De novo design of protein interactions with learned surface fingerprints

Molecular surfaces modeling: Advancements in deep learning for molecular interactions and predictions

Molecular surface analysis can provide a high-dimensional, rich representation of molecular properties and interactions, which is crucial for enabling powerful predictive modeling and rational molecular design across diverse scientific and technological domains. With remarkable successes achieved by artificial intelligence (AI) in different fields such as computer vision and natural language processing, there is a growing imperative to harness AI's potential in accelerating molecular discovery and innovation. The integration of AI techniques with molecular surface analysis has opened up new frontiers, allowing researchers to uncover hidden patterns, relationships, and design principles that were previously elusive. By leveraging the complementary strengths of molecular surface representations and advanced AI algorithms, scientists can now explore chemical space more efficiently, optimize molecular properties with greater precision, and drive transformative advancements in areas like drug development, materials engineering, and catalysis. In this review, we aim to provide an overview of recent advancements in the field of molecular surface analysis and its integration with AI techniques. These AI-driven approaches have led to significant advancements in various downstream tasks, including interface site prediction, protein-protein interaction prediction, surface-centric molecular generation and design.

Hierarchical Engineering of Single-Crystalline Mesoporous Metal-Organic Frameworks with Hollow Structures

Although the superiority of hierarchical structure has driven extensive demand for applications, establishing hierarchy in a long-range-ordered single crystal remains a formidable challenge due to the inherent competition and contradiction between single crystallinity and controllable hierarchical structure. Herein, we demonstrate a growth and dissociation kinetics cooperative strategy for synthesizing a family of hollow single-crystalline mesoporous metal-organic frameworks (meso-MOFs) with hierarchical structures. The approach employs a dual-template method, integrating both hard and soft templates. By adjusting the HCl/CH3COOH ratio, the reaction system's pH can be tuned to regulate the dissociation kinetics of the acid-sensitive seeds serving as hard templates for the formation of hollow structure, while simultaneously modifying the concentration of the dual acids to control the growth kinetics of meso-MOF shells. The competition between maintaining a single crystallinity and achieving a well-defined hierarchical structure can be effectively balanced. Driven by the two interfacial kinetics, we successfully obtained the octahedral meso-MOF nanoparticles that not only exhibit a well-defined hollow structure with precisely controllable hollow size (∼81-1120 nm) and tunable wall thickness (∼28.6-61.3 nm) but also retain their single-crystal integrity. Specifically, the dissociation kinetics of seeds governed the formation of hollow structures, while the growth kinetics of single-crystalline meso-MOF shells ensured uniform coverage and structural integrity. Based on this strategy, we further developed a series of novel hollow meso-MOFs with hierarchical nanostructures, including hollow open-capsule meso-MOFs, 2D hollow meso-MOFs, hollow interlayer-structured meso-MOFs, macro-meso-micro trimodal porous MOFs, and so on.

Targeted protein degradation for cancer therapy

Targeted protein degradation (TPD) aims at reprogramming the target specificity of the ubiquitin-proteasome system, the major cellular protein disposal machinery, to induce selective ubiquitination and degradation of therapeutically relevant proteins. Since its conception over 20 years ago, TPD has gained a lot of attention mainly due to improvements in the design of bifunctional proteolysis targeting chimeras (PROTACs) and understanding the mechanisms underlying molecular glue degraders. Today, PROTACs are on the verge of a first clinical approval and recent structural and mechanistic insights combined with technological leaps promise to unlock the rational design of protein degraders, following the lead of lenalidomide and related clinically approved analogues. At the same time, the TPD universe is expanding at a record speed with the discovery of novel modalities beyond molecular glue degraders and PROTACs. Here we review the recent progress in the field, focusing on newly discovered degrader modalities, the current state of clinical degrader candidates for cancer therapy and upcoming design approaches.

The prediction of RNA-small molecule binding sites in RNA structures based on geometric deep learning

Biological interactions between RNA and small-molecule ligands play a crucial role in determining the specific functions of RNA, such as catalysis and folding, and are essential for guiding drug design in the medical field. Accurately predicting the binding sites of ligands within RNA structures is therefore of significant importance. To address this challenge, we introduced a computational approach named RLBSIF (RNA-Ligand Binding Surface Interaction Fingerprints) based on geometric deep learning. This model utilizes surface geometric features, including shape index and distance-dependent curvature, combined with chemical features represented by atomic charge, to comprehensively characterize RNA-ligand interactions through MaSIF-based surface interaction fingerprints. Additionally, we employ the ResNet18 network to analyze these fingerprints for identifying ligand binding pockets. Trained on 440 binding pockets, RLBSIF achieves an overall pocket-level classification accuracy of 90 %. Through a full-space enumeration method, it can predict binding sites at nucleotide resolution. In two independent tests, RLBSIF outperformed competing models, demonstrating its efficacy in accurately identifying binding sites within complex molecular structures. This method shows promise for drug design and biological product development, providing valuable insights into RNA-ligand interactions and facilitating the design of novel therapeutic interventions. For access to the related source code, please visit RLBSIF on GitHub (https://github.com/ZUSTSTTLAB/RLBSIF).

The prediction of RNA-small-molecule ligand binding affinity based on geometric deep learning

Small molecule-targeted RNA is an emerging technology that plays a pivotal role in drug discovery and inhibitor design, with widespread applications in disease treatment. Consequently, predicting RNA-small-molecule ligand interactions is crucial. With advancements in computer science and the availability of extensive biological data, deep learning methods have shown great promise in this area, particularly in efficiently predicting RNA-small molecule binding sites. However, few computational methods have been developed to predict RNA-small molecule binding affinities. Meanwhile, most of these approaches rely primarily on sequence or structural representations. Molecular surface information, vital for RNA and small molecule interactions, has been largely overlooked. To address these gaps, we propose a geometric deep learning method for predicting RNA-small molecule binding affinity, named RNA-ligand Surface Interaction Fingerprinting (RLASIF). In this study, we create RNA-ligand interaction fingerprints from the geometrical and chemical features present on molecular surface to characterize binding affinity. RLASIF outperformed other computational methods across ten different test sets from PDBbind NL2020. Compared to the second-best method, our approach improves performance by 10.01 %, 6.67 %, 2.01 % and 1.70 % on four evaluation metrics, indicating its effectiveness in capturing key features influencing RNA-ligand binding strength. Additionally, RLASIF holds potential for virtual screening of potential ligands for RNA and predicting small molecule binding nucleotides within RNA structures.

Targeting protein-ligand neosurfaces with a generalizable deep learning tool

Molecular recognition events between proteins drive biological processes in living systems1. However, higher levels of mechanistic regulation have emerged, in which protein-protein interactions are conditioned to small molecules2-5. Despite recent advances, computational tools for the design of new chemically induced protein interactions have remained a challenging task for the field6,7. Here we present a computational strategy for the design of proteins that target neosurfaces, that is, surfaces arising from protein-ligand complexes. To develop this strategy, we leveraged a geometric deep learning approach based on learned molecular surface representations8,9 and experimentally validated binders against three drug-bound protein complexes: Bcl2-venetoclax, DB3-progesterone and PDF1-actinonin. All binders demonstrated high affinities and accurate specificities, as assessed by mutational and structural characterization. Remarkably, surface fingerprints previously trained only on proteins could be applied to neosurfaces induced by interactions with small molecules, providing a powerful demonstration of generalizability that is uncommon in other deep learning approaches. We anticipate that such designed chemically induced protein interactions will have the potential to expand the sensing repertoire and the assembly of new synthetic pathways in engineered cells for innovative drug-controlled cell-based therapies10.

Atomically accurate de novo design of antibodies with RFdiffusion

Despite the central role that antibodies play in modern medicine, there is currently no method to design novel antibodies that bind a specific epitope entirely in silico. Instead, antibody discovery currently relies on animal immunization or random library screening approaches. Here, we demonstrate that combining computational protein design using a fine-tuned RFdiffusion network alongside yeast display screening enables the generation of antibody variable heavy chains (VHHs) and single chain variable fragments (scFvs) that bind user-specified epitopes with atomic-level precision. To verify this, we experimentally characterized VHH binders to four disease-relevant epitopes using multiple orthogonal biophysical methods, including cryo-EM, which confirmed the proper Ig fold and binding pose of designed VHHs targeting influenza hemagglutinin and Clostridium difficile toxin B (TcdB). For the influenza-targeting VHH, high-resolution structural data further confirmed the accuracy of CDR loop conformations. While initial computational designs exhibit modest affinity, affinity maturation using OrthoRep enables production of single-digit nanomolar binders that maintain the intended epitope selectivity. We further demonstrate the de novo design of single-chain variable fragments (scFvs), creating binders to TcdB and a Phox2b peptide-MHC complex by combining designed heavy and light chain CDRs. Cryo-EM structural data confirmed the proper Ig fold and binding pose for two distinct TcdB scFvs, with high-resolution data for one design additionally verifying the atomically accurate conformations of all six CDR loops. Our approach establishes a framework for the rational computational design, screening, isolation, and characterization of fully de novo antibodies with atomic-level precision in both structure and epitope targeting.

Bacterial network for precise plant stress detection and enhanced crop resilience

Understanding plant hormonal responses to stress and their transport dynamics remains challenging, limiting advancements in enhancing plant resilience. Our study presents a novel approach that utilizes genetically engineered bacteria (GEB) as molecular transceivers within plants, aiming to develop revolutionary agricultural biosensors. We focus on abscisic acid (ABA), a key hormone for plant growth and stress response. We propose using Escherichia coli (E. coli) engineered with PYR1-derived receptors that exhibit high affinity for ABA, triggering a bioluminescent response. Simulations investigate the detection time for ABA, bacterial diffusion within plant roots, advection effects through shoots, and chemotaxis in response to attractant gradients in leaves. Results indicate that higher ABA concentrations correlate with shorter response times, with an average of 431.52 s based on bioluminescence. The average internalization time for bacteria through a plant root area of 2 µm2 during the rhizophagy process is estimated at 1220.12 s. Simulations also assess bacterial movement through shoots, the impact of advection, and chemotactic responses. These findings highlight the complex interplay between plant signaling and microbial communities, validating the efficacy of our bacterial-based sensor approach and opening new avenues for agricultural biosensor technology.

Deep Learning for Predicting Biomolecular Binding Sites of Proteins

The rapid evolution of deep learning has markedly enhanced protein-biomolecule binding site prediction, offering insights essential for drug discovery, mutation analysis, and molecular biology. Advancements in both sequence-based and structure-based methods demonstrate their distinct strengths and limitations. Sequence-based approaches offer efficiency and adaptability, while structure-based techniques provide spatial precision but require high-quality structural data. Emerging trends in hybrid models that combine multimodal data, such as integrating sequence and structural information, along with innovations in geometric deep learning, present promising directions for improving prediction accuracy. This perspective summarizes challenges such as computational demands and dynamic modeling and proposes strategies for future research. The ultimate goal is the development of computationally efficient and flexible models capable of capturing the complexity of real-world biomolecular interactions, thereby broadening the scope and applicability of binding site predictions across a wide range of biomedical contexts.

Digital twins as global learning health and disease models for preventive and personalized medicine

Ineffective medication is a major healthcare problem causing significant patient suffering and economic costs. This issue stems from the complex nature of diseases, which involve altered interactions among thousands of genes across multiple cell types and organs. Disease progression can vary between patients and over time, influenced by genetic and environmental factors. To address this challenge, digital twins have emerged as a promising approach, which have led to international initiatives aiming at clinical implementations. Digital twins are virtual representations of health and disease processes that can integrate real-time data and simulations to predict, prevent, and personalize treatments. Early clinical applications of DTs have shown potential in areas like artificial organs, cancer, cardiology, and hospital workflow optimization. However, widespread implementation faces several challenges: (1) characterizing dynamic molecular changes across multiple biological scales; (2) developing computational methods to integrate data into DTs; (3) prioritizing disease mechanisms and therapeutic targets; (4) creating interoperable DT systems that can learn from each other; (5) designing user-friendly interfaces for patients and clinicians; (6) scaling DT technology globally for equitable healthcare access; (7) addressing ethical, regulatory, and financial considerations. Overcoming these hurdles could pave the way for more predictive, preventive, and personalized medicine, potentially transforming healthcare delivery and improving patient outcomes.

An outlook on structural biology after AlphaFold: tools, limits and perspectives

AlphaFold and similar groundbreaking, AI-based tools, have revolutionized the field of structural bioinformatics, with their remarkable accuracy in ab-initio protein structure prediction. This success has catalyzed the development of new software and pipelines aimed at incorporating AlphaFold's predictions, often focusing on addressing the algorithm's remaining challenges. Here, we present the current landscape of structural bioinformatics shaped by AlphaFold, and discuss how the field is dynamically responding to this revolution, with new software, methods, and pipelines. While the excitement around AI-based tools led to their widespread application, it is essential to acknowledge that their practical success hinges on their integration into established protocols within structural bioinformatics, often neglected in the context of AI-driven advancements. Indeed, user-driven intervention is still as pivotal in the structure prediction process as in complementing state-of-the-art algorithms with functional and biological knowledge.

Data and AI-driven synthetic binding protein discovery

Synthetic binding proteins (SBPs) are a class of protein binders that are artificially created and do not exist naturally. Their broad applications in tackling challenges of research, diagnostics, and therapeutics have garnered significant interest. Traditional protein engineering is pivotal to the discovery of SBPs. Recently, this discovery has been significantly accelerated by computational approaches, such as molecular modeling and artificial intelligence (AI). Furthermore, while numerous bioinformatics databases offer a wealth of resources that fuel SBP discovery, the full potential of these data has not yet been fully exploited. In this review, we present a comprehensive overview of SBP data ecosystem and methodologies in SBP discovery, highlighting the critical role of high-quality data and AI technologies in accelerating the discovery of innovative SBPs with promising applications in pharmacological sciences.

PepFuNN: Novo Nordisk Open-Source Toolkit to Enable Peptide in Silico Analysis

We present PepFuNN, a new open-source version of the PepFun package with functions to study the chemical space of peptide libraries and perform structure-activity relationship analyses. PepFuNN is a Python package comprising five modules to study peptides with natural amino acids and, in some cases, sequences with non-natural amino acids based on the availability of a public monomer dictionary. The modules allow calculating physicochemical properties, performing similarity analysis using different peptide representations, clustering peptides using molecular fingerprints or calculated descriptors, designing peptide libraries based on specific requirements, and a module dedicated to extracting matched pairs from experimental campaigns to guide the selection of the most relevant mutations in design new rounds. The code and tutorials are available at https://github.com/novonordisk-research/pepfunn.

SurfDock is a surface-informed diffusion generative model for reliable and accurate protein-ligand complex prediction

Accurately predicting protein-ligand interactions is crucial for understanding cellular processes. We introduce SurfDock, a deep-learning method that addresses this challenge by integrating protein sequence, three-dimensional structural graphs and surface-level features into an equivariant architecture. SurfDock employs a generative diffusion model on a non-Euclidean manifold, optimizing molecular translations, rotations and torsions to generate reliable binding poses. Our extensive evaluations across various benchmarks demonstrate SurfDock's superiority over existing methods in docking success rates and adherence to physical constraints. It also exhibits remarkable generalizability to unseen proteins and predicted apo structures, while achieving state-of-the-art performance in virtual screening tasks. In a real-world application, SurfDock identified seven novel hit molecules in a virtual screening project targeting aldehyde dehydrogenase 1B1, a key enzyme in cellular metabolism. This showcases SurfDock's ability to elucidate molecular mechanisms underlying cellular processes. These results highlight SurfDock's potential as a transformative tool in structural biology, offering enhanced accuracy, physical plausibility and practical applicability in understanding protein-ligand interactions.

De novo design of peptide binders to conformationally diverse targets with contrastive language modeling

Designing binders to target undruggable proteins presents a formidable challenge in drug discovery. In this work, we provide an algorithmic framework to design short, target-binding linear peptides, requiring only the amino acid sequence of the target protein. To do this, we propose a process to generate naturalistic peptide candidates through Gaussian perturbation of the peptidic latent space of the ESM-2 protein language model and subsequently screen these novel sequences for target-selective interaction activity via a contrastive language-image pretraining (CLIP)-based contrastive learning architecture. By integrating these generative and discriminative steps, we create a Peptide Prioritization via CLIP (PepPrCLIP) pipeline and validate highly ranked, target-specific peptides experimentally, both as inhibitory peptides and as fusions to E3 ubiquitin ligase domains. PepPrCLIP-derived constructs demonstrate functionally potent binding and degradation of conformationally diverse, disease-driving targets in vitro. In total, PepPrCLIP empowers the modulation of previously inaccessible proteins without reliance on stable and ordered tertiary structures.

SYNBIP 2.0: epitopes mapping, sequence expansion and scaffolds discovery for synthetic binding protein innovation

Synthetic binding proteins (SBPs) represent a pivotal class of artificially engineered proteins, meticulously crafted to exhibit targeted binding properties and specific functions. Here, the SYNBIP database, a comprehensive resource for SBPs, has been significantly updated. These enhancements include (i) featuring 3D structures of 899 SBP-target complexes to illustrate the binding epitopes of SBPs, (ii) using the structures of SBPs in the monomer or complex forms with target proteins, their sequence space has been expanded five times to 12 025 by integrating a structure-based protein generation framework and a protein property prediction tool, (iii) offering detailed information on 78 473 newly identified SBP-like scaffolds from the RCSB Protein Data Bank, and an additional 16 401 555 ones from the AlphaFold Protein Structure Database, and (iv) the database is regularly updated, incorporating 153 new SBPs. Furthermore, the structural models of all SBPs have been enhanced through the application of the AlphaFold2, with their clinical statuses concurrently refreshed. Additionally, the design methods employed for each SBP are now prominently featured in the database. In sum, SYNBIP 2.0 is designed to provide researchers with essential SBP data, facilitating their innovation in research, diagnosis and therapy. SYNBIP 2.0 is now freely accessible at https://idrblab.org/synbip/.

Computational Approaches for Antimicrobial Peptide Delivery

Peptides constitute alternative molecules for the treatment of infections caused by bacteria, viruses, fungi, and protozoa. However, their therapeutic effectiveness is often limited by enzymatic degradation, chemical and physical instability, and toxicity toward healthy human cells. To improve their pharmacokinetic (PK) and pharmacodynamic (PD) profiles, novel routes of administration are being explored. Among these, nanoparticles have shown promise as potential carriers for peptides, although the design of delivery vehicles remains a slow and painstaking process, heavily reliant on trial and error. Recently, computational approaches have been introduced to accelerate the development of effective drug delivery systems for peptides. Here we present an overview of some of these computational strategies and discuss their potential to optimize drug development and delivery.

Target-conditioned diffusion generates potent TNFR superfamily antagonists and agonists

Despite progress in designing protein-binding proteins, the shape matching of designs to targets is lower than in many native protein complexes, and design efforts have failed for the tumor necrosis factor receptor 1 (TNFR1) and other protein targets with relatively flat and polar surfaces. We hypothesized that free diffusion from random noise could generate shape-matched binders for challenging targets and tested this approach on TNFR1. We obtain designs with low picomolar affinity whose specificity can be completely switched to other family members using partial diffusion. Designs function as antagonists or as superagonists when presented at higher valency for OX40 and 4-1BB. The ability to design high-affinity and high-specificity antagonists and agonists for pharmacologically important targets in silico presages a coming era in protein design in which binders are made by computation rather than immunization or random screening approaches.

Mass spectrometry-complemented molecular modeling predicts the interaction interface for a camelid single-domain antibody targeting the Plasmodium falciparum circumsporozoite protein's C-terminal domain

Background

Bioanalytical methods that enable rapid and high-detail characterization of binding specificities and strengths of protein complexes with low sample consumption are highly desired. The interaction between a camelid single domain antibody (sdAbCSP1) and its target antigen (PfCSP-Cext) was selected as a model system to provide proof-of-principle for the here described methodology.

Research design and methods

The structure of the sdAbCSP1 - PfCSP-Cext complex was modeled using AlphaFold2. The recombinantly expressed proteins, sdAbCSP1, PfCSP-Cext, and the sdAbCSP1 - PfCSP-Cext complex, were subjected to limited proteolysis and mass spectrometric peptide analysis. ITEM MS (Intact Transition Epitope Mapping Mass Spectrometry) and ITC (Isothermal Titration Calorimetry) were applied to determine stoichiometry and binding strength.

Results

The paratope of sdAbCSP1 mainly consists of its CDR3 (aa100-118). PfCSP-Cext's epitope is assembled from its α-helix (aa40-52) and opposing loop (aa83-90). PfCSP-Cext's GluC cleavage sites E46 and E58 were shielded by complex formation, confirming the predicted epitope. Likewise, sdAbCSP1's tryptic cleavage sites R105 and R108 were shielded by complex formation, confirming the predicted paratope. ITEM MS determined the 1:1 stoichiometry and the high complex binding strength, exemplified by the gas phase dissociation reaction enthalpy of 50.2 kJ/mol. The in-solution complex dissociation constant is 5 × 10-10 M.

Conclusions

Combining AlphaFold2 modeling with mass spectrometry/limited proteolysis generated a trustworthy model for the sdAbCSP1 - PfCSP-Cext complex interaction interface.

sesA: A Program for the Analytic Computation of Solvent-Excluded Surface Areas

The surface area of a molecule, an inherent geometric property of its structure, plays important roles in its solvation and functioning. Here we present an accurate and robust program, sesA, for the analytic computation of solvent-excluded surface (SES) areas. The accuracy and robustness are achieved through the analytic computations of all the solvent-accessible surface (SAS) regions for a surface atom and probe-probe intersections. The detailed comparisons of the areas for a large set of protein structures by sesA and msms, a de-facto standard for analytic SAS and SES computations, confirm sesA's accuracy to a good extent and in the same time reveal significant differences between them. The unprecedented accuracy and robustness of sesA make it possible to analyze in great detail the surface areas of any molecules in general and biomolecules in particular.

Nanocarriers for intracellular delivery of proteins in biomedical applications: strategies and recent advances

Protein drugs are of great importance in maintaining the normal functioning of living organisms. Indeed, they have been instrumental in combating tumors and genetic diseases for decades. Among these pharmaceutical agents, those that target intracellular components necessitate the use of therapeutic proteins to exert their effects within the targeted cells. However, the use of protein drugs is limited by their short half-life and potential adverse effects in the physiological environment. The advent of nanoparticles offers a promising avenue for prolonging the half-life of protein drugs. This is achieved by encapsulating proteins, thereby safeguarding their biological activity and ensuring precise delivery into cells. This nanomaterial-based intracellular protein drug delivery system mitigates the rapid hydrolysis and unwarranted diffusion of proteins, thereby minimizing potential side effects and circumventing the limitations inherent in traditional techniques like electroporation. This review examines established protein drug delivery systems, including those based on polymers, liposomes, and protein nanoparticles. We delve into the operational principles and transport mechanisms of nanocarriers, discussing the various considerations essential for designing cutting-edge delivery platforms. Additionally, we investigate innovative designs and applications of traditional cytosolic protein delivery systems in medical research and clinical practice, particularly in areas like tumor treatment, gene editing and fluorescence imaging. This review sheds light on the current restrictions of protein delivery systems and anticipates future research avenues, aiming to foster the continued advancement in this field.

Facilitating and restraining virus infection using cell-attachable soluble viral receptors

SARS-CoV-2 uses the receptor binding domain (RBD) of its spike protein to recognize and infect host cells by binding to the cell surface receptor angiotensin converting enzyme 2 (ACE2). The ACE2 receptor is composed of peptidase domain (PD), collectrin-like domain, transmembrane domain, and short cytoplasmic domain, and may exist as a dimer on cell surface. The RBD binding site is located atop of the ACE2 PD, but the involvement of other domains in virus infection is uncertain. We found that the ACE2 PD alone, whether anchored to cell membrane via a glycosylphosphatidylinositol anchor or attached to another surface protein, is fully functional as a receptor for spike-mediated cell fusion and virus infection. However, for ACE2 to function as the viral receptor, the RBD binding site must be positioned in close proximity to the cell membrane. Elevating the surface height of ACE2 using long and rigid protein spacers reduces or eliminates cell fusion and virus infection. Moreover, we found that the RBD-targeting neutralizing antibodies, nanobodies, and de novo designed miniprotein binders, when present on cell surface, also act as viral receptors, facilitating cell fusion and virus infection. Our data demonstrate that RBD binding and close membrane proximity are essential properties for a receptor to effectively mediate SARS-CoV-2 infection. Importantly, we show that soluble RBD-binders can be engineered to make cells either susceptible or resistant to virus infection, which has significant implications for antiviral therapy and various virus-mediated applications.

De novo protein design with a denoising diffusion network independent of pretrained structure prediction models

The recent success of RFdiffusion, a method for protein structure design with a denoising diffusion probabilistic model, has relied on fine-tuning the RoseTTAFold structure prediction network for protein backbone denoising. Here, we introduce SCUBA-diffusion (SCUBA-D), a protein backbone denoising diffusion probabilistic model freshly trained by considering co-diffusion of sequence representation to enhance model regularization and adversarial losses to minimize data-out-of-distribution errors. While matching the performance of the pretrained RoseTTAFold-based RFdiffusion in generating experimentally realizable protein structures, SCUBA-D readily generates protein structures with not-yet-observed overall folds that are different from those predictable with RoseTTAFold. The accuracy of SCUBA-D was confirmed by the X-ray structures of 16 designed proteins and a protein complex, and by experiments validating designed heme-binding proteins and Ras-binding proteins. Our work shows that deep generative models of images or texts can be fruitfully extended to complex physical objects like protein structures by addressing outstanding issues such as the data-out-of-distribution errors.

The Nobel Prize in Chemistry: past, present, and future of AI in biology

A Comment on the transformative progress of artificial intelligence for structural and protein biology, referencing the 2024 Nobel Prize in Chemistry.

Applying Spatiotemporal Modeling of Cell Dynamics to Accelerate Drug Development

Cells act as physical computational programs that utilize input signals to orchestrate molecule-level protein-protein interactions (PPIs), generating and responding to forces, ultimately shaping all of the physiological and pathophysiological behaviors. Genome editing and molecule drugs targeting PPIs hold great promise for the treatments of diseases. Linking genes and molecular drugs with protein-performed cellular behaviors is a key yet challenging issue due to the wide range of spatial and temporal scales involved. Building predictive spatiotemporal modeling systems that can describe the dynamic behaviors of cells intervened by genome editing and molecular drugs at the intersection of biology, chemistry, physics, and computer science will greatly accelerate pharmaceutical advances. Here, we review the mechanical roles of cytoskeletal proteins in orchestrating cellular behaviors alongside significant advancements in biophysical modeling while also addressing the limitations in these models. Then, by integrating generative artificial intelligence (AI) with spatiotemporal multiscale biophysical modeling, we propose a computational pipeline for developing virtual cells, which can simulate and evaluate the therapeutic effects of drugs and genome editing technologies on various cell dynamic behaviors and could have broad biomedical applications. Such virtual cell modeling systems might revolutionize modern biomedical engineering by moving most of the painstaking wet-laboratory effort to computer simulations, substantially saving time and alleviating the financial burden for pharmaceutical industries.

Revolutionizing Molecular Design for Innovative Therapeutic Applications through Artificial Intelligence

The field of computational protein engineering has been transformed by recent advancements in machine learning, artificial intelligence, and molecular modeling, enabling the design of proteins with unprecedented precision and functionality. Computational methods now play a crucial role in enhancing the stability, activity, and specificity of proteins for diverse applications in biotechnology and medicine. Techniques such as deep learning, reinforcement learning, and transfer learning have dramatically improved protein structure prediction, optimization of binding affinities, and enzyme design. These innovations have streamlined the process of protein engineering by allowing the rapid generation of targeted libraries, reducing experimental sampling, and enabling the rational design of proteins with tailored properties. Furthermore, the integration of computational approaches with high-throughput experimental techniques has facilitated the development of multifunctional proteins and novel therapeutics. However, challenges remain in bridging the gap between computational predictions and experimental validation and in addressing ethical concerns related to AI-driven protein design. This review provides a comprehensive overview of the current state and future directions of computational methods in protein engineering, emphasizing their transformative potential in creating next-generation biologics and advancing synthetic biology.

IEV2Mol: Molecular Generative Model Considering Protein-Ligand Interaction Energy Vectors

Generating drug candidates with desired protein-ligand interactions is a significant challenge in structure-based drug design. In this study, a new generative model, IEV2Mol, is proposed that incorporates interaction energy vectors (IEVs) between proteins and ligands obtained from docking simulations, which quantitatively capture the strength of each interaction type, such as hydrogen bonds, electrostatic interactions, and van der Waals forces. By integrating this IEV into an end-to-end variational autoencoder (VAE) framework that learns the chemical space from SMILES and minimizes the reconstruction error of the SMILES, the model can more accurately generate compounds with the desired interactions. To evaluate the effectiveness of IEV2Mol, we performed benchmark comparisons with randomly selected compounds, unconstrained VAE models (JT-VAE), and compounds generated by RNN models based on interaction fingerprints (IFP-RNN). The results show that the compounds generated by IEV2Mol retain a significantly greater percentage of the binding mode of the query structure than those of the other methods. Furthermore, IEV2Mol was able to generate compounds with interactions similar to those of the input compounds, regardless of structural similarity. The source code and trained models for IEV2Mol, JT-VAE, and IFP-RNN designed for generating compounds active against the DRD2, AA2AR, and AKT1, as well as the data sets (DM-QP-1M, active compounds to each protein, and ChEMBL33) utilized in this study, are released under the MIT License and available at https://github.com/sekijima-lab/IEV2Mol.

NeoaPred: a deep-learning framework for predicting immunogenic neoantigen based on surface and structural features of peptide-human leukocyte antigen complexes

MOTIVATION

Neoantigens, derived from somatic mutations in cancer cells, can elicit anti-tumor immune responses when presented to autologous T cells by human leukocyte antigen. Identifying immunogenic neoantigens is crucial for cancer immunotherapy development. However, the accuracy of current bioinformatic methods remains unsatisfactory. Surface and structural features of peptide-HLA class I (pHLA-I) complexes offer valuable insight into the immunogenicity of neoantigens.

RESULTS

We present NeoaPred, a deep-learning framework for neoantigen prediction. NeoaPred accurately constructs pHLA-I complex structures, with 82.37% of the predicted structures showing an RMSD of < 1 Å. Using these structures, NeoaPred integrates differences in surface, structural, and atom group features between the mutant peptide and its wild-type counterpart to predict a foreignness score. This foreignness score is an effective factor for neoantigen prediction, achieving an AUROC (Area Under the Receiver Operating Characteristic Curve) of 0.81 and an AUPRC (Area Under the Precision-Recall Curve) of 0.54 in the test set, outperforming existing methods.

AVAILABILITY AND IMPLEMENTATION

The source code is released under an Apache v2.0 license and is available at the GitHub repository (https://github.com/Dulab2020/NeoaPred).

Comprehensive assessment of TECENTRIQ® and OPDIVO®: analyzing immunotherapy indications withdrawn in triple-negative breast cancer and hepatocellular carcinoma

Atezolizumab (TECENTRIQ®) and nivolumab (OPDIVO®) are both immunotherapeutic indications targeting programmed cell death 1 ligand 1 (PD-L1) and programmed cell death 1 (PD-1), respectively. These inhibitors hold promise as therapies for triple-negative breast cancer (TNBC) and hepatocellular carcinoma (HCC) and have demonstrated encouraging results in reducing the progression and spread of tumors. However, due to their adverse effects and low response rates, the US Food and Drug Administration (FDA) has withdrawn the approval of atezolizumab in TNBC and nivolumab in HCC treatment. The withdrawals of atezolizumab and nivolumab have raised concerns regarding their effectiveness and the ability to predict treatment responses. Therefore, the current study aims to investigate the immunotherapy withdrawal of PD-1/PD-L1 inhibitors, specifically atezolizumab for TNBC and nivolumab for HCC. This study will examine both the structural and clinical aspects. This review provides detailed insights into the structure of the PD-1 receptor and its ligands, the interactions between PD-1 and PD-L1, and their interactions with the withdrawn antibodies (atezolizumab and nivolumab) as well as PD-1 and PD-L1 modifications. In addition, this review further assesses these antibodies in the context of TNBC and HCC. It seeks to elucidate the factors that contribute to diverse responses to PD-1/PD-L1 therapy in different types of cancer and propose approaches for predicting responses, mitigating the potential risks linked to therapy withdrawals, and optimizing patient outcomes. By better understanding the mechanisms underlying responses to PD-1/PD-L1 therapy and developing strategies to predict these responses, it is possible to create more efficient treatments for TNBC and HCC.

De novo design of mini-binder proteins against IL-2 receptor β chain

IL-2 regulates the immune response by interacting with different IL-2 receptor (IL-2R) subunits. High dose of IL-2 binds to IL-2Rβγc heterodimer, which induce various side effects while activating immune function. Disrupting IL-2 and IL-2R interactions can block IL-2 mediated immune response. Here, we used a computational approach to de novo design mini-binder proteins against IL-2R β chain (IL-2Rβ) to block IL-2 signaling. The hydrophobic region where IL-2 binds to IL-2Rβ was selected and the promising binding mode was broadly explored. Three mini-binders with amino acid numbers ranging from 55 to 65 were obtained and binder 1 showed the best effects in inhibiting CTLL-2 cells proliferation and STAT5 phosphorylation. Molecular dynamics simulation showed that the binding of binder 1 to IL-2Rβ was stable; the free energy of binder1/IL-2Rβ complex was lower, indicating that the affinity of binder 1 to IL-2Rβ was higher than that of IL-2. Free energy decomposition suggested that the ARG35 and ARG131 of IL-2Rβ might be the key to improve the affinity of binder. Our efforts provided new insights in developing of IL-2R blocker, offering a potential strategy for ameliorating the side effects of IL-2 treatment.

BDM: An Assessment Metric for Protein Complex Structure Models Based on Distance Difference Matrix

Protein complex structure prediction is an important problem in computational biology. While significant progress has been made for protein monomers, accurate evaluation of protein complexes remains challenging. Existing assessment methods in CASP, lack dedicated metrics for evaluating complexes. DockQ, a widely used metric, has some limitations. In this study, we propose a novel metric called BDM (Based on Distance difference Matrix) for assessing protein complex prediction structures. Our approach utilizes a distance difference matrix derived from comparing real and predicted protein structures, establishing a linear correlation with Root Mean Square Deviation (RMSD). BDM overcomes limitations associated with receptor-ligand differentiation and eliminates the requirement for structure alignment, making it a more effective and efficient metric. Evaluation of BDM using CASP14 and CASP15 test sets demonstrates superior performance compared to the official CASP scoring. BDM provides accurate and reasonable assessments of predicted protein complexes, wide adoption of BDM has the potential to advance protein complex structure prediction and facilitate related researches across scientific domains. Code is available at http://mialab.ruc.edu.cn/BDMServer/ .

PPInterface: A Comprehensive Dataset of 3D Protein-Protein Interface Structures

The PPInterface dataset contains 815,082 interface structures, providing the most comprehensive structural information on protein-protein interfaces. This resource is extracted from over 215,000 three-dimensional protein structures stored in the Protein Data Bank (PDB). The dataset contains a wide range of protein complexes, providing a wealth of information for researchers investigating the structural properties of protein-protein interactions. The accompanying web server has a user-friendly interface that allows for efficient search and download functions. Researchers can access detailed information on protein interface structures, visualize them, and explore a variety of features, increasing the dataset's utility and accessibility. The dataset and web server can be found at https://3dpath.ku.edu.tr/PPInt/.

De novo-designed minibinders expand the synthetic biology sensing repertoire

Synthetic and chimeric receptors capable of recognizing and responding to user-defined antigens have enabled "smart" therapeutics based on engineered cells. These cell engineering tools depend on antigen sensors which are most often derived from antibodies. Advances in the de novo design of proteins have enabled the design of protein binders with the potential to target epitopes with unique properties and faster production timelines compared to antibodies. Building upon our previous work combining a de novo-designed minibinder of the Spike protein of SARS-CoV-2 with the synthetic receptor synNotch (SARSNotch), we investigated whether minibinders can be readily adapted to a diversity of cell engineering tools. We show that the Spike minibinder LCB1 easily generalizes to a next-generation proteolytic receptor SNIPR that performs similarly to our previously reported SARSNotch. LCB1-SNIPR successfully enables the detection of live SARS-CoV-2, an improvement over SARSNotch which can only detect cell-expressed Spike. To test the generalizability of minibinders to diverse applications, we tested LCB1 as an antigen sensor for a chimeric antigen receptor (CAR). LCB1-CAR enabled CD8+ T cells to cytotoxically target Spike-expressing cells. We further demonstrate that two other minibinders directed against the clinically relevant epidermal growth factor receptor are able to drive CAR-dependent cytotoxicity with efficacy similar to or better than an existing antibody-based CAR. Our findings suggest that minibinders represent a novel class of antigen sensors that have the potential to dramatically expand the sensing repertoire of cell engineering tools.

Annexin A1 binds PDZ and LIM domain 7 to inhibit adipogenesis and prevent obesity

Obesity is a global issue that warrants the identification of more effective therapeutic targets and a better understanding of the pivotal molecular pathogenesis. Annexin A1 (ANXA1) is known to inhibit phospholipase A2, exhibiting anti-inflammatory activity. However, the specific effects of ANXA1 in obesity and the underlying mechanisms of action remain unclear. Our study reveals that ANXA1 levels are elevated in the adipose tissue of individuals with obesity. Whole-body or adipocyte-specific ANXA1 deletion aggravates obesity and metabolic disorders. ANXA1 levels are higher in stromal vascular fractions (SVFs) than in mature adipocytes. Further investigation into the role of ANXA1 in SVFs reveals that ANXA1 overexpression induces lower numbers of mature adipocytes, while ANXA1-knockout SVFs exhibit the opposite effect. This suggests that ANXA1 plays an important role in adipogenesis. Mechanistically, ANXA1 competes with MYC binding protein 2 (MYCBP2) for interaction with PDZ and LIM domain 7 (PDLIM7). This exposes the MYCBP2-binding site, allowing it to bind more readily to the SMAD family member 4 (SMAD4) and promoting its ubiquitination and degradation. SMAD4 degradation downregulates peroxisome proliferator-activated receptor gamma (PPARγ) transcription and reduces adipogenesis. Treatment with Ac2-26, an active peptide derived from ANXA1, inhibits both adipogenesis and obesity through the mechanism. In conclusion, the molecular mechanism of ANXA1 inhibiting adipogenesis was first uncovered in our study, which is a potential target for obesity prevention and treatment.

Current and future directions in network biology

Summary

Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology, focusing on molecular/cellular networks but also on other biological network types such as biomedical knowledge graphs, patient similarity networks, brain networks, and social/contact networks relevant to disease spread. In more detail, we highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on future directions of network biology. Additionally, we discuss scientific communities, educational initiatives, and the importance of fostering diversity within the field. This article establishes a roadmap for an immediate and long-term vision for network biology.

Availability and implementation

Not applicable.

Adsorption-Driven Deformation and Footprints of the RBD Proteins in SARS-CoV-2 Variants on Biological and Inanimate Surfaces

Respiratory viruses, carried through airborne microdroplets, frequently adhere to surfaces, including plastics and metals. However, our understanding of the interactions between viruses and materials remains limited, particularly in scenarios involving polarizable surfaces. Here, we investigate the role of the receptor-binding domain (RBD) of the spike protein mutations on the adsorption of SARS-CoV-2 to hydrophobic and hydrophilic surfaces employing molecular simulations. To contextualize our findings, we contrast the interactions on inanimate surfaces with those on native biological interfaces, specifically the angiotensin-converting enzyme 2. Notably, we identify a 2-fold increase in structural deformations for the protein's receptor binding motif (RBM) onto inanimate surfaces, indicative of enhanced shock-absorbing mechanisms. Furthermore, the distribution of adsorbed amino acids (landing footprints) on the inanimate surface reveals a distinct regional asymmetry relative to the biological interface, with roughly half of the adsorbed amino acids arranged in opposite sites. In spite of the H-bonds formed at the hydrophilic substrate, the simulations consistently show a higher number of contacts and interfacial area with the hydrophobic surface, where the wild-type RBD adsorbs more strongly than the Delta or Omicron RBDs. In contrast, the adsorption of Delta and Omicron to hydrophilic surfaces was characterized by a distinctive hopping-pattern. The novel shock-absorbing mechanisms identified in the virus adsorption on inanimate surfaces show the embedded high-deformation capacity of the RBD without losing its secondary structure, which could lead to current experimental strategies in the design of virucidal surfaces.

PepMLM: Target Sequence-Conditioned Generation of Therapeutic Peptide Binders via Span Masked Language Modeling

Target proteins that lack accessible binding pockets and conformational stability have posed increasing challenges for drug development. Induced proximity strategies, such as PROTACs and molecular glues, have thus gained attention as pharmacological alternatives, but still require small molecule docking at binding pockets for targeted protein degradation. The computational design of protein-based binders presents unique opportunities to access "undruggable" targets, but have often relied on stable 3D structures or structure-influenced latent spaces for effective binder generation. In this work, we introduce PepMLM, a target sequence-conditioned generator of de novo linear peptide binders. By employing a novel span masking strategy that uniquely positions cognate peptide sequences at the C-terminus of target protein sequences, PepMLM fine-tunes the state-of-the-art ESM-2 pLM to fully reconstruct the binder region, achieving low perplexities matching or improving upon validated peptide-protein sequence pairs. After successful in silico benchmarking with AlphaFold-Multimer, outperforming RFDiffusion on structured targets, we experimentally verify PepMLM's efficacy via fusion of model-derived peptides to E3 ubiquitin ligase domains, demonstrating endogenous degradation of emergent viral phosphoproteins and Huntington's disease-driving proteins. In total, PepMLM enables the generative design of candidate binders to any target protein, without the requirement of target structure, empowering downstream therapeutic applications.

Contextual AI models for single-cell protein biology

Understanding protein function and developing molecular therapies require deciphering the cell types in which proteins act as well as the interactions between proteins. However, modeling protein interactions across biological contexts remains challenging for existing algorithms. Here we introduce PINNACLE, a geometric deep learning approach that generates context-aware protein representations. Leveraging a multiorgan single-cell atlas, PINNACLE learns on contextualized protein interaction networks to produce 394,760 protein representations from 156 cell type contexts across 24 tissues. PINNACLE's embedding space reflects cellular and tissue organization, enabling zero-shot retrieval of the tissue hierarchy. Pretrained protein representations can be adapted for downstream tasks: enhancing 3D structure-based representations for resolving immuno-oncological protein interactions, and investigating drugs' effects across cell types. PINNACLE outperforms state-of-the-art models in nominating therapeutic targets for rheumatoid arthritis and inflammatory bowel diseases and pinpoints cell type contexts with higher predictive capability than context-free models. PINNACLE's ability to adjust its outputs on the basis of the context in which it operates paves the way for large-scale context-specific predictions in biology.

Opportunities and challenges in design and optimization of protein function

The field of protein design has made remarkable progress over the past decade. Historically, the low reliability of purely structure-based design methods limited their application, but recent strategies that combine structure-based and sequence-based calculations, as well as machine learning tools, have dramatically improved protein engineering and design. In this Review, we discuss how these methods have enabled the design of increasingly complex structures and therapeutically relevant activities. Additionally, protein optimization methods have improved the stability and activity of complex eukaryotic proteins. Thanks to their increased reliability, computational design methods have been applied to improve therapeutics and enzymes for green chemistry and have generated vaccine antigens, antivirals and drug-delivery nano-vehicles. Moreover, the high success of design methods reflects an increased understanding of basic rules that govern the relationships among protein sequence, structure and function. However, de novo design is still limited mostly to α-helix bundles, restricting its potential to generate sophisticated enzymes and diverse protein and small-molecule binders. Designing complex protein structures is a challenging but necessary next step if we are to realize our objective of generating new-to-nature activities.

Computational tools for plant genomics and breeding

Plant genomics and crop breeding are at the intersection of biotechnology and information technology. Driven by a combination of high-throughput sequencing, molecular biology and data science, great advances have been made in omics technologies at every step along the central dogma, especially in genome assembling, genome annotation, epigenomic profiling, and transcriptome profiling. These advances further revolutionized three directions of development. One is genetic dissection of complex traits in crops, along with genomic prediction and selection. The second is comparative genomics and evolution, which open up new opportunities to depict the evolutionary constraints of biological sequences for deleterious variant discovery. The third direction is the development of deep learning approaches for the rational design of biological sequences, especially proteins, for synthetic biology. All three directions of development serve as the foundation for a new era of crop breeding where agronomic traits are enhanced by genome design.

Starting with screening strains to construct synthetic microbial communities (SynComs) for traditional food fermentation

With the elucidation of community structures and assembly mechanisms in various fermented foods, core communities that significantly influence or guide fermentation have been pinpointed and used for exogenous restructuring into synthetic microbial communities (SynComs). These SynComs simulate ecological systems or function as adjuncts or substitutes in starters, and their efficacy has been widely verified. However, screening and assembly are still the main limiting factors for implementing theoretic SynComs, as desired strains cannot be effectively obtained and integrated. To expand strain screening methods suitable for SynComs in food fermentation, this review summarizes the recent research trends in using SynComs to study community evolution or interaction and improve the quality of food fermentation, as well as the specific process of constructing synthetic communities. The potential for novel screening modalities based on genes, enzymes and metabolites in food microbial screening is discussed, along with the emphasis on strategies to optimize assembly for facilitating the development of synthetic communities.

A Synthetic Multivalent Lipopeptide Derived from Pam3CSK4 with Irreversible Influenza Inhibition and Immuno-Stimulating Effects

The activation of the host adaptive immune system is crucial for eliminating viruses. However, influenza infection often suppresses the innate immune response that precedes adaptive immunity, and the adaptive immune responses are typically delayed. Dendritic cells, serving as professional antigen-presenting cells, have a vital role in initiating the adaptive immune response. In this study, an immuno-stimulating antiviral system (ISAS) is introduced, which is composed of the immuno-stimulating adjuvant lipopeptide Pam3CSK4 that acts as a scaffold onto which it is covalently bound 3 to 4 influenza-inhibiting peptides. The multivalent display of peptides on the scaffold leads to a potent inhibition against H1N1 (EC50 = 20 nM). Importantly, the resulting lipopeptide, Pam3FDA, shows an irreversible inhibition mechanism. The chemical modification of peptides on the scaffold maintains Pam3CSK4's ability to stimulate dendritic cell maturation, thereby rendering Pam3FDA a unique antiviral. This is attributed to its immune activation capability, which also acts in synergy to expedite viral elimination.

Advancements in Precision Prevention: Top Bioinformatics and Translational Informatics Papers of 2023

OBJECTIVE

To identify and summarize the top bioinformatics and translational informatics (BTI) papers published in 2023, focusing on the area of precision prevention.

METHODS

We conducted a literature search to identify the top papers published in 2023 in the field of BTI. Candidate papers from the search were reviewed by the section co-editors and a panel of external reviewers to select the top three papers for this year.

RESULTS

Our literature search returned a total of 550 candidate papers, from which we identified our top 10 papers for external review. The papers were evaluated based on their novelty, significance, and quality. After rigorous review, three papers were selected as the top BTI papers for 2023. These papers showcased innovative approaches in leveraging machine learning models, integrating multi-omics data, and developing new experimental techniques. Highlights include advancements in single-cell genomics, dynamic surveillance systems, and multimodal data integration.

CONCLUSIONS

We found several trends in the ten candidate BTI papers, including the refinement of machine learning models, the expansion of diverse biological datasets, and the development of scalable experimental techniques. These trends reflect the growing importance of bioinformatics and translational informatics as a cornerstone for improving predictive and preventative healthcare measures.

Context-aware geometric deep learning for protein sequence design

Protein design and engineering are evolving at an unprecedented pace leveraging the advances in deep learning. Current models nonetheless cannot natively consider non-protein entities within the design process. Here, we introduce a deep learning approach based solely on a geometric transformer of atomic coordinates and element names that predicts protein sequences from backbone scaffolds aware of the restraints imposed by diverse molecular environments. To validate the method, we show that it can produce highly thermostable, catalytically active enzymes with high success rates. This concept is anticipated to improve the versatility of protein design pipelines for crafting desired functions.

De Novo Design of Peptide Binders to Conformationally Diverse Targets with Contrastive Language Modeling

Designing binders to target undruggable proteins presents a formidable challenge in drug discovery, requiring innovative approaches to overcome the lack of putative binding sites. Recently, generative models have been trained to design binding proteins via three-dimensional structures of target proteins, but as a result, struggle to design binders to disordered or conformationally unstable targets. In this work, we provide a generalizable algorithmic framework to design short, target-binding linear peptides, requiring only the amino acid sequence of the target protein. To do this, we propose a process to generate naturalistic peptide candidates through Gaussian perturbation of the peptidic latent space of the ESM-2 protein language model, and subsequently screen these novel linear sequences for target-selective interaction activity via a CLIP-based contrastive learning architecture. By integrating these generative and discriminative steps, we create a Peptide Prioritization via CLIP (PepPrCLIP) pipeline and validate highly-ranked, target-specific peptides experimentally, both as inhibitory peptides and as fusions to E3 ubiquitin ligase domains, demonstrating functionally potent binding and degradation of conformationally diverse protein targets in vitro. Overall, our design strategy provides a modular toolkit for designing short binding linear peptides to any target protein without the reliance on stable and ordered tertiary structure, enabling generation of programmable modulators to undruggable and disordered proteins such as transcription factors and fusion oncoproteins.

MGPPI: multiscale graph neural networks for explainable protein-protein interaction prediction

Protein-Protein Interactions (PPIs) involves in various biological processes, which are of significant importance in cancer diagnosis and drug development. Computational based PPI prediction methods are more preferred due to their low cost and high accuracy. However, existing protein structure based methods are insufficient in the extraction of protein structural information. Furthermore, most methods are less interpretable, which hinder their practical application in the biomedical field. In this paper, we propose MGPPI, which is a Multiscale graph convolutional neural network model for PPI prediction. By incorporating multiscale module into the Graph Neural Network (GNN) and constructing multi convolutional layers, MGPPI can effectively capture both local and global protein structure information. For model interpretability, we introduce a novel visual explanation method named Gradient Weighted interaction Activation Mapping (Grad-WAM), which can highlight key binding residue sites. We evaluate the performance of MGPPI by comparing with state-of-the-arts methods on various datasets. Results shows that MGPPI outperforms other methods significantly and exhibits strong generalization capabilities on the multi-species dataset. As a practical case study, we predicted the binding affinity between the spike (S) protein of SARS-COV-2 and the human ACE2 receptor protein, and successfully identified key binding sites with known binding functions. Key binding sites mutation in PPIs can affect cancer patient survival statues. Therefore, we further verified Grad-WAM highlighted residue sites in separating patients survival groups in several different cancer type datasets. According to our results, some of the highlighted residues can be used as biomarkers in predicting patients survival probability. All these results together demonstrate the high accuracy and practical application value of MGPPI. Our method not only addresses the limitations of existing approaches but also can assists researchers in identifying crucial drug targets and help guide personalized cancer treatment.

Computational design of soluble and functional membrane protein analogues

De novo design of complex protein folds using solely computational means remains a substantial challenge1. Here we use a robust deep learning pipeline to design complex folds and soluble analogues of integral membrane proteins. Unique membrane topologies, such as those from G-protein-coupled receptors2, are not found in the soluble proteome, and we demonstrate that their structural features can be recapitulated in solution. Biophysical analyses demonstrate the high thermal stability of the designs, and experimental structures show remarkable design accuracy. The soluble analogues were functionalized with native structural motifs, as a proof of concept for bringing membrane protein functions to the soluble proteome, potentially enabling new approaches in drug discovery. In summary, we have designed complex protein topologies and enriched them with functionalities from membrane proteins, with high experimental success rates, leading to a de facto expansion of the functional soluble fold space.

Geometric deep learning methods and applications in 3D structure-based drug design

3D structure-based drug design (SBDD) is considered a challenging and rational way for innovative drug discovery. Geometric deep learning is a promising approach that solves the accurate model training of 3D SBDD through building neural network models to learn non-Euclidean data, such as 3D molecular graphs and manifold data. Here, we summarize geometric deep learning methods and applications that contain 3D molecular representations, equivariant graph neural networks (EGNNs), and six generative model methods [diffusion model, flow-based model, generative adversarial networks (GANs), variational autoencoder (VAE), autoregressive models, and energy-based models]. Our review provides insights into geometric deep learning methods and advanced applications of 3D SBDD that will be of relevance for the drug discovery community.

A suite of designed protein cages using machine learning and protein fragment-based protocols

Designed protein cages and related materials provide unique opportunities for applications in biotechnology and medicine, but their creation remains challenging. Here, we apply computational approaches to design a suite of tetrahedrally symmetric, self-assembling protein cages. For the generation of docked conformations, we emphasize a protein fragment-based approach, while for sequence design of the de novo interface, a comparison of knowledge-based and machine learning protocols highlights the power and increased experimental success achieved using ProteinMPNN. An analysis of design outcomes provides insights for improving interface design protocols, including prioritizing fragment-based motifs, balancing interface hydrophobicity and polarity, and identifying preferred polar contact patterns. In all, we report five structures for seven protein cages, along with two structures of intermediate assemblies, with the highest resolution reaching 2.0 Å using cryo-EM. This set of designed cages adds substantially to the body of available protein nanoparticles, and to methodologies for their creation.