Search

Abstract Pretrained Graph Neural Networks have been widely adopted for various molecular property prediction tasks. Despite their ability to encode structural and relational features of molecules, traditional fine-tuning of such pretrained GNNs on the target task can lead to poor generalization. To address this, we explore the adaptation of pretrained GNNs to the target task by jointly training them with multiple auxiliary tasks. This could enable the GNNs to learn both general and task-specific features, which may benefit the target task. However, a major challenge is to determine the relatedness of auxiliary tasks with the target task. To address this, we investigate multiple strategies to measure the relevance of auxiliary tasks and integrate such tasks by adaptively combining task gradients or by learning task weights via bi-level optimization. Additionally, we propose a novel gradient surgery-based approach, Rotation of Conflicting Gradients ( $$\mathop {\texttt{RCGrad}}\limits$$ RCGrad ), that learns to align conflicting auxiliary task gradients through rotation. Our experiments with state-of-the-art pretrained GNNs demonstrate the efficacy of our proposed methods, with improvements of up to 7.7% over fine-tuning. This suggests that incorporating auxiliary tasks along with target task fine-tuning can be an effective way to improve the generalizability of pretrained GNNs for molecular property prediction. Scientific contribution We introduce a novel framework for adapting pretrained GNNs to molecular tasks using auxiliary learning to address the critical issue of negative transfer. Leveraging novel gradient surgery techniques such as $$\mathop {\texttt{RCGrad}}\limits$$ RCGrad , the proposed adaptation framework represents a significant departure from the dominant pretraining fine-tuning approach for molecular GNNs. Our contributions are significant for drug discovery research, especially for tasks with limited data, filling a notable gap in the efficient adaptation of pretrained models for molecular GNNs.

Objective Riveting quality issues cannot be visually judged. By employing the far-field eddy current testing method, internal quality defects in riveted structural components can be detected, providing theoretical and technical support for product quality inspection. Method Riveting quality inspection and classification of clearance types are conducted without damaging the workpiece. Far-field eddy current testing experiments are carried out for the intermediate plate clearance and rivet hole clearance of rail vehicle riveted structural components respectively. Testing research on metro vehicle anti-roll torsion bar seats riveted to the body frame side beams is also conducted. Result & Conclusion From the results of the three sets of experiments, it is evident that the range of phase angles can distinguish between rivet and hole clearances and plate clearances. The phase amplitude range for hole clearances is 60° to 90°, while for plate clearances, it is 0 to 10°.

Abstract Due to cancer’s complex nature and variable response to therapy, precision oncology informed by omics sequence analysis has become the current standard of care. However, the amount of data produced for each patient makes it difficult to quickly identify the best treatment regimen. Moreover, limited data availability has hindered computational methods’ abilities to learn patterns associated with effective drug-cell line pairs. In this work, we propose the use of contrastive learning to improve learned drug and cell line representations by preserving relationship structures associated with drug mechanisms of action and cell line cancer types. In addition to achieving enhanced performance relative to a state-of-the-art method, we find that classifiers using our learned representations exhibit a more balanced reliance on drug- and cell line-derived features when making predictions. This facilitates more personalized drug prioritizations that are informed by signals related to drug resistance.

The developmental toxicity and human health risks of triazole fungicides (TFs) have attracted worldwide attention due to the ability to enter the human body in a variety of ways. Nevertheless, the specific mechanism by which TFs exert remains incompletely understood. Given that retinoic acid (RA) signaling pathway are closely related to development, this study aimed to screen and identify developmentally disabled chemicals in commonly used TFs and to reveal the potential effects of TFs on developmental retardation through the RA signaling pathway in mouse embryonic stem cells (mESCs). Specifically, six typical TFs (myclobutanil, tebuconazole, hexaconazole, propiconazole, difenoconazole, and flusilazole) were exposed through the construction of an embryoid bodies (EBs)-based in vitro global differentiation models. Our results clarified that various TFs disturbed lineage commitment during early embryonic development. Crucially, the activation of RA signaling pathway, which alters the expression of key genes and interferes the transport and metabolism of retinol, may be responsible for this effect. Furthermore, molecular docking, molecular dynamics simulations, and experiments using a retinoic acid receptor α inhibitor provide evidence supporting the potential modulatory role of the retinoic acid signaling pathway in developmental injury. The current study offers new insights into the TFs involved in the RA signaling pathway that interfere with the differentiation process of mESCs, which is crucial for understanding the impact of TFs on pregnancy and early development.

ObjectiveExisting literature has not clearly elucidated whether SARS-CoV-2 infection increases the incidence of Parkinson’s disease or if Parkinson’s disease patients are more susceptible to the effects of SARS-CoV-2 infection. To clarify the issue, this study employs a genetic epidemiological approach to investigate the association.MethodsThis study utilizes a two-sample Mendelian randomization analysis. The primary analysis employs the inverse variance-weighted (IVW) method, supplemented by secondary analyses including MR-Egger regression, weighted median, IVW radial method, and weighted mode, to evaluate the bidirectional causal relationship between Parkinson’s disease and SARS-CoV-2 infection.ResultsIVW results showed no genetic causality between SARS-CoV-2 susceptibility, hospitalization rate and severity and Parkinson’s disease. (IVW method: p = 0.408 OR = 1.10 95% CI: 0.87 ~ 1.39; p = 0.744 OR = 1.11 95% CI: 0.94 ~ 1.09; p = 0.436 OR = 1.05 95% CI: 0.93 ~ 1.17). Parkinson’s disease was not genetically associated with susceptibility to new crown infections, hospitalization rates, and severity (IVW method: p = 0.173 OR = 1.01 95% CI: 0.99 ~ 1.03; p = 0.109 OR = 1.05 95% CI: 0.99 ~ 1.12; p = 0.209 OR = 1.03 95% CI: 0.99 ~ 1.07). MR-Egger regression, weighted median, IVW radial method, and weighted mode results are consistent with the results of the IVW method.ConclusionThis study does not support a genetic link between Parkinson’s disease and SARS-CoV-2 infection, and the association observed in previous cohort studies and observational studies may be due to other confounding factors.

Background: Colorectal cancer (CRC) patients experience multiple types of chemotoxicity affecting treatment compliance, survival, and quality of life (QOL). Prior research shows clinician-reported chemotoxicity (i.e., grading scales or diagnostic codes) predicts rehospitalization and cancer survival. However, a comprehensive synthesis of clinician-reported chemotoxicity is still lacking. Objectives: We conducted a systematic review and meta-analysis to determine chemotoxicity’s prevalence and risk factors in CRC. Methods: A systematic search from 2009 to 2024 yielded 30 studies for review, with 25 included in the meta-analysis. Results: Pooled prevalences of overall, non-hematological, and hematological moderate-to-severe toxicities were 45.7%, 39.2%, and 25.3%, respectively. The most common clinician-reported chemotoxicities were gastrointestinal (GI) toxicity (22.9%) and neuropathy or neutropenia (17.9%). Significant risk factors at baseline were malnutritional status, frailty, impaired immune or hepato-renal functions, short telomere lengths, low gut lactobacillus levels, age, female sex, aggressive chemotherapy, and low QOL. Age was associated with neutropenia (β: −1.44) and GI toxicity (β:1.85) (p-values < 0.01). Older adults (>65 y.o.) had higher prevalences of overall (OR: 1.14) and GI (OR: 1.65) toxicities, but a lower prevalence of neutropenia (OR: 0.65) than younger adults (p-values < 0.05). Conclusions. Our findings highlight the importance of closely monitoring and managing chemotoxicity in CRC patients receiving chemotherapy.

Odor compounds produced in salted egg yolk during thermal processing were identify by sensory evaluation and gas chromatography-mass spectrometry (GC-MS) combined with multivariate statistical analysis such as hierarchical cluster analysis (HCA), orthogonal partial least squares-discriminant analysis (OPLS-DA) and principal component analysis (PCA). By using quantitative descriptive sensory analysis, it was found that there was a significant difference in the flavor profile between egg yolk samples with and without unpleasant odor, and it was determined that some egg yolks had obvious off-flavor during hot processing. Cluster analysis showed that the six groups of salted egg yolk samples were clearly divided into two categories, which was consistent with the sensory evaluation results. Furthermore, OPLS-DA identified 33 major differential components with variable importance in the projection (VIP) scores greater than one between samples with and without unpleasant odor, and aldehydes and alcohols were the most significant differential components. Finally, the volatile compounds showing a positive correlation with sour odor were screened by PCA, and n-hexanal, n-valeraldehyde, 1-octen-3-ol, trans,trans-2,4-decadienal, styrene, dimethyl disulfide and 2-nonone were identified due to their odor activity values (OAV) greater than one as the major odor compounds of salted egg yolk during thermal processing. The results provide a reference for analysis of the flavor characteristics and possible off-flavor components of salted egg yolk after thermal processing and provide a scientific basis for accessing the quality of salted egg yolk.

Particulate matter of size ≤ 2.5 μm (PM2.5) is a critical environmental threat that considerably contributes to the global disease burden. However, accompanied by the rapid research progress in this field, the existing research on developmental toxicity is still constrained by limited data sources, varying quality, and insufficient in-depth mechanistic analysis. This review includes the currently available epidemiological and laboratory evidence and comprehensively characterizes the adverse effects of PM2.5 on developing individuals in different regions and various pollution sources. In addition, this review explores the effect of PM2.5 exposure to individuals of different ethnicities, genders, and socioeconomic levels on adverse birth outcomes and cardiopulmonary and neurological development. Furthermore, the molecular mechanisms involved in the adverse health effects of PM2.5 primarily encompass transcriptional and translational regulation, oxidative stress, inflammatory response, and epigenetic modulation. The primary findings and novel perspectives regarding the association between public health and PM2.5 were examined, highlighting the need for future studies to explore its sources, composition, and sex-specific effects. Additionally, further research is required to delve deeper into the more intricate underlying mechanisms to effectively prevent or mitigate the harmful effects of air pollution on human health.

Abstract Background Computational drug repurposing is crucial for identifying candidate therapeutic medications to address the urgent need for developing treatments for newly emerging infectious diseases. The recent COVID-19 pandemic has taught us the importance of rapidly discovering candidate drugs and providing them to medical and pharmaceutical experts for further investigation. Network-based approaches can provide repurposable drugs quickly by leveraging comprehensive relationships among biological components. However, in a case of newly emerging disease, applying a repurposing methods with only pre-existing knowledge networks may prove inadequate due to the insufficiency of information flow caused by the novel nature of the disease. Methods We proposed a network-based complementary linkage method for drug repurposing to solve the lack of incoming new disease-specific information in knowledge networks. We simulate our method under the controlled repurposing scenario that we faced in the early stage of the COVID-19 pandemic. First, the disease-gene-drug multi-layered network was constructed as the backbone network by fusing comprehensive knowledge database. Then, complementary information for COVID-19, containing data on 18 comorbid diseases and 17 relevant proteins, was collected from publications or preprint servers as of May 2020. We estimated connections between the novel COVID-19 node and the backbone network to construct a complemented network. Network-based drug scoring for COVID-19 was performed by applying graph-based semi-supervised learning, and the resulting scores were used to validate prioritized drugs for population-scale electronic health records-based medication analyses. Results The backbone networks consisted of 591 diseases, 26,681 proteins, and 2,173 drug nodes based on pre-pandemic knowledge. After incorporating the 35 entities comprised of complemented information into the backbone network, drug scoring screened top 30 potential repurposable drugs for COVID-19. The prioritized drugs were subsequently analyzed in electronic health records obtained from patients in the Penn Medicine COVID-19 Registry as of October 2021 and 8 of these were found to be statistically associated with a COVID-19 phenotype. Conclusion We found that 8 of the 30 drugs identified by graph-based scoring on complemented networks as potential candidates for COVID-19 repurposing were additionally supported by real-world patient data in follow-up analyses. These results show that our network-based complementary linkage method and drug scoring algorithm are promising strategies for identifying candidate repurposable drugs when new emerging disease outbreaks.

Abstract Retrosynthesis is a procedure where a target molecule is transformed into potential reactants and thus the synthesis routes can be identified. Recently, computational approaches have been developed to accelerate the design of synthesis routes. In this paper,we develop a generative framework G 2 Retro for one-step retrosynthesis prediction. G 2 Retro imitates the reversed logic of synthetic reactions. It first predicts the reaction centers in the target molecules (products), identifies the synthons needed to assemble the products, and transforms these synthons into reactants. G 2 Retro defines a comprehensive set of reaction center types, and learns from the molecular graphs of the products to predict potential reaction centers. To complete synthons into reactants, G 2 Retro considers all the involved synthon structures and the product structures to identify the optimal completion paths, and accordingly attaches small substructures sequentially to the synthons. Here we show that G 2 Retro is able to better predict the reactants for given products in the benchmark dataset than the state-of-the-art methods.

Objective: To investigate the performance of machine learning (ML) methods for predicting outcomes from inpatient rehabilitation for subjects with TBI using a dataset with a large number of predictor variables. Our second objective was to identify top predictive features selected by the ML models for each outcome and to validate the interpretability of the models. Design: Secondary analysis using computational modeling of relationships between patients, injury and treatment activities and 6 outcomes, applied to the large multi-site, prospective, longitudinal observational dataset collected during the traumatic brain injury inpatient rehabilitation study. Setting: Acute inpatient rehabilitation. Participants: 1946 patients aged 14 years or older, who sustained a severe, moderate, or complicated mild TBI, and were admitted to 1 of 9 US inpatient rehabilitation sites between 2008 and 2011 (N=1946). Main Outcome Measures: Rehabilitation length of stay, discharge to home, FIM cognitive and FIM motor at discharge and at 9-months post discharge. Results: Advanced ML models, specifically gradient boosting tree model, performed consistently better than all other models, including classical linear regression models. Top ranked predictive features were identified for each of the 6 outcome variables. Level of effort, days to rehabilitation admission, age at rehabilitation admission, and advanced mobility activities were the most frequently top ranked predictive features. The highest-ranking predictive feature differed across the specific outcome variable. Conclusions: Identifying patient, injury, and rehabilitation treatment variables that are predictive of better outcomes will contribute to cost-effective care delivery and guide evidence-based clinical practice. ML methods can contribute to these efforts.