**4. Prediction of siRNA potency**

Computational prediction of siRNA potency relies on assessment of appropriate designing parameters combined with their optimal weight distribution. Since the early era of siRNA designing researches, many studies are made for finding optimal weights for siRNA selection parameters. Raynolds et al. proposed a method for rational siRNA designing with appropriate parameter weights, by empirical study of 180 experimentally validated efficient siRNAs [10]. The designed siRNAs were given a score based on weighted summation of these parameters and a score threshold was used to identify efficient siRNAs. Table 3 lists the parameters used in the study with their weight distributions.


**Table 3.** Parameters used in Raynold's algorithm with their weights

266 Bioinformatics

**siRNA selection parameter**

F1 2nd nucleotide = A

F2 4th nucleotide = C

F3 6th nucleotide ≠ C

F4 7th nucleotide ≠ U

F5 9th nucleotide = C

F6 17th nucleotide = A

F7 18th nucleotide ≠ C

F8 19th nucleotide = (A/U)

F9 At least three (A/U)s in the seven nucleotides at the 3' end

F11 No occurrences of G/C stretches of length 7 or longer

F12 G/C content is between 35 and 60%

**4. Prediction of siRNA potency** 

F14 Binding energy of N16–N19 > -9 KCal/Mol

F16 Local folding potential (mean) ≥ -22.72 KCal/Mol

the parameters used in the study with their weight distributions.

F13 Tm is between 20 and 60°C

F17 Target site is on CDS

et al.

F10 No occurrences of four or more identical nucleotides in a row

F15 Binding energy of N16–N19 – binding energy of N1–N4 is between 0 and 1 KCal/Mol

**Table 2.** Feature sets predicted to be associated with greater siRNA efficacy as described by Gong

Computational prediction of siRNA potency relies on assessment of appropriate designing parameters combined with their optimal weight distribution. Since the early era of siRNA designing researches, many studies are made for finding optimal weights for siRNA selection parameters. Raynolds et al. proposed a method for rational siRNA designing with appropriate parameter weights, by empirical study of 180 experimentally validated efficient siRNAs [10]. The designed siRNAs were given a score based on weighted summation of these parameters and a score threshold was used to identify efficient siRNAs. Table 3 lists Since then many siRNA designing algorithm worked on different weight distribution schemes for improved prediction of siRNA potency and some even used machine learning algorithms.
