RESUMO
Human language learning differs significantly across individuals in the process and ultimate attainment. Although decades of research exploring the neural substrates of language learning have identified distinct and overlapping neural networks subserving learning of different components, the neural mechanisms that drive the large interindividual differences are still far from being understood. Here we examine to what extent the neural dynamics of multiple brain networks in men and women across sessions of training contribute to explaining individual differences in learning multiple linguistic components (i.e., vocabulary, morphology, and phrase and sentence structures) of an artificial language in a 7 d training and imaging paradigm with functional MRI. With machine-learning and predictive modeling, neural activation patterns across training sessions were highly predictive of individual learning success profiles derived from the four components. We identified four neural learning networks (i.e., the Perisylvian, frontoparietal, salience, and default-mode networks) and examined their dynamic contributions to the learning success prediction. Moreover, the robustness of the predictions systematically changes across networks depending on specific training phases and the learning components. We further demonstrate that a subset of network nodes in the inferior frontal, insular, and frontoparietal regions increasingly represent newly acquired language knowledge, while the multivariate connectivity between these representation regions is enhanced during learning for more successful learners. These findings allow us to understand why learners differ and are the first to attribute not only the degree of success but also patterns of language learning across components, to neural fingerprints summarized from multiple neural network dynamics.SIGNIFICANCE STATEMENT Individual differences in learning a language are widely observed not only within the same component of language but also across components. This study demonstrates that the dynamics of multiple brain networks across four imaging sessions of a 7 d artificial language training contribute to individual differences in learning-outcome profiles derived from four language components. With machine-learning predictive modeling, we identified four neural learning networks, including the Perisylvian, frontoparietal, salience, and default-mode networks, that contribute to predicting individual learning-outcome profiles and revealed language-component-general and component-specific prediction patterns across training sessions. These findings provide significant insights in understanding training-dependent neural dynamics underlying individual differences in learning success across language components.
Assuntos
Mapeamento Encefálico , Córtex Cerebral/fisiologia , Individualidade , Desenvolvimento da Linguagem , Aprendizagem/fisiologia , Rede Nervosa/fisiologia , Vias Neurais/fisiologia , Adulto , Conectoma , Rede de Modo Padrão/fisiologia , Feminino , Humanos , Idioma , Testes de Linguagem , Aprendizado de Máquina , Imageamento por Ressonância Magnética , Masculino , Memória de Longo Prazo/fisiologia , Rememoração Mental/fisiologia , Testes de Estado Mental e Demência , Modelos Neurológicos , Adulto JovemRESUMO
Working memory (WM) is defined as the ability to maintain a representation online to guide goal-directed behavior. Its capacity in early childhood predicts academic achievements in late childhood and its deficits are found in various neurodevelopmental disorders. We employed resting-state fMRI (rs-fMRI) of 468 participants aged from 4 to 55 years and connectome-based predictive modeling (CPM) to explore the potential predictive power of intrinsic functional networks to WM in preschoolers, early and late school-age children, adolescents, and adults. We defined intrinsic functional networks among brain regions identified by activation likelihood estimation (ALE) meta-analysis on existing WM functional studies (ALE-based intrinsic functional networks) and intrinsic functional networks generated based on the whole brain (whole-brain intrinsic functional networks). We employed the CPM on these networks to predict WM in each age group. The CPM using the ALE-based and whole-brain intrinsic functional networks predicted WM of individual adults, while the prediction power of the ALE-based intrinsic functional networks was superior to that of the whole-brain intrinsic functional networks. Nevertheless, the CPM using the whole-brain but not the ALE-based intrinsic functional networks predicted WM in adolescents. And, the CPM using neither the ALE-based nor whole-brain networks predicted WM in any of the children groups. Our findings showed the trend of the prediction power of the intrinsic functional networks to cognition in individuals from early childhood to adulthood.
Assuntos
Encéfalo/fisiologia , Conectoma , Desenvolvimento Humano/fisiologia , Memória de Curto Prazo/fisiologia , Rede Nervosa/fisiologia , Adolescente , Adulto , Encéfalo/diagnóstico por imagem , Criança , Pré-Escolar , Feminino , Humanos , Imageamento por Ressonância Magnética , Masculino , Pessoa de Meia-Idade , Rede Nervosa/crescimento & desenvolvimento , Adulto JovemRESUMO
We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each molecule separately. These fingerprints are further non-linearly transformed, their inner product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E, MUV and PDBBind databases.