Fig. 1

(a) Cumulative distribution curve of the three scores extracted for all possible drugs independently; lines represent the drug score (red), the SL score (green), and the gene score (blue). An 80% threshold has been set to identify the initial minimum significant threshold of scores for candidate filtering, according to Pareto principle. By intersecting the curves and the 80% cutoff, preliminary thresholds were identified at DScore > 0.3, SLScore > 0.2, GScore > 0.1 (b) Probability distribution curves for the three scores are delineated; lines signify the drug score (red), the SL score (green), and the gene score (blue). The probability distribution of scores is a tool in statistics and data analysis, offering valuable insights into variable understanding, hypothesis testing, and outcome prediction. The area under the probability density function curve between two points corresponds to the probability that the variable falls within that interval of score. The score corresponding to the first notable peak beyond the minimum threshold, determined by the individual score corresponding to a cumulative percent greater than 80%, is chosen for each score. Consequently, the final thresholds were determined to be DScore > 0.35, SLScore > 0.5, and GScore > 0.35.