This research article presents a QSPR (Quantitative Structure-Property Relationship) analysis of distance-based topological indices for anti-tuberculosis drugs. The study focuses on developing QSPR models using various distance-based topological indices, including Wiener, Szeged, PI, and Mostar indices, to correlate these indices with the physicochemical properties of 13 different anti-tuberculosis drugs. The analysis involves calculating these indices for each drug compound and comparing them with their physicochemical properties to establish predictive models. The study employs a cut method to decompose the molecular graphs of the drugs into convex components, allowing for the computation of topological indices. The results show that the Wiener index correlates well with properties such as boiling point, enthalpy, and flash point, while the Padmakar-Ivan (PI) index correlates well with molar refraction, polarizability, and molar volume. The study also compares the performance of distance-based models with degree-based models, finding that distance-based models provide more reliable predictions for large compounds. The findings suggest that distance-based topological indices are effective in predicting the physicochemical properties of anti-tuberculosis drugs, which could aid in the development of new drugs and vaccines. The research highlights the importance of QSPR models in drug discovery and development, particularly in the context of tuberculosis treatment. The study also emphasizes the potential of distance-dependent models for further research, especially in the context of COVID-19 drug molecules.This research article presents a QSPR (Quantitative Structure-Property Relationship) analysis of distance-based topological indices for anti-tuberculosis drugs. The study focuses on developing QSPR models using various distance-based topological indices, including Wiener, Szeged, PI, and Mostar indices, to correlate these indices with the physicochemical properties of 13 different anti-tuberculosis drugs. The analysis involves calculating these indices for each drug compound and comparing them with their physicochemical properties to establish predictive models. The study employs a cut method to decompose the molecular graphs of the drugs into convex components, allowing for the computation of topological indices. The results show that the Wiener index correlates well with properties such as boiling point, enthalpy, and flash point, while the Padmakar-Ivan (PI) index correlates well with molar refraction, polarizability, and molar volume. The study also compares the performance of distance-based models with degree-based models, finding that distance-based models provide more reliable predictions for large compounds. The findings suggest that distance-based topological indices are effective in predicting the physicochemical properties of anti-tuberculosis drugs, which could aid in the development of new drugs and vaccines. The research highlights the importance of QSPR models in drug discovery and development, particularly in the context of tuberculosis treatment. The study also emphasizes the potential of distance-dependent models for further research, especially in the context of COVID-19 drug molecules.