The political fallout of air pollution.

This paper studies the effect of air pollution on voting outcomes. We use data from 60 federal and state elections in Germany from 2000 to 2018 and exploit plausibly exogenous fluctuations in ambient air pollution within counties across election dates. Higher air pollution on election day shifts votes away from incumbent parties and toward opposition parties. An increase in the concentration of particulate matter (PM10) by 10 [Formula: see text]g/m[Formula: see text]-around two within-county SDs-reduces the vote share of incumbent parties by two percentage points, which is equivalent to 4% of the mean vote share. We generalize these findings by documenting similar effects with data from a weekly opinion poll and a large-scale panel survey. We provide further evidence that poor air quality leads to more negative emotions such as anger, worry, and unhappiness, which, in turn, may reduce the support for the political status quo. Overall, these results suggest that poor air quality affects decision-making in the population at large, including consequential political decisions.

Inflation in 2022 did not affect congressional voting, but abortion did.

This study examines voting in the 2022 United States congressional elections, contests that were widely expected to produce a sizable defeat for Democratic candidates for largely economic reasons. Based on a representative national probability sample of voters interviewed in both 2020 and 2022, individuals who changed their vote from one party's congressional candidate to another party's candidate did not do so in response to the salience of inflation or declining economic conditions. Instead, we find strong evidence that views on abortion were central to shifting votes in the midterm elections. Americans who favored (opposed) legal abortions were more likely to shift from voting for Republican (Democratic) candidates in 2020 to Democratic (Republican) candidates in 2022. Since a larger number of Americans supported than opposed legal abortions, the combination of these shifts ultimately improved the electoral prospects of Democratic candidates. New voters were especially likely to weigh abortion views heavily in their vote-shifting calculus. Likewise, those respondents whose confidence in the US Supreme Court declined from 2020 to 2022 were more likely to shift from voting for Republican to Democratic congressional candidates. We provide direct empirical evidence that changes in support for the Supreme Court, a nonpartisan branch of the federal government, are implicated in partisan voting behavior in another branch of government. We explore the implications of these findings for prevalent assumptions about how economic conditions influence voting, as well as for the relationship between the judiciary and electoral politics.

Part of the gender gap in voting for Democrats arises because a higher proportion of women than men voters are Black.

Women voted for the Democratic candidate more than men did in each US presidential election since 1980. We show that part of the gender gap stems from the fact that a higher proportion of women than men voters are Black, and Black voters overwhelmingly choose Democratic candidates. Past research shows that Black men have especially high rates of death, incarceration, and disenfranchisement due to criminal convictions. These disparities reduce the share of men voters who are Black. We show that the gender difference in racial composition explains 24% of the gender gap in voting Democratic. The gender gap in voting Democratic is especially large among those who are never-married, and, among them, the differing racial composition of men and women voters is more impactful than in the population at large, explaining 43% of the gender gap. We consider an alternative hypothesis that income differences between single men and women explain the gender gap in voting, but our analysis leads us to reject it. Although unmarried women are poorer than unmarried men, and lower-income voters vote slightly more Democratic, the latter difference is too small for income to explain much of the gender gap in voting. In short, the large gender gap among unmarried voters is not a reflection of the lower incomes of women's households but does reflect the fact that women voters are disproportionately Black. We used the General Social Survey as the data source for the analysis, then replicated results with the American National Election Survey data.

Comprehensive assessment of nine target prediction web services: which should we choose for target fishing?

Identification of potential targets for known bioactive compounds and novel synthetic analogs is of considerable significance. In silico target fishing (TF) has become an alternative strategy because of the expensive and laborious wet-lab experiments, explosive growth of bioactivity data and rapid development of high-throughput technologies. However, these TF methods are based on different algorithms, molecular representations and training datasets, which may lead to different results when predicting the same query molecules. This can be confusing for practitioners in practical applications. Therefore, this study systematically evaluated nine popular ligand-based TF methods based on target and ligand-target pair statistical strategies, which will help practitioners make choices among multiple TF methods. The evaluation results showed that SwissTargetPrediction was the best method to produce the most reliable predictions while enriching more targets. High-recall similarity ensemble approach (SEA) was able to find real targets for more compounds compared with other TF methods. Therefore, SwissTargetPrediction and SEA can be considered as primary selection methods in future studies. In addition, the results showed that k = 5 was the optimal number of experimental candidate targets. Finally, a novel ensemble TF method based on consensus voting is proposed to improve the prediction performance. The precision of the ensemble TF method outperforms the individual TF method, indicating that the ensemble TF method can more effectively identify real targets within a given top-k threshold. The results of this study can be used as a reference to guide practitioners in selecting the most effective methods in computational drug discovery.

Americans discount the effect of friction on voter turnout.

Whether or not someone turns out to vote depends on their beliefs (such as partisanship or sense of civic duty) and on friction-external barriers such as long travel distance to the polls. In this exploratory study, we tested whether people underestimate the effect of friction on turnout and overestimate the effect of beliefs. We surveyed a representative sample of eligible US voters before and after the 2020 election (n = 1,280). Participants' perceptions consistently underemphasized friction and overemphasized beliefs (mean d = 0.94). In participants' open-text explanations, 91% of participants listed beliefs, compared with just 12% that listed friction. In contrast, turnout was shaped by beliefs only slightly more than friction. The actual belief-friction difference was about one-fourth the size of participants' perceptions (d = 0.24). This bias emerged across a range of survey measures (open- and close-ended; other- and self-judgments) and was implicated in downstream consequences such as support for friction-imposing policies and failing to plan one's vote.

Wolf attacks predict far-right voting.

Does the return of large carnivores affect voting behavior? We study this question through the lens of wolf attacks on livestock. Sustained environmental conservation has allowed the wolf (Canis lupus) to make an impressive and unforeseen comeback across Central Europe in recent years. While lauded by conservationists, local residents often see the wolf as a threat to economic livelihoods, particularly those of farmers. As populists appear to exploit such sentiments, the wolf's reemergence is a plausible source for far-right voting behavior. To test this hypothesis, we collect fine-grained spatial data on wolf attacks and construct a municipality-level panel in Germany. Using difference-in-differences models, we find that wolf attacks are accompanied by a significant rise in far-right voting behavior, while the Green party, if anything, suffers electoral losses. We buttress this finding using local-level survey data, which confirms a link between wolf attacks and negative sentiment toward environmental protection. To explore potential mechanisms, we analyze Twitter posts, election manifestos, and Facebook ads to show that far-right politicians frame the wolf as a threat to economic livelihoods.

msBERT-Promoter: a multi-scale ensemble predictor based on BERT pre-trained model for the two-stage prediction of DNA promoters and their strengths.

BACKGROUND: A promoter is a specific sequence in DNA that has transcriptional regulatory functions, playing a role in initiating gene expression. Identifying promoters and their strengths can provide valuable information related to human diseases. In recent years, computational methods have gained prominence as an effective means for identifying promoter, offering a more efficient alternative to labor-intensive biological approaches. RESULTS: In this study, a two-stage integrated predictor called "msBERT-Promoter" is proposed for identifying promoters and predicting their strengths. The model incorporates multi-scale sequence information through a tokenization strategy and fine-tunes the DNABERT model. Soft voting is then used to fuse the multi-scale information, effectively addressing the issue of insufficient DNA sequence information extraction in traditional models. To the best of our knowledge, this is the first time an integrated approach has been used in the DNABERT model for promoter identification and strength prediction. Our model achieves accuracy rates of 96.2% for promoter identification and 79.8% for promoter strength prediction, significantly outperforming existing methods. Furthermore, through attention mechanism analysis, we demonstrate that our model can effectively combine local and global sequence information, enhancing its interpretability. CONCLUSIONS: msBERT-Promoter provides an effective tool that successfully captures sequence-related attributes of DNA promoters and can accurately identify promoters and predict their strengths. This work paves a new path for the application of artificial intelligence in traditional biology.

Unlocking Potential of Pyrochlore in Energy Systems via Soft Voting Ensemble Learning.

In traditional machine learning (ML)-based material design, the defects of low prediction accuracy, overfitting and low generalization ability are mainly caused by the training of a single ML model. Here, a Soft Voting Ensemble Learning (SVEL) approach is proposed to solve the above issues by integrating multiple ML models in the same scene, thus pursuing more stable and reliable prediction. As a case study, SVEL is applied to develop the broad chemical space of novel pyrochlore electrocatalysts with the molecular formula of A2B2O7, to explore promising pyrochlore oxides and accelerate predictions of unknown pyrochlore in the periodic table. The model successfully established the structure-property relationship of pyrochlore, and selected six cost-effective pyrochlore from the periodic table with a high prediction accuracy of 91.7%, all of which showed good electrocatalytic performance. SVEL not only effectively avoids the high costs of experimentation and lengthy computations, but also addresses biases arising from data scarcity in single models. Furthermore, it has significantly reduced the research cycle of pyrochlore by ≈ 22 years, offering broad prospects for accelerating the development of materials genomics. SVEL method is intended to integrate multiple AI models to provide broader model training clues for the AI material design community.

R5hmCFDV: computational identification of RNA 5-hydroxymethylcytosine based on deep feature fusion and deep voting.

RNA 5-hydroxymethylcytosine (5hmC) is a kind of RNA modification, which is related to the life activities of many organisms. Studying its distribution is very important to reveal its biological function. Previously, high-throughput sequencing was used to identify 5hmC, but it is expensive and inefficient. Therefore, machine learning is used to identify 5hmC sites. Here, we design a model called R5hmCFDV, which is mainly divided into feature representation, feature fusion and classification. (i) Pseudo dinucleotide composition, dinucleotide binary profile and frequency, natural vector and physicochemical property are used to extract features from four aspects: nucleotide composition, coding, natural language and physical and chemical properties. (ii) To strengthen the relevance of features, we construct a novel feature fusion method. Firstly, the attention mechanism is employed to process four single features, stitch them together and feed them to the convolution layer. After that, the output data are processed by BiGRU and BiLSTM, respectively. Finally, the features of these two parts are fused by the multiply function. (iii) We design the deep voting algorithm for classification by imitating the soft voting mechanism in the Python package. The base classifiers contain deep neural network (DNN), convolutional neural network (CNN) and improved gated recurrent unit (GRU). And then using the principle of soft voting, the corresponding weights are assigned to the predicted probabilities of the three classifiers. The predicted probability values are multiplied by the corresponding weights and then summed to obtain the final prediction results. We use 10-fold cross-validation to evaluate the model, and the evaluation indicators are significantly improved. The prediction accuracy of the two datasets is as high as 95.41% and 93.50%, respectively. It demonstrates the stronger competitiveness and generalization performance of our model. In addition, all datasets and source codes can be found at https://github.com/HongyanShi026/R5hmCFDV.

Valence and interactions in judicial voting.

The collective statistics of voting on judicial courts present hints about their inner workings. Many approaches for studying these statistics, however, assume that judges' decisions are conditionally independent: a judge reaches a decision based on the case at hand and his or her personal views. In reality, judges interact. We develop a minimal model that accounts for judge bias, depending on the context of the case, and peer interaction. We apply the model to voting data from the US Supreme Court. We find strong evidence that interaction is an important factor across natural courts from 1946 to 2021. We also find that, after accounting for interaction, the recovered biases differ from highly cited ideological scores. Our method exemplifies how physics and complexity-inspired modelling can drive the development of theoretical models and improved measures for political voting. This article is part of the theme issue 'A complexity science approach to law and governance'.

Heterogeneous Thresholds, Social Ranking, and the Emergence of Vague Categories.

Threshold models in which an individual's response to a particular state of the world depends on whether an associated measured value exceeds a given threshold are common in a variety of social learning and collective decision-making scenarios in both natural and artificial systems. If thresholds are heterogeneous across a population of agents, then graded population level responses can emerge in a context in which individual responses are discrete and limited. In this article, I propose a threshold-based model for social learning of shared quality categories. This is then combined with the voting model of fuzzy categories to allow individuals to learn membership functions from their peers, which can then be used for decision-making, including ranking a set of available options. I use agent-based simulation experiments to investigate variants of this model and compare them to an individual learning benchmark when applied to the ranking problem. These results show that a threshold-based approach combined with category-based voting across a social network provides an effective social mechanism for ranking that exploits emergent vagueness.

Artificial intelligence in tongue diagnosis: classification of tongue lesions and normal tongue images using deep convolutional neural network.

OBJECTIVE: This study aims to classify tongue lesion types using tongue images utilizing Deep Convolutional Neural Networks (DCNNs). METHODS: A dataset consisting of five classes, four tongue lesion classes (coated, geographical, fissured tongue, and median rhomboid glossitis), and one healthy/normal tongue class, was constructed using tongue images of 623 patients who were admitted to our clinic. Classification performance was evaluated on VGG19, ResNet50, ResNet101, and GoogLeNet networks using fusion based majority voting (FBMV) approach for the first time in the literature. RESULTS: In the binary classification problem (normal vs. tongue lesion), the highest classification accuracy performance of 93,53% was achieved utilizing ResNet101, and this rate was increased to 95,15% with the application of the FBMV approach. In the five-class classification problem of tongue lesion types, the VGG19 network yielded the best accuracy rate of 83.93%, and the fusion approach improved this rate to 88.76%. CONCLUSION: The obtained test results showed that tongue lesions could be identified with a high accuracy by applying DCNNs. Further improvement of these results has the potential for the use of the proposed method in clinic applications.

Big Five personality traits predict small but robust differences in civic engagement.

OBJECTIVE: This preregistered study provides robust estimates of the links between Big Five personality traits and civic engagement across different samples and life stages. METHODS: We recruited two samples from the United States and United Kingdom (total N = 1593) and measured Big Five domains, Big Five aspects, and six civic engagement indicators: volunteerism, charitable giving, donating blood, posthumous organ donation, political voting, and vaccination. We compared the links between these measures across samples and tested moderation across life stages and several sociodemographic variables. We explored whether these links replicate between self- and peer-reports. RESULTS: We found small but robust effects. Agreeable, extraverted, and open/intellectual participants reported more civic engagement, especially volunteerism and charitable giving. Neurotic and conscientious participants mainly reported less civic engagement, especially blood and organ donations. One of the two Big Five aspects often drove these links, such as Compassion in the link between Agreeableness and volunteerism. We found some differences between younger and middle-aged adults. CONCLUSIONS: Big Five personality traits predict civic engagement modestly but consistently, with adequate study power being critical to detecting these links. Lower-order traits, such as Big Five aspects, clarify the relationships between traits and engagement. Life stages and sociodemographic variables have limited effects.

Individual vulnerability to industrial robot adoption increases support for the radical right.

The increasing success of populist and radical-right parties is one of the most remarkable developments in the politics of advanced democracies. We investigate the impact of industrial robot adoption on individual voting behavior in 13 western European countries between 1999 and 2015. We argue for the importance of the distributional consequences triggered by automation, which generates winners and losers also within a given geographic area. Analysis that exploits only cross-regional variation in the incidence of robot adoption might miss important facets of this process. In fact, patterns in individual indicators of economic distress and political dissatisfaction are masked in regional-level analysis, but can be clearly detected by exploiting individual-level variation. We argue that traditional measures of individual exposure to automation based on the current occupation of respondents are potentially contaminated by the consequences of automation itself, due to direct and indirect occupational displacement. We introduce a measure of individual exposure to automation that combines three elements: 1) estimates of occupational probabilities based on employment patterns prevailing in the preautomation historical labor market, 2) occupation-specific automatability scores, and 3) the pace of robot adoption in a given country and year. We find that individuals more exposed to automation tend to display higher support for the radical right. This result is robust to controlling for several other drivers of radical-right support identified by earlier literature: nativism, status threat, cultural traditionalism, and globalization. We also find evidence of significant interplay between automation and these other drivers.

A polygenic score for educational attainment partially predicts voter turnout.

Twin and adoption studies have shown that individual differences in political participation can be explained, in part, by genetic variation. However, these research designs cannot identify which genes are related to voting or the pathways through which they exert influence, and their conclusions rely on possibly restrictive assumptions. In this study, we use three different US samples and a Swedish sample to test whether genes that have been identified as associated with educational attainment, one of the strongest correlates of political participation, predict self-reported and validated voter turnout. We find that a polygenic score capturing individuals' genetic propensity to acquire education is significantly related to turnout. The strongest associations we observe are in second-order midterm elections in the United States and European Parliament elections in Sweden, which tend to be viewed as less important by voters, parties, and the media and thus present a more information-poor electoral environment for citizens to navigate. A within-family analysis suggests that individuals' education-linked genes directly affect their voting behavior, but, for second-order elections, it also reveals evidence of genetic nurture. Finally, a mediation analysis suggests that educational attainment and cognitive ability combine to account for between 41% and 63% of the relationship between the genetic propensity to acquire education and voter turnout.

Results from a 2020 field experiment encouraging voting by mail.

The ability to cast a mail ballot can safeguard the franchise. However, because there are often additional procedural protections to ensure that a ballot cast in person counts, voting by mail can also jeopardize people's ability to cast a recorded vote. An experiment carried out during the COVID-19 pandemic illustrates both forces. Philadelphia officials randomly sent 46,960 Philadelphia registrants postcards encouraging them to apply to vote by mail in the lead-up to the June 2020 primary election. While the intervention increased the likelihood a registrant cast a mail ballot by 0.4 percentage points (P = 0.017)-or 3%-many of these additional mail ballots counted only because a last-minute policy intervention allowed most mail ballots postmarked by Election Day to count.

A comprehensive prediction system for silkworm acute toxicity assessment of environmental and in-silico pesticides.

The excessive application and loss of pesticides poses a great risk to the ecosystem, and the environmental safety assessment of pesticides is time-consuming and expensive using traditional animal toxicity tests. In this work, a pesticide acute toxicity dataset was created for silkworm integrating extensive experiments and various common pesticide formulations considering the sensitivity of silkworm to adverse environment, its economic value in China, and a gap in machine learning (ML) research on the toxicity prediction of this species, which addressed the previous limitation of only being able to predict toxicity classification without specific toxicity values. A new comprehensive voting model (CVR) was developed based on ML, combined with three regression algorithms, namely, Bayesian Ridge (BR), K Neighbors Regressor (KNN), Random Forest Regressor (RF) to accurately calculate lethal concentration 50 % (LC50). Three conformal models were successfully constructed, marking the first combination of conformal models with confidence intervals to predict silkworm toxicity. Further, the mechanism by analyzing structural alerts was summarized, and identified 25 warning structures, 24 positive compounds and 14 negative compounds. Importantly, a novel comprehensive prediction system was constructed that can provide LC50 and confidence intervals, structural alerts analysis, lipid-water partition coefficient (LogP) and similarity analysis, which can comprehensively evaluate the ecological toxicity risk of substances to make up for the incomplete toxicity data of new pesticides. The validity and generalization of the CVR model were verified by an external validation set. In addition, five new, low-toxic and green pesticide alternatives were designed through 50,000 cycles. Moreover, our software and ST Profiler can provide low-cost information access to accelerate environmental risk assessment, which can predict not only a single chemical, but also batches of chemicals, simply by inputting the SMILES / CAS / (Chinese / English) name of chemicals.

Improved liver disease prediction from clinical data through an evaluation of ensemble learning approaches.

PURPOSE: Liver disease causes two million deaths annually, accounting for 4% of all deaths globally. Prediction or early detection of the disease via machine learning algorithms on large clinical data have become promising and potentially powerful, but such methods often have some limitations due to the complexity of the data. In this regard, ensemble learning has shown promising results. There is an urgent need to evaluate different algorithms and then suggest a robust ensemble algorithm in liver disease prediction. METHOD: Three ensemble approaches with nine algorithms are evaluated on a large dataset of liver patients comprising 30,691 samples with 11 features. Various preprocessing procedures are utilized to feed the proposed model with better quality data, in addition to the appropriate tuning of hyperparameters and selection of features. RESULTS: The models' performances with each algorithm are extensively evaluated with several positive and negative performance metrics along with runtime. Gradient boosting is found to have the overall best performance with 98.80% accuracy and 98.50% precision, recall and F1-score for each. CONCLUSIONS: The proposed model with gradient boosting bettered in most metrics compared with several recent similar works, suggesting its efficacy in predicting liver disease. It can be further applied to predict other diseases with the commonality of predicate indicators.

Voter emotional responses and voting behaviour in the 2020 US presidential election.

Political polarisation in the United States offers opportunities to explore how beliefs about candidates - that they could save or destroy American society - impact people's thoughts, feelings, and behaviour. Participants forecast their future emotional responses to the contentious 2020 U.S. presidential election, and reported their actual responses after the election outcome. Stronger beliefs about candidates were associated with forecasts of greater emotion in response to the election, but the strength of this relationship differed based on candidate preference. Trump supporters' forecast happiness more strongly related to beliefs that their candidate would save society than for Biden supporters. Biden supporters' forecast anger and fear were more strongly related to beliefs that Trump would destroy society than vice versa. These forecasts mattered: predictions of lower happiness and greater anger if the non-preferred candidate won predicted voting, with Biden supporters voting more than Trump supporters. Generally, participants forecast more emotion than they experienced, but beliefs altered this tendency. Stronger beliefs predicted experiencing more happiness or more anger and fear about the election outcome than had been forecast. These findings have implications for understanding the mechanisms through which political polarisation and rhetoric can influence voting behaviour.

A Crowdsourced AI Framework for Atrial Fibrillation Detection in Apple Watch and Kardia Mobile ECGs.

Background: Atrial fibrillation (AFib) detection via mobile ECG devices is promising, but algorithms often struggle to generalize across diverse datasets and platforms, limiting their real-world applicability. Objective: This study aims to develop a robust, generalizable AFib detection approach for mobile ECG devices using crowdsourced algorithms. Methods: We developed a voting algorithm using random forest, integrating six open-source AFib detection algorithms from the PhysioNet Challenge. The algorithm was trained on an AliveCor dataset and tested on two disjoint AliveCor datasets and one Apple Watch dataset. Results: The voting algorithm outperformed the base algorithms across all metrics: the average of sensitivity (0.884), specificity (0.988), PPV (0.917), NPV (0.985), and F1-score (0.943) on all datasets. It also demonstrated the least variability among datasets, signifying its highest robustness and effectiveness in diverse data environments. Moreover, it surpassed Apple's algorithm on all metrics and showed higher specificity but lower sensitivity than AliveCor's Kardia algorithm. Conclusions: This study demonstrates the potential of crowdsourced, multi-algorithmic strategies in enhancing AFib detection. Our approach shows robust cross-platform performance, addressing key generalization challenges in AI-enabled cardiac monitoring and underlining the potential for collaborative algorithms in wearable monitoring devices.