Ivan Anishchenko, Yakov Kipnis, Indrek Kalvet, Guangfeng Zhou, Rohith Krishna, Samuel J. Pellock, Anna Lauko, Gyu Rie Lee, Linna An, Justas Dauparas, Frank DiMaio, David Baker <<<

AbstractModeling the conformational heterogeneity of protein-small molecule systems is an outstanding challenge. We reasoned that while residue level descriptions of biomolecules are efficient for de novo structure prediction, for probing heterogeneity of interactions with small molecules in the folded state an entirely atomic level description could have advantages in speed and generality. We developed a graph neural network called ChemNet trained to recapitulate correct atomic positions from partially corrupted input structures from the Cambridge Structural Database and the Protein Data Bank; the nodes of the graph are the atoms in the system. ChemNet accurately generates structures of diverse organic small molecules given knowledge of their atom composition and bonding, and given a description of the larger protein context, and builds up structures of small molecules and protein side chains for protein-small molecule docking. Because ChemNet is rapid and stochastic, ensembles of predictions can be readily generated to map conformational heterogeneity. In enzyme design efforts described here and elsewhere, we find that using ChemNet to assess the accuracy and pre-organization of the designed active sites results in higher success rates and higher activities; we obtain a preorganized retroaldolase with akcat/KMof 11000 M-1min- 1, considerably higher than any pre-deep learning design for this reaction. We anticipate that ChemNet will be widely useful for rapidly generating conformational ensembles of small molecule and small molecule-protein systems, and for designing higher activity preorganized enzymes. <<<

The grand challenge in structure-based drug design is achieving accurate prediction of binding free energies. Molecular dynamics (MD) simulations enable modeling of conformational changes critical to the binding process, leading to calculation of thermodynamic quantities involved in estimation of binding affinities. With recent advancements in computing capability and predictive accuracy, MD based virtual screening has progressed from the domain of theoretical attempts to real application in drug development. Approaches including the Molecular Mechanics Poisson Boltzmann Surface Area (MM-PBSA), Linear Interaction Energy (LIE), and alchemical methods have been broadly applied to model molecular recognition for drug discovery and lead optimization. Here we review the varied methodology of these approaches, developments enhancing simulation efficiency and reliability, remaining challenges hindering predictive performance, and applications to problems in the fields of medicine and biochemistry. <<<

AbstractThe rational targeting of RNA with small molecules is hampered by our still limited understanding of RNA structural and dynamic properties. Mostin silicotools for binding site identification rely on static structures and therefore cannot face the challenges posed by the dynamic nature of RNA molecules. Here, we present SHAMAN, a computational technique to identify potential small-molecule binding sites in RNA structural ensembles. SHAMAN enables exploring the conformational landscape of RNA with atomistic molecular dynamics and at the same time identifying RNA pockets in an efficient way with the aid of probes and enhanced-sampling techniques. In our benchmark composed of large, structured riboswitches as well as small, flexible viral RNAs, SHAMAN successfully identified all the experimentally resolved pockets and ranked them among the most favorite probe hotspots. Overall, SHAMAN sets a solid foundation for future drug design efforts targeting RNA with small molecules, effectively addressing the long-standing challenges in the field. <<<

INTRODUCTION: KRAS is a critical oncogenic protein intricately involved in tumor progression, and the difficulty in targeting KRAS has led it to be classified as an 'undruggable target.' Among the various KRAS mutations, KRASG12D is highly prevalent and represents a promising therapeutic target, yet there are currently no approved inhibitors for it.AREA COVERED: This review summarizes numerous patents and literature featuring inhibitors or degraders of KRASG12D through searching relevant information in PubMed, SciFinder and Web of Science databases from 2021 to February 2024, providing an overview of the research progress on inhibiting KRASG12D in terms of design strategies, chemical structures, biological activities, and clinical advancements.EXPERT OPINION: Since the approval of AMG510 (Sotorasib), there has been an increasing focus on the inhibition of KRASG12D, leading to numerous reports of related inhibitors and degraders. Among them, MRTX1133, as the first KRASG12D inhibitor to enter clinical trials, has demonstrated excellent tumor suppression in various KRASG12D-bearing human tumor xenograft models. It is important to note, however, that understanding the mechanisms of acquired resistance caused by KRAS inhibition and developing additional combination therapies is crucial. Moreover, seeking covalent inhibition of KRASG12D also holds significant potential. <<<

Growing evidence indicates that collagen-binding integrins are important costimulatory molecules of effector T cells. In this study, we demonstrate that the major collagen-binding integrin expressed by human Th17 cells is alpha2beta1 (α2β1) or VLA-2, also known as the receptor for collagen I on T cells. Our results show that human naïve CD4(+) T cells cultured under Th17 polarization conditions preferentially upregulate α2β1 integrin rather than α1β1 integrin, which is the receptor for collagen IV on T cells. Double staining analysis for integrin receptors and intracellular IL-17 showed that α2 integrin but not α1 integrin is associated with Th17 cells. Cell adhesion experiments demonstrated that Th17 cells attach to collagen I and collagen II using α2β1 integrin but did not attach to collagen IV. Functional studies revealed that collagens I and II but not collagen IV costimulate the production of IL-17A, IL-17F and IFN-γ by human Th17 cells activated with anti-CD3. These results identify α2β1 integrin as the major collagen receptor expressed on human Th17 cells and suggest that it can be an important costimulatory molecule of Th17 cell responses. <<<

Abstract Collagen structure in biological tissues imparts its intrinsic physical properties by the formation of several covalent crosslinks. For the first time, two major crosslinks in the skin dihydroxylysinonorleucine (HLNL) and histidinohydroxymerodesmosine (HHMD), were isotopically labelled and then analysed by liquid-chromatography high-resolution accurate-mass mass spectrometry (LC-HRMS) and small-angle neutron scattering (SANS). The isotopic labelling followed by LC-HRMS confirmed the presence of one imino group in both HLNL and HHMD, making them more susceptible to degrade at low pH. The structural changes in collagen due to extreme changes in the pH and chrome tanning were highlighted by the SANS contrast variation between isotopic labelled and unlabelled crosslinks. This provided a better understanding of the interaction of natural crosslinks with the chromium sulphate in collagen suggesting that the development of a benign crosslinking method can help retain the intrinsic physical properties of the leather. This analytical method can also be applied to study artificial crosslinking in other collagenous tissues for biomedical applications. Graphical abstract <<<

Confocal Raman spectroscopy (CRS) is a powerful tool that has been widely used for biological tissue analysis because of its noninvasive nature, high specificity, and rich biochemical information. However, current commercial CRS systems suffer from limited detection regions (450-1750 cm), bulky sizes, nonflexibilities, slow acquisitions by consecutive excitations, and high costs if using a Fourier transform (FT) Raman spectroscopy with an InGaAs detector, which impede their adoption in clinics. In this study, we developed a portable CRS system with a simultaneous dual-wavelength source and a miniaturized handheld probe (120 mm × 60 mm × 50 mm) that can acquire spectra in both fingerprint (FP, 450-1750 cm) and high wavenumber (HW, 2800-3800 cm) regions simultaneously. An innovative design combining 671 and 785 nm lasers for simultaneous excitation through a compact and high-efficiency (>90%) wavelength combiner was implemented. Moreover, to decouple the fused FP and HW spectra, a first-of-its-kind precise Raman spectra separation algorithm (PRSSA) was developed based on the maximum probability (MAP) estimate. The accuracy of spectra separation was greater than 99%, demonstrated in both phantom experiments and human skin measurements. The total data acquisition time was reduced by greater than 50% compared to other CRS systems. The results proved our proposed CRS system and PRSSA's superior capability in fast and ultrawideband spectra acquisition will significantly improve the integration of CRS in the clinical workflow. <<<

Ruichen Li, Haotian Ye, Du Jiang, Xuelan Wen, Chuwei Wang, Zhe Li, Xiang Li, Di He, Ji Chen, Weiluo Ren, Liwei Wang <<<

Abstract Collagen structure in biological tissues imparts its intrinsic physical properties by the formation of several covalent crosslinks. For the first time, two major crosslinks in the skin dihydroxylysinonorleucine (HLNL) and histidinohydroxymerodesmosine (HHMD), were isotopically labelled and then analysed by liquid-chromatography high-resolution accurate-mass mass spectrometry (LC-HRMS) and small-angle neutron scattering (SANS). The isotopic labelling followed by LC-HRMS confirmed the presence of one imino group in both HLNL and HHMD, making them more susceptible to degrade at low pH. The structural changes in collagen due to extreme changes in the pH and chrome tanning were highlighted by the SANS contrast variation between isotopic labelled and unlabelled crosslinks. This provided a better understanding of the interaction of natural crosslinks with the chromium sulphate in collagen suggesting that the development of a benign crosslinking method can help retain the intrinsic physical properties of the leather. This analytical method can also be applied to study artificial crosslinking in other collagenous tissues for biomedical applications. Graphical abstract <<<

Mammalian collagen has been widely used as a biomedical material. Nevertheless, there are still concerns about the variability between preparations, particularly with the possibility that the products may transmit animal-based diseases. Many groups have examined the possible application of bioengineered mammalian collagens. However, translating laboratory studies into large-scale manufacturing has often proved difficult, although certain yeast and plant systems seem effective. Production of full-length mammalian collagens, with the required secondary modification to give proline hydroxylation, has proved difficult in E. coli. However, recently, a new group of collagens, which have the characteristic triple helical structure of collagen, has been identified in bacteria. These proteins are stable without the need for hydroxyproline and are able to be produced and purified from E. coli in high yield. Initial studies indicate that they would be suitable for biomedical applications. <<<

The COVID-19 pandemic has emphasized the need for novel drug discovery process. However, the journey from conceptualizing a drug to its eventual implementation in clinical settings is a long, complex, and expensive process, with many potential points of failure. Over the past decade, a vast growth in medical information has coincided with advances in computational hardware (cloud computing, GPUs, and TPUs) and the rise of deep learning. Medical data generated from large molecular screening profiles, personal health or pathology records, and public health organizations could benefit from analysis by Artificial Intelligence (AI) approaches to speed up and prevent failures in the drug discovery pipeline. We present applications of AI at various stages of drug discovery pipelines, including the inherently computational approaches of design and prediction of a drug's likely properties. Open-source databases and AI-based software tools that facilitate drug design are discussed along with their associated problems of molecule representation, data collection, complexity, labeling, and disparities among labels. How contemporary AI methods, such as graph neural networks, reinforcement learning, and generated models, along with structure-based methods, (i.e., molecular dynamics simulations and molecular docking) can contribute to drug discovery applications and analysis of drug responses is also explored. Finally, recent developments and investments in AI-based start-up companies for biotechnology, drug design and their current progress, hopes and promotions are discussed in this article. <<<

Wenyi Yang, Pingping Wang, Meng Luo, Yideng Cai, Chang Xu, Guangfu Xue, Xiyun Jin, Rui Cheng, Jinhao Que, Fenglan Pang, Yuexin Yang, Huan Nie, Qinghua Jiang, Zhigang Liu, Zhaochun Xu <<<

MOTIVATION: Cell-cell interactions (CCIs) play critical roles in many biological processes such as cellular differentiation, tissue homeostasis, and immune response. With the rapid development of high throughput single-cell RNA sequencing (scRNA-seq) technologies, it is of high importance to identify CCIs from the ever-increasing scRNA-seq data. However, limited by the algorithmic constraints, current computational methods based on statistical strategies ignore some key latent information contained in scRNA-seq data with high sparsity and heterogeneity.RESULTS: Here, we developed a deep learning framework named DeepCCI to identify meaningful CCIs from scRNA-seq data. Applications of DeepCCI to a wide range of publicly available datasets from diverse technologies and platforms demonstrate its ability to predict significant CCIs accurately and effectively. Powered by the flexible and easy-to-use software, DeepCCI can provide the one-stop solution to discover meaningful intercellular interactions and build CCI networks from scRNA-seq data.AVAILABILITY AND IMPLEMENTATION: The source code of DeepCCI is available online at https://github.com/JiangBioLab/DeepCCI. <<<

Daniel Levine, Syed Asad Rizvi, Sacha Lévy, Nazreen Pallikkavaliyaveetil, Ruiming Wu, Zihe Zheng, Antonio Oliveira Fonseca, Xingyu Chen, Sina Ghadermarzi, Rahul M. Dhodapkar, David van Dijk <<<

AbstractLarge language models like GPT have shown impressive performance on natural language tasks. Here, we present a novel method to directly adapt these pretrained models to a biological context, specifically single-cell transcriptomics, by representing gene expression data as text. Our Cell2Sentence approach converts each cell’s gene expression profile into a sequence of gene names ordered by expression level. We show that these gene sequences, which we term “cell sentences”, can be used to fine-tune causal language models like GPT-2. Critically, we find that natural language pretraining boosts model performance on cell sentence tasks. When fine-tuned on cell sentences, GPT-2 generates biologically valid cells when prompted with a cell type. Conversely, it can also accurately predict cell type labels when prompted with cell sentences. This demonstrates that language models fine-tuned using Cell2Sentence can gain a biological understanding of single-cell data, while retaining their ability to generate text. Our approach provides a simple, adaptable framework to combine natural language and transcriptomics using existing models and libraries. Our code is available at:https://github.com/vandijklab/cell2sentence-ft. <<<

AbstractThe potential of engineered enzymes in practical applications is often constrained by limitations in their expression levels, thermal stability, and the diversity and magnitude of catalytic activities.De-novoenzyme design, though exciting, is challenged by the complex nature of enzymatic catalysis. An alternative promising approach involves expanding the capabilities of existing natural enzymes to enable functionality across new substrates and operational parameters. To this end we introduce CoSaNN (Conformation Sampling using Neural Network), a novel strategy for enzyme design that utilizes advances in deep learning for structure prediction and sequence optimization. By controlling enzyme conformations, we can expand the chemical space beyond the reach of simple mutagenesis. CoSaNN uses a context-dependent approach that accurately generates novel enzyme designs by considering non-linear relationships in both sequence and structure space. Additionally, we have further developed SolvIT, a graph neural network trained to predict protein solubility inE.Coli, as an additional optimization layer for producing highly expressed enzymes. Through this approach, we have engineered novel enzymes exhibiting superior expression levels, with 54% of our designs expressed in E.Coli, and increased thermal stability with more than 30% of our designs having a higher Tm than the template enzyme. Furthermore, our research underscores the transformative potential of AI in protein design, adeptly capturing high order interactions and preserving allosteric mechanisms in extensively modified enzymes. These advancements pave the way for the creation of diverse, functional, and robust enzymes, thereby opening new avenues for targeted biotechnological applications. <<<

Neurodegeneration is a phenomenon that occurs in the central nervous system through the hallmarks associating the loss of neuronal structure and function. Neurodegeneration is observed after viral insult and mostly in various so-called 'neurodegenerative diseases', generally observed in the elderly, such as Alzheimer's disease, multiple sclerosis, Parkinson's disease and amyotrophic lateral sclerosis that negatively affect mental and physical functioning. Causative agents of neurodegeneration have yet to be identified. However, recent data have identified the inflammatory process as being closely linked with multiple neurodegenerative pathways, which are associated with depression, a consequence of neurodegenerative disease. Accordingly, pro‑inflammatory cytokines are important in the pathophysiology of depression and dementia. These data suggest that the role of neuroinflammation in neurodegeneration must be fully elucidated, since pro‑inflammatory agents, which are the causative effects of neuroinflammation, occur widely, particularly in the elderly in whom inflammatory mechanisms are linked to the pathogenesis of functional and mental impairments. In this review, we investigated the role played by the inflammatory process in neurodegenerative diseases. <<<

Ramya Undamatla, Olayemi G Fagunloye, Jeffrey Chen, Lia R Edmunds, Anjana Murali, Amanda Mills, Bingxian Xie, Martha M Pangburn, Ian Sipula, Gregory Gibson, Claudette St Croix, Michael J Jurczak <<<

Nonalcoholic fatty liver disease (NAFLD) encompasses a spectrum of pathologies that includes steatosis, steatohepatitis (NASH) and fibrosis and is strongly associated with insulin resistance and type 2 diabetes. Changes in mitochondrial function are implicated in the pathogenesis of NAFLD, particularly in the transition from steatosis to NASH. Mitophagy is a mitochondrial quality control mechanism that allows for the selective removal of damaged mitochondria from the cell via the autophagy pathway. While past work demonstrated a negative association between liver fat content and rates of mitophagy, when changes in mitophagy occur during the pathogenesis of NAFLD and whether such changes contribute to the primary endpoints associated with the disease are currently poorly defined. We therefore undertook the studies described here to establish when alterations in mitophagy occur during the pathogenesis of NAFLD, as well as to determine the effects of genetic inhibition of mitophagy via conditional deletion of a key mitophagy regulator, PARKIN, on the development of steatosis, insulin resistance, inflammation and fibrosis. We find that loss of mitophagy occurs early in the pathogenesis of NAFLD and that loss of PARKIN hastens the onset but not severity of key NAFLD disease features. These observations suggest that loss of mitochondrial quality control in response to nutritional stress may contribute to mitochondrial dysfunction and the pathogenesis of NAFLD. <<<

Mingkun Lu , Jiayi Yin , Qi Zhu , Gaole Lin , Minjie Mou , Fuyao Liu , Ziqi Pan , Nanxin You , Xichen Lian , Fengcheng Li , Hongning Zhang , Lingyan Zheng , Wei Zhang , Hanyu Zhang , Zihao Shen , Zhen Gu , Honglin Li , Feng Zhu <<<

Drug discovery and development affects various aspects of human health and dramatically impacts the pharmaceutical market. However, investments in a new drug often go unrewarded due to the long and complex process of drug research and development (R&D). With the advancement of experimental technology and computer hardware, artificial intelligence (AI) has recently emerged as a leading tool in analyzing abundant and high-dimensional data. Explosive growth in the size of biomedical data provides advantages in applying AI in all stages of drug R&D. Driven by big data in biomedicine, AI has led to a revolution in drug R&D, due to its ability to discover new drugs more efficiently and at lower cost. This review begins with a brief overview of common AI models in the field of drug discovery; then, it summarizes and discusses in depth their specific applications in various stages of drug R&D, such as target discovery, drug discovery and design, preclinical research, automated drug synthesis, and influences in the pharmaceutical market. Finally, the major limitations of AI in drug R&D are fully discussed and possible solutions are proposed. <<<

Pablo Gainza, Sarah Wehrle, Alexandra Van Hall-Beauvais, Anthony Marchand, Andreas Scheck, Zander Harteveld, Stephen Buckley, Dongchun Ni, Shuguang Tan, Freyr Sverrisson, Casper Goverde, Priscilla Turelli, Charlène Raclot, Alexandra Teslenko, Martin Pacesa, Stéphane Rosset, Sandrine Georgeon, Jane Marsden, Aaron Petruzzella, Kefang Liu, Zepeng Xu, Yan Chai, Pu Han, George F Gao, Elisa Oricchio, Beat Fierz, Didier Trono, Henning Stahlberg, Michael Bronstein, Bruno E Correia <<<

Physical interactions between proteins are essential for most biological processes governing life. However, the molecular determinants of such interactions have been challenging to understand, even as genomic, proteomic and structural data increase. This knowledge gap has been a major obstacle for the comprehensive understanding of cellular protein-protein interaction networks and for the de novo design of protein binders that are crucial for synthetic biology and translational applications. Here we use a geometric deep-learning framework operating on protein surfaces that generates fingerprints to describe geometric and chemical features that are critical to drive protein-protein interactions. We hypothesized that these fingerprints capture the key aspects of molecular recognition that represent a new paradigm in the computational design of novel protein interactions. As a proof of principle, we computationally designed several de novo protein binders to engage four protein targets: SARS-CoV-2 spike, PD-1, PD-L1 and CTLA-4. Several designs were experimentally optimized, whereas others were generated purely in silico, reaching nanomolar affinity with structural and mutational characterization showing highly accurate predictions. Overall, our surface-centric approach captures the physical and chemical determinants of molecular recognition, enabling an approach for the de novo design of protein interactions and, more broadly, of artificial proteins with function. <<<