Biology subjects

Petrosyan, G.

Publications and source records attributed to Petrosyan, G..

3 recordsLinked to original sources

bioRxiv2026

Overcoming the accuracy-generalization tradeoff in docking and scoring for prospective virtual screening

Virtual screening promises access to tens of billions of synthetically accessible, diverse compounds, yet it is rarely used as a primary hit-discovery strategy in contemporary drug-discovery campaigns. We argue that this gap reflects the real-world underperformance of the underlying docking and scoring methods: classical docking is generalizable but limited in accuracy by simple functional forms and parsimonious parameterization, whereas recent machine-learning approaches are highly expressive but do not generalize well to novel molecules and pockets, their reported accuracy often inflated by train-test leakage. To address these challenges, we introduce DODock and DOScore, docking and scoring ML/physics hybrid frameworks that are also highly expressive, yet generalize much better out of distribution compared with the prior ML approaches. This generalization has been prospectively tested in several ways. First, DODocks blind prediction of a drug candidate binding to PCSK9 was compared to the crystal structure that was subsequently solved, recovering the binding pose to 1.2 [A] RMSD. We also used DODock and DOScore in prospective virtual screening campaigns against four therapeutic targets, spanning an ectoenzyme (CD73), a kinase (IRAK4), an extended-substrate protease (FXI), and an allosteric inhibition of protein-protein interface (IL17). These screens yielded many chemically novel, biochemically and cellularly active inhibitors. In the case of CD73, which is a historically challenging target for virtual screening, our screen resulted in a roughly hundredfold improvement in hit rate over a recent machine-learning screen. Our results indicate that the apparent ceiling in the accuracy of virtual screening that seemed to have somewhat plateaued in the last two decades is not fundamental, and that structure-based interrogation of ultralarge chemical space may eventually become a credible primary route to novel chemical matter.

biophysics↗

bioRxiv2024

SMART DATA FACTORY: VOLUNTEER COMPUTING PLATFORM FOR ACTIVE LEARNING-DRIVEN MOLECULAR DATA ACQUISITION

This paper presents the Smart Distributed Data Factory (SDDF), an AI-driven distributed computing platform designed to address challenges in drug discovery by creating comprehensive datasets of molecular conformations and their properties. SDDF uses volunteer computing, leveraging the processing power of personal computers worldwide to accelerate quantum chemistry (DFT) calculations. To tackle the vast chemical space and limited high-quality data, SDDF employs an ensemble of machine learning models to predict molecular properties and selectively choose the most challenging data points for further DFT calculations. The platform also generates new molecular conformations using molecular dynamics with the forces derived from these models. SDDF makes several contributions: the volunteer computing platform for DFT calculations; an active learning framework for constructing a dataset of molecular conformations; a large public dataset of diverse ENAMINE molecules with calculated energies; an ensemble of state-of-the-art ML models for accurate energy prediction. The energy dataset was generated to validate the SDDF approach of reducing the need for extensive calculations. With its strict scaffold split, the dataset can be used for training and benchmarking energy models. By combining active learning, distributed computing, and quantum chemistry, SDDF offers a scalable, cost-effective solution for developing accurate molecular models and ultimately accelerating drug discovery.

biophysics↗

bioRxiv2024

Elucidating the Impact of Hypericum alpestre Extract and L-NAME on the PI3K/Akt Signaling Pathway in A549 Lung Adenocarcinoma Cells

Plants within the Hypericaceae family have been traditionally used for their medicinal properties, showcasing a wide range of effects such as antibacterial, antiviral, and antioxidant qualities. Hypericum alpestre (HA) extracts have exhibited significant cytotoxicity against various cancer cell lines. The phenolic compounds found in HA extracts have attracted attention for their potential in cancer prevention. L-NAME, known for its ability to inhibit nitric oxide synthase (NOS) activity, has emerged as a promising approach in cancer therapy. However, the precise molecular mechanisms underlying the anticancer effects of HA and L-NAME remain unclear. This study aims to clarify the impact of HA and L-NAME on the PI3K/Akt signaling pathway in A549 lung adenocarcinoma cells, with a specific focus on TNFa/COX-2 and VEGFa/MMP-2 pathways. In silico analysis, they identified the compounds with the highest affinity for PI3K/Akt, a finding validated by subsequent in vitro experiments. Furthermore, the combination of herbs and L-NAME exhibited superior efficacy compared to the herb and 5-FU combination, as evidenced by the promotion of apoptosis. Both the herb alone and the combination of the herb with L-NAME demonstrated inhibitory effects on the TNFa/COX-2 and VEGFa/MMP-2 pathways. This therapeutic approach is hypothesized to operate through the PI3k/Akt cell signaling pathway. A better understanding of the interaction between HA polyphenols and PI3K/Akt signaling could pave the way for novel therapeutic strategies against cancer, including drug-resistant tumors.

cancer biology↗