Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun 10;14(1):13251.
doi: 10.1038/s41598-024-63762-w.

Potential inhibitors of VEGFR1, VEGFR2, and VEGFR3 developed through Deep Learning for the treatment of Cervical Cancer

Anuraj Nayarisseri  1   2 , Mohnad Abdalla  3 , Isha Joshi  4 , Manasi Yadav  4 , Anushka Bhrdwaj  4   5 , Ishita Chopra  4   6 , Arshiya Khan  4   5 , Arshiya Saxena  4 , Khushboo Sharma  4   5 , Aravind Panicker  4 , Umesh Panwar  5 , Francisco Jaime Bezerra Mendonça Junior  7 , Sanjeev Kumar Singh  8
Affiliations

Potential inhibitors of VEGFR1, VEGFR2, and VEGFR3 developed through Deep Learning for the treatment of Cervical Cancer

Anuraj Nayarisseri et al. Sci Rep. .

Abstract

Cervical cancer stands as a prevalent gynaecologic malignancy affecting women globally, often linked to persistent human papillomavirus infection. Biomarkers associated with cervical cancer, including VEGF-A, VEGF-B, VEGF-C, VEGF-D, and VEGF-E, show upregulation and are linked to angiogenesis and lymphangiogenesis. This research aims to employ in-silico methods to target tyrosine kinase receptor proteins-VEGFR-1, VEGFR-2, and VEGFR-3, and identify novel inhibitors for Vascular Endothelial Growth Factors receptors (VEGFRs). A comprehensive literary study was conducted which identified 26 established inhibitors for VEGFR-1, VEGFR-2, and VEGFR-3 receptor proteins. Compounds with high-affinity scores, including PubChem ID-25102847, 369976, and 208908 were chosen from pre-existing compounds for creating Deep Learning-based models. RD-Kit, a Deep learning algorithm, was used to generate 43 million compounds for VEGFR-1, VEGFR-2, and VEGFR-3 targets. Molecular docking studies were conducted on the top 10 molecules for each target to validate the receptor-ligand binding affinity. The results of Molecular Docking indicated that PubChem IDs-71465,645 and 11152946 exhibited strong affinity, designating them as the most efficient molecules. To further investigate their potential, a Molecular Dynamics Simulation was performed to assess conformational stability, and a pharmacophore analysis was also conducted for indoctrinating interactions.

Keywords: ADMET studies; Deep learning; Machine-learning; Molecular docking; Molecular dynamics simulation; Python; R programming; VEGFR inhibitors.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Comprehensive Illustration of the VEGFR-VEGF Signaling Pathway Mechanism inCancer Initiation and Progression.
Figure 2
Figure 2
(E)-N′-(3,4-dimethoxybenzylidene)-2-(quinazolin-4-yloxy) acetohydrazide.
Figure 3
Figure 3
The De-novo shape-based compounds generated for VEGFR1 by VAE and RNN sampling using seed 1 and seed 2 as reference molecules.
Figure 4
Figure 4
Workflow used to generate shape- based features for de-novo designing of novel compound.
Figure 5
Figure 5
Representation of Protein 3D structure of VEGFR’s obtained from PDB—(A). VEGFR-1 (PDBID: 3HNG); (B). VEGFR-2 (PDBID: 1Y6A); (C). VEGFR-1 (PDBID: 4BSK); in which, each color represents as helix (Cyan), sheet (pink), loop (dark tints), and co-crystalized compound as yellow with elements color, as well as binding pocket in green.
Figure 6
Figure 6
Re-rank Score Comparison between Established versus Machine Learning (ML) model compounds. BEI = Best established inhibitor; BMLI = Best ML model inhibitor; RRS = Re-rank score.
Figure 7
Figure 7
Molecular dynamics Root Mean Square Deviation (RMSD) and Root Mean Square Fluctuation (RMSF) analyses of VEGFR-1, VEGFR-2, and VEGFR-3 complexes with both the best-established compounds and Machine Learning-based generated compounds. The VEGFR-1 complexes are represented with PubChem ID: 25102847 for the best-established compound (A & B) and PubChem ID: 71465645 for the best ML Model compound (C & D). Similarly, the VEGFR-2 complexes are illustrated with PubChem ID: 369976 for the best-established compound (E & F) and PubChem ID: 11152946 for the best ML Model compound (G & H). Lastly, the VEGFR-3 complexes are depicted with PubChem ID: 208908 for the best-established compound (I & J) and PubChem ID: 68155180 for the best ML Model compound (K & L).
Figure 8
Figure 8
Illustrating the 3D interaction profiles of the most effective established and machine-learning (ML) model compounds against VEGFRs: (A) The most effective established compound PubChem ID: 25102847, shows H-bond interactions with VEGFR-1 [Pink—Y Chain Residues, Green—Ligand], (B) The most effective Machine Learning model compound PubChem ID: 71465645, shows H-bond interactions with VEGFR-1 [Pink—Y Chain & Purple—V Chain Residues, Green—Ligand]; (C) The most effective established compound PubChem ID: 369976, shows H-bond interactions with VEGFR-2 [Golden—A Chain Residues, Green—Ligand], (D) The most effective machine learning model compound PubChem ID: 11152946, shows H-bond interactions with VEGFR-2 [Golden—A Chain & Cyan—V Chain Residues, Green—Ligand]; (E) The most effective established compound PubChem CID: 208908, shows H-bond interactions with VEGFR-3 [Golden—A Chain Residues, Green—Ligand], (F) The most effective machine learning model compound PubChem CID: 68155180 shows H-bond interactions with VEGFR-3[Golden—A Chain Residues, Green—Ligand].
Figure 9
Figure 9
Bioavailability radar related to physicochemical properties of two of each best compound from established and machine learning compounddocked result.
Figure 10
Figure 10
Comparative analysis of HIA, BBB, AMES toxicity, LD50 values of established compounds against machine learning compounds.
Figure 11
Figure 11
Boiled Egg Plot of six most effective machine learning compounds and established compounds.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. https://www.cancer.net/cancer-types/cervical-cancer/statistics.
    1. https://www.who.int/health-topics/cervical-cancer#tab=tab_1
    1. https://www.nccc-online.org/hpvcervical-cancer/cervical-cancer-overview/
    1. Ceci C, Atzori MG, Lacal PM, Graziani G. Role of VEGFs/VEGFR-1 Signaling and its inhibition in modulating tumor invasion: Experimental evidence in different metastatic cancer models. Int. J. Mol. Sci. 2020;21(4):1388. doi: 10.3390/ijms21041388. - DOI - PMC - PubMed
    1. Willmott LJ, Monk BJ. Cervical cancer therapy: current, future and anti-angiogensis targeted treatment. Expert Rev. Anticancer Ther. 2009;9(7):895–903. doi: 10.1586/era.09.58. - DOI - PubMed

MeSH terms

Substances