Design Pipeline Research Articles

Deep learning for NAD/NADP cofactor prediction and engineering using transformer attention analysis in enzymes

Understanding and manipulating the cofactor preferences of NAD(P)-dependent oxidoreductases, the most widely distributed enzyme group in nature, is increasingly crucial in bioengineering. However, large-scale identification of the cofactor preferences and the design of mutants to switch cofactor specificity remain as complex tasks. Here, we introduce DISCODE (Deep learning-based iterative pipeline to analyze Specificity of Cofactors and to Design Enzyme), a novel transformer-based deep learning model to predict NAD(P) cofactor preferences. For model training, a total of 7,132 NAD(P)-dependent enzyme sequences were collected. Leveraging whole-length sequence information, DISCODE classifies the cofactor preferences of NAD(P)-dependent oxidoreductase protein sequences without structural or taxonomic limitation. The model showed 97.4% and 97.3% of accuracy and F1 score, respectively. A notable feature of DISCODE is the interpretability of its transformer layers. Analysis of attention layers in the model enables identification of several residues that showed significantly higher attention weights. They were well aligned with structurally important residues that closely interact with NAD(P), facilitating the identification of key residues for determining cofactor specificities. These key residues showed high consistency with verified cofactor switching mutants. Integrated into an enzyme design pipeline, DISCODE coupled with attention analysis, enables a fully automated approach to redesign cofactor specificity.

DEVS-Based CDC Synchronizer Design for Fast Debugging of Metastability

This paper proposes a DEVS (Discrete Event System Specification) formalism-based approach to analyze Clock Domain Crossing (CDC) issues in digital circuit design. As modern System on Chip (SoC) designs increasingly integrate multiple clock domains, the verification of CDC-related metastability becomes more challenging and costly. While conventional EDA tools offer solutions for CDC analysis, they often involve substantial computational resources and licensing costs. We present a DEVS-based simulation framework that leverages its inherent advantages in time management and modular structuring to model and analyze CDC scenarios. The framework includes a CDC synchronizer model implemented within the HDL partially compatible DEVS environment, enabling precise analysis of metastability violations based on setup time and hold time requirements. Circuit designers or related engineers can potentially solve timing issues such as CDC by incorporating DEVS-based analysis tools into the design pipeline.

Genome-Scale DNA Methylome and Transcriptome Profiles of Prostate Cancer Recurrence After Prostatectomy

Prostate cancer (PCa) is a major health burden worldwide, and despite early treatment, many patients present with biochemical recurrence (BCR) post-treatment, reflected by a rise in prostate-specific antigen (PSA) over a clinical threshold. Novel transcriptomic and epigenomic biomarkers can provide a powerful tools for the clinical management of PCa. Here, we provide matched RNA sequencing and array-based genome-wide DNA methylome data of PCa patients (n = 17) with or without evidence of BCR following radical prostatectomy. Formalin-fixed paraffin-embedded (FFPE) tissues were used to generate these data, which included technical replicates to provide further validity of the data. We describe the sample features, experimental design, methods and bioinformatic pipelines for processing these multi-omic data. Importantly, comprehensive clinical, histopathological, and follow-up data for each patient were provided to enable the correlation of transcriptome and methylome features with clinical features. Our data will contribute towards the efforts of developing epigenomic and transcriptomic markers for BCR and also facilitate a deeper understanding of the molecular basis of PCa recurrence.

Development of a Universal Material Characterization, Evaluation and Estimation System via Microstructure Construction

In recent decades, advancements in material-scanning technologies have enabled detailed acquisition of microstructural data, yet direct integration of this data into simulation models remains challenging. This study develops a system that utilizes scanning electron microscope (SEM) micrographs to construct a 2D spatial map, which categorizes microstructural attributes. Employing the Marching Cubes algorithm, we create the contours and shapes of grain clusters based on consistent grey values, facilitating the precise generation of grain areas in simulation software. This generated model is then applied to simulate a uniaxial tensile test, revealing irregular principal stress distributions along grain boundaries and notable stress concentrations at void-grain interfaces. These results emphasize the system’s efficacy in providing precise material characterization, evaluation, and estimation. Additionally, the system accommodates further refinements, such as incorporating crystal orientations and conducting analyses like creep deformation and electrical property evaluation. Ultimately, this approach supports a comprehensive pipeline for material design, testing, analysis, and simulation, thereby enhancing the potential for targeted material improvements. Figure 1

Combination of Coevolutionary Information and Supervised Learning Enables Generation of Cyclic Peptide Inhibitors with Enhanced Potency from a Small Data Set.

Computational generation of cyclic peptide inhibitors using machine learning models requires large size training data sets often difficult to generate experimentally. Here we demonstrated that sequential combination of Random Forest Regression with the pseudolikelihood maximization Direct Coupling Analysis method and Monte Carlo simulation can effectively enhance the design pipeline of cyclic peptide inhibitors of a tumor-associated protease even for small experimental data sets. Further in vitro studies showed that such in silico-evolved cyclic peptides are more potent than the best peptide inhibitors previously developed to this target. Crystal structure of the cyclic peptides in complex with the protease resembled those of protein complexes, with large interaction surfaces, constrained peptide backbones, and multiple inter- and intramolecular interactions, leading to good binding affinity and selectivity.

Optimized shock-protecting microstructures

Mechanical shock is a common occurrence in various settings, there are two different scenarios for shock protection: catastrophic protection (e.g. car collisions and falls) and routine protection (e.g. shoe soles and mattresses). The former protects against one-time events, the latter against periodic shocks and loads. Common shock absorbers based on plasticity and fracturing materials are suitable for the former, while our focus is on the latter, where elastic structures are useful. Further, we optimize the effective elastic material properties which control the critical shock parameter, maximal stress, with energy dissipation by viscous forces assumed adequate. Improved elastic materials protecting against shock can be used in applications such as automotive suspension, furniture like sofas and mattresses, landing gear systems, etc. Materials offering optimal protection against shock have a highly non-linear elastic response: their reaction force needs to be as close as possible to constant with respect to deformation. In this paper, we use shape optimization and topology search to design 2D families of microstructures approximating the ideal behavior across a range of deformations, leading to superior shock protection. We present an algorithmic pipeline for the optimal design of such families combining differentiable nonlinear homogenization with self-contact and an optimization algorithm. We validate the effectiveness of our advanced 2D designs by extruding and fabricating them with 3D printing technologies and performing material and drop testing.

Jointly Embedding Protein Structures and Sequences through Residue Level Alignment

The relationships between protein sequences, structures, and functions are determined by complex codes that scientists aim to decipher. While structures contain key information about proteins' biochemical functions, they are often experimentally difficult to obtain. In contrast, protein sequences are abundant but are a step removed from function. In this paper, we propose residue level alignment (RLA)—a self-supervised objective for aligning sequence and structure embedding spaces. By situating sequence and structure encoders within the same latent space, RLA enriches the sequence encoder with spatial information. Moreover, our framework enables us to measure the similarity between a sequence and structure by comparing their RLA embeddings. We show how RLA similarity scores can be used for binder design by selecting true binders from sets of designed binders. RLA scores are informative even when they are calculated given only the backbone structure of the binder and no binder sequence information, which simulates the information available in many early-stage binder design libraries. RLA performs similarly to benchmark methods and is orders of magnitude faster, making it a valuable new screening tool for binder design pipelines. Published by the American Physical Society 2024

Host-Guest Binding Free Energies à la Carte: An Automated OneOPES Protocol.

Estimating absolute binding free energies from molecular simulations is a key step in computer-aided drug design pipelines, but the agreement between computational results and experiments is still very inconsistent. Both the accuracy of the computational model and the quality of the statistical sampling contribute to this discrepancy, yet disentangling the two remains a challenge. In this study, we present an automated protocol based on OneOPES, an enhanced sampling method that exploits replica exchange and can accelerate several collective variables to address the sampling problem. We apply this protocol to 37 host-guest systems. The simplicity of setting up the simulations and producing well-converged binding free energy estimates without the need to optimize simulation parameters provides a reliable solution to the sampling problem. This, in turn, allows for a systematic force field comparison and ranking according to the correlation between simulations and experiments, which can inform the selection of an appropriate model. The protocol can be readily adapted to test more force field combinations and study more complex protein-ligand systems, where the choice of an appropriate physical model is often based on heuristic considerations rather than systematic optimization.

Scalable protein design using optimization in a relaxed sequence space.

Machine learning (ML)-based design approaches have advanced the field of de novo protein design, with diffusion-based generative methods increasingly dominating protein design pipelines. Here, we report a "hallucination"-based protein design approach that functions in relaxed sequence space, enabling the efficient design of high-quality protein backbones over multiple scales and with broad scope of application without the need for any form of retraining. We experimentally produced and characterized more than 100 proteins. Three high-resolution crystal structures and two cryo-electron microscopy density maps of designed single-chain proteins comprising up to 1000 amino acids validate the accuracy of the method. Our pipeline can also be used to design synthetic protein-protein interactions, as validated experimentally by a set of protein heterodimers. Relaxed sequence optimization offers attractive performance with respect to designability, scope of applicability for different design problems, and scalability across protein sizes.

GRNAde: Geometric Deep Learning for 3D RNA inverse design.

Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity. We introduce gRNAde, a geometric RNA design pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. gRNAde uses a multi-state Graph Neural Network and autoregressive decoding to generates candidate RNA sequences conditioned on one or more 3D backbone structures where the identities of the bases are unknown. On a single-state fixed backbone re-design benchmark of 14 RNA structures from the PDB identified by Das et al. (2010), gRNAde obtains higher native sequence recovery rates (56% on average) compared to Rosetta (45% on average), taking under a second to produce designs compared to the reported hours for Rosetta. We further demonstrate the utility of gRNAde on a new benchmark of multi-state design for structurally flexible RNAs, as well as zero-shot ranking of mutational fitness landscapes in a retrospective analysis of a recent ribozyme. Open source code: github.com/chaitjo/geometric-rna-design.

Incremental Inverse Design of Desired Soybean Phenotypes.

We present an application of computational inverse design, which reverses the conventional trial-and-error forward design paradigm, optimizes biological phenotype by directly modifying genotype. The limitations of inverse design in genotype-to-bulk phenotype (G-BP) mapping can be addressed via an established design paradigm: "design, build, test, learn" (DBTL), where computational inverse design automates both the design and learn phases. In any context, inverse design is limited by the fundamental "one-to-many" nature of the inverse function. G-BP inverse design is further limited by the number of single nucleotide polymorphisms that can be made to a member of the population while maintaining feasibility of genotype creation and biological viability. Considering these limitations, we propose a design paradigm based on incremental optimization of phenotype through a combined computational and experimental approach. We intend this work to be a foundational synthesis of well-known techniques applied to the context of genotype-to-bulk phenotype inverse design, which has not yet been performed in the literature. The design pipeline can optimize phenotype by either directly proposing genotypic changes, or simply by suggesting parents to be used for selective breeding. The soybean nested association matrix data set is used to present an in silico case study of the design pipeline by performing optimization that maximizes protein content while constraining other phenotypes. A random forest (RF) is used to model the genotype-to-phenotype relationship, and a genetic algorithm is used to query the RF until a feasible genotype with desired phenotype is discovered. After 20 in silico DBTL cycles, a final population of individuals with a mean protein content of 36.13%, an increase of three standard deviations above the original mean is suggested.

GRNAde: A Geometric Deep Learning Pipeline for 3D RNA Inverse Design.

Fundamental to the diverse biological functions of RNA are its 3D structure and conformational flexibility, which enable single sequences to adopt a variety of distinct 3D states. Currently, computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity. In this tutorial, we present gRNAde, a geometric RNA design pipeline operating on sets of 3D RNA backbone structures to design sequences that explicitly account for RNA 3D structure and dynamics. gRNAde is a graph neural network that uses an SE (3) equivariant encoder-decoder framework for generating RNA sequences conditioned on backbone structures where the identities of the bases are unknown. We demonstrate the utility of gRNAde for fixed-backbone re-design of existing RNA structures of interest from the PDB, including riboswitches, aptamers, and ribozymes. gRNAde is more accurate in terms of native sequence recovery while being significantly faster compared to existing physics-based tools for 3D RNA inverse design, such as Rosetta.

A comprehensive design pipeline for FCEV powertrain configuration considering the evolutionary development process and extreme economic performance

Due to stringent emission regulations, the zero-emission hydrogen fuel cell electric vehicles (FCEVs) are gaining significant attention, but their slow power response requires careful selection of auxiliary energy sources and power systems to optimize energy efficiency. This paper presents a comprehensive design pipeline for the FCEV powertrain, encompassing methods for powertrain configuration design, feasible domain design for component parameters, and parameter matching. Initially, a powertrain configuration design method based on evolutionary game theory is introduced, forecasting trends in energy-efficient powertrain configurations using a dynamic cost function that adjusts based on the proportions of different configurations. Next, a feasible domain design method is developed to establish fixed constraints on component parameters, ensuring a fair balance between performance needs and overall costs, including development and lifecycle expenses associated with the powertrain configuration. Subsequently, dynamic programming (DP) is used for parameter matching, assessing the utmost energy-saving potential. The cost function in this method incorporates the degradation cost of powertrain components, underscoring the economic performance of the target FCEV over its lifespan. Finally, simulation assessments indicate that the proposed design pipeline effectively identifies the optimal powertrain configuration for FCEVs, endowing each possible configuration with exceptional economic efficiency across different component parameters.

A Comparative Analysis of Computational Strategies in Multi-Epitope Vaccine Design Against Human Papillomavirus and Cervical Cancer.

Given the critical role of human papillomavirus (HPV) in the cause of cervical cancer and other malignancies, there is a need for innovative approaches to preventing this infection. It has been shown that immunoinformatics is an important strategy in computational vaccinology. It is used to design new multi-epitope vaccines against different types of HPV and subsequent cervical cancer. This paper reviews the scope of the entire computational pipeline of HPV vaccine design, starting from data analysis at the genomic and proteomic levels and continuing to epitope predictions of the innate and adaptive immune systems. The search strategy was based on investigating original articles published in "Google Scholar" and "PubMed" from 2015 to 2023-2024. The terms "Immunoinformatics", "Bioinformatics", "Human papillomavirus (HPV)", "Vaccine design", "In silico vaccine design", "Multi-epitope vaccine design", "Vaccinology" and "HPV vaccine" were used to for this purpose. We discussed various essential tools involved in the computational design of the vaccine process, e.g., sequence analysis, epitope prediction, conservancy analysis, tertiary structure modeling, refinement, molecular docking, molecular dynamics (MD) simulation, and in silico cloning. This review article describes immunoinformatics methods that facilitate the design of a multi-epitope vaccine against HPV. However, this pipeline can also be used to design novel chimeric vaccines for other pathogens.

Generative AIBIM: An automatic and intelligent structural design pipeline integrating BIM and generative AI

AI-based intelligent structural design represents a transformative approach that addresses the inefficiencies inherent in traditional structural design practices. This paper innovates the existing AI-based design frameworks from four aspects and proposes Generative AIBIM: an automatic and intelligent structural design pipeline that integrates Building Information Modeling (BIM) and generative AI. First, the proposed pipeline not only broadens the application scope of BIM, which aligns with BIM's growing relevance in civil engineering, but also marks a significant supplement to previous methods that relied solely on CAD drawings. Second, in Generative AIBIM, a two-stage generation framework incorporating generative AI (TGAI), inspired by the human drawing process, is designed to simplify the complexity of the structural design problem. Third, for the generative AI model in TGAI, this paper pioneers to fuse physical conditions into diffusion models (DMs) to build a novel physics-based conditional diffusion model (PCDM). In contrast to conventional DMs, on the one hand, PCDM directly predicts shear wall drawings to focus on similarity, and on the other hand, PCDM effectively fuses cross-domain information, i.e., design drawings (image data), timesteps, and physical conditions, by integrating well-designed attention modules. Additionally, a new evaluation system including objective and subjective measures (i.e., ScoreIoU and FID) is designed to comprehensively evaluate models' performance, complementing the evaluation system in the traditional methods only adopting the objective metric. The quantitative results demonstrate that PCDM significantly surpasses recent state-of-the-art (SOTA) techniques (StructGAN and its variants) across both measures: ScoreIoU of PCDM is 30% higher and FID of PCDM is lower than 1/3 of that of the best competitor. The qualitative experimental results highlight PCDM's superior capabilities in generating high perceptual quality design drawings adhering to essential design criteria. In addition, benefiting from the fusion of physical conditions, PCDM effectively supports diverse and creative designs tailored to building heights and seismic precautionary intensities, showcasing its unique and powerful generation and generalization capabilities. Associated ablation studies further demonstrate the effectiveness of our method.

Insilico Simulation Studies for Tuberculosis Drug Discovery and its Response

From high treatment and with such precaution measures TB (Tuberculosis) came with leading cause of deaths in the world. For Tuberculosis it increasing drug resistance for different kind of TB like Multidrug-resistant TB and Extensively drug-resistant TB, increasing relapse and in efficiency of drug for TB pathogen.it take longer duration, it affect on human body with infection from HIV and other autoimmune disorder have pushed it to a lethal level and for this we need more effective drugs. With the help of CADD technology we can findout more viable drug molecules for the better treatment of Mycobacterium tuberculosis .Insilico drug design is a more efficient ,time saving and cost effective process. With the help of inslico drug design we can identify/Generate lead molecules that can inhibit the activity of TB. In inslico process we took 4GZR protein which is Crystal structure of the Mycobacterium tuberculosis and lead(ligand) with the support of computer aided drug design (CADD) pipeline and bioinformatics software tools. Key words: Tuberculosis, Insilico Drug Design, Computer Aided Drug Design (CADD), Bioinformatics Tool and Technology.

Deep Learning Conceptual Design of Sit-to-Stand Parallel Motion Six-Bar Mechanisms

Abstract The sit-to-stand (STS) motion is a crucial activity in the daily lives of individuals, and its impairment can significantly impact independence and mobility, particularly among disabled individuals. Addressing this challenge necessitates the design of mobility assist devices that can simultaneously satisfy multiple conflicting constraints. The effective design of such devices often involves the generation of numerous conceptual mechanism designs. This paper introduces an innovative single-degree-of-freedom (DOF) mechanism synthesis process for developing a highly customizable sit-to-stand (STS) mechanical device by integrating rigid body kinematics with machine learning. Unlike traditional mechanism synthesis approaches that primarily focus on limited functional requirements, such as path or motion generation, our proposed design pipeline efficiently generates a large number of 1DOF mechanism geometries and their corresponding motion paths, known as coupler curves. Leveraging a generative deep neural network, we establish a probabilistic distribution of coupler curves and their mapping to mechanism parameters. Additionally, we introduce novel metrics for quantitatively evaluating and prioritizing design concepts. The methodology yields a diverse set of viable conceptual design solutions that adhere to the specified constraints. We showcase various single-degree-of-freedom six-bar linkage mechanisms designed for STS motion, presenting them in a ranked order based on established criteria. While the primary focus is on the integration of STS motion into a versatile mobility assist device, the proposed approach holds broad applicability for addressing design challenges in various applications.

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.

Heuristic energy-based cyclic peptide design.

Rational computational design is crucial to the pursuit of novel drugs and therapeutic agents. Meso-scale cyclic peptides, which consist of 7-40 amino acid residues, are of particular interest due to their conformational rigidity, binding specificity, degradation resistance, and potential cell permeability. Because there are few natural cyclic peptides, de novo design involving non-canonical amino acids is a potentially useful goal. Here, we develop an efficient pipeline (CyclicChamp) for cyclic peptide design. After converting the cyclic constraint into an error function, we employ a variant of simulated annealing to search for low-energy peptide backbones while maintaining peptide closure. Compared to the previous random sampling approach, which was capable of sampling conformations of cyclic peptides of up to 14 residues, our method both greatly accelerates the computation speed for sampling conformations of small macrocycles (ca. 7 residues), and addresses the high-dimensionality challenge that large macrocycle designs often encounter. As a result, CyclicChamp makes conformational sampling tractable for 15- to 24-residue cyclic peptides, thus permitting the design of macrocycles in this size range. Microsecond-length molecular dynamics simulations on the resulting 15, 20, and 24 amino acid cyclic designs identify trajectories with kinetic stability. To test their thermodynamic stability, we perform additional replica exchange molecular dynamics simulations and generate free energy surfaces. Two 15-residue designs and one 20-residue design emerge as promising candidates, along with one viable 24-residue candidate.

Exploring Biomedical Engineering (BME): Advances within Accelerated Computing and Regenerative Medicine for a Computational and Medical Science Perspective Exploration Analysis

The field of molecular engineering in medicine has made significant strides in recent years, transforming healthcare, diagnostics, and therapy development. However, the COVID-19 pandemic highlighted the ongoing need for further innovative progress and detailed investigation. This research delves into the interdisciplinary domain of biomedical engineering with molecular engineering, examining its impact on the domains of regenerative medicine, biomaterials, tissue engineering, and the acceleration of health science through advanced biotechnologies. The primary objective of this research is to conduct an in-depth exploration of biomaterial applications and their roles in regenerative medicine, along with advancements in tissue engineering, organon-a-chip device mechanics, and the transformative potential of bioprinting in creating functional tissues and organs. This research also includes a case study analysis of drug discovery, immune engineering, precision medicine, and gene editing, with insights into the processing, design, and screening pipelines for biologics, as well as the future role of therapeutics and drugs in healthcare. Throughout this exploration, meaningful discussions with conclusions are drawn regarding the advanced technologies investigated, employing systematic technical computing methods at each step of the research process. The rapid advancements in terms of technological computing have brought about significant growth and transformation in various types of domains of biomedical engineering, particularly in the field of medical science and human health. With the progress in artificial intelligence (AI), computer vision, deep learning, image processing, machine learning there has been a revolutionary change in healthcare, addressing a wide range of medical conditions and human anatomy perspectives. The integration of these immersive technologies has not only improved in the realm of medication and disease control but has also provided solutions for complex tasks and issues related to human anatomy threats within the health sector. This research also focuses on the impact of accelerated computing in biomedical engineering, providing insights into the modern utility of toolsets in Bioinformatics and mechanics with artificial intelligence within medical science and also diving into understanding the human anatomy. Additionally, it explores the concept of functional genomics and its potential to provide insights into future disease and health issues, paving the way for advancements in healthcare for the foreseeable future and beyond.