1. Progress in Transmembrane Protein Research 12 Month Report Tim Nugent

2. Assignment of PROSITE motifs to topological regions We explored the possibility that motifs from the PROSITE database could be used as constraints in subsequent topology prediction steps, by identifying a bias in their inside/outside frequency. Extracelullar Cytoplasm

3. Alpha-helical protein PROSITE motif assignments

4. Using PROSITE motifs to enhance topology prediction

5. CLN3 Topology Prediction

6. Model is in agreement with all published experimental data. Potential amphipathic helix. Bias is hydrophobic/polar residue placement 2 Arginine residues in close proximity – possible anion channel?

7. Using Support Vector Machines for Topology prediction Earlier approaches have relied on physiochemical properties such as hydrophobicity to identify transmembrane helices (e.g Kyte-Doolittle). Recently, more advanced methods using machine learning algorithms such as hidden Markov models (e.g. TMHMM, PHOBIUS) and neural networks (MEMSAT3) have been developed, They have achieved significant improvements in prediction accuracy (~80%). However, none of the top scoring methods use SVMs. While hidden Markov models and neural networks may have multiple outputs, SVMs are binary classifiers. In order to deal with TM topology prediction, multiple SVM will have to be combined, e.g. TM helix / Loop Inside Loop / Outside Loop Signal Peptide / TM helix Re-entrant Loop / TM helix

8. Helix / Loop SVM Prediction Accuracy TM helix / Loop SVM: PSI-BLAST profiles Normalised by Z-score 29 residue sliding window 3 rd order polynomial kernel function Mathews Correlation Coefficient = 0.75 Precision = 0.86 Recall = 0.32 TP= 8384 FP= 1355 TN= 17773 FN= 1969 Kyte-Doolittle MCC: 0.64 MEMSAT3 MMC: 0.76 Overlap of at least 37 sequences between Moller dataset and novel training set.

9. Inside Loop/Outside Loop SVM Prediction Accuracy Inside Loop/Outside Loop SVM 27 residue sliding window Mathews Correlation Coefficient = 0.60 Precision = 0.78 Recall = 0.50 TP= 4060 FP=1028 TN=4081 FN=1007 Signal Peptide/TM Helix and Re-entrant Loop/TM Helix SVMs in training!

10. SVM Results – Glycerol uptake facilitator

11. SVM Results – Photosystem II subunit A

12. SVM Results – Particulate Methane Monooxygenase subunit C

13. SVM Results – Cytochrome b6f subunit A

14. Further work Expand training set: ~45 sequences to add. Additional sequences where the TMH are known but the topology is not can be used to train the Helix/Loop classifier. Parameter optimisation. Window size Kernel type Signal peptide SVM. Re-entrant loop SVM. Combine SVM raw scores/probabilities into a topology.

15. Whole-Proteome TM Protein Analysis

18. Identifying Pore-forming TM Helices