3 Identification of phosphopeptides: Challenges and issues
-
FDR calculations should formally consider the phosphopopulation independently
Here, it is postulated that FDR calculations should formally consider the
phosphopopulation independently, reasoning that the underlying physicochemical properties of the phosphorylated peptides are different from the nonphosphorylated ones leading to different characteristic fragmentation behaviors (such as dominant neutral loss of the phosphate described previously) and by extension phosphospecific and nonphospho-specific scoring distributions.
-
In principle, fragmentation can occur via the intact ion, a neutral loss of 80 Da (HPO3), or a neutral loss of 98 Da (H3PO4 or HPO3 and H20) [49].
Typically, a loss of 98 Da (H3PO4) is observed from serine and threonine residues, while phosphotyrosine normally remains intact [50] but can suffer a neutral loss of 80 or 98 Da (HPO3 and H2O) should there be a nearby side chain bearing a hydroxyl group. The latter neutral loss where there is a concurrent loss of water is an especially difficult situation because this loss can be derived from S/T, making it difficult to distinguish whether the phosphate is present on Y or S/T should there be insufficient product ions available.
4 Activation methods that improve phosphorylation analyses
CID是主流，ETD是新趋势
6 Site localization
The phosphopeptide above generates a product ion spectrum from which it is challenging to unambiguously determine the true site determining ions. In this particular case, two b ions highlighted in green boxes are consistent with serine at position 7 in the peptide being modified, or alternately, the threonine at position 9 could be modified yielding a characteristic y9 ion (green box, lower panel). Experts inspecting the spectrum were divided on which is the most likely interpretation. The possibility that both peptides were present is also not excluded, since they would have the same precursor ion m/z value (figure adapted from ABRF web site, http://www.abrf.org/index.cfm/group.show/ProteomicsInformaticsResearchGroup.53.htm).
7 localization algorithms
There are two classes of localization algorithms available to the public:
- probability-based localizers (PBLs)
The algorithm designed by Olsen and Mann formulates the localization problem as a binomial probability calculation, attempting to calculate a probability for each candidate phosphosite
- search engine difference (SED) scores [78].
All search engines consider candidate PSMs in rank-ordered lists to assign confidence and help determine the most likely match. A key principle embodied in the first automatic spectrum search tool, SEQUEST, has been exploited for phosphoproteomic localization purposes too, namely that the top hit should score significantly higher than the second-ranked hit if it is truly correct. The higher the quality, the greater the score difference and more confident the identification (or in this case, localization). SED scores are computed in the situation where multiple sites are possible for a given modification and the first- and second-ranked candidates are PTM isomers of each other.
10 The status of the false localization rate
Chalkley and Klauser[78]对应FDR提出了FLR的概念：false localization rate
In 2013, Fermin and colleagues 提出了计算FLR的 LuciPHOr algorithm [86],The current version of LuciPHOr is compatible with most of the popular search engines and their scoring metrics, including Peptide-Prophet (p-values), X!Tandem (translated e-values), Mascot (ion scores), and SEQUEST/COMET (Xcorr), and presently works with CID and HCD-derived MS/MS. It has been integrated with the Trans-Proteomic Pipeline [89].
