#hamm dist 1, should be joined
AAACCTGAGAAGCCCA	ATGGAAATTT	1	32 #gene 1, transcript 1, uniquely mapped

#distance 2, should not be joined since they are not connected
AAACCTGAGAAGCCCA	AAAAAAAATT	1	1
AAACCTGAGAAGCCCA	AAAAAAAAAA	1	31

#distance 2, connected, but not neighbors, should be two copies. A bit random which is chosen
AAACCTGAGAAGCCCA	TTTAAAAATT	1	34
AAACCTGAGAAGCCCA	TTTAAAAAAA	1	3

#uncertain gene, should be joined (however as 2 separate ECs, meaning that only the UMI will be changed, the records will remain)
AAACCTGAGAAGCCCA	TTTTTTTTTA	1	31 #gene 1, transcript 1, uniquely mapped
AAACCTGAGAAGCCCA	TTTTTTTTTA	8	1 #gene 1 or 2, transcript 1 or 7

#gene set mismatch, all but one (or two) should be joined. A bit random which is chosen. Only one record will disappear.
AAACCTGAGAAGCCCA	CCCCCCCCCC	1	3 #gene 1, transcript 1, uniquely mapped
AAACCTGAGAAGCCCA	CCCCCCCCCC	8	31 #gene 1 or 2, transcript 1 or 7
AAACCTGAGAAGCCCA	CACCCCCCCC	6	1 #gene 2, transcript 6, uniquely mapped, excluded

#two connected different original molecules. A bit random how it is resolved
AAACCTGAGAAGCCCA	CCTTCCCCCC	1	18 #gene 1, transcript 1, uniquely mapped
AAACCTGAGAAGCCCA	CCTTCCCAAA	1	2 #gene 1, transcript 1, uniquely mapped

#One original molecule, many ones. 
AAACCTGAGAAGCCCA	GGTTCGGGCC	1	6 #gene 1, transcript 1, uniquely mapped

#results in more than one gene
AAACCTGAGAAGCCCA	CCTTCGAACC	21  1 #gene 1, 2 or 3, transcript 1, 6 or 11
AAACCTGAGAAGCCCA	CCTTCGAACC	22	1 #gene 2, 3 or 4, transcript 6, 11 or 12

#another barcode but same UMI, should not be joined with the ones above (but with eachother)
CCACCTGAGAAGCCCA	CCTTCGAACC	21	1 #gene 1, 2 or 3, transcript 1, 6 or 11
CCACCTGAGAAGCCCA	CCTTCGAACC	22	1 #gene 2, 3 or 4, transcript 6, 11 or 12
