Synthetic Task Research Articles

Recent Advancements in the Application of Artificial Intelligence in Drug Molecular Generation and Synthesis Planning

AbstractThe design and synthesis of drug molecules is a pivotal stage in drug development that traditionally requires significant investment in time and finances. However, the integration of artificial intelligence (AI) in drug design accelerates the identification of potential drug candidates, optimizes the drug development process, and contributes to more informed decision-making. The application of AI in molecular generation is changing the way researchers explore the chemical space and design novel compounds. It accelerates the process of drug discovery and materials science, enabling rapid exploration of the vast chemical landscapes for the identification of promising candidates for further experimental validation. The application of AI in predicting reaction products accelerates the synthesis planning process, contributes to the automation of synthetic chemistry tasks, and supports chemists in making informed decisions during drug discovery. This paper reviewed the recent advances in two interrelated areas: the application of AI in molecular generation and synthesis routes. It will provide insights into the innovative ways in which AI is transforming traditional approaches in drug development and predict its future progress in these key fields.

ProcessGAN: Generating Privacy-Preserving Time-Aware Process Data with Conditional Generative Adversarial Nets

Process data constructed from event logs provides valuable insights into procedural dynamics over time. The confidential information in process data, together with the data’s intricate nature, makes the datasets not sharable and challenging to collect. Consequently, research is limited using process data and analytics in the process mining domain. In this study, we introduced a synthetic process data generation task to address the limitation of sharable process data. We introduced a generative adversarial network, called ProcessGAN, to generate process data with activity sequences and corresponding timestamps. ProcessGAN consists of a transformer-based network as the generator, and a time-aware self-attention network as the discriminator. It can generate privacy-preserving process data from random noise. ProcessGAN considers the duration of the process and time intervals between activities to generate realistic activity sequences with timestamps. We evaluated ProcessGAN on five real-world datasets, two that are public and three collected in medical domains that are private. To evaluate the synthetic data, in addition to statistical metrics, we trained a supervised model to score the synthetic processes. We also used process mining to discover workflows for synthetic medical processes and had domain experts evaluate the clinical applicability of the synthetic workflows. ProcessGAN outperformed the existing generative models in generating complex processes with valid parallel pathways. The synthetic process data generated by ProcessGAN better represented the long-range dependencies between activities, a feature relevant to complicated medical and other processes. The timestamps generated by the ProcessGAN model showed similar distributions with the authentic timestamps. In addition, we trained a transformer-based network to generate synthetic contexts (e.g., patient demographics) that were associated with the synthetic processes. The synthetic contexts generated by our model outperformed the baseline models, with the distributions similar to the authentic contexts. We conclude that ProcessGAN can generate sharable synthetic process data indistinguishable from authentic data. Our source code is available in https://github.com/raaachli/ProcessGAN .

RadShap: An Explanation Tool for Highlighting the Contributions of Multiple Regions of Interest to the Prediction of Radiomic Models.

Explaining the decisions made by a radiomic model is of significant interest, as it can provide valuable insights into the information learned by complex models and foster trust in well-performing ones, thereby facilitating their clinical adoption. Promising radiomic approaches that aggregate information from multiple regions within an image currently lack suitable explanation tools that could identify the regions that most significantly influence their decisions. Here we present a model- and modality-agnostic tool (RadShap, https://github.com/ncaptier/radshap), based on Shapley values, that explains the predictions of multiregion radiomic models by highlighting the contribution of each individual region. Methods: The explanation tool leverages Shapley values to distribute the aggregative radiomic model's output among all the regions of interest of an image, highlighting their individual contribution. RadShap was validated using a retrospective cohort of 130 patients with advanced non-small cell lung cancer undergoing first-line immunotherapy. Their baseline PET scans were used to build 1,000 synthetic tasks to evaluate the degree of alignment between the tool's explanations and our data generation process. RadShap's potential was then illustrated through 2 real case studies by aggregating information from all segmented tumors: the prediction of the progression-free survival of the non-small cell lung cancer patients and the classification of the histologic tumor subtype. Results: RadShap demonstrated strong alignment with the ground truth, with a median frequency of 94% for consistently explained predictions in the synthetic tasks. In both real-case studies, the aggregative models yielded superior performance to the single-lesion models (average [±SD] time-dependent area under the receiver operating characteristic curve was 0.66 ± 0.02 for the aggregative survival model vs. 0.55 ± 0.04 for the primary tumor survival model). The tool's explanations provided relevant insights into the behavior of the aggregative models, highlighting that for the classification of the histologic subtype, the aggregative model used information beyond the biopsy site to correctly classify patients who were initially misclassified by a model focusing only on the biopsied tumor. Conclusion: RadShap aligned with ground truth explanations and provided valuable insights into radiomic models' behaviors. It is implemented as a user-friendly Python package with documentation and tutorials, facilitating its smooth integration into radiomic pipelines.

Access to Valuable Chalcogen-Containing Biaryl Derivatives via Regioselective 2,2'-Dichalcogenation of 2-Bromobiaryls.

The regioselective installation of chalcogen atoms into biaryl scaffolds is an important synthetic task due to the great value of chalcogen-containing biaryl derivatives in many fields. Here we undertake this task by developing a regioselective 2,2'-dichalcogenation of 2-bromobiaryls with common chalcogen sources using an organolanthanum-mediated one-pot, two-step protocol. This strategy features high regioselectivity, readily available substrates, transition-metal-free conditions, and performance superior to those of previous methods, thereby demonstrating the unique advantages of organolanthanum reagents in organic synthesis.

Amplitude rise time sensitivity in children with and without dyslexia: differential task effects and longitudinal relations to phonology and literacy.

The speech amplitude envelope carries important acoustic information required for speech intelligibility and contains sensory cues (amplitude rise times, ARTs) that play a key role in both sensory rhythm perception and neural speech encoding. Individual differences in children's sensitivity to ARTs have been related to the development of children's phonological processing skills across languages by the Temporal Sampling theory. Impaired processing of ARTs also characterises children with dyslexia. However, different ART tasks have been employed in different studies, in different languages, and at different ages. Here, we compare the sensitivity of three frequently used ART tasks (based on synthetic syllables, sine tones, and speech-shaped noise) in a longitudinal study of English-speaking children with and without dyslexia. Children's ability to discriminate rising frequency, duration, and intensity was also tested. ART discrimination in all 3 tasks was significantly inter-related, but different relations to phonology and literacy were found for different ART tasks at different ages. In particular, the often-used sine tone and speech-shaped noise ART tasks showed greater sensitivity in older children, while the synthetic syllable task (/ba/ rise) showed greater sensitivity in younger children. Sensitivity to rising frequency was also related to phonology and literacy across ages. The data are interpreted with respect to the Temporal Sampling theory of developmental dyslexia.

Synthesis of All‐Benzene Multi‐Macrocyclic Nanocarbons by Post‐Functionalization of meta‐Cycloparaphenylenes

AbstractExpanding the diversity of multi‐macrocyclic nanocarbons, particularly those with all‐benzene scaffolds, represents intriguing yet challenging synthetic tasks. Complementary to the existing synthetic approaches, here we report an efficient and modular post‐functionalization strategy that employs iridium‐catalyzed C−H borylation of the highly strained meta‐cycloparaphenylenes (mCPPs) and an mCPP‐derived catenane. Based on the functionalized macrocyclic synthons, a number of novel all‐benzene topological structures including linear and cyclic chains, polycatenane, and pretzelane have been successfully prepared and characterized, thereby showcasing the synthetic utility and potential of the post‐functionalization strategy.

Synthesis of All-Benzene Multi-Macrocyclic Nanocarbons by Post-Functionalization of meta-Cycloparaphenylenes.

Expanding the diversity of multi-macrocyclic nanocarbons, particularly those with all-benzene scaffolds, represents intriguing yet challenging synthetic tasks. Complementary to the existing synthetic approaches, here we report an efficient and modular post-functionalization strategy that employs iridium-catalyzed C-H borylation of the highly strained meta-cycloparaphenylenes (mCPPs) and an mCPP-derived catenane. Based on the functionalized macrocyclic synthons, a number of novel all-benzene topological structures including linear and cyclic chains, polycatenane, and pretzelane have been successfully prepared and characterized, thereby showcasing the synthetic utility and potential of the post-functionalization strategy.

Learning With Constraint Learning: New Perspective, Solution Strategy and Various Applications.

The complexity of learning problems, such as Generative Adversarial Network (GAN) and its variants, multi-task and meta-learning, hyper-parameter learning, and a variety of real-world vision applications, demands a deeper understanding of their underlying coupling mechanisms. Existing approaches often address these problems in isolation, lacking a unified perspective that can reveal commonalities and enable effective solutions. Therefore, in this work, we proposed a new framework, named Learning with Constraint Learning (LwCL), that can holistically examine challenges and provide a unified methodology to tackle all the above-mentioned complex learning and vision problems. Specifically, LwCL is designed as a general hierarchical optimization model that captures the essence of these diverse learning and vision problems. Furthermore, we develop a gradient-response based fast solution strategy to overcome optimization challenges of the LwCL framework. Our proposed framework efficiently addresses a wide range of applications in learning and vision, encompassing three categories and nine different problem types. Extensive experiments on synthetic tasks and real-world applications verify the effectiveness of our approach. The LwCL framework offers a comprehensive solution for tackling complex machine learning and computer vision problems, bridging the gap between theory and practice.

Unsupervised Test-Time Adaptation Learning for Effective Hyperspectral Image Super-Resolution With Unknown Degeneration.

Fusing a low-resolution hyperspectral image (HSI) with a high-resolution (HR) multi-spectral image has provided an effective way for HSI super-resolution (SR). The key lies on inferring the posteriori of the latent (i.e., HR) HSI using an appropriate image prior and the likelihood determined by the degeneration between the latent HSI and the observed images. However, in scenarios with complex imaging environments and various imaging scenes, the prior of HSIs can be prohibitively complicated and the degeneration is often unknown, which causes it difficult to accurately infer the posteriori of each latent HSI. To tackle this problem, we present an unsupervised test-time adaptation learning (UTAL) framework for HSI SR under unknown degeneration. Instead of directly modeling the complicated image prior, it first implicitly learns a content-agnostic prior shared across different images through supervisedly pre-training a mutual-guiding fusion module on extensive synthetic data. Then, it adapts the shared prior to those private characteristics in the latent HSI for posteriori inference through unsupervisedly learning a self-guiding adaptation module and a degeneration estimation network on two observed images in the test phase. Such a two-stage learning scheme models the complicated image prior in a divide-and-conquer manner, which eases the modeling difficulty and improves the prior accuracy. Moreover, the unknown degeneration can be estimated properly. Both of these two advantages empower us to accurately infer the posteriori of the latent HSI, thereby increasing the generalization performance in real applications. Additionally, in order to further mitigate the over-fitting in coping with more challenging cases (e.g., degenerations in both spectral and spatial domains are unknown) and speed up, we propose to meta-train UTAL on extensive synthetic SR tasks and solve it using an alternative optimization strategy such that UTAL learns to produce good generalization performance in real challenging cases with a small number of gradient descent steps. To verify the efficacy of UTAL, we evaluate it on HSI SR tasks with different unknown degenerations as well as some other HSI restoration tasks (e.g., compressive sensing), and report strong results superior to that of existing competitors.

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional data representations. However, how many training examples are required to learn such representations remains unknown. To quantitatively study this question, we introduce the random hierarchy model: a family of synthetic tasks inspired by the hierarchical structure of language and images. The model is a classification task where each class corresponds to a group of high-level features, chosen among several equivalent groups associated with the same class. In turn, each feature corresponds to a group of subfeatures chosen among several equivalent groups and so on, following a hierarchy of composition rules. We find that deep networks learn the task by developing internal representations invariant to exchanging equivalent groups. Moreover, the number of data required corresponds to the point where correlations between low-level features and classes become detectable. Overall, our results indicate how deep networks overcome the curse of dimensionality by building invariant representations and provide an estimate of the number of data required to learn a hierarchical task. Published by the American Physical Society 2024

Quantum Fisher kernel for mitigating the vanishing similarity issue

Quantum kernel (QK) methods exploit quantum computers to calculate QKs for the use of kernel-based learning models. Despite a potential quantum advantage of the method, the commonly used fidelity-based QK suffers from a detrimental issue, which we call the vanishing similarity issue; the exponential decay of the expectation value and the variance of the QK deteriorates implementation feasibility and trainability of the model with the increase of the number of qubits. This implies the need to design QKs alternative to the fidelity-based one. In this work, we propose a new class of QKs called the quantum Fisher kernels (QFKs) that take into account the geometric structure of the data source. We analytically and numerically demonstrate that the QFK can avoid the issue when shallow alternating layered ansatzes are used. In addition, the Fourier analysis numerically elucidates that the QFK can have the expressivity comparable to the fidelity-based QK. Moreover, we demonstrate synthetic classification tasks where QFK outperforms the fidelity-based QK in performance due to the absence of vanishing similarity. These results indicate that QFK paves the way for practical applications of quantum machine learning toward possible quantum advantages.

A Novel Hybrid Fuzzy Multiple-Criteria Decision-Making Model for the Selection of the Most Suitable Land Reclamation Variant at Open-Pit Coal Mines

The expansion of the open-pit exploitation of mineral raw materials, and especially the energy resources of fossil fuels, makes open-pit coal mines spatially dominant objects of large mining basins. Exploitation activities are accompanied by negative ecological impacts on the environment, which requires the integral planning, revitalization, reclamation, and rehabilitation of the disturbed area for human use in the post-exploitation period. The post-exploitation remediation and rehabilitation of open-pit mining areas and disposal sites, i.e., space disturbed by mining activities and accompanying facilities, are complex synthetic multidisciplinary multiphase engineering project tasks. In this paper, a hybrid fuzzy MCDM model (Multiple-Criteria Decision-Making) was developed for the selection of a reclamation solution for the Tamnava-West Field open-pit mine. IMF SWARA (Improved Fuzzy Stepwise Weight Assessment Ratio Analysis) was applied to define the weights of 12 criteria of different structures used in the evaluation of reclamation solutions. The Fuzzy ROV (Range of Value) method was applied to select the reclamation solution from a total of 11 solutions previously obtained using a process approach. The results of the hybrid IMF SWARA—Fuzzy ROV model show that forestry is the best solution for the Tamnava-West Field open-pit mine. After the results had been obtained, verification analyses of the proposed model were performed and the best stable proposed reclamation solution was determined.

McmIQA: Multi-Module Collaborative Model for No-Reference Image Quality Assessment

No reference image quality assessment is a technique that uses computers to simulate the human visual system and automatically evaluate the perceived quality of images. In recent years, with the widespread success of deep learning in the field of computer vision, many end-to-end image quality assessment algorithms based on deep learning have emerged. However, unlike other computer vision tasks that focus on image content, an excellent image quality assessment model should simultaneously consider distortions in the image and comprehensively evaluate their relationships. Motivated by this, we propose a Multi-module Collaborative Model for Image Quality Assessment (McmIQA). The image quality assessment is divided into three subtasks: distortion perception, content recognition, and correlation mapping. And specific modules are constructed for each subtask: the distortion perception module, the content recognition module, and the correlation mapping module. Specifically, we apply two contrastive learning frameworks on two constructed datasets to train the distortion perception module and the content recognition module to extract two types of features from the image. Subsequently, using these extracted features as input, we employ a ranking loss to train the correlation mapping module to predict image quality on image quality assessment datasets. Extensive experiments conducted on seven relevant datasets demonstrated that the proposed method achieves state-of-the-art performance in both synthetic distortion and natural distortion image quality assessment tasks.

Provably Powerful Graph Neural Networks for Directed Multigraphs

This paper analyses a set of simple adaptations that transform standard message-passing Graph Neural Networks (GNN) into provably powerful directed multigraph neural networks. The adaptations include multigraph port numbering, ego IDs, and reverse message passing. We prove that the combination of these theoretically enables the detection of any directed subgraph pattern. To validate the effectiveness of our proposed adaptations in practice, we conduct experiments on synthetic subgraph detection tasks, which demonstrate outstanding performance with almost perfect results. Moreover, we apply our proposed adaptations to two financial crime analysis tasks. We observe dramatic improvements in detecting money laundering transactions, improving the minority-class F1 score of a standard message-passing GNN by up to 30%, and closely matching or outperforming tree-based and GNN baselines. Similarly impressive results are observed on a real-world phishing detection dataset, boosting three standard GNNs’ F1 scores by around 15% and outperforming all baselines. An extended version with appendices can be found on arXiv: https://arxiv.org/abs/2306.11586.

IWO-IGA—A Hybrid Whale Optimization Algorithm Featuring Improved Genetic Characteristics for Mapping Real-Time Applications onto 2D Network on Chip

Network on Chip (NoC) has emerged as a potential substitute for the communication model in modern computer systems with extensive integration. Among the numerous design challenges, application mapping on the NoC system poses one of the most complex and demanding optimization problems. In this research, we propose a hybrid improved whale optimization algorithm with enhanced genetic properties (IWOA-IGA) to optimally map real-time applications onto the 2D NoC Platform. The IWOA-IGA is a novel approach combining an improved whale optimization algorithm with the ability of a refined genetic algorithm to optimally map application tasks. A comprehensive comparison is performed between the proposed method and other state-of-the-art algorithms through rigorous analysis. The evaluation consists of real-time applications, benchmarks, and a collection of arbitrarily scaled and procedurally generated large-task graphs. The proposed IWOA-IGA indicates an average improvement in power reduction, improved energy consumption, and latency over state-of-the-art algorithms. Performance based on the Convergence Factor, which assesses the algorithm’s efficiency in achieving better convergence after running for a specific number of iterations over other efficiently developed techniques, is introduced in this research work. These results demonstrate the algorithm’s superior convergence performance when applied to real-world and synthetic task graphs. Our research findings spotlight the superior performance of hybrid improved whale optimization integrated with enhanced GA features, emphasizing its potential for application mapping in NoC-based systems.

Node-Aligned Graph-to-Graph: Elevating Template-free Deep Learning Approaches in Single-Step Retrosynthesis.

Single-step retrosynthesis in organic chemistry increasingly benefits from deep learning (DL) techniques in computer-aided synthesis design. While template-free DL models are flexible and promising for retrosynthesis prediction, they often ignore vital 2D molecular information and struggle with atom alignment for node generation, resulting in lower performance compared to the template-based and semi-template-based methods. To address these issues, we introduce node-aligned graph-to-graph (NAG2G), a transformer-based template-free DL model. NAG2G combines 2D molecular graphs and 3D conformations to retain comprehensive molecular details and incorporates product-reactant atom mapping through node alignment, which determines the order of the node-by-node graph outputs process in an autoregressive manner. Through rigorous benchmarking and detailed case studies, we have demonstrated that NAG2G stands out with its remarkable predictive accuracy on the expansive data sets of USPTO-50k and USPTO-FULL. Moreover, the model's practical utility is underscored by its successful prediction of synthesis pathways for multiple drug candidate molecules. This proves not only NAG2G's robustness but also its potential to revolutionize the prediction of complex chemical synthesis processes for future synthetic route design tasks.

EGGNet, a Generalizable Geometric Deep Learning Framework for Protein Complex Pose Scoring.

Computational prediction of molecule-protein interactions has been key for developing new molecules to interact with a target protein for therapeutics development. Previous work includes two independent streams of approaches: (1) predicting protein-protein interactions (PPIs) between naturally occurring proteins and (2) predicting binding affinities between proteins and small-molecule ligands [also known as drug-target interaction (DTI)]. Studying the two problems in isolation has limited the ability of these computational models to generalize across the PPI and DTI tasks, both of which ultimately involve noncovalent interactions with a protein target. In this work, we developed Equivariant Graph of Graphs neural Network (EGGNet), a geometric deep learning (GDL) framework, for molecule-protein binding predictions that can handle three types of molecules for interacting with a target protein: (1) small molecules, (2) synthetic peptides, and (3) natural proteins. EGGNet leverages a graph of graphs (GoG) representation constructed from the molecular structures at atomic resolution and utilizes a multiresolution equivariant graph neural network to learn from such representations. In addition, EGGNet leverages the underlying biophysics and makes use of both atom- and residue-level interactions, which improve EGGNet's ability to rank candidate poses from blind docking. EGGNet achieves competitive performance on both a public protein-small-molecule binding affinity prediction task (80.2% top 1 success rate on CASF-2016) and a synthetic protein interface prediction task (88.4% area under the precision-recall curve). We envision that the proposed GDL framework can generalize to many other protein interaction prediction problems, such as binding site prediction and molecular docking, helping accelerate protein engineering and structure-based drug development.

Personnel Training for Common Facility Management Issues in Thermal-Energy-Storage Chiller Plant using a Serious 3D Game

Background This study introduces an innovative personnel training method for facility management and maintenance of Thermal-Energy-Storage (TES) chiller plants using a serious 3D game. Training games can improve the decision-making of personnel where they can learn to deal with management of TES chiller plants in the context of this study in an active learning approach. Intervention The research aims to investigate the effectiveness of an immersive learning experience with computerized simulation and synthetic task environments as a training game for facility managers. The serious 3D game adopts a first-person perspective, allowing players to assume the role of a facility manager and actively learn how to address maintenance issues commonly encountered in chiller plants. Methods The study implemented a first-person-based serious 3D game centered around a TES chiller plant. Participants, in the role of facility managers, engaged with the game and followed instructions to gain practical knowledge in managing maintenance issues within a controlled and simulated setting. Results The findings demonstrate increased engagement and interest among personnel when learning how to manage chiller plant issues within a serious 3D game environment. Notably, personnel experienced reduced pressure compared to real-life scenarios, as they navigated the challenges without the presence of a supervisor. Limitations The study’s limitations include a higher proportion of male participants in the qualitative content analysis, which may affect the generalizability of the findings. Additionally, the absence of a control group limits the ability to make direct comparisons with traditional training methods. Conclusion The results suggest that serious 3D games hold potential as an effective training tool for facility management and maintenance personnel. By engaging in active training within simulated and synthetic task environments, personnel can enhance their skills and decision-making capabilities. However, further research with a more diverse participant sample and a control group is warranted to fully evaluate the effectiveness of this innovative personnel training approach.

Machine learning at the mesoscale: A computation-dissipation bottleneck.

The cost of information processing in physical systems calls for a trade-off between performance and energetic expenditure. Here we formulate and study a computation-dissipation bottleneck in mesoscopic systems used as input-output devices. Using both real data sets and synthetic tasks, we show how nonequilibrium leads to enhanced performance. Our framework sheds light on a crucial compromise between information compression, input-output computation and dynamic irreversibility induced by nonreciprocal interactions.

Transition Metal Complexes with Amino Acids, Peptides and Carbohydrates in Catalytic Asymmetric Synthesis: A Short Review

The present review is devoted to the application of transition metal complexes with such ligands as amino acids, peptides and carbohydrates in catalysis. The literature published over the past 20 years is surveyed. Among the distinctive features of these ligands are their versatility, optical activity, stability and availability. Furthermore, depending on the specific synthetic task to be solved, these ligands open up almost infinite opportunity for modification. Largely thanks to their multifaceted reactivity, transition metal complexes with amino acids, peptides and carbohydrates can catalyze most of the known chemical reactions affording optically pure compounds. In this review, the emphasis is placed upon C(sp3)–H activation, cross-coupling and hydrogenation (including traditional hydrogenation in the presence of hydrogen gas and hydrogenation with hydrogen transfer) reactions. The choice is not accidental, since these reactions on the one hand display the catalytic versatility of the above complexes, and on the other hand, they are widely employed in industry.