Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Remove C models #214

Open
wants to merge 6 commits into
base: releases
Choose a base branch
from
Open

Remove C models #214

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
777f64e
Use more accurate mass values
RalfG Feb 9, 2024
1d713a8
Replace remaining C model files with .xgboost models
RalfG Feb 9, 2024
062db9d
Format C and Cython code
RalfG Feb 9, 2024
994cd68
Fix calculating correlations if some peptides could not be processed …
RalfG Feb 9, 2024
00e96d6
Avoid type conversions
RalfG Feb 9, 2024
41198c9
Clean up setup.py
RalfG Feb 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
253 changes: 137 additions & 116 deletions ms2pip/_cython_modules/ms2pip_features_c.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,128 +1,149 @@
// Compute feature vectors from peptide
unsigned int* get_v_ms2pip(int peplen, unsigned short* peptide, unsigned short* modpeptide, int charge)
{
int i,j,k;
unsigned int *get_v_ms2pip(int peplen, unsigned short *peptide, unsigned short *modpeptide, int charge)
{
int i, j, k;

int fnum = 1; //first value in v is its length
int fnum = 1; // first value in v is its length

for (i=0; i < 19; i++) {
count_n[i] = 0;
count_c[i] = 0;
}
for (i = 0; i < 19; i++)
{
count_n[i] = 0;
count_c[i] = 0;
}

//I need this for Omega
//important for sptms!!
peptide_buf[0] = peptide[0];
for (i=0; i < peplen; i++) {
if (peptide[i+1] > 18) {
peptide_buf[i+1] = sptm_mapper[peptide[i+1]];
}
else {
peptide_buf[i+1] = peptide[i+1];
}
count_c[peptide_buf[i+1]]++;
}
// I need this for Omega
// important for sptms!!
peptide_buf[0] = peptide[0];
for (i = 0; i < peplen; i++)
{
if (peptide[i + 1] > 18)
{
peptide_buf[i + 1] = sptm_mapper[peptide[i + 1]];
}
else
{
peptide_buf[i + 1] = peptide[i + 1];
}
count_c[peptide_buf[i + 1]]++;
}

int num_shared = 0;
int num_shared = 0;

shared_features[num_shared++] = peplen;
shared_features[num_shared++] = charge;
shared_features[num_shared++] = peplen;
shared_features[num_shared++] = charge;

shared_features[num_shared] = 0;
if (charge == 1) {
shared_features[num_shared] = 1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge == 2) {
shared_features[num_shared] =1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge == 3) {
shared_features[num_shared] =1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge == 4) {
shared_features[num_shared] =1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge >= 5) {
shared_features[num_shared] =1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge == 1)
{
shared_features[num_shared] = 1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge == 2)
{
shared_features[num_shared] = 1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge == 3)
{
shared_features[num_shared] = 1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge == 4)
{
shared_features[num_shared] = 1;
}
num_shared++;
shared_features[num_shared] = 0;
if (charge >= 5)
{
shared_features[num_shared] = 1;
}
num_shared++;

for (j=0; j < num_props; j++) {
for (i=0; i < peplen; i++) {
props_buffer[i] = props[j][peptide_buf[i+1]];
}
qsort(props_buffer,peplen,sizeof(unsigned int),cmpfunc);
shared_features[num_shared++] = props_buffer[0];
shared_features[num_shared++] = props_buffer[(int)(0.25*(peplen-1))];
shared_features[num_shared++] = props_buffer[(int)(0.5*(peplen-1))];
shared_features[num_shared++] = props_buffer[(int)(0.75*(peplen-1))];
shared_features[num_shared++] = props_buffer[peplen-1];
}
for (j = 0; j < num_props; j++)
{
for (i = 0; i < peplen; i++)
{
props_buffer[i] = props[j][peptide_buf[i + 1]];
}
qsort(props_buffer, peplen, sizeof(unsigned int), cmpfunc);
shared_features[num_shared++] = props_buffer[0];
shared_features[num_shared++] = props_buffer[(int)(0.25 * (peplen - 1))];
shared_features[num_shared++] = props_buffer[(int)(0.5 * (peplen - 1))];
shared_features[num_shared++] = props_buffer[(int)(0.75 * (peplen - 1))];
shared_features[num_shared++] = props_buffer[peplen - 1];
}

for (i=0; i < peplen-1; i++) {
for (j=0; j<num_shared; j++) {
v[fnum++] = shared_features[j];
}
v[fnum++] = i+1; // length of N-term ion
v[fnum++] = peplen-i; // length of C-term ion
count_n[peptide_buf[i+1]]++;
count_c[peptide_buf[peplen-i]]--;
for (i = 0; i < peplen - 1; i++)
{
for (j = 0; j < num_shared; j++)
{
v[fnum++] = shared_features[j];
}
v[fnum++] = i + 1; // length of N-term ion
v[fnum++] = peplen - i; // length of C-term ion
count_n[peptide_buf[i + 1]]++;
count_c[peptide_buf[peplen - i]]--;

for (j=0; j < 19; j++) {
v[fnum++] = count_n[j]; // amino acid count in N-term ion
v[fnum++] = count_c[j]; // amino acid count in C-term ion
}
for (j = 0; j < 19; j++)
{
v[fnum++] = count_n[j]; // amino acid count in N-term ion
v[fnum++] = count_c[j]; // amino acid count in C-term ion
}

for (j=0; j < num_props; j++) {
v[fnum++] = props[j][peptide_buf[1]];
v[fnum++] = props[j][peptide_buf[peplen]];
if (i==0) {
v[fnum++] = 0;
}
else {
v[fnum++] = props[j][peptide_buf[i-1]];
}
v[fnum++] = props[j][peptide_buf[i]];
v[fnum++] = props[j][peptide_buf[i+1]];
if (i==(peplen-1)) {
v[fnum++] = 0;
}
else {
v[fnum++] = props[j][peptide_buf[i+2]];
}
unsigned int s = 0;
for (k=0; k <= i; k++) {
props_buffer[k] = props[j][peptide_buf[k+1]];
s+= props_buffer[k];
}
v[fnum++] = s;
qsort(props_buffer,i+1,sizeof(unsigned int),cmpfunc);
v[fnum++] = props_buffer[0];
v[fnum++] = props_buffer[(int)(0.25*i)];
v[fnum++] = props_buffer[(int)(0.5*i)];
v[fnum++] = props_buffer[(int)(0.75*i)];
v[fnum++] = props_buffer[i];
s = 0;
for (k=i+1; k < peplen; k++) {
props_buffer[k-i-1] = props[j][peptide_buf[k+1]];
s+= props_buffer[k-i-1];
}
v[fnum++] = s;
qsort(props_buffer,peplen-i-1,sizeof(unsigned int),cmpfunc);
v[fnum++] = props_buffer[0];
v[fnum++] = props_buffer[(int)(0.25*(peplen-i-1))];
v[fnum++] = props_buffer[(int)(0.5*(peplen-i-1))];
v[fnum++] = props_buffer[(int)(0.75*(peplen-i-1))];
v[fnum++] = props_buffer[peplen-i-2];
}
}
v[0] = fnum-1;
return v;
for (j = 0; j < num_props; j++)
{
v[fnum++] = props[j][peptide_buf[1]];
v[fnum++] = props[j][peptide_buf[peplen]];
if (i == 0)
{
v[fnum++] = 0;
}
else
{
v[fnum++] = props[j][peptide_buf[i - 1]];
}
v[fnum++] = props[j][peptide_buf[i]];
v[fnum++] = props[j][peptide_buf[i + 1]];
if (i == (peplen - 1))
{
v[fnum++] = 0;
}
else
{
v[fnum++] = props[j][peptide_buf[i + 2]];
}
unsigned int s = 0;
for (k = 0; k <= i; k++)
{
props_buffer[k] = props[j][peptide_buf[k + 1]];
s += props_buffer[k];
}
v[fnum++] = s;
qsort(props_buffer, i + 1, sizeof(unsigned int), cmpfunc);
v[fnum++] = props_buffer[0];
v[fnum++] = props_buffer[(int)(0.25 * i)];
v[fnum++] = props_buffer[(int)(0.5 * i)];
v[fnum++] = props_buffer[(int)(0.75 * i)];
v[fnum++] = props_buffer[i];
s = 0;
for (k = i + 1; k < peplen; k++)
{
props_buffer[k - i - 1] = props[j][peptide_buf[k + 1]];
s += props_buffer[k - i - 1];
}
v[fnum++] = s;
qsort(props_buffer, peplen - i - 1, sizeof(unsigned int), cmpfunc);
v[fnum++] = props_buffer[0];
v[fnum++] = props_buffer[(int)(0.25 * (peplen - i - 1))];
v[fnum++] = props_buffer[(int)(0.5 * (peplen - i - 1))];
v[fnum++] = props_buffer[(int)(0.75 * (peplen - i - 1))];
v[fnum++] = props_buffer[peplen - i - 2];
}
}
v[0] = fnum - 1;
return v;
}
Loading
Loading