases over the next-best mapper for Pacific Biosciences and Oxford Nanopore sequencing data, respectively. In addition, pathMap is more robust to sequence errors and more sensitive to species- and strain-specific identification of pathogens using MinION reads.

Multi-modal domain adaptation for revealing spatial functional landscape from spatially resolved transcriptomics.

Spatially resolved transcriptomics (SRT) has emerged as a powerful tool for investigating gene expression in spatial contexts, providing insights into the molecular mechanisms underlying organ development and disease pathology. However, the expression sparsity poses a computational challenge to integrate other modalities (e.g. histological images and spatial locations) that are simultaneously captured in SRT datasets for spatial clustering and variation analyses. In this study, to meet such a challenge, we propose multi-modal domain adaption for spatial transcriptomics (stMDA), a novel multi-modal unsupervised domain adaptation method, which integrates gene expression and other modalities to reveal the spatial functional landscape. Specifically, stMDA first learns the modality-specific representations from spatial multi-modal data using multiple neural network architectures and then aligns the spatial distributions across modal representations to integrate these multi-modal representations, thus facilitating the integration of global and spatially local information and improving the consistency of clustering assignments. Our results demonstrate that stMDA outperforms existing methods in identifying spatial domains across diverse platforms and species. Furthermore, stMDA excels in identifying spatially variable genes with high prognostic potential in cancer tissues. In conclusion, stMDA as a new tool of multi-modal data integration provides a powerful and flexible framework for analyzing SRT datasets, thereby advancing our understanding of intricate biological systems.

NIPT-PG: empowering non-invasive prenatal testing to learn from population genomics through an incremental pan-genomic approach.

Non-invasive prenatal testing (NIPT) is a quite popular approach for detecting fetal genomic aneuploidies. However, due to the limitations on sequencing read length and coverage, NIPT suffers a bottleneck on further improving performance and conducting earlier detection. The errors mainly come from reference biases and population polymorphism. To break this bottleneck, we proposed NIPT-PG, which enables the NIPT algorithm to learn from population data. A pan-genome model is introduced to incorporate variant and polymorphic loci information from tested population. Subsequently, we proposed a sequence-to-graph alignment method, which considers the read mis-match rates during the mapping process, and an indexing method using hash indexing and adjacency lists to accelerate the read alignment process. Finally, by integrating multi-source aligned read and polymorphic sites across the pan-genome, NIPT-PG obtains a more accurate z-score, thereby improving the accuracy of chromosomal aneuploidy detection. We tested NIPT-PG on two simulated datasets and 745 real-world cell-free DNA sequencing data sets from pregnant women. Results demonstrate that NIPT-PG outperforms the standard z-score test. Furthermore, combining experimental and theoretical analyses, we demonstrate the probably approximately correct learnability of NIPT-PG. In summary, NIPT-PG provides a new perspective for fetal chromosomal aneuploidies detection. NIPT-PG may have broad applications in clinical testing, and its detection results can serve as a reference for false positive samples approaching the critical threshold.

Signatures of cross-modal alignment in children's early concepts.

Whether supervised or unsupervised, human and machine learning is usually characterized as event-based. However, learning may also proceed by systems alignment in which mappings are inferred between entire systems, such as visual and linguistic systems. Systems alignment is possible because items that share similar visual contexts, such as a car and a truck, will also tend to share similar linguistic contexts. Because of the mirrored similarity relationships across systems, the visual and linguistic systems can be aligned at some later time absent either input. In a series of simulation studies, we considered whether children's early concepts support systems alignment. We found that children's early concepts are close to optimal for inferring novel concepts through systems alignment, enabling agents to correctly infer more than 85% of visual-word mappings absent supervision. One possible explanation for why children's early concepts support systems alignment is that they are distinguished structurally by their dense semantic neighborhoods. Artificial agents using these structural features to select concepts proved highly effective, both in environments mirroring children's conceptual world and those that exclude the concepts that children commonly acquire. For children, systems alignment and event-based learning likely complement one another. Likewise, artificial systems can benefit from incorporating these developmental principles.

Feasibility of dopamine as a vector-valued feedback signal in the basal ganglia.

It is well established that midbrain dopaminergic neurons support reinforcement learning (RL) in the basal ganglia by transmitting a reward prediction error (RPE) to the striatum. In particular, different computational models and experiments have shown that a striatum-wide RPE signal can support RL over a small discrete set of actions (e.g., no/no-go, choose left/right). However, there is accumulating evidence that the basal ganglia functions not as a selector between predefined actions but rather as a dynamical system with graded, continuous outputs. To reconcile this view with RL, there is a need to explain how dopamine could support learning of continuous outputs, rather than discrete action values. Inspired by the recent observations that besides RPE, the firing rates of midbrain dopaminergic neurons correlate with motor and cognitive variables, we propose a model in which dopamine signal in the striatum carries a vector-valued error feedback signal (a loss gradient) instead of a homogeneous scalar error (a loss). We implement a local, "three-factor" corticostriatal plasticity rule involving the presynaptic firing rate, a postsynaptic factor, and the unique dopamine concentration perceived by each striatal neuron. With this learning rule, we show that such a vector-valued feedback signal results in an increased capacity to learn a multidimensional series of real-valued outputs. Crucially, we demonstrate that this plasticity rule does not require precise nigrostriatal synapses but remains compatible with experimental observations of random placement of varicosities and diffuse volume transmission of dopamine.

Whole-genome sequences from wild-type and laboratory-evolved strains define the alleleome and establish its hallmarks.

The genomic diversity across strains of a species forms the genetic basis for differences in their behavior. A large-scale assessment of sequence variation has been made possible by the growing availability of strain-specific whole-genome sequences (WGS) and with the advent of large-scale databases of laboratory-acquired mutations. We define the Escherichia coli "alleleome" through a genome-scale assessment of amino acid (AA) sequence diversity in open reading frames across 2,661 WGS from wild-type strains. We observe a highly conserved alleleome enriched in mutations unlikely to affect protein function. In contrast, 33,000 mutations acquired in laboratory evolution experiments result in more severe AA substitutions that are rarely achieved by natural selection. Large-scale assessment of the alleleome establishes a method for the quantification of bacterial allelic diversity, reveals opportunities for synthetic biology to explore novel sequence space, and offers insights into the constraints governing evolution.

A values-aligned intervention fosters growth mindset-supportive teaching and reduces inequality in educational outcomes.

Group-based educational disparities are smaller in classrooms where teachers express a belief that students can improve their abilities. However, a scalable method for motivating teachers to adopt such growth mindset-supportive teaching practices has remained elusive. In part, this is because teachers often already face overwhelming demands on their time and attention and have reason to be skeptical of the professional development advice they receive from researchers and other experts. We designed an intervention that overcame these obstacles and successfully motivated high-school teachers to adopt specific practices that support students' growth mindsets. The intervention used the values-alignment approach. This approach motivates behavioral change by framing a desired behavior as aligned with a core value-one that is an important criterion for status and admiration in the relevant social reference group. First, using qualitative interviews and a nationally representative survey of teachers, we identified a relevant core value: inspiring students' enthusiastic engagement with learning. Next, we designed a ~45-min, self-administered, online intervention that persuaded teachers to view growth mindset-supportive practices as a way to foster such student engagement and thus live up to that value. We randomly assigned 155 teachers (5,393 students) to receive the intervention and 164 teachers (6,167 students) to receive a control module. The growth mindset-supportive teaching intervention successfully promoted teachers' adoption of the suggested practices, overcoming major barriers to changing teachers' classroom practices that other scalable approaches have failed to surmount. The intervention also substantially improved student achievement in socioeconomically disadvantaged classes, reducing inequality in educational outcomes.

Distinct SAP102 and PSD-95 Nano-organization Defines Multiple Types of Synaptic Scaffold Protein Domains at Single Synapses.

MAGUK scaffold proteins play a central role in maintaining and modulating synaptic signaling, providing a framework to retain and position receptors, signaling molecules, and other synaptic components. In particular, the MAGUKs SAP102 and PSD-95 are essential for synaptic function at distinct developmental timepoints and perform both overlapping and unique roles. While their similar structures allow for common binding partners, SAP102 is expressed earlier in synapse development and is required for synaptogenesis, whereas PSD-95 expression peaks later and is associated with synapse maturation. PSD-95 and other key synaptic proteins organize into subsynaptic nanodomains that have a significant impact on synaptic transmission, but the nanoscale organization of SAP102 is unknown. How SAP102 is organized within the synapse, and how it relates spatially to PSD-95 on a nanometer scale, could underlie its unique functions and impact how SAP102 scaffolds synaptic proteins. Here we used DNA-PAINT super-resolution microscopy to measure SAP102 nano-organization and its spatial relationship to PSD-95 at individual synapses in mixed-sex rat cultured neurons. We found that like PSD-95, SAP102 accumulates in high-density subsynaptic nanoclusters (NCs). However, SAP102 NCs were smaller and denser than PSD-95 NCs across development. Additionally, only a subset of SAP102 NCs co-organized with PSD-95, revealing MAGUK nanodomains within individual synapses containing either one or both proteins. These MAGUK nanodomain types had distinct NC properties and were differentially enriched with the presynaptic release protein Munc13-1. This organization into both shared and distinct subsynaptic nanodomains may underlie the ability of SAP102 and PSD-95 to perform both common and unique synaptic functions.

The adenomatous polyposis coli protein 30 years on.

Mutations in the gene encoding the Adenomatous polyposis coli protein (APC) were discovered as driver mutations in colorectal cancers almost 30 years ago. Since then, the importance of APC in normal tissue homeostasis has been confirmed in a plethora of other (model) organisms spanning a large evolutionary space. APC is a multifunctional protein, with roles as a key scaffold protein in complexes involved in diverse signalling pathways, most prominently the Wnt signalling pathway. APC is also a cytoskeletal regulator with direct and indirect links to and impacts on all three major cytoskeletal networks. Correspondingly, a wide range of APC binding partners have been identified. Mutations in APC are extremely strongly associated with colorectal cancers, particularly those that result in the production of truncated proteins and the loss of significant regions from the remaining protein. Understanding the complement of its role in health and disease requires knowing the relationship between and regulation of its diverse functions and interactions. This in turn requires understanding its structural and biochemical features. Here we set out to provide a brief overview of the roles and function of APC and then explore its conservation and structure using the extensive sequence data, which is now available, and spans a broad range of taxonomy. This revealed conservation of APC across taxonomy and new relationships between different APC protein families.

Sugar ring alignment and dynamics underline cytarabine and gemcitabine inhibition on Pol η catalyzed DNA synthesis.

Nucleoside analogue drugs are pervasively used as antiviral and chemotherapy agents. Cytarabine and gemcitabine are anti-cancer nucleoside analogue drugs that contain C2' modifications on the sugar ring. Despite carrying all the required functional groups for DNA synthesis, these two compounds inhibit DNA extension once incorporated into DNA. It remains unclear how the C2' modifications on cytarabine and gemcitabine affect the polymerase active site during substrate binding and DNA extension. Using steady-state kinetics, static and time-resolved X-ray crystallography with DNA polymerase η (Pol η) as a model system, we showed that the sugar ring C2' chemical groups on cytarabine and gemcitabine snugly fit within the Pol η active site without occluding the steric gate. During DNA extension, Pol η can extend past gemcitabine but with much lower efficiency past cytarabine. The Pol η crystal structures show that the -OH modification in the ß direction on cytarabine locks the sugar ring in an unfavorable C2'-endo geometry for product formation. On the other hand, the addition of fluorine atoms on gemcitabine alters the proper conformational transition of the sugar ring for DNA synthesis. Our study illustrates mechanistic insights into chemotherapeutic drug inhibition and resistance and guides future optimization of nucleoside analogue drugs.

Kinesin-7 CENP-E mediates chromosome alignment and spindle assembly checkpoint in meiosis I.

In eukaryotes, meiosis is the genetic basis for sexual reproduction, which is important for chromosome stability and species evolution. The defects in meiosis usually lead to chromosome aneuploidy, reduced gamete number, and genetic diseases, but the pathogenic mechanisms are not well clarified. Kinesin-7 CENP-E is a key regulator in chromosome alignment and spindle assembly checkpoint in cell division. However, the functions and mechanisms of CENP-E in male meiosis remain largely unknown. In this study, we have revealed that the CENP-E gene was highly expressed in the rat testis. CENP-E inhibition influences chromosome alignment and spindle organization in metaphase I spermatocytes. We have found that a portion of misaligned homologous chromosomes is located at the spindle poles after CENP-E inhibition, which further activates the spindle assembly checkpoint during the metaphase-to-anaphase transition in rat spermatocytes. Furthermore, CENP-E depletion leads to abnormal spermatogenesis, reduced sperm count, and abnormal sperm head structure. Our findings have elucidated that CENP-E is essential for homologous chromosome alignment and spindle assembly checkpoint in spermatocytes, which further contribute to chromosome stability and sperm cell quality during spermatogenesis.