1. Artificial intelligence-based screening of molecules from traditional medicines
   • Aim: Screening molecules for potential therapeutic properties
   • Area: Chemistry/Drug Discovery
   • Theoretical Knowledge: Machine learning algorithms, Cheminformatics tools, Organic chemistry
   • Software/Tools: Machine learning algorithms
2. Virtual screening of NIH 10000 molecules for discovering anti-TB drug leads
   • Aim: Identifying potential anti-TB compounds from a large dataset
   • Area: Chemistry/Drug Discovery
   • Theoretical Knowledge: Virtual screening software, Machine learning algorithms, Chemistry, Cheminformatics, Machine learning
   • Software/Tools: Virtual screening software (e.g., AutoDock, Vina), Machine learning algorithms
3. Repurposing of FDA approved drugs against tuberculosis targets
   • Aim: Repurposing existing drugs (FDA) for tuberculosis treatment
   • Area: Chemistry/Drug Repurposing
   • Theoretical Knowledge: Cheminformatics tools, Machine learning algorithms, Chemistry, Cheminformatics, Machine learning
   • Software/Tools: Cheminformatics tools, Machine learning algorithms
4. Molecular dynamics simulation of anti-TB molecules
   • Aim: Understanding the dynamic behavior of anti-TB compounds at the molecular level
   • Area: Chemistry/Physics/Molecular Dynamics Simulation
   • Theoretical Knowledge: Molecular dynamics software, Visualization tools, Computational chemistry, Molecular dynamics, Physics
   • Software/Tools: Molecular dynamics software (e.g., GROMACS, AMBER), Visualization tools
5. Machine learning-based prioritization of organic molecules
   • Aim: Prioritizing molecules for further experimental validation
   • Area: Chemistry/Drug Discovery
   • Theoretical Knowledge: Machine learning algorithms
   • Software/Tools: Machine learning algorithms
6. Prediction of electronic properties of molecules
   • Aim: Predicting electronic properties (e.g., charge, energy levels) of molecules
   • Area: Computational Chemistry
   • Theoretical Knowledge: Quantum chemistry software, Machine learning tools, Quantum chemistry
   • Software/Tools: Quantum chemistry software (e.g., Gaussian, GAMESS), Machine learning tools
7. Development of innate immunity model for preclinical prioritization of drug-like organic molecules
   • Aim: Modeling innate immunity to prioritize drug candidates
   • Area: Chemistry/Drug Discovery
   • Theoretical Knowledge: Machine learning algorithms, Immunology models, Immunology, Drug discovery
   • Software/Tools: Machine learning algorithms
8. Spectroscopic analysis of FDA approved drug
   • Aim: Analyzing the spectroscopic properties of FDA-approved drugs
   • Area: Analytical Chemistry
   • Theoretical Knowledge: Spectroscopy instruments, Data analysis software, Spectroscopy, Analytical chemistry
   • Software/Tools: Spectroscopy instruments, Data analysis software
9. Prioritization anti-viral molecules based on quantum chemical descriptors
   • Aim: Prioritizing anti-viral compounds based on their quantum chemical properties
   • Area: Chemistry/Drug Discovery
   • Theoretical Knowledge: Quantum chemistry software, Machine learning algorithms, Quantum chemistry, Machine learning
   • Software/Tools: Quantum chemistry software (e.g., Gaussian), Machine learning algorithms
10. Deep learning-based prediction of drug-protein interactions for tuberculosis targets
    • Aim: Predicting interactions between drugs and tuberculosis proteins
    • Area: Chemistry/Drug Discovery
    • Theoretical Knowledge: Deep learning frameworks, Bioinformatics tools, AI/Bioinformatics, Machine learning
    • Software/Tools: Deep learning frameworks (e.g., TensorFlow, PyTorch), Bioinformatics tools
11. Virtual screening of natural compounds from medicinal plants for anti-tuberculosis activity
    • Aim: Screening natural compounds for potential anti-TB activity
    • Area: Chemistry/Drug Discovery
    • Theoretical Knowledge: Virtual screening software, Machine learning algorithms, Molecular biology, Cheminformatics, Machine learning
    • Software/Tools: Virtual screening software, Machine learning algorithms
12. Molecular docking studies of FDA-approved drugs against tuberculosis targets
    • Aim: Studying the binding of FDA-approved drugs to tuberculosis targets
    • Area: Chemistry/Drug Discovery
    • Theoretical Knowledge: Molecular docking software, Molecular dynamics tools, Molecular biology, Computational chemistry, Molecular dynamics
    • Software/Tools: Molecular docking software (e.g., AutoDock, GOLD), Molecular dynamics tools
13. Design and implementation of a machine learning model for predicting drug resistance in tuberculosis
    • Aim: Predicting drug resistance in tuberculosis using machine learning techniques
    • Area: Chemistry/Drug Resistance
    • Theoretical Knowledge: Machine learning algorithms
    • Software/Tools: Machine learning algorithms
14. Deep learning-based prediction of pharmacokinetic properties of potential anti-TB drugs
    • Aim: Predicting pharmacokinetic properties of potential anti-TB drugs
    • Area: Chemistry/Drug Discovery
    • Theoretical Knowledge: Deep learning frameworks, Pharmacokinetic modeling tools
    • Software/Tools: Deep learning frameworks, Pharmacokinetic modeling tools
15. Molecular dynamics simulation of drug delivery systems for tuberculosis treatment
    • Aim: Simulating drug delivery systems to understand their behavior in tuberculosis treatment
    • Area: Drug Delivery
    • Theoretical Knowledge: Molecular dynamics software, Visualization tools, Computational chemistry, Drug delivery
    • Software/Tools: Molecular dynamics software, Visualization tools
16. Predicting the potential toxicity of anti-TB drugs
    • Aim: Predicting the toxicity of anti-TB drugs to enhance safety profiles
    • Area: Chemistry/Drug Discovery/Toxicology
    • Theoretical Knowledge: Machine learning algorithms
    • Software/Tools: Machine learning algorithms
17. Integrating AI algorithms for predicting drug synergies in tuberculosis combination therapy
    • Aim: Predicting synergistic effects of drug combinations for tuberculosis treatment
    • Area: Combination Therapy
    • Theoretical Knowledge: Machine learning algorithms
    • Software/Tools: Machine learning algorithms
18. Virtual screening of chemical libraries for novel anti-tuberculosis compounds using AI-driven methodologies
    • Aim: Screening chemical libraries for potential anti-TB compounds using AI-driven methodologies
    • Area: Chemistry/Drug Discovery
    • Theoretical Knowledge: Virtual screening software, Machine learning algorithms, Molecular biology, Cheminformatics, Machine learning
    • Software/Tools: Virtual screening software, Machine learning algorithms
19. Deep learning-based analysis of high-throughput screening data for identifying promising hits against TB
    • Aim: Analyzing high-throughput screening data to identify potential anti-TB compounds
    • Area: Chemistry/Drug Discovery
    • Theoretical Knowledge: Deep learning frameworks, High-throughput screening data analysis tools, Bioinformatics, Machine learning
    • Software/Tools: Deep learning frameworks, High-throughput screening data analysis tools
20. Utilizing AI techniques to analyze omics data for understanding host-pathogen interactions in TB
    • Aim: Analyzing omics data to understand host-pathogen interactions in tuberculosis infection
    • Area: Artificial Intelligence/Chemistry/Drug Discovery
    • Theoretical Knowledge: Bioinformatics tools, Machine learning algorithms, Bioinformatics, Immunology
    • Software/Tools: Bioinformatics tools, Machine learning algorithms
21. Deep learning-based prediction of drug-induced liver injury for potential anti-tuberculosis compounds
    • Aim: Predicting drug-induced liver injury for potential anti-TB compounds
    • Area: Drug Safety
    • Theoretical Knowledge: Deep learning frameworks, Toxicology data, Pharmacology, Toxicology
    • Software/Tools: Deep learning frameworks, Toxicology data
22. Virtual screening of natural product databases for compounds targeting tuberculosis persistence
    • Aim: Screening natural product databases for compounds targeting persistent tuberculosis infections
    • Area: Medicinal Chemistry/Drug Discovery
    • Theoretical Knowledge: Virtual screening software, Machine learning algorithms, Molecular biology, Cheminformatics, Machine learning
    • Software/Tools: Virtual screening software, Machine learning algorithms
23. Machine learning-driven identification of novel drug combinations for tuberculosis treatment
    • Aim: Identifying novel drug combinations for tuberculosis treatment based on synergy prediction
    • Area: Combination Therapy
    • Theoretical Knowledge: Machine learning algorithms
    • Software/Tools: Machine learning algorithms
24. Predicting off-target effects of anti-tuberculosis drugs using AI techniques to enhance safety profiles
    • Aim: Predicting off-target effects of anti-TB drugs to improve drug safety profiles
    • Area: Drug Safety
    • Theoretical Knowledge: Machine learning algorithms
    • Software/Tools: Machine learning algorithms
25. Development of a deep learning model for predicting the binding affinity of small molecules to tuberculosis protein targets
    • Aim: Predicting the binding affinity of small molecules to tuberculosis protein targets using deep learning
    • Area: Drug Discovery
    • Theoretical Knowledge: Deep learning frameworks, Bioinformatics tools, Bioinformatics, Pharmacology
    • Software/Tools: Deep learning frameworks, Bioinformatics tools
26. Virtual screening of compound databases for repurposing candidates targeting tuberculosis biofilms guided by AI
    • Aim: Screening compound databases for repurposing candidates targeting tuberculosis biofilms using AI
    • Area: Drug Repurposing
    • Theoretical Knowledge: Virtual screening software, Machine learning algorithms, Molecular biology, Cheminformatics, Machine learning
    • Software/Tools: Virtual screening software, Machine learning algorithms
27. Utilizing generative adversarial networks (GANs) for de novo design of anti-tuberculosis compounds with desired properties
    • Aim: Designing anti-TB compounds with desired properties using GANs
    • Area: Computer Science/Drug Discovery
    • Theoretical Knowledge: Generative adversarial networks (GANs), Computational chemistry
    • Software/Tools: Computational chemistry, Drug design
28. Machine learning-based prediction of drug metabolism pathways for anti-tuberculosis agents to aid in optimization
    • Aim: Predicting drug metabolism pathways for anti-TB agents to optimize drug design
    • Area: Pharmacokinetics
    • Theoretical Knowledge: Machine learning algorithms, Pharmacokinetic modeling tools, Pharmacokinetics, Machine learning
    • Software/Tools: Machine learning algorithms, Pharmacokinetic modeling tools
29. Deep learning-driven prediction of drug permeability across the blood-brain barrier for potential tuberculosis treatments
    • Aim: Predicting drug permeability across the blood-brain barrier for potential TB treatments
    • Area: Drug Delivery
    • Theoretical Knowledge: Deep learning frameworks, Pharmacokinetic modeling tools, Pharmacokinetics, Drug delivery
    • Software/Tools: Deep learning frameworks, Pharmacokinetic modeling tools
30. Integrating AI algorithms for identifying potential drug resistance mechanisms in tuberculosis bacteria from genomic data
    • Aim: Identifying potential drug resistance mechanisms in TB bacteria from genomic data
    • Area: Drug Resistance
    • Theoretical Knowledge: Machine learning algorithms, Genomic analysis tools, Pharmacology, Genomics
    • Software/Tools: Machine learning algorithms, Genomic analysis tools
31. Computational study of HOMO and LUMO energies in organic semiconductors
    • Aim: Analyzing the electronic properties of organic semiconductors using HOMO and LUMO energies
    • Area: Materials Science, Electronic Structure Calculation
    • Theoretical Knowledge: Quantum chemistry software, Visualization tools, Computational chemistry, Semiconductor physics
    • Software/Tools: Quantum chemistry software, Visualization tools
32. Machine learning-based prediction of organic semiconductor properties
    • Aim: Predicting properties (e.g., charge transport, optical properties) of organic semiconductors
    • Area: Materials Science, Machine Learning
    • Theoretical Knowledge: Machine learning algorithms
    • Software/Tools: Machine learning algorithms
33. Deep learning-driven design of novel organic semiconductors with optimized electronic properties
    • Aim: Designing organic semiconductors with desired electronic properties using deep learning techniques
    • Area: Chemistry/AI/Materials Science, Deep Learning
    • Theoretical Knowledge: Deep learning frameworks, Computational chemistry tools, Materials science, Computational chemistry, Machine learning
    • Software/Tools: Deep learning frameworks, Computational chemistry tools
34. Molecular dynamics simulation of organic semiconductor materials
    • Aim: Understanding the dynamic behavior of organic semiconductor materials at the molecular level
    • Area: Materials Science, Molecular Dynamics Simulation
    • Theoretical Knowledge: Molecular dynamics software, Visualization tools, Computational chemistry, Materials science, Molecular dynamics
    • Software/Tools: Molecular dynamics software, Visualization tools
35. Prediction of antibacterial/antiviral activity using quantitative structure-activity relationship (QSAR)
    • Aim: Predicting the activity of antibacterial/antiviral molecules based on their chemical structures
    • Area: Chemistry/Drug Discovery, Cheminformatics
    • Theoretical Knowledge: QSAR modeling software, Machine learning algorithms, Pharmacology, Cheminformatics, Machine learning
    • Software/Tools: QSAR modeling software, Machine learning algorithms
36. Virtual screening of compound libraries for novel antibacterial agents using QSAR
    • Aim: Screening compound libraries for potential antibacterial agents using QSAR modeling
    • Area: Drug Discovery, Cheminformatics
    • Theoretical Knowledge: Virtual screening software, QSAR modeling tools, Cheminformatics, Pharmacology, Drug discovery
    • Software/Tools: Virtual screening software, QSAR modeling tools
37. Molecular docking studies of potential antiviral compounds against viral targets
    • Aim: Studying the binding interactions between potential antiviral compounds and viral protein targets
    • Area: Drug Discovery, Molecular Docking
    • Theoretical Knowledge: Molecular docking software, Molecular dynamics tools, Molecular biology, Computational chemistry, Drug discovery
    • Software/Tools: Molecular docking software, Molecular dynamics tools
38. Machine learning-driven prediction of drug resistance mechanisms in bacteria and viruses
    • Aim: Predicting drug resistance mechanisms in bacteria and viruses using machine learning techniques
    • Area: Drug Resistance, Machine Learning
    • Theoretical Knowledge: Machine learning algorithms, Pharmacology, Microbiology, Machine learning
    • Software/Tools: Machine learning algorithms
39. Computational analysis of pharmacophore features in antibacterial/antiviral molecules
    • Aim: Identifying key pharmacophore features in antibacterial/antiviral molecules
    • Area: Drug Discovery, Cheminformatics
    • Theoretical Knowledge: Molecular modeling software, Cheminformatics tools, Pharmacology, Cheminformatics
    • Software/Tools: Molecular modeling software, Cheminformatics tools
40. Virtual screening of natural product databases for novel antiviral compounds
    • Aim: Screening natural product databases for potential antiviral compounds
    • Area: Drug Discovery, Cheminformatics
    • Theoretical Knowledge: Virtual screening software, Cheminformatics tools
    • Software/Tools: Virtual screening software, Cheminformatics tools