; SEPARATE PROTEIN AND RNA (spr.spi) ;--------------------------------------------------------------- ; BEGINING OF INPUT PARAMETERS ;INPUT VOLUME NAME FR G 40s ;OUTPUT LOW-PASS FILTERED VOLUME NAME FR G output/vol_fq ;INPUT LARGE SPHERICAL MASK FILE NAME (USED FOR 'CC C') ; MAY USE "MO 3" FOR CREATING THE SPHERICAL MASK FR G maskball ;INPUT FITTED RNA PDB FILE NAME FR G rna_parts.pdb ;INPUT FITTED PROTEIN PDB FILE NAME FR G pro_parts.pdb ;OUTPUT RNA HISTOGRAM DOCUMENT FILE NAME FR G output/hist_rna ;OUTPUT PROTEIN HISTOGRAM DOCUMENT FILE NAME FR G output/hist_pro ;OUTPUT FUNNY VOLUME NAME FR G output/funny_volume ;OUTPUT DOCUMENT FILE NAME TO STORE RNA HISTOGRAM PERCENTAGE FR G output/histoRNA_percent ;OUTPUT DOCUMENT FILE NAME TO STORE PROTEIN HISTOGRAM PERCENTAGE FR G output/histoPROTEIN_percent ;OUTPUT SEGMENTED PROTEIN FILE NAME FR G output/MaskedProtein_fq ;OUTPUT SEGMENTED RNA FILE NAME FR G output/MaskedRNA_fq X20 = 17.8 ; resolution of the map in Angstrom X21 = 3.72 ; pixel size in Angstrom X23 = 50 ; protein and rna voxels are increased by this percentage to ; include solvent X24 = 550 ; molecular weight of protein (kDa) in the input volume X25 = 573 ; molecular weight of RNA (kDa) in the input volume X35 = 7 ; molecular weight of the smallest protein (kDa) in the input volume X43 = 35 ; lowest threshold for proteins at which no noise is visible. use EXPLORER X32 = 70 ; minimum size of protein at higher threshold, should be less than x33, see below X45 = 50 ; cluster size to remove small rna or protein cluster; seems arbitrary X46 = 25 ; threshold level 2 for unrestricted growth, x43 - 10 ; END OF INPUT PARAMETERS ;---------------------------------------------------------------- ; MAKE PROTEIN AND RNA HISTOGRAMS @SPR_MakeHist ; input vol ; input fitted RNA PDB file ; input fitted Protein PDB file ; output RNA histogram ; output Protein Histogram ; output lowpass filtered volume x20 ; resolution x21 ; pixel size ; LOOK AT USING GNUPLOT AND FIND THE THRESHOLD AT WHICH NO PROTEIN WILL BE VISIBLE RR X41 ;X41 = 120 ? DENSITY THRESHOLD AT WHICH ONLY RNA (IN FRAGMENTED FORM) IS VISIBLE ? ; LOOK AT USING GNUPLOT AND FIND OUT THE VALUE RR X42 ;X42 = 90 ? DENSITY THRESHOLD AT MAXIMUM PEAK OF RNA HISTOGRAM ? ; LOOK AT USING GNUPLOT AND FIND OUT THE VALUE RR X44 ;X44 = 50 ? DENSITY THAT CORRESPONDS TO MAXIMUM IN PROTEIN HISTOGRAM ? ; FIND PROTEIN VOXELS x26 = INT(((x24 * 1000)/0.82)/(x21 * x21 *x21)) ; FIND RNA VOXELS x27 = INT(((x25 * 1000)/1.14)/(x21 * x21 *x21)) ; 10% PROTEIN VOLUME IN VOXEL (WITHOUT SOLVENT) X50 = x26/10 ;10% RNA VOLUME IN VOXEL (WITHOUT SOLVENT) X51 = x27/10 x28 = x26 + x26 * (x23/100) ; protein voxels including solvent x29 = x27 + x27 * (x23/100) ; rna voxels including solvent ; FIND RNA FRACTION x30 = x29 /(x28 + x29) ; FIND PROTEIN FRACTION x31 = 1 - x30 ; FIND MINIMUM SIZE OF THE PROTEIN AND TAKE 50% OF IT TO BE CONSERVATIVE X33 = INT(((x35 * 1000)/0.82)/(x21 * x21 *x21))/2 X60 = X21/X20 ; x21 = pixel size, x20 = resolution of the em map X61 = X60 - 0.05 ; pass-band frequency for butterworth low-pass filter X62 = X60 + 0.05 ; stop-band frequency for butterworth low-pass filter ; FIND PROTEIN AND RNA HISTOGRAM PERCENTAGE AND MAKE SEED FOR USE IN REFINEMENT @SPR_FindHistPer ; input volume ; output seed for refinement (fuuny volume) ; input RNA histogram ; input protein histogram ; output RNA histogram percentage ; output protein histogram percentage X30 ; rna fraction X31 ; protein fraction ; THRESHOLD FOR 20% OF THE PROTEIN AND RNA VOLUMES, RESPECTIVELY ; NUMBERS OBTAINED FROM AND ; LOOKING AT THE 5TH COLUMN (= 3RD REGISTER) FOR THE VALUE ~.20 AND THE ; CORRESPONDING VALUE IN THE 3RD COLUMN (= 1ST REGISTER) ;X52 = 74 ; threshold for 20% of protein ;X53 = 103 ; threshold for 20% of RNA RR X52 ? THRESHOLD FOR 20% OF PROTEIN ? RR X53 ? THRESHOLD FOR 20% OF RNA ? ; X54 = THE HISTOGRAM (PROTEIN) BIN CORRESPONDING TO 30 % OF PROTEIN VOLUME. ; THIS NUMBER NUMBER IS OBTAINED FROM BY ; LOOKING AT THE 5TH COLUMN (= 3RD REGISTER) FOR THE VALUE ~.30 AND THE ; CORRESPONDING VALUE IN THE 1ST COLUMN (KEY) ; X54 = 62 RR X54 ? THE HISTOGRAM (PROTEIN) BIN CORRESPONDING TO 30 % OF PROTEIN VOLUME ? @SPR_InitSep ; input lowpass filtered volume ; maskball used for cross-correlation coefficient calculations X41 ; density threshold at which only rna (in fragmented form) is visible X42 ; density threshold at maximum peak of rna histogram X43 ; lowest threshold for proteins X33 ; minimum size of protein X44 ; density that corresponds to maximum in protein histogram X32 ; minimum size of protein at higher threshold VM echo "COMPARE THE HISTOGRAMS histo-RNAcore***mu***-g*** WITH THE RNA HISTOGRAM AND\n" VM echo "ENTER THE CORRESPONDING RNAcore***mu***-g*** FILE NAME : \n" ; INITIALLY SEPARATED RNA MASK FR ?output/RNAcore{***x41}mu{***x42}-g*** FILE NAME ? [RNA_mask_ini] ;output/RNAcore120mu090-g002 @SPR_InitSep ; input lowpass filtered volume ; maskball used for cross-correlation coefficient calculations X41 ; density threshold at which only rna (in fragmented form) is visible X42 ; density threshold at maximum peak of rna histogram X43 ; lowest threshold for proteins X33 ; minimum size of protein X44 ; density that corresponds to maximum in protein histogram X32 ; minimum size of protein at higher threshold [RNA_mask_ini] ; initially separated rna mask VM echo "COMPARE THE HISTOGRAMS histo-mask-Protein004***mu***-g*** WITH THE PROTEIN HISTOGRAM\n" VM echo "AND ENTER THE CORRESPONDING output/mask-Protein004***mu***-g***.dat FILE NAME :\n" ; INITIALLY SEPARATED PROTEIN MASK FR ?output/mask-Protein004***mu***-g*** FILE NAME ? [pro_mask_ini] ;output/mask-Protein004120mu090-g002 @SPR_RefSep ; input volume ; spherical mask for CC operation [pro_mask_ini] ; protein mask determined by initial separation output/mask{***x41}mu{***x42}-RNA002 ; RNA mask determined by initial separation ; the funny volume ; fraction of total mass occupied by protein above a threshold ; fraction of total mass occupied by rna above a threshold x41 ; density threshold at which only rna (in fragmented form) is visible x42 ; density threshold at maximum peak of rna histogram x29 ; % of rna volume derived from mw and density x28 ; % of protein volume derived from mw and density x45 ; cluster size to remove small rna or protein cluster X43 ; threshold level 1 for unrestricted growth X46 ; threshold level 2 for unrestricted growth X51 ; 10% rna volume in voxel (without solvent) X50 ; 10% protein volume in voxel (without solvent) X52 ; threshold for 20% of the protein X53 ; threshold for 20% of the rna X54 ; the histogram (protein) bin corresponding to 30 % of protein volume ; LAST VERSION OF THE SEED X69 = 27 ; you may change this to see if you like any other seed. Usually, the last one is the bset @SPR_MakeSepVol ; input volume ; separated protein volume ; separated RNA volume output/seed{***x41}mu{***x42}-RNA{***x69} ; final rna seed file name output/seed{***x41}mu{***x42}-Protein{***x69} ; final protein seed file name X61 ; pass-band frequency for butterworth low-pass filter X62 ; stop-band frequency for butterworth low-pass filter X21 ; pixel size in Angstrom EN