Background: Retention in treatment is crucial for the success of interventions targeting alcohol use disorder (AUD), which affects over 100 million people globally. Most previous studies have used classical statistical techniques to predict treatment dropout, and their results remain inconclusive. This study aimed to use novel machine learning tools to identify models that predict dropout with greater precision, enabling the development of better retention strategies for those at higher risk. Methods: A retrospective observational study of 39,030 (17.3% female) participants enrolled in outpatient-based treatment for alcohol use disorder in a state-wide public treatment network has been used. Participants were recruited between 1 January 2015 and 31 December 2019. We applied different machine learning algorithms to create models that allow one to predict the premature cessation of treatment (dropout). With the objective of increasing the explainability of those models with the best precision, considered as black-box models, explainability technique analyses were also applied. Results: Considering as the best models those obtained with one of the so-called black-box models (support vector classifier (SVC)), the results from the best model, from the explainability perspective, showed that the variables that showed greater explanatory capacity for treatment dropout are previous drug use as well as psychiatric comorbidity. Among these variables, those of having undergone previous opioid substitution treatment and receiving coordinated psychiatric care in mental health services showed the greatest capacity for predicting dropout. Conclusions: By using novel machine learning techniques on a large representative sample of patients enrolled in alcohol use disorder treatment, we have identified several machine learning models that help in predicting a higher risk of treatment dropout. Previous treatment for other substance use disorders (SUDs) and concurrent psychiatric comorbidity were the best predictors of dropout, and patients showing these characteristics may need more intensive or complementary interventions to benefit from treatment.
27 May 2024 in Journal of Integrative Bioinformatics
Protein structure determination has made progress with the aid of deep learning models, enabling the prediction of protein folding from protein sequences. However, obtaining accurate predictions becomes essential in certain cases where the protein structure remains undescribed. This is particularly challenging when dealing with rare, diverse structures and complex sample preparation. Different metrics assess prediction reliability and offer insights into result strength, providing a comprehensive understanding of protein structure by combining different models. In a previous study, two proteins named ARM58 and ARM56 were investigated. These proteins contain four domains of unknown function and are present in Leishmania spp. ARM refers to an antimony resistance marker. The study’s main objective is to assess the accuracy of the model’s predictions, thereby providing insights into the complexities and supporting metrics underlying these findings. The analysis also extends to the comparison of predictions obtained from other species and organisms. Notably, one of these proteins shares an ortholog with Trypanosoma cruzi and Trypanosoma brucei, leading further significance to our analysis. This attempt underscored the importance of evaluating the diverse outputs from deep learning models, facilitating comparisons across different organisms and proteins. This becomes particularly pertinent in cases where no previous structural information is available.
Protein sequence alignments are essential for identifying proteins’ shared structural and functional features. Detecting short amino acid sequences, termed patterns, across lung cancer and other related datasets facilitates the identification of relevant features. This study builds on previous findings by exploring proteins that share common patterns already identified. Using sequence matching at 5% and 10% occurrence thresholds, we identified 2,368 and 47 patterns, respectively. To reduce complexity and refine the dataset, shorter patterns from the 10% occurrence streamlined the analysis by isolating highly relevant patterns while reducing redundancy among proteins sharing sequence segments. Subsequent analyses integrated structural predictions for protein folding comparison, enabling the detection of patterns in different proteins and the identification of potential key residues. During cavity detection prediction, some amino acids were inspected in detail to assess their impact on protein function and their relevance in drug-target interactions. These insights were considered during docking studies, focusing on proteins used in treatments with pre-described ligands. By connecting raw sequence data to folding structures and functional features, we identified critical protein cavities that underscore the role of mutations in altering protein behavior and influencing drug-target interactions. These findings highlight protein activity’s structural foundations and their importance in understanding cancer biology. By uncovering conserved sequence patterns and their structural implications, this study provides insights into potential biomarkers and therapeutic targets, that could aid in developing more effective cancer treatments.
The determination of protein structure has been facilitated using deep learning models, which can predict protein folding from protein sequences. In some cases, the predicted structure can be compared to the already-known distribution if there is information from classic methods such as nuclear magnetic resonance (NMR) spectroscopy, X-ray crystallography, or electron microscopy (EM). However, challenges arise when the proteins are not abundant, their structure is heterogeneous, and protein sample preparation is difficult. To determine the level of confidence that supports the prediction, different metrics are provided. These values are important in two ways: they offer information about the strength of the result and can supply an overall picture of the structure when different models are combined. This work provides an overview of the different deep-learning methods used to predict protein folding and the metrics that support their outputs. The confidence of the model is evaluated in detail using two proteins that contain four domains of unknown function.