Handling Big Data Scalability in Biological Domain Using Parallel and Distributed Processing: A Case of Three Biological Semantic Similarity Measures

Table 19

Average time reduction obtained using Threaded Resnik with a distributed system and input data divided by their similarity versus input data divided equally.

Number of Gene Pairs	Improvement Percentage (IP)
	2 Slaves	3 Slaves	4 Slaves
10	-99.96	4.05	-95.71
100	-3.36	-52.76	-94.75
1000	10.12	200	-94.72
10000	957.29	1999.38	-94.62
100000	258.33	183.48	-98.46
1000000	417.40	232.39	-73.99
Average	256.64	45588.22	-92.04