Predicting blood-brain barrier permeability of molecules with a large language model and machine learning.

Predicting the blood-brain barrier (BBB) permeability of small-molecule compounds using a novel artificial intelligence platform is necessary for drug discovery. Machine learning and a large language model on artificial intelligence (AI) tools improve the accuracy and shorten the time for new drug development. The primary goal of this research is to develop artificial intelligence (AI) computing models and novel deep learning architectures capable of predicting whether molecules can permeate the human blood-brain barrier (BBB). The in silico (computational) and in vitro (experimental) results were validated by the Natural Products Research Laboratories (NPRL) at China Medical University Hospital (CMUH). The transformer-based MegaMolBART was used as the simplified molecular input line entry system (SMILES) encoder with an XGBoost classifier as an in silico method to check if a molecule could cross through the BBB. We used Morgan or Circular fingerprints to apply the Morgan algorithm to a set of atomic invariants as a baseline encoder also with an XGBoost classifier to compare the results. BBB permeability was assessed in vitro using three-dimensional (3D) human BBB spheroids (human brain microvascular endothelial cells, brain vascular pericytes, and astrocytes). Using multiple BBB databases, the results of the final in silico transformer and XGBoost model achieved an area under the receiver operating characteristic curve of 0.88 on the held-out test dataset. Temozolomide (TMZ) and 21 randomly selected BBB permeable compounds (Pred scores = 1, indicating BBB-permeable) from the NPRL penetrated human BBB spheroid cells. No evidence suggests that ferulic acid or five BBB-impermeable compounds (Pred scores < 1.29423E-05, which designate compounds that pass through the human BBB) can pass through the spheroid cells of the BBB. Our validation of in vitro experiments indicated that the in silico prediction of small-molecule permeation in the BBB model is accurate. Transformer-based models like MegaMolBART, leveraging the SMILES representations of molecules, show great promise for applications in new drug discovery. These models have the potential to accelerate the development of novel targeted treatments for disorders of the central nervous system.

Examining the cultural influence on online stances towards COVID-19 preventive measures and their impact on incidence and mortality: A global stance detection analysis of tweets.

During the COVID-19 pandemic, nations implemented various preventive measures, triggering varying online responses. This study examines cultural influences on public online stances toward these measures and their impacts on COVID-19 cases/deaths. Stance detection analysis was used to analyze 16,428,557 Tweets regarding COVID-19 preventive measures from 95 countries, selected based on Hofstede's cultural dimensions. To ensure the variety of population, countries were chosen based on Twitter data availability and a minimum sample size of 385 tweets, achieving a 95% confidence level with a 5% margin of error. The weighted regression analysis revealed that the relationship between culture and online stances depends on the cultural congruence of each measure. Specifically, power distance positively predicted stances for all measures, while indulgence had a negative effect overall. Effects of other cultural indices varied across measures. Individualism negatively affected face coverings stances. Uncertainty avoidance influenced lockdown and vaccination stances negatively but had a positive effect on social distancing stances. Long-term orientation negatively affected lockdown and social distancing stances but positively influenced quarantine stances. Cultural tightness only negatively affected face coverings and quarantine stances. Online stances toward face coverings mediated the relationship between cultural indices and COVID-19 cases/deaths. As such, public health officials should consider cultural profiles and use culturally congruent communication strategies when implementing preventive measures for future pandemics. Furthermore, leveraging digital tools is vital in navigating and shaping online stances to enhance the effectiveness of these measures.

CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation.

Radiology report generation (RRG) has gained increasing research attention because of its huge potential to mitigate medical resource shortages and aid the process of disease decision making by radiologists. Recent advancements in Radiology Report Generation (RRG) are largely driven by improving a model's capabilities in encoding single-modal feature representations, while few studies explicitly explore the cross-modal alignment between image regions and words. Radiologists typically focus first on abnormal image regions before composing the corresponding text descriptions, thus cross-modal alignment is of great importance to learn a RRG model which is aware of abnormalities in the image. Motivated by this, we propose a Class Activation Map guided Attention Network (CAMANet) which explicitly promotes cross-modal alignment by employing aggregated class activation maps to supervise cross-modal attention learning, and simultaneously enrich the discriminative information. Experimental results demonstrate that CAMANet outperforms previous SOTA methods on two commonly used RRG benchmarks.

Deep learning-based photodamage reduction on harmonic generation microscope at low-level optical power.

The trade-off between high-quality images and cellular health in optical bioimaging is a crucial problem. We demonstrated a deep-learning-based power-enhancement (PE) model in a harmonic generation microscope (HGM), including second harmonic generation (SHG) and third harmonic generation (THG). Our model can predict high-power HGM images from low-power images, greatly reducing the risk of phototoxicity and photodamage. Furthermore, the PE model trained only on normal skin data can also be used to predict abnormal skin data, enabling the dermatopathologist to successfully identify and label cancer cells. The PE model shows potential for in-vivo and ex-vivo HGM imaging.

Transfer Learning With Singular Value Decomposition of Multichannel Convolution Matrices.

The task of transfer learning using pretrained convolutional neural networks is considered. We propose a convolution-SVD layer to analyze the convolution operators with a singular value decomposition computed in the Fourier domain. Singular vectors extracted from the source domain are transferred to the target domain, whereas the singular values are fine-tuned with a target data set. In this way, dimension reduction is achieved to avoid overfitting, while some flexibility to fine-tune the convolution kernels is maintained. We extend an existing convolution kernel reconstruction algorithm to allow for a reconstruction from an arbitrary set of learned singular values. A generalization bound for a single convolution-SVD layer is devised to show the consistency between training and testing errors. We further introduce a notion of transfer learning gap. We prove that the testing error for a single convolution-SVD layer is bounded in terms of the gap, which motivates us to develop a regularization model with the gap as the regularizer. Numerical experiments are conducted to demonstrate the superiority of the proposed model in solving classification problems and the influence of various parameters. In particular, the regularization is shown to yield a significantly higher prediction accuracy.

Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation.

Despite the recent success of deep learning models for text generation, generating clinically accurate reports remains challenging. More precisely modeling the relationships of the abnormalities revealed in an X-ray image has been found promising to enhance the clinical accuracy. In this paper, we first introduce a novel knowledge graph structure called an attributed abnormality graph (ATAG). It consists of interconnected abnormality nodes and attribute nodes for better capturing more fine-grained abnormality details. In contrast to the existing methods where the abnormality graph are constructed manually, we propose a methodology to automatically construct the fine-grained graph structure based on annotated X-ray reports and the RadLex radiology lexicon. We then learn the ATAG embeddings as part of a deep model with an encoder-decoder architecture for the report generation. In particular, graph attention networks are explored to encode the relationships among the abnormalities and their attributes. A hierarchical attention attention and a gating mechanism are specifically designed to further enhance the generation quality. We carry out extensive experiments based on the benchmark datasets, and show that the proposed ATAG-based deep model outperforms the SOTA methods by a large margin in ensuring the clinical accuracy of the generated reports.

Self-Supervised Video Representation Learning by Video Incoherence Detection.

This article introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It stems from the observation that the visual system of human beings can easily identify video incoherence based on their comprehensive understanding of videos. Specifically, we construct the incoherent clip by multiple subclips hierarchically sampled from the same raw video with various lengths of incoherence. The network is trained to learn the high-level representation by predicting the location and length of incoherence given the incoherent clip as input. Additionally, we introduce intravideo contrastive learning to maximize the mutual information between incoherent clips from the same raw video. We evaluate our proposed method through extensive experiments on action recognition and video retrieval using various backbone networks. Experiments show that our proposed method achieves remarkable performance across different backbone networks and different datasets compared to previous coherence-based methods.

Improving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework.

Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R 2 = 0.88; support vector regression, MAE = 4.42 years, R 2 = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R 2 = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Deep learning with evolutionary and genomic profiles for identifying cancer subtypes.

Cancer subtype identification is an unmet need in precision diagnosis. Recently, evolutionary conservation has been indicated to contain informative signatures for functional significance in cancers. However, the importance of evolutionary conservation in distinguishing cancer subtypes remains largely unclear. Here, we identified the evolutionarily conserved genes (i.e. core genes) and observed that they are primarily involved in cellular pathways relevant to cell growth and metabolisms. By using these core genes, we developed two novel strategies, namely a feature-based strategy (FES) and an image-based strategy (IMS) by integrating their evolutionary and genomic profiles with the deep learning algorithm. In comparison with the FES using the random set and the strategy using the PAM50 classifier, the core gene set-based FES achieved a higher accuracy for identifying breast cancer subtypes. The IMS and FES using the core gene set yielded better performances than the other strategies, in terms of classifying both breast cancer subtypes and multiple cancer types. Moreover, the IMS is reproducible even using different gene expression data (i.e. RNA-seq and microarray). Comprehensive analysis of eight cancer types demonstrates that our evolutionary conservation-based models represent a valid and helpful approach for identifying cancer subtypes and the core gene set offers distinguishable clues of cancer subtypes.

Fast MPEG-CDVS Encoder With GPU-CPU Hybrid Computing.

The compact descriptors for visual search (CDVS) standard from ISO/IEC moving pictures experts group has succeeded in enabling the interoperability for efficient and effective image retrieval by standardizing the bitstream syntax of compact feature descriptors. However, the intensive computation of a CDVS encoder unfortunately hinders its widely deployment in industry for large-scale visual search. In this paper, we revisit the merits of low complexity design of CDVS core techniques and present a very fast CDVS encoder by leveraging the massive parallel execution resources of graphics processing unit (GPU). We elegantly shift the computation-intensive and parallel-friendly modules to the state-of-the-arts GPU platforms, in which the thread block allocation as well as the memory access mechanism are jointly optimized to eliminate performance loss. In addition, those operations with heavy data dependence are allocated to CPU for resolving the extra but non-necessary computation burden for GPU. Furthermore, we have demonstrated the proposed fast CDVS encoder can work well with those convolution neural network approaches which enables to leverage the advantages of GPU platforms harmoniously, and yield significant performance improvements. Comprehensive experimental results over benchmarks are evaluated, which has shown that the fast CDVS encoder using GPU-CPU hybrid computing is promising for scalable visual search.