About the full predicted scores (Yeast) downloading

 

 

·        We made predictions on all possible Yeast pairs ( 6270 * 6270 ) for co-complex PPI task and the physical PPI task.

 

·        We share these full predicted PPI score files, with each of them having  19653315 lines

 

·        Note, we have to point out that the positive training data used here were collected in 2004. They were small and noisy. There are quite some bigger and better Yeast PPI reference sets coming out recently. The predictions would be definitely improved with a better and larger positive training set. However our shared score files are still good baseline sets.

 

·        Note: the following full predicted score files were derived from a modified feature version with 158 features.

o       Derived From our detailed 162 features version with the four homology based PPI features removed.

o       This is to avoid the double usage of the homology based PPI information, when using these computational scores for helping other organisms’ PPI estimation.

o       In this way, our predictions were purely from yeast and thus, we could easily use the predicted evidence to derive PPI evidence for other organisms, like human and fly

 

 

·        There are five files shared totally ( All are zipped for size limit)

o       Files Downloads directory:

o       Note: there is no self interacting

 

Protein Pairs List:

 

·        File: full_pair_list.zip

·        Containing the protein ORF pair list

·        This list maps to all the other four score files

·        Format in each line: ORF1  ORF2

 

For Physical PPI task: SVM

·        File: full_pair_list.dips.svm.result.zip

·        Trained from Rand: 118184 ; Pos:  2865

·        SVM light (-t 1 -d 2 -j 15)

·        Score range: [69.5920, -44.4740]

·        Format:  each line contains the score for a yeast protein pair

 

For Co-complex PPI task: SVM

·        full_pair_list.mips.svm.result.zip

·        Trained from : Rand: 236786 ; Pos:  8236

·        SVMlight para: (-t 1 -d 2 -j 15)

·        Score range: [16.2720, -5.1995]

·        Format:  each line contains the score for a yeast protein pair

 

For Co-complex PPI task: RF

·        full_pair_list.mips.rf.result.zip

·        Trained from data: Rand: 236786 ; Pos:  8236

·        RF para: jtree = 300, jwt = 0.95

·        Score range: [1, 0]

 

 

 

·        We provided two PPI top cut list before. They were derived from SVM predictions for these two tasks. The scores got transformed to [0,1] in the old version of data share.

 

·        For the files shared here, we put the raw predicted scores.

 

·        Note: these three full predicted files were derived from the  feature version with 158 features.

o       Derived From our detailed 162 features version with the four homology based PPI features removed.

o       This is to avoid the double usage of the homology based PPI information, when using these computational scores for helping other organisms’ PPI estimation.

o       In this way, our predictions were purely from yeast and thus, we could easily use the predicted evidence to derive PPI evidence for other organisms, like human and fly

 

o       FAQ page