you can learn about the scoring in the program from the original paper: http://genome.cshlp.org/content/13/9/2178.full

The OrthoMCL procedure starts with all-against-all BLASTP comparisons of a set of protein sequences from genomes of interest (Fig. 1). Putative orthologous relationships are identified between pairs of genomes by reciprocal best similarity pairs. For each putative ortholog, probable “recent” paralogs are identified as sequences within the same genome that are (reciprocally) more similar to each other than either is to any sequence from another genome. A P-value cut-off of 1e-5 was chosen for putative orthologs or paralogs, based on empirical studies. Next, putative orthologous and paralogous relationships are converted into a graph in which the nodes represent protein sequences, and the weighted edges represent their relationships. As shown in Figure 2, weights are initially computed as the average –log10 (P-value) of BLAST results for each pair of sequences. Because the high similarity of “recent” paralogs relative to orthologs can bias the clustering process, edge weights are then normalized to reflect the average weight for all ortholog pairs in these two species (or “recent” paralogs when comparing within species).