The evolution of endocrine disruptor chemical assessments worldwide in the last three decades.

Endocrine Disrupting Chemicals (EDCs) encompass a wide variety of substances capable of interfering with the endocrine system, including but not limited to bisphenol A, organochlorines, polybrominated flame retardants, alkylphenols and phthalates. These compounds are widely produced and used in everyday modern life and have increasingly been detected in aquatic matrices worldwide. In this context, this study aimed to carry out a literature review to assess the evolution of EDCs detected in different matrices in the last thirty years. A bibliometric analysis was conducted at the Scopus, Web of Science, and Google Scholar databases. Data were evaluated using the Vosviewer 1.6.17 software. A total of 3951 articles in English were retrieved following filtering. The results demonstrate a gradual and significant growth in the number of published documents, strongly associated with the increasing knowledge on the real environmental impacts of these compounds. Studied were mostly conducted by developed countries in the first two decades, 1993 to 2012, but in the last decade (2013 to 2022), an exponential leap in the number of publications by countries such as China and an advance in research by developing countries, such as Brazil, was verified.

Predicting lifespan-extending chemical compounds for C. elegans with machine learning and biologically interpretable features.

Recently, there has been a growing interest in the development of pharmacological interventions targeting ageing, as well as in the use of machine learning for analysing ageing-related data. In this work, we use machine learning methods to analyse data from DrugAge, a database of chemical compounds (including drugs) modulating lifespan in model organisms. To this end, we created four types of datasets for predicting whether or not a compound extends the lifespan of C. elegans (the most frequent model organism in DrugAge), using four different types of predictive biological features, based on: compound-protein interactions, interactions between compounds and proteins encoded by ageing-related genes, and two types of terms annotated for proteins targeted by the compounds, namely Gene Ontology (GO) terms and physiology terms from the WormBase's Phenotype Ontology. To analyse these datasets, we used a combination of feature selection methods in a data pre-processing phase and the well-established random forest algorithm for learning predictive models from the selected features. In addition, we interpreted the most important features in the two best models in light of the biology of ageing. One noteworthy feature was the GO term "Glutathione metabolic process", which plays an important role in cellular redox homeostasis and detoxification. We also predicted the most promising novel compounds for extending lifespan from a list of previously unlabelled compounds. These include nitroprusside, which is used as an antihypertensive medication. Overall, our work opens avenues for future work in employing machine learning to predict novel life-extending compounds.

Different criteria for body mass index classification for excess weight screening in children aged six to ten years.

OBJECTIVE: To evaluate the agreement between body mass index (BMI) parameters applied to children aged six to ten years in the city of Montes Claros (MG), Brazil with national and international criteria, also calculating their sensitivity and specificity regarding excess weight screening. METHODS: A sample comprising 4151 children aged six to ten years was assessed, with height and body mass determined for BMI calculation. The obtained values were classified according to cutoff points established by the World Health Organization (WHO), International Obesity Task Force (IOTF), Centers for Disease Control and Prevention (CDC), Conde & Monteiro, and a recent local proposal. The agreement index between the mentioned criteria was calculated and thereafter the sensitivity and specificity. RESULTS: The local proposal was proven to be highly consistent in most combinations, especially concerning the excess weight criteria of the World Health Organization (WHO) (k=0.895). Regarding excess weight, the local proposal presented sensitivity and specificity values of 0.8680 and 0.9956, respectively, indicating high BMI discrimination power. CONCLUSIONS: The locally applied BMI parameters for children aged six to ten years represent a valid, highly viable and practical proposal for excess weight screening in this population group, improving professional decision-making in their follow-up.

Body morphology and bone age in girls with obesity and without obesity aged 8 to 15 years: a cross-sectional study / Morfologia corporal e idade óssea em meninas com obesidade e sem obesidade de 8 a 15 anos: um estudo transversal

Introduction: childhood obesity is one of the main public health problems worldwide, leading to health status repercussions and growth and maturation process implications in both children and adolescents. Objective: the aim of this study was to verify body morphology and bone age variations in girls with obesity and without obesity. Methodology: this comprises a cross-sectional study conducted with 140 girls aged 8 to 15 years old, 70 with obesity and 70 without obesity. Hip and waist circumferences, body mass, height and and Body Mass Index (BMI) were determined. For maturation status determinations, bone ages were determined by a left wrist and hand radiography employing the Fels method. Results: the findigs indicate significant correlations between nutritional and maturation statuses (r=0.80; p˂0.01). Girls with obesity presented higher weight and BMI values, larger waist and hip circumferences and more advanced bone age compared to girls without obesity (p˂0.01). The same significant differences (p˂0.01) were noted in the contrasting maturational group analysis, where girls presenting advanced maturation always exhibited the highest parameter values. Conclusion: nutritional status is associated to maturation status, and girls with obesity exhibit more advanced bone age than girls without obesity.

Introdução: a obesidade infantil é um dos principais problemas de saúde pública mundial, com repercussões no estado de saúde e implicações no processo de crescimento e maturação de crianças e adolescentes. Objetivo: verificar a variação da morfologia corporal e da idade óssea em meninas com e sem obesidade. Metodologia: estudo transversal conduzido com 140 meninas de 8 a 15 anos de idade, sendo 70 meninas com obesidade e 70 sem obesidade. Foram mensuradas as circunferências do quadril e da cintura, massa corporal, altura e o Índice de Massa Corporal (IMC). Para o status maturacional foi determinada a idade óssea por meio de radiografia de punho e mão esquerdos pelo Método Fels. Resultados: os resultados apontaram a existência de correlação entre o status nutricional e o status maturacional (r=0,80; p˂0,01). As meninas com obesidade apresentaram maior peso, IMC mais elevado, circunferências maiores e idade óssea mais avançada quando comparadas às meninas sem obesidade (p˂0,01). Na análise dos grupos maturacionais contrastantes as mesmas diferenças se apresentaram com valores significativos (p˂0,01), sendo as meninas avançadas maturacionalmente sempre com valores superiores. Conclusão: o status nutricional apresentou correlação com o status maturacional, e as meninas com obesidade apresentam idade óssea mais avançada que aquelas sem obesidade

Machine learning methods applied to audit of surgical margins after curative surgery for facial (non-melanoma) skin cancer.

We aimed to build a model to predict positive margin status after curative excision of facial non-melanoma skin cancer based on known risk factors that contribute to the complexity of the case mix. A pathology output of consecutive histology reports was requested from three oral and maxillofacial units in the south east of England. The dependent variable was a deep margin with peripheral margin clearance at a 0.5 mm threshold. A total of 3354 cases were analysed. Positivity of either the peripheral or deep margin for both squamous cell carcinoma (SCC) and basal cell carcinoma (BCC) was 15.4% at Unit 1, 21.1% at Unit 2, and 15.4% at Unit 3. Predictive models accounting for patient and tumour factors were developed using automated machine learning methods. The champion models demonstrated good discrimination for predicting margin status after excision of BCCs (AUROC = 0.67) and SCCs (AUROC = 0.71). We demonstrate that rates of positive excision margins of facial non-melanoma skin cancer (fNMSC), when adjusted by the risk prediction model, can be used to compare unit performance fairly once variations in tumour factors and patient factors are accounted for.

Interpretable Ensembles of Classifiers for Uncertain Data With Bioinformatics Applications.

Data uncertainty remains a challenging issue in many applications, but few classification algorithms can effectively cope with it. An ensemble approach for uncertain categorical features has recently been proposed, achieving promising results. It consists in biasing the sampling of features for each model in an ensemble so that less uncertain features are more likely to be sampled. Here we extend this idea of biased sampling and propose two new approaches: one for selecting training instances for each model in an ensemble and another for sampling features to be considered when splitting a node in a Random Forest training. We applied these approaches to classify ageing-related genes and predict drugs' side effects based on uncertain features representing protein-protein and protein-chemical interactions. We show that ensembles based on our proposed approaches achieve better predictive performance. In particular, our proposed approaches improved the performance of a Random Forest based on the most sophisticated approach for handling uncertain data in ensembles of this kind. Furthermore, we propose two new approaches for interpreting an ensemble of Naive Bayes classifiers and analyse their results on our datasets of ageing-related genes and drug's side effects.

Different criteria for body mass index classification for excess weight screening in children aged six to ten years / Diferentes critérios de classificação do índice de massa corporal para o rastreio do excesso de peso em crianças de seis a dez anos

ABSTRACT Objective: To evaluate the agreement between body mass index (BMI) parameters applied to children aged six to ten years in the city of Montes Claros (MG), Brazil with national and international criteria, also calculating their sensitivity and specificity regarding excess weight screening. Methods: A sample comprising 4151 children aged six to ten years was assessed, with height and body mass determined for BMI calculation. The obtained values were classified according to cutoff points established by the World Health Organization (WHO), International Obesity Task Force (IOTF), Centers for Disease Control and Prevention (CDC), Conde & Monteiro, and a recent local proposal. The agreement index between the mentioned criteria was calculated and thereafter the sensitivity and specificity. Results: The local proposal was proven to be highly consistent in most combinations, especially concerning the excess weight criteria of the World Health Organization (WHO) (k=0.895). Regarding excess weight, the local proposal presented sensitivity and specificity values of 0.8680 and 0.9956, respectively, indicating high BMI discrimination power. Conclusions: The locally applied BMI parameters for children aged six to ten years represent a valid, highly viable and practical proposal for excess weight screening in this population group, improving professional decision-making in their follow-up.

RESUMO Objetivo: Analisar a concordância dos parâmetros de índice de massa corporal (IMC) para crianças com idade de seis a dez anos da cidade de Montes Claros/MG com os demais critérios de abrangência nacional e internacional, bem como sua sensibilidade e especificidade no rastreio do excesso de peso. Métodos: Foi utilizada uma amostra de 4.151 crianças de seis a dez anos, sendo mensuradas estatura e massa corporal para a determinação do IMC. Os valores obtidos foram classificados de acordo com os pontos de corte da World Health Organization (WHO), International Obesity Task Force (IOTF), Centers for Disease Control and Prevention (CDC), Conde & Monteiro e uma recente proposta local. Calculou-se o índice de concordância entre os critérios mencionados e, em seguida, a sensibilidade e a especificidade. Resultados: A proposta local mostrou-se altamente concordante na maioria das combinações, principalmente para o excesso de peso com a WHO (k=0,895). Com relação ao excesso de peso, a proposta local apresentou valores de 0,8680 e 0,9956 para a sensibilidade e especificidade respectivamente, mostrando alto poder de discriminação do IMC. Conclusões: Conclui-se que os parâmetros locais de IMC para crianças de seis a dez anos representam uma proposta válida, altamente viável e utilizável para o rastreio do excesso de peso desse grupo populacional, melhorando a tomada de decisão profissional no acompanhamento de tais indivíduos.

Machine learning methods applied to risk adjustment of cumulative sum chart methodology to audit free flap outcomes after head and neck surgery.

We describe a risk adjustment algorithm to benchmark and report free flap failure rates after immediate reconstruction of head and neck defects. A dataset of surgical care episodes for curative surgery for head and neck cancer and immediate reconstruction (n = 1593) was compiled from multiple NHS hospitals (n = 8). The outcome variable was complete flap failure. Classification models using preoperative patient demographic data, operation data, functional status data and tumour stage data, were built. Machine learning processes are described to model free flap failure. Overall complete flap failure was uncommon (4.7%) with a non-statistical difference seen between hospitals. The champion predictive model had acceptable discrimination (AUROC 0.66). This model was used to risk-adjust cumulative sum (CuSUM) charts. The use of CuSUM charts is a viable way to monitor in a 'Live Dashboard' this quality metric as part of the quality outcomes in oral and maxillofacial surgery audit.

Pharmaceuticals, natural and synthetic hormones and phenols in sediments from an eutrophic estuary, Jurujuba Sound, Guanabara Bay, Brazil.

A screening for microcontaminants performed by gas chromatography detected several microcontaminants in 12 sediment samples from the eutrophic estuary Guanabara Bay (GB) in southeastern Brazil. Bisphenol A (BPA) ranged from 1.4 to 20.3 ng g-1, 4-octylphenol, from

Multiproxy analysis in contaminated sediments from Niterói Harbour (Guanabara Bay), Brazil.

Harbours are located in major urban centres around the world and are of great economic importance to the cities in their surroundings. However, the intense traffic of boats and ships can generate environmental impacts that can directly affect the local biota as well as the population that lives in surrounding areas. Therefore, this work aimed to analyse the surface sediment of the Niterói Harbour using chemical, biological and micropalaeontological tools to investigate the environmental condition of this important harbour in Rio de Janeiro State. The pseudototal trace metal data analysed in the surface samples showed values far above those of the greater Guanabara Bay background. These data were corroborated by a high mortality rate of Artemia sp. and elevated presence of the bacterium Vibrio fischeri, indicating a high rate of local pollution. Dinoflagellate cysts also showed a direct response to high values of pseudototal trace metals. The data obtained in this study emphasize a need for greater monitoring of ports since the experience gained through this study in a Brazilian harbour can serve as an example for the management of other harbours located in large urban centres around the world.

Machine learning-based predictions of dietary restriction associations across ageing-related genes.

BACKGROUND: Dietary restriction (DR) is the most studied pro-longevity intervention; however, a complete understanding of its underlying mechanisms remains elusive, and new research directions may emerge from the identification of novel DR-related genes and DR-related genetic features. RESULTS: This work used a Machine Learning (ML) approach to classify ageing-related genes as DR-related or NotDR-related using 9 different types of predictive features: PathDIP pathways, two types of features based on KEGG pathways, two types of Protein-Protein Interactions (PPI) features, Gene Ontology (GO) terms, Genotype Tissue Expression (GTEx) expression features, GeneFriends co-expression features and protein sequence descriptors. Our findings suggested that features biased towards curated knowledge (i.e. GO terms and biological pathways), had the greatest predictive power, while unbiased features (mainly gene expression and co-expression data) have the least predictive power. Moreover, a combination of all the feature types diminished the predictive power compared to predictions based on curated knowledge. Feature importance analysis on the two most predictive classifiers mostly corroborated existing knowledge and supported recent findings linking DR to the Nuclear Factor Erythroid 2-Related Factor 2 (NRF2) signalling pathway and G protein-coupled receptors (GPCR). We then used the two strongest combinations of feature type and ML algorithm to predict DR-relatedness among ageing-related genes currently lacking DR-related annotations in the data, resulting in a set of promising candidate DR-related genes (GOT2, GOT1, TSC1, CTH, GCLM, IRS2 and SESN2) whose predicted DR-relatedness remain to be validated in future wet-lab experiments. CONCLUSIONS: This work demonstrated the strong potential of ML-based techniques to identify DR-associated features as our findings are consistent with literature and recent discoveries. Although the inference of new DR-related mechanistic findings based solely on GO terms and biological pathways was limited due to their knowledge-driven nature, the predictive power of these two features types remained useful as it allowed inferring new promising candidate DR-related genes.

Ageing transcriptome meta-analysis reveals similarities and differences between key mammalian tissues.

By combining transcriptomic data with other data sources, inferences can be made about functional changes during ageing. Thus, we conducted a meta-analysis on 127 publicly available microarray and RNA-Seq datasets from mice, rats and humans, identifying a transcriptomic signature of ageing across species and tissues. Analyses on subsets of these datasets produced transcriptomic signatures of ageing for brain, heart and muscle. We then applied enrichment analysis and machine learning to functionally describe these signatures, revealing overexpression of immune and stress response genes and underexpression of metabolic and developmental genes. Further analyses revealed little overlap between genes differentially expressed with age in different tissues, despite ageing differentially expressed genes typically being widely expressed across tissues. Additionally we show that the ageing gene expression signatures (particularly the overexpressed signatures) of the whole meta-analysis, brain and muscle tend to include genes that are central in protein-protein interaction networks. We also show that genes underexpressed with age in the brain are highly central in a co-expression network, suggesting that underexpression of these genes may have broad phenotypic consequences. In sum, we show numerous functional similarities between the ageing transcriptomes of these important tissues, along with unique network properties of genes differentially expressed with age in both a protein-protein interaction and co-expression networks.

A Novel Feature Selection Method for Uncertain Features: An Application to the Prediction of Pro-/Anti-Longevity Genes.

Understanding the ageing process is a very challenging problem for biologists. To help in this task, there has been a growing use of classification methods (from machine learning) to learn models that predict whether a gene influences the process of ageing or promotes longevity. One type of predictive feature often used for learning such classification models is Protein-Protein Interaction (PPI) features. One important property of PPI features is their uncertainty, i.e., a given feature (PPI annotation) is often associated with a confidence score, which is usually ignored by conventional classification methods. Hence, we propose the Lazy Feature Selection for Uncertain Features (LFSUF) method, which is tailored for coping with the uncertainty in PPI confidence scores. In addition, following the lazy learning paradigm, LFSUF selects features for each instance to be classified, making the feature selection process more flexible. We show that our LFSUF method achieves better predictive accuracy when compared to other feature selection methods that either do not explicitly take PPI confidence scores into account or deal with uncertainty globally rather than using a per-instance approach. Also, we interpret the results of the classification process using the features selected by LFSUF, showing that the number of selected features is significantly reduced, assisting the interpretability of the results. The datasets used in the experiments and the program code of the LFSUF method are freely available on the web at http://github.com/pablonsilva/FSforUncertainFeatureSpaces.

NEW REFERENCE PARAMETERS FOR BODY MASS INDEX IN CHILDREN AGED SIX TO TEN YEARS.

OBJECTIVE: To determine new body mass index (BMI) reference values to classify the nutritional status of children aged six to ten years old from the city of Montes Claros (state of Minas Gerais), Southeast Brazil. METHODS: The sample consisted of 3,863 individuals from both genders. Body mass and height were measured to determine the BMI. We adopted the Lambda, Mu, and Sigma (LMS) method to obtain the cut-off points. After that, each stratum curve was smoothed using quartic polynomials by gender. Average interpolation was used to determine the biannual distribution values. We calculated the 3rd, 85th, and 95th centiles to classify underweight, overweight, and obesity, respectively, according to gender and age. RESULTS: After tabulating the LMS parameters at biannual intervals by gender, we plotted a graphic with seven centiles of BMI distribution and calculated the new BMI parameters for children aged 6-10 years old from the city of Montes Claros. The cut-off values for underweight, overweight, and obesity classification were, respectively, 17.5, 25 and 30 kg/m2. CONCLUSIONS: For the studied children, the use of traditional BMI references may result in the overestimation of underweight and underestimation of overweight and obesity. Studies should be carried out with periodic updates, respecting the characteristics of each location in order to use BMI reference values to classify the nutritional status of children and adolescents.

New reference parameters for body mass index in children aged six to ten years / Novos parâmetros de referência do índice de massa corpórea para crianças de seis a dez anos

ABSTRACT Objective: To determine new body mass index (BMI) reference values to classify the nutritional status of children aged six to ten years old from the city of Montes Claros (state of Minas Gerais), Southeast Brazil. Methods: The sample consisted of 3,863 individuals from both genders. Body mass and height were measured to determine the BMI. We adopted the Lambda, Mu, and Sigma (LMS) method to obtain the cut-off points. After that, each stratum curve was smoothed using quartic polynomials by gender. Average interpolation was used to determine the biannual distribution values. We calculated the 3rd, 85th, and 95th centiles to classify underweight, overweight, and obesity, respectively, according to gender and age. Results: After tabulating the LMS parameters at biannual intervals by gender, we plotted a graphic with seven centiles of BMI distribution and calculated the new BMI parameters for children aged 6-10 years old from the city of Montes Claros. The cut-off values for underweight, overweight, and obesity classification were, respectively, 17.5, 25 and 30 kg/m2. Conclusions: For the studied children, the use of traditional BMI references may result in the overestimation of underweight and underestimation of overweight and obesity. Studies should be carried out with periodic updates, respecting the characteristics of each location in order to use BMI reference values to classify the nutritional status of children and adolescents.

RESUMO Objetivo: Determinar novos valores de referência do índice de massa corporal (IMC) para a classificação do estado nutricional de crianças de seis a 10 anos da cidade de Montes Claros (MG) Brasil. Métodos: Foi utilizada uma amostra de 3.863 sujeitos de ambos os sexos, sendo mensurados massa corporal e estatura para a determinação do IMC. Para a obtenção dos pontos de corte utilizou-se o método Lambda, Sigma e Mu (LMS). Em seguida, as curvas de cada estrato foram suavizadas por polinômios de 4º grau por sexo, e, por interpolação das médias aritméticas, foram obtidos os valores semestrais da distribuição. Foram calculados os percentis 3%, 85% e 95% para a classificação de baixo peso, sobrepeso e obesidade, respectivamente, de acordo com sexo e idade. Resultados: Após a tabulação em intervalos semestrais dos valores dos parâmetros LMS por sexo, foi possível construir o gráfico com sete centis da distribuição do IMC, sendo apresentados os novos parâmetros do IMC para crianças de 6 a 10 anos de Montes Claros, equivalentes aos valores 17,5, 25 e 30 kg/m2 para baixo peso, sobrepeso e obesidade respectivamente. Conclusões: Em relação à população de Montes Claros, a utilização das tradicionais referências para o IMC pode resultar em uma superestimativa do baixo peso e subestimativa do sobrepeso e obesidade. O que se sugere é que, para o uso de valores de referência do IMC para classificar o estado nutricional de crianças e adolescentes, sejam realizados estudos com atualizações periódicas, respeitando as características de cada localidade.

Comparing enrichment analysis and machine learning for identifying gene properties that discriminate between gene classes.

Biologists very often use enrichment methods based on statistical hypothesis tests to identify gene properties that are significantly over-represented in a given set of genes of interest, by comparison with a 'background' set of genes. These enrichment methods, although based on rigorous statistical foundations, are not always the best single option to identify patterns in biological data. In many cases, one can also use classification algorithms from the machine-learning field. Unlike enrichment methods, classification algorithms are designed to maximize measures of predictive performance and are capable of analysing combinations of gene properties, instead of one property at a time. In practice, however, the majority of studies use either enrichment or classification methods (rather than both), and there is a lack of literature discussing the pros and cons of both types of method. The goal of this paper is to compare and contrast enrichment and classification methods, offering two contributions. First, we discuss the (to some extent complementary) advantages and disadvantages of both types of methods for identifying gene properties that discriminate between gene classes. Second, we provide a set of high-level recommendations for using enrichment and classification methods. Overall, by highlighting the strengths and the weaknesses of both types of methods we argue that both should be used in bioinformatics analyses.

Investigating the role of Simpson's paradox in the analysis of top-ranked features in high-dimensional bioinformatics datasets.

An important problem in bioinformatics consists of identifying the most important features (or predictors), among a large number of features in a given classification dataset. This problem is often addressed by using a machine learning-based feature ranking method to identify a small set of top-ranked predictors (i.e. the most relevant features for classification). The large number of studies in this area has, however, an important limitation: they ignore the possibility that the top-ranked predictors occur in an instance of Simpson's paradox, where the positive or negative association between a predictor and a class variable reverses sign upon conditional on each of the values of a third (confounder) variable. In this work, we review and investigate the role of Simpson's paradox in the analysis of top-ranked predictors in high-dimensional bioinformatics datasets, in order to avoid the potential danger of misinterpreting an association between a predictor and the class variable. We perform computational experiments using four well-known feature ranking methods from the machine learning field and five high-dimensional datasets of ageing-related genes, where the predictors are Gene Ontology terms. The results show that occurrences of Simpson's paradox involving top-ranked predictors are much more common for one of the feature ranking methods.

Using deep learning to associate human genes with age-related diseases.

MOTIVATION: One way to identify genes possibly associated with ageing is to build a classification model (from the machine learning field) capable of classifying genes as associated with multiple age-related diseases. To build this model, we use a pre-compiled list of human genes associated with age-related diseases and apply a novel Deep Neural Network (DNN) method to find associations between gene descriptors (e.g. Gene Ontology terms, protein-protein interaction data and biological pathway information) and age-related diseases. RESULTS: The novelty of our new DNN method is its modular architecture, which has the capability of combining several sources of biological data to predict which ageing-related diseases a gene is associated with (if any). Our DNN method achieves better predictive performance than standard DNN approaches, a Gradient Boosted Tree classifier (a strong baseline method) and a Logistic Regression classifier. Given the DNN model produced by our method, we use two approaches to identify human genes that are not known to be associated with age-related diseases according to our dataset. First, we investigate genes that are close to other disease-associated genes in a complex multi-dimensional feature space learned by the DNN algorithm. Second, using the class label probabilities output by our DNN approach, we identify genes with a high probability of being associated with age-related diseases according to the model. We provide evidence of these putative associations retrieved from the DNN model with literature support. AVAILABILITY AND IMPLEMENTATION: The source code and datasets can be found at: https://github.com/fabiofabris/Bioinfo2019. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.

BACKGROUND: The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. RESULTS: Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility. We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. CONCLUSION: We conclude that while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging; although the performance of the top methods is significantly better than the expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. Finally, we report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bio-ontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.