Journal: Journal of Cheminformatics

Article Title: A beginner’s approach to deep learning applied to VS and MD techniques

doi: 10.1186/s13321-025-00985-7

Figure Lengend Snippet: Overview of the DeepScreening workflow employed by Joshi et al. for the screening of natural compounds against 3CL pro . Through a LBVS step employing a DL predictive model, a SBVS step employing a traditional molecular docking method, additional in silico screenings for characteristics such as pharmacokinetics and toxicity, and MD simulations, a database of 1,611 compounds was narrowed down to two specific hit compounds for further testing

Article Snippet: Tam et al. developed the Deep Learning Ramachandran Plot-Molecular Dynamics Simulations workflow, or DL-RP-MDS, for the functional classification of genetic variants (Fig. ) [ ].

Techniques: In Silico, Drug discovery

Journal: Journal of Cheminformatics

Article Title: A beginner’s approach to deep learning applied to VS and MD techniques

doi: 10.1186/s13321-025-00985-7

Figure Lengend Snippet: Overview of the workflow employed by Arshia et al. for the in silico compound generation of 3CL pro inhibitors. An LSTM RNN architecture was trained through DTL for the generation of 3CL pro binding molecules. Each generation step, the generated molecules were further validated and tested using traditional molecular docking methods. A genetic algorithm then selected a limited number of compounds for further finetuning of the RNN model. After ten generation steps, all molecules with high binding affinity for 3CL pro were clustered through a hierarchical clustering method, and the compounds with the highest binding affinity in each cluster were selected for further testing

Article Snippet: Tam et al. developed the Deep Learning Ramachandran Plot-Molecular Dynamics Simulations workflow, or DL-RP-MDS, for the functional classification of genetic variants (Fig. ) [ ].

Techniques: In Silico, Binding Assay, Generated

Journal: Journal of Cheminformatics

Article Title: A beginner’s approach to deep learning applied to VS and MD techniques

doi: 10.1186/s13321-025-00985-7

Figure Lengend Snippet: Summary of DL models mentioned throughout the “ Deep learning and virtual screening ” section of this review used to aid in performing VS workflows

Article Snippet: Tam et al. developed the Deep Learning Ramachandran Plot-Molecular Dynamics Simulations workflow, or DL-RP-MDS, for the functional classification of genetic variants (Fig. ) [ ].

Techniques: Generated, Binding Assay, Drug discovery, In Silico, In Vitro, In Vivo, Plasmid Preparation, Diffusion-based Assay, Sequencing, Modification, Protein Binding, Sampling, Molecular Weight

Journal: Journal of Cheminformatics

Article Title: A beginner’s approach to deep learning applied to VS and MD techniques

doi: 10.1186/s13321-025-00985-7

Figure Lengend Snippet: Summary of DL models mentioned throughout the “ Deep learning and molecular dynamics simulations ” section of this review used to aid in performing MD workflows

Article Snippet: Tam et al. developed the Deep Learning Ramachandran Plot-Molecular Dynamics Simulations workflow, or DL-RP-MDS, for the functional classification of genetic variants (Fig. ) [ ].

Techniques: Sampling, Residue, Functional Assay

Journal: Briefings in Bioinformatics

Article Title: Comprehensive classification of TP53 somatic missense variants based on their impact on p53 structural stability

doi: 10.1093/bib/bbae400

Figure Lengend Snippet: Ramachandran density plot of TP53 deleterious somatic missense variants. (A) RDPs for deleterious variants (p.A159D, p.Q192L, p.N210K, and p.T231N). The colours from blue to red represent low to high density. (B) The differences between the variants and the based files. The colours from blue to red represent from diminished to increased density.

Article Snippet: We previously developed a method named Ramachandran Plot–Molecular Dynamics Simulations (RP-MDS), aiming to predict the function of germline missense variants based on their effects on protein structure stability, and successfully applied to predict the deleteriousness of unclassified germline missense variants in multiple cancer genes.

Techniques:

Journal: International Journal of Molecular Sciences

Article Title: Comprehensive Identification of Deleterious TP53 Missense VUS Variants Based on Their Impact on TP53 Structural Stability

doi: 10.3390/ijms222111345

Figure Lengend Snippet: Examples of structural impact of known pathogenic variants classified by RPMDS. The known pathogenic variants of R175H, Y220C, G245S, R248Q, R273C, and R282W had a structural derivation of 43.7–49.9% from the WT TP53 structure, indicating their deleterious nature by destructing the TP53 structure. The structures of mutant TP53 and WT TP53 extracted from the last 10 ns of simulations were overlaid to reveal structural changes. Orange: α-helix; blue: β sheet; grey: the secondary structure linkers.

Article Snippet: We recently developed a protein-structure-based method, named Ramachandran Plot Molecular Dynamics Simulation (RPMDS), to study the effects of genetic variation on gene function [ ].

Techniques: Mutagenesis

Journal: International Journal of Molecular Sciences

Article Title: Comprehensive Identification of Deleterious TP53 Missense VUS Variants Based on Their Impact on TP53 Structural Stability

doi: 10.3390/ijms222111345

Figure Lengend Snippet: Spatial change of the substituted residues by missense VUS variants. ( A ) Superimposed variant protein structure; ( B ) Ramachandran scatter plot of the WT residue (black) and the substituted residue (red); ( C ) RMSD plot of the substituted residue (red) relative to the global protein structure. The substituted residues (red) fluctuated at different positions in comparison to the WT residues (black), implying the substituted residues caused different spatial coordination. See detailed description in Results.

Article Snippet: We recently developed a protein-structure-based method, named Ramachandran Plot Molecular Dynamics Simulation (RPMDS), to study the effects of genetic variation on gene function [ ].

Techniques: Variant Assay, Residue, Comparison

Journal: International Journal of Molecular Sciences

Article Title: Comprehensive Identification of Deleterious TP53 Missense VUS Variants Based on Their Impact on TP53 Structural Stability

doi: 10.3390/ijms222111345

Figure Lengend Snippet: Impact of missense VUS on TP53 local structure. ( A ) Ramachandran density plot for missense VUS M169V, N239T, R249S, I255S, and P278R. The β strand regions (ϕ, ψ = (−130, 140)) for Y107D, M169V, R249S, T253N, and I255S were notably diminished, and the PII-spirals (ϕ, ψ = (−45, +135)) for R249S were intensified in comparison to the wildtype. The color change from red to blue represented the density from high to low, respectively. ( B ) Graphical illustration for local structural changes in Y107D, M169V, R249S, T253N, and I225S. WT residue positions were shown only for Y107D with the residues 108–114, 165–172, and 204–208. R249S showed global misfolded structure of TP53. Blue: β strand; orange: α helix; grey: linker joint; cyan: additional structural features.

Article Snippet: We recently developed a protein-structure-based method, named Ramachandran Plot Molecular Dynamics Simulation (RPMDS), to study the effects of genetic variation on gene function [ ].

Techniques: Comparison, Residue

Journal: International Journal of Molecular Sciences

Article Title: Comprehensive Identification of Deleterious TP53 Missense VUS Variants Based on Their Impact on TP53 Structural Stability

doi: 10.3390/ijms222111345

Figure Lengend Snippet: Comparison of RPMDS-based missense VUS classification with other methods.

Article Snippet: We recently developed a protein-structure-based method, named Ramachandran Plot Molecular Dynamics Simulation (RPMDS), to study the effects of genetic variation on gene function [ ].

Techniques: Comparison, Variant Assay, In Silico