Traditional drug design faces significant challenges due to inherent chemical and biological complexities, often resulting in high failure rates in clinical trials. Deep learning advancements, particularly generative models, offer potential solutions to these challenges. One promising algorithm is DrugGPT, a transformer-based model, that generates small molecules for input protein sequences. Although promising, it generates both chemically valid and invalid structures and does not incorporate the features of approved drugs, resulting in time-consuming and inefficient drug discovery. To address these issues, we introduce DrugGen, an enhanced model based on the DrugGPT structure. DrugGen is fine-tuned on approved drug-target interactions and optimized with proximal policy optimization. By giving reward feedback from protein-ligand binding affinity prediction using pre-trained transformers (PLAPT) and a customized invalid structure assessor, DrugGen significantly improves performance. Evaluation across multiple targets demonstrated that DrugGen achieves 100% valid structure generation compared to 95.5% with DrugGPT and produced molecules with higher predicted binding affinities (7.22 [6.30-8.07]) compared to DrugGPT (5.81 [4.97-6.63]) while maintaining diversity and novelty. Docking simulations further validate its ability to generate molecules targeting binding sites effectively. For example, in the case of fatty acid-binding protein 5 (FABP5), DrugGen generated molecules with superior docking scores (FABP5/11, -9.537 and FABP5/5, -8.399) compared to the reference molecule (Palmitic acid, -6.177). Beyond lead compound generation, DrugGen also shows potential for drug repositioning and creating novel pharmacophores for existing targets. By producing high-quality small molecules, DrugGen provides a high-performance medium for advancing pharmaceutical research and drug discovery.

Target discovery is crucial in drug development, especially for complex chronic diseases. Recent advances in high-throughput technologies and the explosion of biomedical data have highlighted the potential of computational druggability prediction methods. However, most current methods rely on sequence-based features with machine learning, which often face challenges related to hand-crafted features, reproducibility, and accessibility. Moreover, the potential of raw sequence and protein structure has not been fully investigated. Here, we leveraged both protein sequence and structure using deep learning techniques, revealing that protein sequence, especially pre-trained embeddings, is more informative than protein structure. Next, we developed DrugTar, a high‑performance deep learning algorithm integrating sequence embeddings from the ESM-2 pre-trained protein language model with protein ontologies to predict druggability. DrugTar achieved areas under the curve and precision-recall curve values above 0.90, outperforming state-of-the-art methods. In conclusion, DrugTar streamlines target discovery as a bottleneck in developing novel therapeutics.

Aims: A meta-analysis was done to investigate the association of two cardiac biomarkers of N-terminal prohormone of B-type natriuretic peptide (NT-proBNP) and circulating troponin T (TnT) with the progression of diabetic nephropathy (DN). Methods: A thorough search of the PubMed, Scopus, and Web of Science databases was done until June 2022. The outcome (progression of DN) was described as either of the followings: a) eGFR decline, b) albuminuria, c) end-stage renal disease, or d) mortality. A pooled analysis of eligible studies was performed using random-effect models to compensate for the differences in measurement standards between the studies. We further carried out subgroup analyses to examine our results' robustness and find the source of heterogeneity. A sensitivity analysis was performed to assess the influence of individual studies on the pooled result and the funnel plot and Egger's test were used to assess publication bias. Results: For NT-proBNP, 8741 participants from 14 prospective cohorts, and for TnT, 7292 participants from 9 prospective cohorts were included in the meta-analysis. Higher NT-proBNP levels in diabetic patients were associated with a higher probability of DN progression (relative risk [RR]: 1.67, 95% confidence interval [CI]: 1.44 to 1.92). Likewise, elevated levels of TnT were associated with an increased likelihood of DN (RR: 1.57, 95% CI: 1.34 to 1.83). The predictive power of both biomarkers for DN remained significant when the subgroup analyses were performed. The risk estimates were sensitive to none of the studies. The funnel plot and Egger's tests indicated publication bias for both biomarkers. Hence, trim and fill analysis was performed to compensate for this putative bias and the results remained significant both for NT-proBNP (RR: 1.50, 95% CI: 1.31 to 1.79) and TnT (RR: 1.35, 95% CI 1.15 to 1.60). Conclusions: The increased blood levels of TnT and NT-proBNP can be considered as predictors of DN progression in diabetic individuals. PROSPERO registration code: CRD42022350491.

COVID-19 is a newly recognized illness with a predominantly respiratory presentation. Although initial analyses have identified groups of candidate gene biomarkers for the diagnosis of COVID-19, they have yet to identify clinically applicable biomarkers, so we need disease-specific diagnostic biomarkers in biofluid and differential diagnosis in comparison with other infectious diseases. This can further increase knowledge of pathogenesis and help guide treatment. Eight transcriptomic profiles of COVID-19 infected versus control samples from peripheral blood (PB), lung tissue, nasopharyngeal swab and bronchoalveolar lavage fluid (BALF) were considered. In order to find COVID-19 potential Specific Blood Differentially expressed genes (SpeBDs), we implemented a strategy based on finding shared pathways of peripheral blood and the most involved tissues in COVID-19 patients. This step was performed to filter blood DEGs with a role in the shared pathways. Furthermore, nine datasets of the three types of Influenza (H1N1, H3N2, and B) were used for the second step. Potential Differential Blood DEGs of COVID-19 versus Influenza (DifBDs) were found by extracting DEGs involved in only enriched pathways by SpeBDs and not by Influenza DEGs. Then in the third step, a machine learning method (a wrapper feature selection approach supervised by four classifiers of k-NN, Random Forest, SVM, Naïve Bayes) was utilized to narrow down the number of SpeBDs and DifBDs and find the most predictive combination of them to select COVID-19 potential Specific Blood Biomarker Signatures (SpeBBSs) and COVID-19 versus influenza Differential Blood Biomarker Signatures (DifBBSs), respectively. After that, models based on SpeBBSs and DifBBSs and the corresponding algorithms were built to assess their performance on an external dataset. Among all the extracted DEGs from the PB dataset (from common PB pathways with BALF, Lung and Swab), 108 unique SpeBD were obtained. Feature selection using Random Forest outperformed its counterparts and selected IGKC, IGLV3-16 and SRP9 among SpeBDs as SpeBBSs. Validation of the constructed model based on these genes and Random Forest on an external dataset resulted in 93.09% Accuracy. Eighty-three pathways enriched by SpeBDs and not by any of the influenza strains were identified, including 87 DifBDs. Using feature selection by Naive Bayes classifier on DifBDs, FMNL2, IGHV3-23, IGLV2-11 and RPL31 were selected as the most predictable DifBBSs. The constructed model based on these genes and Naive Bayes on an external dataset was validated with 87.2% accuracy. Our study identified several candidate blood biomarkers for a potential specific and differential diagnosis of COVID-19. The proposed biomarkers could be valuable targets for practical investigations to validate their potential.