HNSPPI: a hybrid computational model combing network and sequence information for predicting protein–protein interaction

Briefings in Bioinformatics, Journal Year: 2023, Volume and Issue: 24(5)

Published: June 28, 2023

Most life activities in organisms are regulated through protein complexes, which mainly controlled via Protein-Protein Interactions (PPIs). Discovering new interactions between proteins and revealing their biological functions of great significance for understanding the molecular mechanisms processes identifying potential targets drug discovery. Current experimental methods only capture stable interactions, lead to limited coverage. In addition, expensive cost time consuming also obvious shortcomings. recent years, various computational have been successfully developed predicting PPIs based on homology, primary sequences or gene ontology information. Computational efficiency data complexity still main bottlenecks algorithm generalization. this study, we proposed a novel framework, HNSPPI, predict PPIs. As hybrid supervised learning model, HNSPPI comprehensively characterizes intrinsic relationship two by integrating amino acid sequence information connection properties PPI network. The results show that works very well six benchmark datasets. Moreover, comparison analysis proved our model significantly outperforms other five existing algorithms. Finally, used explore SARS-CoV-2-Human interaction system found several regulations. summary, is promising from known data.

Language: Английский

---

Using artificial intelligence to identify drugs for repurposing to treat l-DOPA-induced dyskinesia

Neuropharmacology, Journal Year: 2024, Volume and Issue: 248, P. 109880 - 109880

Published: Feb. 25, 2024

Repurposing regulatory agency-approved molecules, with proven safety in humans, is an attractive option for developing new treatments disease. We identified and assessed the efficacy of 3 drugs predicted by silico screen as having potential to treat l-DOPA-induced dyskinesia (LID) Parkinson's analyzed ∼1.3 million Medline abstracts using natural language processing ranked 3539 existing based on ability reduce LID. from top 5% candidates; lorcaserin, acamprosate ganaxolone, were prioritized preclinical testing i) a novel mechanism action, ii) not been previously validated treatment LID, iii) being blood-brain-barrier penetrant orally bioavailable iv) clinical trial ready. acamprosate, ganaxolone lorcaserin rodent model hyperactivity, affording 58% reduction rotational asymmetry (P < 0.05) compared vehicle. Acamprosate failed demonstrate efficacy. Lorcaserin, 5HT2C agonist, was then further tested MPTP lesioned dyskinetic macaques where it afforded 82% LID 0.05), unfortunately accompanied significant increase parkinsonian disability. In conclusion, although our data do support repurposing or per se we value approach identify candidate molecules which, combination vivo screen, can facilitate development decisions. The present study adds growing literature this paradigm shifting pipeline.

Language: Английский

---

A clustering and graph deep learning-based framework for COVID-19 drug repurposing

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 249, P. 123560 - 123560

Published: March 1, 2024

Drug repurposing (or repositioning) is the process of finding new therapeutic uses for drugs already approved by drug regulatory authorities (e.g., Food and Administration (FDA) Therapeutic Goods (TGA)) other diseases. This involves analysing interactions between different biological entities, such as targets (genes/proteins pathways) properties, to discover novel drug–target or drug–disease relations. Machine learning deep models have successfully analysed complex heterogeneous data with applications in biomedical domain, also been used repurposing. study presents a unsupervised machine framework that utilizes graph-based autoencoder multi-feature type clustering on data. The dataset consists 438 drugs, which 224 are under clinical trials COVID-19 (category A). rest systematically filtered ensure safety efficacy treatment B). solely relies reported data, including its pharmacological chemical/physical interaction host, publicly available assays. Our machine-learning revealed three clusters interest provided recommendations featuring top 15 repurposing, were shortlisted based predicted dominated category A drugs. can be extended support datasets studies availability our open-source code.

Language: Английский

---

Machine Learning Applications for Drug Repurposing

Published: June 19, 2024

Machine learning (ML) is revolutionizing drug repurposing, offering a more efficient, cost-effective approach to discovery by identifying new therapeutic uses for existing drugs. ML algorithms process large, complex biomedical datasets, find hidden patterns that reveal unexpected links between drugs and diseases, predict potential side effects. This advancement holds significant promise precision medicine personalized healthcare. chapter aims explore the growing role of in an emergent frontier identify drugs, thereby accelerating pace medical innovation while mitigating cost risk. The discusses various case studies, demonstrating application drug–disease connections predicting adverse reactions, significantly contributing medicine. In addition, investigates successes challenges encountered this nascent field, highlighting modernize discovery. Emphasis placed on ethical privacy concerns surrounding use patient data models, urging need robust regulations. comprehensive review serves as practical guide those at intersection pharmaceutical research, clinical practice, computer sciences, advocating synergetic these fields advancing

Language: Английский

---

Integrated ML-Based Strategy Identifies Drug Repurposing for Idiopathic Pulmonary Fibrosis

ACS Omega, Journal Year: 2024, Volume and Issue: 9(27), P. 29870 - 29883

Published: June 27, 2024

Idiopathic pulmonary fibrosis (IPF) affects an estimated global population of around 3 million individuals. IPF is a medical condition with unknown cause characterized by the formation scar tissue in lungs, leading to progressive respiratory disease. Currently, there are only two FDA-approved small molecule drugs specifically for treatment and this has created demand rapid development treatment. Moreover, denovo drug time cost-intensive less than 10% success rate. Drug repurposing currently most feasible option rapidly making market rare sporadic Normally, begins screening using computational tools, which results low hit Here, integrated machine learning-based strategy developed significantly reduce false positive outcomes introducing predock machine-learning-based predictions followed literature GSEA-assisted validation pathway prediction. The deployed 1480 clinical trial screen them against "TGFB1", "TGFB2", "PDGFR-a", "SMAD-2/3", "FGF-2", more proteins resulting 247 total 27 potentially repurposable drugs. GSEA suggested that 72 (29.14%) have been tried IPF, 13 (5.2%) already used lung fibrosis, 20 (8%) tested other fibrotic conditions such as cystic renal fibrosis. Pathway prediction remaining 142 was carried out 118 distinct pathways. Furthermore, analysis revealed 29 pathways were directly or indirectly involved 11 involved. 15 potential combinations showing strong synergistic effect IPF. reported here will be useful developing treating related conditions.

Language: Английский

---