Citations

We present an efficient feature selection algorithm for computer aided detection (CAD) computed tomographic (CT) colonography. The algorithm (1) determines an appropriate piecewise linear network (PLN) model by cross validation, (2) applies the orthonormal least square (OLS) procedure to the PLN model utilizing a Modified Schmidt procedure, and (3) uses a floating search algorithm to select features that minimize the output variance. The undesirable "nesting effect" is prevented by the floating search approach, and the piecewise linear OLS procedure makes this algorithm very computationally efficient because the Modified Schmidt procedure only requires one data pass during the whole searching process. The selected features are compared to those obtained by other methods, through cross validation with support vector machines (SVMs).

Frontotemporal dementia with parkinsonism linked to chromosome 17 (FTDP-17) is caused by mutations in the gene encoding the microtubule-associated protein, tau. Some FTDP-17 mutations affect exon 10 splicing. To correct aberrant exon 10 splicing while retaining endogenous transcriptional control, we evaluated the feasibility of using spliceosome-mediated RNA trans-splicing (SMaRT) to reprogram tau mRNA. We designed a pre-trans-splicing molecule containing human tau exons 10 to 13 and a binding domain complementary to the 3′ end of tau intron 9. A minigene comprising tau exons 9, 10, and 11 and minimal flanking intronic sequences was used as a target. RT-PCR analysis of SH-SY5Y cells or COS cells cotransfected with a minigene and a pre-trans-splicing molecule using primers to opposite sides of the predicted splice junction generated products containing exons 9 to 13. Sequencing of the chimeric products showed that an exact exon 9–exon 10 junction had been created, thus demonstrating that tau RNA can be reprogrammed by trans-splicing. Furthermore, by using the same paradigm with a minigene containing full-length intronic sequences, we show that cis-splicing exclusion of exon 10 can be by-passed by trans-splicing and that conversion of exon 10 – tau RNA into exon 10 + tau RNA could be achieved with ≈34% efficiency. Our results demonstrate that an alternatively spliced exon can be replaced by trans-splicing and open the way to novel therapeutic applications of SMaRT for tauopathies and other disorders linked to aberrant alternative splicing.