Design Graphs Research Articles

Learning Joint 2-D and 3-D Graph Diffusion Models for Complete Molecule Generation.

Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in narrowing down the chemical research space and generating high-fidelity molecules. However, current generative models only focus on modeling 2-D bonding graphs or 3-D geometries, which are two complementary descriptors for molecules. The lack of ability to jointly model them limits the improvement of generation quality and further downstream applications. In this article, we propose a joint 2-D and 3-D graph diffusion model (JODO) that generates geometric graphs representing complete molecules with atom types, formal charges, bond information, and 3-D coordinates. To capture the correlation between 2-D molecular graphs and 3-D geometries in the diffusion process, we develop a diffusion graph transformer (DGT) to parameterize the data prediction model that recovers the original data from noisy data. The DGT uses a relational attention mechanism that enhances the interaction between node and edge representations. This mechanism operates concurrently with the propagation and update of scalar attributes and geometric vectors. Our model can also be extended for inverse molecular design targeting single or multiple quantum properties. In our comprehensive evaluation pipeline for unconditional joint generation, the experimental results show that JODO remarkably outperforms the baselines on the QM9 and GEOM-Drugs datasets. Furthermore, our model excels in few-step fast sampling, as well as in inverse molecule design and molecular graph generation. Our code is provided in https://github.com/GRAPH-0/JODO.

Optimizing task-analysis instruction: Effects of descriptions and pictures of antecedent stimuli and outcomes.

Little research has examined specific instructional variables that influence the development and effectiveness of task-analysis instruction. We conducted two experiments using text-based task analyses to teach college students to create single-subject reversal design graphs. In Experiment 1, we tested the effects of presenting antecedent and outcome stimuli on graphing performance (accuracy, yield, time to completion). Different groups of participants experienced graphing tutorials with descriptions and pictures of (a) responses; (b) antecedent stimuli and responses; (c) responses and outcomes of correct responses; and (d) antecedent stimuli, responses, and outcomes. In Experiment 2, we compared tutorials with and without pictures. Collectively, the results suggest that graphing accuracy was positively affected by task analyses that included pictures and descriptions of antecedent stimuli and that adding outcome stimuli further benefited graphing accuracy. These results suggest critical instructional elements that should be included in future task analyses of graphing or other complex behavior chains.

Enhancing stability graphs for stope design in deep metal mines using machine learning

Stope structural parameters, which are human-controllable, directly impact the safety and economics performance of underground mineral extraction. Current stope design still relies heavily on empirical methods such as stability graphs, due to the complex nature of rock masses and varied stope failure mechanisms. This study aims to enhance stability graphs with machine learning techniques. Firstly, a dataset of 980 records from unsupported stopes was compiled, representing perhaps the largest dataset of its kind so far in the literature. This was achieved through extensive literature review and the collation of an additional 289 records from Chinese mines which were previously not included. An analysis of data reveals that over 90 % of the records fall within a stability coefficient of 0–100 and a hydraulic radius of 0–20 m. Secondly, a stability graphs optimization process was established using Python, eliminating the subjectivity of partitioning. Nine supervised machine learning algorithms were employed and trained to test their performance in partitioning form and predicting accuracy. It was found that the neural network algorithm demonstrated the best overall performance. At last, a neural network with the Keras framework was used to establish a new multilayer perceptron model to generate safety factor probability curves, which were then used to construct the stability graph. To facilitate practical use, mathematical functions fitting safety factor curves within the unstable zone were further formulated. Compared with other empirical stability graphs, our new approach allows designers to more efficiently and reliably select safety factors to determine the stability state according to site specific conditions and technical support systems, thereby providing enhanced guidance for stope design.

Reading a graph is like reading a paragraph.

Vision provides rapid processing for some tasks, but encounters strong constraints from others. Although many tasks encounter a capacity limit of processing four visual objects at once, some evidence suggests far lower limits for processing relationships among objects. What is our capacity limit for relational processing? If it is indeed limited, then people may miss important relationships between data values in a graph. To test this question, we asked people to explore graphs of trivially simple 2 × 2 data sets and found that half of the viewers missed surprising and improbable relationships (e.g., a child's height decreasing over time). These relationships were spotted easily in a control condition, which implicitly directed viewers to prioritize inspecting the key relationships. Thus, a severe limit on relational processing, combined with a cascade of other capacity-limited operations (e.g., linking values to semantic content), makes understanding a graph more like slowly reading a paragraph then immediately recognizing an image. These results also highlight the practical importance of "data storytelling" techniques, where communicators design graphs that help their audience prioritize the most important relationships in data. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Reconstruction of gene regulatory networks using graph neural networks

Gene regulatory network (GRN) inference, a longstanding challenge in computational biology, aims to construct GRNs from genomic data. Graph Neural Networks (GNNs) are well-suited for this task due to their ability to leverage both node features and topological relationships. This research systematically evaluated various GNN variants, gradually narrowing the focus through a filtering process. The study considered multiple design aspects, including layers, epochs, decoders, activation functions, graph structures, aggregation methods, skip connections, dropout, and hidden dimensions. Ultimately, two promising models emerged, one based on the Chebyshev spectral graph convolutional operator and the other on the Hypergraph convolutional operator, demonstrating state-of-the-art performance. Notably, hypergraphs demonstrated superior performance on real datasets with higher-order dependencies, while the Chebyshev model showed greater generalization across both simulated and real datasets. The code for this research is available online at https://github.com/EmmaDPaul/GRN-inference-using-GNN.

A Simplified Design Method for the Mechanical Stability of Slit-Shaped Additively Manufactured Reactor Modules

Equipment integrity is an essential aspect of process engineering. Design guidelines facilitate the design and production of safe-to-operate and economic devices. Thin-walled, slit-shaped modules form a subgroup of process engineering devices made via additive manufacturing (AM). Being subject to internal pressure, they have lacked design guidelines until now. We derived a user-centered calculation model for such modules with regular internal structures. It was validated with Finite Element Analysis (FEA) and practical pressure tests for which the modules were manufactured additively. The performance of the calculation could be confirmed, and a design graph was derived. Slit-shaped modules with appropriate internal structures can withstand high pressure at a minimum wall thickness, and they are efficiently fabricated. These structures, being pins, fins, lattice, or heat transfer enhancing fluid-guiding elements (FGEs), occupied approximately 10% of the modules’ internal volume.

Generalized Linear Mixed Effects Modeling (GLMM) of Functional Analysis Graphical Construction Elements on Visual Analysis

Multielement designs are the quintessential design tactic to evaluate outcomes of a functional analysis in applied behavior analysis. Protecting the credibility of the data collection, graphing, and visual analysis processes from a functional analysis increases the likelihood that optimal intervention decisions are made for individuals. Time-series graphs and visual analysis are the most prevalent method used to interpret functional analysis data. The current project included two principal aims. First, we tested whether the graphical construction manipulation of the x-to-y axes ratio (i.e., data points per x- axis to y-axis ratio [DPPXYR]) influenced visual analyst’s detection of a function on 32 multielement design graphs displaying functional analyses. Second, we investigated the alignment between board certified behavior analysts (BCBAs; N = 59) visual analysis with the modified visual inspection criteria (Roane et al., Journal of Applied Behavior Analysis, 46, 130-146, 2013). We found that the crossed GLMM that included random slopes, random intercepts, and did not include an interaction effect (AIC = 1406.1, BIC = 1478.2) performed optimally. Second, alignment between BCBAs decisions and the MVI appeared to be low across data sets. We also leveraged current best practices in Open Science for raw data and analysis transparency.

A Study on Degree Based Topological Indices of Harary Subdivision Graphs With Application

Combinatorial design theory and graph decompositions play a critical role in the exploration of combinatorial design theory and are essential in mathematical sciences. The process of graph decomposition involves partitioning the set of edges in a graph G. An n-sun graph, characterized by a cycle with an edge connecting each vertex to a terminating vertex of degree one, is introduced in this study. The concept of n-sun decomposition is applied to certain even-order graphs. The indices covered in this study include the general connectivity index of the harary graphs, Zagreb indices, symmetric division degree indices and randic indices.

CUTS+: High-Dimensional Causal Discovery from Irregular Time-Series

Causal discovery in time-series is a fundamental problem in the machine learning community, enabling causal reasoning and decision-making in complex scenarios. Recently, researchers successfully discover causality by combining neural networks with Granger causality, but their performances degrade largely when encountering high-dimensional data because of the highly redundant network design and huge causal graphs. Moreover, the missing entries in the observations further hamper the causal structural learning. To overcome these limitations, We propose CUTS+, which is built on the Granger-causality-based causal discovery method CUTS and raises the scalability by introducing a technique called Coarse-to-fine-discovery (C2FD) and leveraging a message-passing-based graph neural network (MPGNN). Compared to previous methods on simulated, quasi-real, and real datasets, we show that CUTS+ largely improves the causal discovery performance on high-dimensional data with different types of irregular sampling.

Analytical formulations of tunnel–soil–pile interaction under seismic excitations

AbstractTunnel–soil–pile interaction (TSPI) is a vital issue during seismic excitation because of the evaluation of the interactive structural behaviors of the tunnel. This study derives analytical formulae for the proposed TSPI model under transverse horizontal shear, vertical shear, and body waves, considering a series of piles along the tunnel's longitudinal axis. For this reason, the soil medium is considered to be an isotropic, homogeneous, elastic, and infinite. Also, the tunnel is assumed to be a beam element to connect to the series of piles by the linear elastic springs. Parametric studies of proposed formulae show the parabolic and exponential variations of tunnel forces and soil pressures when increases the number of piles. Also, recalculated tunnel moments of previous studies by using proposed formulae vary closely, which may indicate the accuracy of the present formulations. Similar variations are obtained for the previous field study verification by the present formulations. Therefore, the design charts and graphs are addressed in the present research which may be used as a standard to enhance this research in the future.

Development of a new design methodology for slab track systems

Owing to the rapid increase in the demands of train speed and axle loads, the slab track has been introduced to replace the ballast in the classical ballasted track with reinforced concrete slab or asphalt-bearing layer to improve the track stability, strength, and durability. This paper aims to develop a new methodology for estimating the rail deformations for the most common slab track systems (BÖGL, Shinkansen, and RHEDA 2000. This methodology yielded the first design aid for slab track systems based on design equations and graphs for high-speed systems. Using a regression analysis of more than 300 finite element models which are validated by experimental tests, the relationship between the rail deflection, modulus of elasticity for subgrade and replacement, and the replacement thickness was determined for the most common slab tracks under the American (AREMA) and European (EN) loads. According to EN, it was found that the minimum modulus of elasticity for subgrade to fulfill the rail deflection criterion without a replacement soil ranges from 128 to 143 MPa for the most common slab track systems; meanwhile, for AREMA, it ranges from 59 to 70 MPa. Furthermore, for these slab track systems, one simple design chart was introduced to aid engineers with the design of the slab track replacement layer according to each design code.

Strongly regular graphs decomposable into a divisible design graph and a Hoffman coclique

Strongly regular graphs decomposable into a divisible design graph and a Hoffman coclique

Alernative Designs of an Active RC Realization of the Fourth Order Lowpass Butterworth Filter

In this tutorial article, we present two alternative designs of an active RC realization of the fourth-order lowpass Butterworth filter, in order to reduce the element spreads below those of an existing design, which uses a single amplifier of gain 2. The first method is based on simple observation of the design graphs given there, while the second one is a cascade of two second-order realizations, each using a unity gain amplifier. It is shown that retaining the capacitor spread to unity in the first design, a small adjustment of the gain reduces the resistance spread to less than half of the value obtained earlier. It is also shown that in the cascade design, the resistance spread can be made unity, but only at the cost of capacitor spread of 6.834.

A machine learning regression approach for predicting uplift capacity of buried pipelines in anisotropic clays

The uplift capacity of pipeline systems in geotechnical engineering is influenced by internal loading and external factors, making it a significant consideration in pipeline design problems. Previous research has conducted experimental tests and numerical solutions to investigate the relationship between force and displacement or the resistance of pipelines in numerous soil media. This paper proposes a machine-learning regression technique to predict the uplift capacity of buried pipelines in anisotropic clays with parametric analysis. Specifically, the Multivariate Adaptive Regression Spline (MARS) is employed to establish the relationship between input parameters, namely the depth ratio (H/D), anisotropic strength ratio (re), load inclination (β), overburden factor (γH/Suc), adhesion factor (α), and the output uplift resistance (N) obtained from the finite element limit analysis (FELA), utilizing the AUS material model integrated with the OptumG2 commercial program. Furthermore, the sensitivity analysis outcome shows the embedded depth ratio is the most critical parameter, followed by the anisotropic strength ratio, overburden factor, load inclination, and adhesion factor. Additionally, the shear velocity field contours show that when the depth ratio and the load inclination increase, the dissipation of shear changes. Design data visualizations, tables, graph contours, and empirical equations are created and can be utilized to aid in the development of practical designs.

System integration based on packing, piping and harness routing automation using graph-based design languages

The implementation of a fully instrumented, automated and simulation-enabled engineering software platform capable of automating the currently still manual model-based systems engineering (MBSE) design process for physical systems architecture generation and optimization in an aircraft wing is presented. The software platform uses graph-based design languages to integrate and entirely automate the mainly manual packing, piping and harness routing design. This design automation and optimization is achieved by a novel software stack of an optimization software coupled with a design compiler. It is shown that through rule-based model generation by a design compiler in the form of a design graph as a central data model, a cross-domain data consistency is achieved. This allows for automated execution and coupling of engineering tasks over several different domains such as packing, piping and routing design to converge to an optimized wing physical architecture design variant in agreement with given predetermined design constraints.

A Comprehensive Survey on Electronic Design Automation and Graph Neural Networks: Theory and Applications

Driven by Moore’s law, the chip design complexity is steadily increasing. Electronic Design Automation (EDA) has been able to cope with the challenging very large-scale integration process, assuring scalability, reliability, and proper time-to-market. However, EDA approaches are time and resource demanding, and they often do not guarantee optimal solutions. To alleviate these, Machine Learning (ML) has been incorporated into many stages of the design flow, such as in placement and routing. Many solutions employ Euclidean data and ML techniques without considering that many EDA objects are represented naturally as graphs. The trending Graph Neural Networks (GNNs) are an opportunity to solve EDA problems directly using graph structures for circuits, intermediate Register Transfer Levels, and netlists. In this article, we present a comprehensive review of the existing works linking the EDA flow for chip design and GNNs. We map those works to a design pipeline by defining graphs, tasks, and model types. Furthermore, we analyze their practical implications and outcomes. We conclude by summarizing challenges faced when applying GNNs within the EDA design flow.

A New Construction of Strongly Regular Graphs with Parameters of the Complement Symplectic Graph

The symplectic graph $Sp(2d, q)$ is the collinearity graph of the symplectic space of dimension $2d$ over the finite field of order $q$. A $k$-regular graph on $v$ vertices is a divisible design graph with parameters $(v,k,\lambda_1,\lambda_2,m,n)$ if its vertex set can be partitioned into $m$ classes of size $n$, such that any two different vertices from the same class have $\lambda_1$ common neighbours, and any two vertices from different classes have $\lambda_2$ common neighbours whenever it is not complete or edgeless. In this paper we propose a new construction of strongly regular graphs with the parameters of the complement of the symplectic graph using divisible design graphs.

사출금형용 직선형 냉각회로의 정량적 설계 방법론 개발

During injection molding, the cooling process generally consumes more than 50% of the total processing time. Therefore, the cooling efficiency is typically improved by optimizing the cooling channel arrangement. However, it takes significant time to optimize and is challenging to apply to mold design. A quantitative design methodology that efficiently generates a cooling circuit within a short period was developed. First, a cooling-channel design equation was derived based on a simulation of the heat transfer process in the mold to express the relationship between the diameter, depth, and distance of the cooling channel. Next, the design equation was used to plot a cooling-channel design graph by applying PP, ABS, PC, and PMMA, materials widely used for injection molding. Finally, the cooling channel was generated by applying this graph to the shape of the actual automotive bumper, and the cooling analysis was performed. The proposed method demonstrates an efficient cooling-channel design.

Evaluating System Buckling Load of a Plane Non-sway Frame by Hand

Presented in this paper is a simple method for system buckling analysis of plane non-sway frames. The “bracing” of a non-sway frame is first released and becomes a sway frame named accompanying sway frame. The upper-bound of the system buckling load of the accompanying sway frame can be found by a story buckling method developed. From the comparison study of a single sway column and a non-sway column, a modification factor can be obtained. The upper-bound of the system buckling load of the non-sway frame can be determined by the upper-bound of the system buckling load of its accompanying sway frame, multiplied with this modification factor. The upper-bound of system buckling load is the buckling load when the rigidity of the beams connected to the columns can be considered infinite. The system buckling load can be evaluated from the upper-bound, modified by real parameters of the frame with the design graphs developed. Examples are presented and the procedures are demonstrated. The system buckling load produced by the suggested approach is compared with that produced by system buckling analysis with FEA. The accuracy, efficiency and simplicity of the suggested system buckling approach are demonstrated.

Methodological Guidance for Single-Case Graph Construction in Counseling Outcome Research and Program Evaluation

In this article, we outline standards and recommendations for single-case research design (SCRD) graph construction to improve readability, transparency, and interpretation. Prior research indicates large variability among graph representation resulting in misinterpretation and lack of clarity of reported findings. Prominent graph features are discussed including esthetic and analysis altering characteristics. We provide a conceptual checklist along with visual and narrative descriptions to support the construction of SCRD graphs and help guide practitioners and researchers with reporting and displaying SCRD data.