BACKGROUND: Drug-target affinity (DTA) prediction is a critical step in the field of drug discovery. In recent years, deep learning-based methods have emerged for DTA prediction. In order to solve the problem of fusion of substructure information of drug molecular graphs and utilize multi-scale information of protein, a self-supervised pre-training model based on substructure extraction and multi-scale features is proposed in this paper. RESULTS: For drug molecules, the model obtains substructure information through the method of probability matrix, and the contrastive learning method is implemented on the graph-level representation and subgraph-level representation to pre-train the graph encoder for downstream tasks. For targets, a BiLSTM method that integrates multi-scale features is used to capture long-distance relationships in the amino acid sequence. The experimental results showed that our model achieved better performance for DTA prediction. CONCLUSIONS: The proposed model improves the performance of the DTA prediction, which provides a novel strategy based on substructure extraction and multi-scale features.

BACKGROUND: Hepatitis C is a prevalent disease that poses a high risk to the human liver. Early diagnosis of hepatitis C is crucial for treatment and prognosis. Therefore, developing an effective medical decision system is essential. In recent years, many computational methods have been proposed to identify hepatitis C patients. Although existing hepatitis prediction models have achieved good results in terms of accuracy, most of them are black-box models and cannot gain the trust of doctors and patients in clinical practice. As a result, this study aims to use various Machine Learning (ML) models to predict whether a patient has hepatitis C, while also using explainable models to elucidate the prediction process of the ML models, thus making the prediction process more transparent. RESULT: We conducted a study on the prediction of hepatitis C based on serological testing and provided comprehensive explanations for the prediction process. Throughout the experiment, we modeled the benchmark dataset, and evaluated model performance using fivefold cross-validation and independent testing experiments. After evaluating three types of black-box machine learning models, Random Forest (RF), Support Vector Machine (SVM), and AdaBoost, we adopted Bayesian-optimized RF as the classification algorithm. In terms of model interpretation, in addition to using common SHapley Additive exPlanations (SHAP) to provide global explanations for the model, we also utilized the Local Interpretable Model-Agnostic Explanations with stability (LIME_stabilitly) to provide local explanations for the model. CONCLUSION: Both the fivefold cross-validation and independent testing show that our proposed method significantly outperforms the state-of-the-art method. IHCP maintains excellent model interpretability while obtaining excellent predictive performance. This helps uncover potential predictive patterns of the model and enables clinicians to better understand the model's decision-making process.

BACKGROUND: To present an approach that autonomously identifies and selects a self-selective optimal target for the purpose of enhancing learning efficiency to segment infected regions of the lung from chest computed tomography images. We designed a semi-supervised dual-branch framework for training, where the training set consisted of limited expert-annotated data and a large amount of coarsely annotated data that was automatically segmented based on Hu values, which were used to train both strong and weak branches. In addition, we employed the Lovasz scoring method to automatically switch the supervision target in the weak branch and select the optimal target as the supervision object for training. This method can use noisy labels for rapid localization during the early stages of training, and gradually use more accurate targets for supervised training as the training progresses. This approach can utilize a large number of samples that do not require manual annotation, and with the iterations of training, the supervised targets containing noise become closer and closer to the fine-annotated data, which significantly improves the accuracy of the final model. RESULTS: The proposed dual-branch deep learning network based on semi-supervision together with cost-effective samples achieved 83.56 ± 12.10 and 82.67 ± 8.04 on our internal and external test benchmarks measured by the mean Dice similarity coefficient (DSC). Through experimental comparison, the DSC value of the proposed algorithm was improved by 13.54% and 2.02% on the internal benchmark and 13.37% and 2.13% on the external benchmark compared with U-Net without extra sample assistance and the mean-teacher frontier algorithm, respectively. CONCLUSION: The cost-effective pseudolabeled samples assisted the training of DL models and achieved much better results compared with traditional DL models with manually labeled samples only. Furthermore, our method also achieved the best performance compared with other up-to-date dual branch structures.

BACKGROUND: Over the past several decades, metrics have been defined to assess the quality of various types of models and to compare their performance depending on their capacity to explain the variance found in real-life data. However, available validation methods are mostly designed for statistical regressions rather than for mechanistic models. To our knowledge, in the latter case, there are no consensus standards, for instance for the validation of predictions against real-world data given the variability and uncertainty of the data. In this work, we focus on the prediction of time-to-event curves using as an application example a mechanistic model of non-small cell lung cancer. We designed four empirical methods to assess both model performance and reliability of predictions: two methods based on bootstrapped versions of parametric statistical tests: log-rank and combined weighted log-ranks (MaxCombo); and two methods based on bootstrapped prediction intervals, referred to here as raw coverage and the juncture metric. We also introduced the notion of observation time uncertainty to take into consideration the real life delay between the moment when an event happens, and the moment when it is observed and reported. RESULTS: We highlight the advantages and disadvantages of these methods according to their application context. We have shown that the context of use of the model has an impact on the model validation process. Thanks to the use of several validation metrics we have highlighted the limit of the model to predict the evolution of the disease in the whole population of mutations at the same time, and that it was more efficient with specific predictions in the target mutation populations. The choice and use of a single metric could have led to an erroneous validation of the model and its context of use. CONCLUSIONS: With this work, we stress the importance of making judicious choices for a metric, and how using a combination of metrics could be more relevant, with the objective of validating a given model and its predictions within a specific context of use. We also show how the reliability of the results depends both on the metric and on the statistical comparisons, and that the conditions of application and the type of available information need to be taken into account to choose the best validation strategy.

BACKGROUND: Longitudinal data on key cancer outcomes for clinical research, such as response to treatment and disease progression, are not captured in standard cancer registry reporting. Manual extraction of such outcomes from unstructured electronic health records is a slow, resource-intensive process. Natural language processing (NLP) methods can accelerate outcome annotation, but they require substantial labeled data. Transfer learning based on language modeling, particularly using the Transformer architecture, has achieved improvements in NLP performance. However, there has been no systematic evaluation of NLP model training strategies on the extraction of cancer outcomes from unstructured text. RESULTS: We evaluated the performance of nine NLP models at the two tasks of identifying cancer response and cancer progression within imaging reports at a single academic center among patients with non-small cell lung cancer. We trained the classification models under different conditions, including training sample size, classification architecture, and language model pre-training. The training involved a labeled dataset of 14,218 imaging reports for 1112 patients with lung cancer. A subset of models was based on a pre-trained language model, DFCI-ImagingBERT, created by further pre-training a BERT-based model using an unlabeled dataset of 662,579 reports from 27,483 patients with cancer from our center. A classifier based on our DFCI-ImagingBERT, trained on more than 200 patients, achieved the best results in most experiments; however, these results were marginally better than simpler "bag of words" or convolutional neural network models. CONCLUSION: When developing AI models to extract outcomes from imaging reports for clinical cancer research, if computational resources are plentiful but labeled training data are limited, large language models can be used for zero- or few-shot learning to achieve reasonable performance. When computational resources are more limited but labeled training data are readily available, even simple machine learning architectures can achieve good performance for such tasks.

BACKGROUND: Alcohol use disorder (AUD) causes significant morbidity, mortality, and injuries. According to reports, approximately 5% of all registered deaths in Denmark could be due to AUD. The problem is compounded by the late identification of patients with AUD, a situation that can cause enormous problems, from psychological to physical to economic problems. Many individuals suffering from AUD never undergo specialist treatment during their addiction due to obstacles such as taboo and the poor performance of current screening tools. Therefore, there is a lack of rapid intervention. This can be mitigated by the early detection of patients with AUD. A clinical decision support system (DSS) powered by machine learning (ML) methods can be used to diagnose patients' AUD status earlier. METHODS: This study proposes an effective AUD prediction model (AUDPM), which can be used in a DSS. The proposed model consists of four distinct components: (1) imputation to address missing values using the k-nearest neighbours approach, (2) recursive feature elimination with cross validation to select the most relevant subset of features, (3) a hybrid synthetic minority oversampling technique-edited nearest neighbour approach to remove noise and balance the distribution of the training data, and (4) an ML model for the early detection of patients with AUD. Two data sources, including a questionnaire and electronic health records of 2571 patients, were collected from Odense University Hospital in the Region of Southern Denmark for the AUD-Dataset. Then, the AUD-Dataset was used to build ML models. The results of different ML models, such as support vector machine, K-nearest neighbour, decision tree, random forest, and extreme gradient boosting, were compared. Finally, a combination of all these models in an ensemble learning approach was selected for the AUDPM. RESULTS: The results revealed that the proposed ensemble AUDPM outperformed other single models and our previous study results, achieving 0.96, 0.94, 0.95, and 0.97 precision, recall, F1-score, and accuracy, respectively. In addition, we designed and developed an AUD-DSS prototype. CONCLUSION: It was shown that our proposed AUDPM achieved high classification performance. In addition, we identified clinical factors related to the early detection of patients with AUD. The designed AUD-DSS is intended to be integrated into the existing Danish health care system to provide novel information to clinical staff if a patient shows signs of harmful alcohol use; in other words, it gives staff a good reason for having a conversation with patients for whom a conversation is relevant.

BACKGROUND: The study of de novo variation is important for assessing biological characteristics of new variation and for studies related to human phenotypes. Software programs exist to call de novo variants and programs also exist to test the burden of these variants in genomic regions; however, I am unaware of a program that fits in between these two aspects of de novo variant assessment. This intermediate space is important for assessing the quality of de novo variants and to understand the characteristics of the callsets. For this reason, I developed an R package called acorn. RESULTS: Acorn is an R package that examines various features of de novo variants including subsetting the data by individual(s), variant type, or genomic region; calculating features including variant change counts, variant lengths, and presence/absence at CpG sites; and characteristics of parental age in relation to de novo variant counts. CONCLUSIONS: Acorn is an R package that fills a critical gap in assessing de novo variants and will be of benefit to many investigators studying de novo variation.

BACKGROUND AND OBJECTIVE: Diabetes is a life-threatening chronic disease with a growing global prevalence, necessitating early diagnosis and treatment to prevent severe complications. Machine learning has emerged as a promising approach for diabetes diagnosis, but challenges such as limited labeled data, frequent missing values, and dataset imbalance hinder the development of accurate prediction models. Therefore, a novel framework is required to address these challenges and improve performance. METHODS: In this study, we propose an innovative pipeline-based multi-classification framework to predict diabetes in three classes: diabetic, non-diabetic, and prediabetes, using the imbalanced Iraqi Patient Dataset of Diabetes. Our framework incorporates various pre-processing techniques, including duplicate sample removal, attribute conversion, missing value imputation, data normalization and standardization, feature selection, and k-fold cross-validation. Furthermore, we implement multiple machine learning models, such as k-NN, SVM, DT, RF, AdaBoost, and GNB, and introduce a weighted ensemble approach based on the Area Under the Receiver Operating Characteristic Curve (AUC) to address dataset imbalance. Performance optimization is achieved through grid search and Bayesian optimization for hyper-parameter tuning. RESULTS: Our proposed model outperforms other machine learning models, including k-NN, SVM, DT, RF, AdaBoost, and GNB, in predicting diabetes. The model achieves high average accuracy, precision, recall, F1-score, and AUC values of 0.9887, 0.9861, 0.9792, 0.9851, and 0.999, respectively. CONCLUSION: Our pipeline-based multi-classification framework demonstrates promising results in accurately predicting diabetes using an imbalanced dataset of Iraqi diabetic patients. The proposed framework addresses the challenges associated with limited labeled data, missing values, and dataset imbalance, leading to improved prediction performance. This study highlights the potential of machine learning techniques in diabetes diagnosis and management, and the proposed framework can serve as a valuable tool for accurate prediction and improved patient care. Further research can build upon our work to refine and optimize the framework and explore its applicability in diverse datasets and populations.

BACKGROUND: The human gut microbiome (HGM), consisting of trillions of microorganisms, is crucial to human health. Adverse drug use is one of the most important causes of HGM disorder. Thus, it is necessary to identify drugs or compounds with anti-commensal effects on HGM in the early drug discovery stage. This study proposes a novel anti-commensal effects classification using a machine learning method and optimal molecular features. To improve the prediction performance, we explored combinations of six fingerprints and three descriptors to filter the best characterization as molecular features. RESULTS: The final consensus model based on optimal features yielded the F1-score of 0.725 ± 0.014, ACC of 82.9 ± 0.7%, and AUC of 0.791 ± 0.009 for five-fold cross-validation. In addition, this novel model outperformed the prior studies by using the same algorithm. Furthermore, the important chemical descriptors and misclassified anti-commensal compounds are analyzed to better understand and interpret the model. Finally, seven structural alerts responsible for the chemical anti-commensal effect are identified, implying valuable information for drug design. CONCLUSION: Our study would be a promising tool for screening anti-commensal compounds in the early stage of drug discovery and assessing the potential risks of these drugs in vivo.

BACKGROUND: Biological research is generating high volumes of data distributed across various sources. The inconsistent naming of proteins and their encoding genes brings great challenges to protein data integration: proteins and their coding genes usually have multiple related names and notations, which are difficult to match absolutely; the nomenclature of genes and proteins is complex and varies from species to species; some less studied species have no nomenclature of genes and proteins; The annotation of the same protein/gene varies greatly in different databases. In summary, a comprehensive set of protein/gene synonyms is necessary for relevant studies. RESULTS: In this study, we propose an approach for protein and its encoding gene synonym integration based on protein ontology. The workflow of protein and gene synonym integration is composed of three modules: data acquisition, entity and attribute alignment, attribute integration and deduplication. Finally, the integrated synonym set of proteins and their coding genes contains over 128.59 million terminologies covering 560,275 proteins/genes and 13,781 species. As the semantic basis, the comprehensive synonym set was used to develop a data platform to provide one-stop data retrieval without considering the diversity of protein nomenclature and species. CONCLUSION: The synonym set constructed here can serve as an important resource for biological named entity identification, text mining and information retrieval without name ambiguity, especially synonyms associated with well-defined species categories can help to study the evolutionary relationships between species at the molecular level. More importantly, the comprehensive synonyms set is the semantic basis for our subsequent studies on Protein-protein Interaction (PPI) knowledge graph.

BACKGROUND: Residue Interaction Networks (RINs) map the crystallographic description of a protein into a graph, where amino acids are represented as nodes and non-covalent bonds as edges. Determination and visualization of a protein as a RIN provides insights on the topological properties (and hence their related biological functions) of large proteins without dealing with the full complexity of the three-dimensional description, and hence it represents an invaluable tool of modern bioinformatics. RESULTS: We present RINmaker, a fast, flexible, and powerful tool for determining and visualizing RINs that include all standard non-covalent interactions. RINmaker is offered as a cross-platform and open source software that can be used either as a command-line tool or through a web application or a web API service. We benchmark its efficiency against the main alternatives and provide explicit tests to show its performance and its correctness. CONCLUSIONS: RINmaker is designed to be fully customizable, from a simple and handy support for experimental research to a sophisticated computational tool that can be embedded into a large computational pipeline. Hence, it paves the way to bridge the gap between data-driven/machine learning approaches and numerical simulations of simple, physically motivated, models.

Circular RNA (CircRNA) is a type of non-coding RNAs in which both ends are covalently linked. Researchers have demonstrated that many circRNAs can act as biomarkers of diseases. However, traditional experimental methods for circRNA-disease associations identification are labor-intensive. In this work, we propose a novel method based on the heterogeneous graph neural network and metapaths for circRNA-disease associations prediction termed as HMCDA. First, a heterogeneous graph consisting of circRNA-disease associations, circRNA-miRNA associations, miRNA-disease associations and disease-disease associations are constructed. Then, six metapaths are defined and generated according to the biomedical pathways. Afterwards, the entity content transformation, intra-metapath and inter-metapath aggregation are implemented to learn the embeddings of circRNA and disease entities. Finally, the learned embeddings are used to predict novel circRNA-disase associations. In particular, the result of extensive experiments demonstrates that HMCDA outperforms four state-of-the-art models in fivefold cross validation. In addition, our case study indicates that HMCDA has the ability to identify novel circRNA-disease associations.