Relationship Between Temporomandibular Joint Effusion, Pain, and Jaw Function Limitation: A 2D and 3D Comparative Study.

Purpose: This study aimed to investigate the relationship between temporomandibular joint (TMJ) effusion and TMJ pain, as well as jaw function limitation in patients via two-dimensional (2D) and three-dimensional (3D) magnetic resonance imaging (MRI) evaluation. Patients and Methods: 121 patients diagnosed with temporomandibular disorder (TMD) were included. TMJ effusion was assessed qualitatively using MRI and quantified with 3D Slicer software, then graded accordingly. In addition, a visual analogue scale (VAS) was employed for pain reporting and an 8-item Jaw Functional Limitations Scale (JFLS-8) was utilized to evaluate jaw function limitation. Statistical analyses were performed appropriately for group comparisons and association determination. A probability of p<0.05 was considered statistically significant. Results: 2D qualitative and 3D quantitative strategies were in high agreement for TMJ effusion grades (κ = 0.766). No significant associations were found between joint effusion and TMJ pain, nor with disc displacement and JLFS-8 scores. Moreover, the binary logistic regression analysis showed significant association between sex and the presence of TMJ effusion, exhibiting an Odds Ratio of 5.168 for females (p = 0.008). Conclusion: 2D qualitative evaluation was as effective as 3D quantitative assessment for TMJ effusion diagnosis. No significant associations were found between TMJ effusion and TMJ pain, disc displacement or jaw function limitation. However, it was suggested that female patients suffering from TMD may be at a risk for TMJ effusion. Further prospective research is needed for validation.

Reducing false positive rate of docking-based virtual screening by active learning.

Machine learning-based scoring functions (MLSFs) have become a very favorable alternative to classical scoring functions because of their potential superior screening performance. However, the information of negative data used to construct MLSFs was rarely reported in the literature, and meanwhile the putative inactive molecules recorded in existing databases usually have obvious bias from active molecules. Here we proposed an easy-to-use method named AMLSF that combines active learning using negative molecular selection strategies with MLSF, which can iteratively improve the quality of inactive sets and thus reduce the false positive rate of virtual screening. We chose energy auxiliary terms learning as the MLSF and validated our method on eight targets in the diverse subset of DUD-E. For each target, we screened the IterBioScreen database by AMLSF and compared the screening results with those of the four control models. The results illustrate that the number of active molecules in the top 1000 molecules identified by AMLSF was significantly higher than those identified by the control models. In addition, the free energy calculation results for the top 10 molecules screened out by the AMLSF, null model and control models based on DUD-E also proved that more active molecules can be identified, and the false positive rate can be reduced by AMLSF.

Pushing the Boundaries of Molecular Property Prediction for Drug Discovery with Multitask Learning BERT Enhanced by SMILES Enumeration.

Accurate prediction of pharmacological properties of small molecules is becoming increasingly important in drug discovery. Traditional feature-engineering approaches heavily rely on handcrafted descriptors and/or fingerprints, which need extensive human expert knowledge. With the rapid progress of artificial intelligence technology, data-driven deep learning methods have shown unparalleled advantages over feature-engineering-based methods. However, existing deep learning methods usually suffer from the scarcity of labeled data and the inability to share information between different tasks when applied to predicting molecular properties, thus resulting in poor generalization capability. Here, we proposed a novel multitask learning BERT (Bidirectional Encoder Representations from Transformer) framework, named MTL-BERT, which leverages large-scale pre-training, multitask learning, and SMILES (simplified molecular input line entry specification) enumeration to alleviate the data scarcity problem. MTL-BERT first exploits a large amount of unlabeled data through self-supervised pretraining to mine the rich contextual information in SMILES strings and then fine-tunes the pretrained model for multiple downstream tasks simultaneously by leveraging their shared information. Meanwhile, SMILES enumeration is used as a data enhancement strategy during the pretraining, fine-tuning, and test phases to substantially increase data diversity and help to learn the key relevant patterns from complex SMILES strings. The experimental results showed that the pretrained MTL-BERT model with few additional fine-tuning can achieve much better performance than the state-of-the-art methods on most of the 60 practical molecular datasets. Additionally, the MTL-BERT model leverages attention mechanisms to focus on SMILES character features essential to target properties for model interpretability.