int main(){
int n;
scanf("%d", &n);
int x1, x2, y1, y2, r1, r2, p;
double dist,distP;
int shorter, longer;
for (int i = 0; i < n;i++)
{
scanf("%d %d %d %d %d %d", &x1, &y1, &r1, &x2, &y2, &r2);
shorter = ((r1 < r2) ? r1 : r2);
longer = ((r1 < r2) ? r2 : r1);
distP = calDist(x1, x2, y1, y2);
//중심이 같다면
if (x1 == x2 && y1 == y2)
{
if (r1 == r2) p = -1;
else p = 0;
}
//한 점이 다른 원 내부에 있다면
else if (distP <= r1 || distP <= r2)
{
if (distP + shorter == longer) p = 1;
else if (distP + shorter < longer) p = 0;
else p = 2;
}
// 두점 사이의 거리가 충분히 먼 나머지 경우
else
{
if (shorter + longer == distP) p = 1;
else if (shorter + longer < distP) p = 0;
else p = 2;
}
printf("%d\n", p);
}
return 0;
}
int main(int argc, char *argv[])
{
struct sqlConnection *conn, *conn2;
char query2[256];
struct sqlResult *sr2;
char **row2;
char cond_str[255];
char *proteinDatabaseName;
FILE *o1, *o2, *o3;
FILE *fh[23];
char temp_str[1000];;
char *accession;
char *aaSeq;
char *chp;
int i, j, len;
int ihi, ilow;
char *answer;
char *protDisplayId;
int aaResCnt[30];
char aaAlphabet[30];
int aaResFound;
float fvalue1, fvalue2;
float p1, p2;
int icnt, jcnt;
char *taxon;
char *database;
int sortedCnt;
if (argc != 4) usage();
strcpy(aaAlphabet, "WCMHYNFIDQKRTVPGEASLXZB");
proteinDatabaseName = argv[1];
taxon = argv[2];
database = argv[3];
o2 = mustOpen("pbResAvgStd.tab", "w");
for (i=0; i<20; i++)
{
safef(temp_str, sizeof(temp_str), "%c.txt", aaAlphabet[i]);
fh[i] = mustOpen(temp_str, "w");
}
conn = hAllocConn(hDefaultDb());
conn2 = hAllocConn(hDefaultDb());
safef(query2, sizeof(query2), "select proteinID from %s.knownGene;", database);
sr2 = sqlMustGetResult(conn2, query2);
row2 = sqlNextRow(sr2);
icnt = 0;
jcnt = 0;
for (j=0; j<MAXRES; j++)
{
sumJ[j] = 0;
}
while (row2 != NULL)
{
protDisplayId = row2[0];
safef(cond_str, sizeof(cond_str), "val='%s'", protDisplayId);
accession = sqlGetField(proteinDatabaseName, "displayId", "acc", cond_str);
if (accession == NULL)
{
safef(cond_str, sizeof(cond_str), "acc='%s'", protDisplayId);
accession = sqlGetField(proteinDatabaseName, "displayId", "acc", cond_str);
if (accession == NULL)
{
verbose(2, "'%s' not found.\n", protDisplayId);
goto skip;
}
}
safef(cond_str, sizeof(cond_str), "accession='%s'", accession);
answer = sqlGetField("proteins040115", "spXref2", "biodatabaseID", cond_str);
if (answer == NULL)
{
/* this protein might be a variant splice protein, and then it won't be in spXref2 */
goto skip;
}
if (answer[0] != '1')
{
/* printf("%s not in SWISS-PROT\n", protDisplayId);fflush(stdout); */
goto skip;
}
safef(cond_str, sizeof(cond_str), "acc='%s'", accession);
aaSeq = sqlGetField(proteinDatabaseName, "protein", "val", cond_str);
if (aaSeq == NULL)
{
printf("Can't find peptide sequence for %s, exiting ...\n", protDisplayId);
fflush(stdout);
exit(1);
}
len = strlen(aaSeq);
if (len < 100) goto skip;
lenDouble = (double)len;
for (j=0; j<MAXRES; j++)
{
aaResCnt[j] = 0;
}
chp = aaSeq;
for (i=0; i<len; i++)
{
aaResFound = 0;
for (j=0; j<MAXRES; j++)
{
if (*chp == aaAlphabet[j])
{
aaResFound = 1;
aaResCnt[j] ++;
}
}
if (!aaResFound)
{
fprintf(stderr, "%c %d not a valid AA residue.\n", *chp, *chp);
}
chp++;
}
for (j=0; j<MAXRES; j++)
{
freq[icnt][j] = (double)aaResCnt[j]/lenDouble;
sumJ[j] = sumJ[j] + freq[icnt][j];
}
for (j=0; j<20; j++)
{
fprintf(fh[j], "%15.7f\t%s\n", freq[icnt][j], accession);
fflush(fh[j]);
}
icnt++;
if (icnt >= MAXN)
errAbort("Too many proteins - please set MAXN to be more than %d\n", MAXN);
skip:
row2 = sqlNextRow(sr2);
}
recordCnt = icnt;
recordCntDouble = (double)recordCnt;
for (j=0; j<20; j++)
{
carefulClose(&(fh[j]));
}
sqlFreeResult(&sr2);
hFreeConn(&conn);
hFreeConn(&conn2);
for (j=0; j<MAXRES; j++)
{
avg[j] = sumJ[j]/recordCntDouble;
}
for (j=0; j<20; j++)
{
sum = 0.0;
for (i=0; i<recordCnt; i++)
{
sum = sum + (freq[i][j] - avg[j]) * (freq[i][j] - avg[j]);
}
sigma[j] = sqrt(sum/(double)(recordCnt-1));
fprintf(o2, "%c\t%f\t%f\n", aaAlphabet[j], avg[j], sigma[j]);
}
carefulClose(&o2);
o1 = mustOpen("pbAnomLimit.tab", "w");
for (j=0; j<20; j++)
{
safef(temp_str, sizeof(temp_str), "cat %c.txt|sort|uniq > %c.srt", aaAlphabet[j], aaAlphabet[j]);
mustSystem(temp_str);
/* figure out how many unique entries */
safef(temp_str, sizeof(temp_str), "wc %c.srt > %c.tmp", aaAlphabet[j], aaAlphabet[j]);
mustSystem(temp_str);
safef(temp_str, sizeof(temp_str), "%c.tmp", aaAlphabet[j]);
o3 = mustOpen(temp_str, "r");
mustGetLine(o3, temp_str, 1000);
chp = temp_str;
while (*chp == ' ') chp++;
while (*chp != ' ') chp++;
*chp = '\0';
sscanf(temp_str, "%d", &sortedCnt);
safef(temp_str, sizeof(temp_str), "rm %c.tmp", aaAlphabet[j]);
mustSystem(temp_str);
/* cal hi and low cutoff threshold */
ilow = (int)((float)sortedCnt * 0.025);
ihi = (int)((float)sortedCnt * 0.975);
safef(temp_str, sizeof(temp_str), "%c.srt", aaAlphabet[j]);
o2 = mustOpen(temp_str, "r");
i=0;
for (i=0; i<ilow; i++)
{
mustGetLine(o2, temp_str, 1000);
}
sscanf(temp_str, "%f", &fvalue1);
mustGetLine(o2, temp_str, 1000);
sscanf(temp_str, "%f", &fvalue2);
p1 = (fvalue1 + fvalue2)/2.0;
for (i=ilow+1; i<ihi; i++)
{
mustGetLine(o2, temp_str, 1000);
}
sscanf(temp_str, "%f", &fvalue1);
mustGetLine(o2, temp_str, 1000);
sscanf(temp_str, "%f", &fvalue2);
p2 = (fvalue1 + fvalue2)/2.0;
carefulClose(&o2);
fprintf(o1, "%c\t%f\t%f\n", aaAlphabet[j], p1, p2);
fflush(stdout);
for (i=0; i<recordCnt; i++)
{
measure[i] = freq[i][j];
}
safef(temp_str, sizeof(temp_str), "pbAaDist%c.tab", aaAlphabet[j]);
calDist(measure, recordCnt, 51, 0.0, 0.005, temp_str);
}
carefulClose(&o1);
return(0);
}
int main( int argc, char **argv) {
libusb_device_handle *zena;
int channel = -1; // no default 802.15.4 channel
int format = FORMAT_PCAP; // PCAP is default output format
int scan_mode = FALSE;
int drop_bad_packets = TRUE;
int exit_time = -1;
int status;
int c;
// Setup signal handler. Catching SIGPIPE allows for exit when
// piping to Wireshark for live packet feed.
// signal(SIGPIPE, signal_handler);
struct sigaction act;
memset(&act, 0, sizeof(act));
act.sa_sigaction = signal_handler;
act.sa_flags = SA_SIGINFO;
sigaction(SIGPIPE, &act, NULL);
// Parse command line arguments. See usage() for details.
while ((c = getopt(argc, argv, "bc:d:f:hqs:t:vx:r")) != -1) {
switch(c) {
case 'b':
drop_bad_packets = FALSE;
break;
case 'c':
channel = atoi (optarg);
if (channel < 11 || channel > 26) {
fprintf (stderr, "ERROR: Invalid channel. Must be in rage 11 to 26. Use -h for help.\n");
exit(-1);
}
break;
case 'd':
debug_level = atoi (optarg);
break;
case 'f':
if (strcmp(optarg,"pcap")==0) {
format = FORMAT_PCAP;
} else if (strcmp(optarg,"usbhex")==0) {
format = FORMAT_USBHEX;
} else if (strcmp(optarg, "ranger")==0) {
format = FORMAT_RANGER;
} else {
fprintf(stderr,"ERROR: unrecognized output format '%s'. Only pcap, usbhex, ranger allowed.\n",optarg);
exit(-1);
}
break;
case 'h':
version();
usage();
exit(EXIT_SUCCESS);
case 'q':
quiet_mode = TRUE;
break;
case 's':
scan_mode = TRUE;
usb_timeout = atoi (optarg);
break;
case 't':
exit_time = atoi(optarg);
break;
case 'v':
version();
exit(EXIT_SUCCESS);
case 'x':
pcap_lqi_rssi_write = TRUE;
break;
case 'r':
rangeDevice();
break;
case '?': // case when a command line switch argument is missing
if (optopt == 'c') {
fprintf (stderr,"ERROR: 802.15.4 channel 11 to 26 must be specified with -c\n");
exit(-1);
}
if (optopt == 'd') {
fprintf (stderr,"ERROR: debug level 0 .. 9 must be specified with -d\n");
exit(-1);
}
if (optopt == 'f') {
fprintf (stderr,"ERROR: pcap or usbhex format must be specified with -f\n");
exit(-1);
}
break;
}
}
if (debug_level > 0) {
fprintf (stderr,"DEBUG: debug level %d\n",debug_level);
}
// Locate ZENA on the USB bus and get handle.
if ((zena = setup_libusb_access()) == NULL) {
fprintf (stderr, "ERROR: ZENA device not found or not accessible\n");
exit(EXIT_FAILURE);
}
if (channel == -1 && (selected_profile->flags & CHANNEL_SELECTABLE)) {
fprintf (stderr,"ERROR: 802.15.4 channel is mandatory. Specify with -c. Use -h for help.\n");
exit(EXIT_FAILURE);
}
if (channel != -1) {
// Set 802.15.4 channel
status = zena_set_channel (zena,channel);
if (status < 0) {
fprintf (stderr, "ERROR: error setting ZENA to 802.15.4 channel %d, errorCode=%d\n",channel,status);
exit(EXIT_FAILURE);
}
}
// Write PCAP header
if (format == FORMAT_PCAP) {
fwrite(&PCAP_MAGIC, sizeof(int), 1, stdout);
fwrite(&PCAP_VERSION_MAJOR, sizeof(short), 1, stdout);
fwrite(&PCAP_VERSION_MINOR, sizeof(short), 1, stdout);
fwrite(&PCAP_TZ, sizeof(int), 1, stdout); // thiszone: GMT to local correction
fwrite(&PCAP_SIGFIGS, sizeof(int), 1, stdout); // sigfigs: accuracy of timestamps
fwrite(&PCAP_SNAPLEN, sizeof(int), 1, stdout); // snaplen: max len of packets, in octets
fwrite(&PCAP_LINKTYPE, sizeof(int), 1, stdout); // data link type
}
int i,j,data_len,packet_len,packet_len_plus_2,ts_sec,ts_usec;
// Allocate buffer for usb_interrupt_read requests
unsigned char usbbuf[64];
//unsigned char packetbuf[128];
// Get start time of capture. Won't worry about subsecond resolution for this.
struct timespec tp;
clock_gettime(CLOCK_REALTIME, &tp);
int start_sec = tp.tv_sec;
// Store the number of bytes actually transferred here
int nbytes;
// Seitz added: Store corresponding RSS from MRF24J40
float rss;
// Seitz added: Store estimated distance returned from calDist()
float estDist;
// Packet counter
int npacket=0;
zena_packet_t zena_packet;
// Main loop
while ( ! exit_flag ) {
// If scan_mode is TRUE, cycle through all the 802.15.4 channels looking
// for packets. For some reason it seems to be necessary to close the
// USB device and libusb library and reopen it for the channel change to
// work reliably. Why?
if (scan_mode) {
channel++;
if (channel > 26) {
channel = 11;
}
// It seems to be necessary to reset libusb (close library and
// re-initialize it) for zena_set_channel() to be successful.
debug(9,"Closing ZENA to facilitate 802.15.4 channel change");
libusb_close (zena);
debug(9,"Closing libusb library to facilitate 802.15.4 channel change");
libusb_exit(NULL);
debug(9,"Reopening ZENA");
if ((zena = setup_libusb_access()) == NULL) {
fprintf (stderr, "ERROR: unable to reopen ZENA during 80.15.4 channel change\n");
exit(EXIT_FAILURE);
}
debug (1,"Setting 802.15.4 channel to %d",channel);
status = zena_set_channel(zena,channel);
if (status<0) {
fprintf (stderr,"ERROR: error setting 802.15.4 channel to %d during scan, errorCode=%d\n",channel, status);
exit(EXIT_FAILURE);
}
// TODO: bug - we can have packet received from the
// previous 802.15.4 channel in the buffer at this
// point. When outputted it will be incorrectly
// tagged with the new channel number. Can we purge
// the buffer somehow?
}
switch (format) {
//Seitz Added: Prints the packet: Time/chan/pkt len/src/possible dst/LQI/RSSI/pkt count
case FORMAT_RANGER:
status = zena_get_packet (zena, &zena_packet);
if (status == LIBUSB_ERROR_TIMEOUT) {
// A timeout is a normal event. No action.
break;
}
if (status != 0) {
fprintf (stderr,"ERROR: retrieving packet, errorCode=%d\n",status);
break;
}
// Ensure that zena_packet.packet_len is a sane value. Occasionally getting crazy
// values which causes segv when accessing the zena_packet.packet[] buffer.
//Lu: added case of 0 byte length here which causes tshark to crash
zena_packet.packet_len &= 0xff;
if (zena_packet.packet_len > 125 || zena_packet.packet_len == 0) {
fprintf (stderr,"ERROR: invalid packet length, len=%d\n",zena_packet.packet_len);
break;
}
if ( ( ! zena_packet.fcs_ok) && drop_bad_packets ) {
warning ("dropping corrupted packet\n");
break;
}
/*
//Zena reported second.usecond
fprintf (stdout,"%d.%d ", zena_packet.zena_ts_sec, zena_packet.zena_ts_usec);
// 802.15.4 channel
fprintf (stdout, "Channel: %02d ", channel);
// Packet length
fprintf (stdout, "Packet Length: %03d ", zena_packet.packet_len);
// Source Addr: 2 bytes zena_packet.packet[7-8]
fprintf(stdout, "Src: %04d \t", zena_packet.packet[7]);
// Destination Addr: 2 bytes zena_packet.packet[5-6]
fprintf (stdout, "Dst: %04d \t", zena_packet.packet[5]);
// LQI: Based off of SNR and RSSI for MRF24J40
// Values range from [0-255] Higher is better
fprintf(stdout, "LQI: %02d \t", zena_packet.lqi);
// RSSI Based off MRF24J40 received signal strength
// Values range from [0-255] Higher is better
fprintf(stdout, "RSSI: %02d\t", zena_packet.rssi);
fprintf(stdout, "Packet count: %02d ", npacket); //Packet count
// Calculate estimated distance from target
fprintf(stdout, "\nCal Dist: %dm\n", estDist);
fprintf(stdout, "RSS: %3.2f\t", rss);
*/
rss = RSSI_TO_RSS[zena_packet.rssi];
estDist = calDist(rss);
fprintf(stdout, "Packet Count:%d,\tSrc ID:%04d,\tDst ID: %04d,\tLQI:%d,\tRSS:%2.2f,\tDist Est:%2.2fm",npacket,zena_packet.packet[7],zena_packet.packet[5],zena_packet.lqi,rss,estDist);
fprintf(stdout, "\n");
// fprintf(stdout, "Packet Count: %d, \tRSS = %2.2f\n",npacket,rss);
fflush(stdout);
npacket++;
break;
// End Seitz
case FORMAT_USBHEX:
bzero(usbbuf, 64);
status = selected_profile->transfer(zena, selected_profile->ep_packets, usbbuf, 64, &nbytes, usb_timeout);
// check for timeout and silently ignore
if (status == LIBUSB_ERROR_TIMEOUT) {
debug(9,"libusb_transfer(): timeout");
continue;
}
// get host time of packet reception
clock_gettime(CLOCK_REALTIME, &tp);
if ( (exit_time>0) && (tp.tv_sec > (start_sec + exit_time))) {
debug(1,"Exit time reached. Exiting.");
exit(EXIT_SUCCESS);
}
// a real error (ie not timeout)
if (status < 0) {
fprintf (stderr,"ERROR: error retrieving ZENA packet, errorCode=%d\n", status);
continue;
}
// Packet timestamp
fprintf (stdout,"%ld.%ld ",tp.tv_sec,tp.tv_nsec);
// 802.15.4 channel
fprintf (stdout, "%02x ", channel);
// Echo USB 64 byte packet to screen. Each byte as hex separated by space.
// One line per packet.
for (j = 0; j < 64; j++) {
fprintf (stdout, "%02x ", usbbuf[j] & 0xff);
}
fprintf (stdout, "\n");
fflush (stdout);
break;
//Seitz Added: Printing last two bytes of Rx beacon for LQI and RSSI values
// for (j = 17; j < 19; j++) {
// fprintf (stdout, "%02x ", usbbuf[j] & 0xff);
// fprintf (stdout, "%02d ", usbbuf[j]);
// }
//End Seitz
fprintf (stdout, "\n");
fflush (stdout);
break;
case FORMAT_PCAP:
status = zena_get_packet (zena, &zena_packet);
if (status == LIBUSB_ERROR_TIMEOUT) {
// A timeout is a normal event. No action.
break;
}
if (status != 0) {
fprintf (stderr,"ERROR: retrieving packet, errorCode=%d\n",status);
break;
}
// Ensure that zena_packet.packet_len is a sane value. Occasionally getting crazy
// values which causes segv when accessing the zena_packet.packet[] buffer.
//Lu: added case of 0 byte length here which causes tshark to crash
zena_packet.packet_len &= 0xff;
if (zena_packet.packet_len > 125 || zena_packet.packet_len == 0) {
fprintf (stderr,"ERROR: invalid packet length, len=%d\n",zena_packet.packet_len);
break;
}
if ( ( ! zena_packet.fcs_ok) && drop_bad_packets ) {
warning ("dropping corrupted packet\n");
break;
}
npacket++;
// Write PCAP packet header
fwrite (&zena_packet.host_ts_sec, sizeof(int), 1, stdout); // ts_sec: timestamp seconds
fwrite (&zena_packet.host_ts_usec, sizeof(int), 1, stdout); // ts_usec: timestamp microseconds
if (selected_profile->flags & HAS_FCS_FIELD) {
fwrite (&zena_packet.packet_len, sizeof(int), 1, stdout);
fwrite (&zena_packet.packet_len, sizeof(int), 1, stdout);
fwrite (zena_packet.packet, 1, zena_packet.packet_len, stdout);
} else if (pcap_lqi_rssi_write) {
packet_len_plus_2 = zena_packet.packet_len + 2;
fwrite (&packet_len_plus_2, sizeof(int), 1, stdout);
fwrite (&packet_len_plus_2, sizeof(int), 1, stdout);
fwrite (zena_packet.packet, 1, zena_packet.packet_len, stdout);
} else
// Small problem re FCS. Old HW ZENA does not provide this information.
// Solution is in the case of a good packet not to include FCS
// and Wireshark will ignore it. In the case were the FCS is
// known to be bad, we'll include a deliberatly wrong FCS. For
// the moment this will be a fixed value (0x0000), but ideally
// it should be computed from the packet and the +1 to guarantee
// it is a bad FCS.
if (zena_packet.fcs_ok) {
packet_len_plus_2 = zena_packet.packet_len + 2;
// write packet excluding FCS
fwrite (&zena_packet.packet_len, sizeof(int), 1, stdout);
fwrite (&packet_len_plus_2, sizeof(int), 1, stdout); // full frame included 2 FCS octets
fwrite (zena_packet.packet, 1, zena_packet.packet_len, stdout);
} else {
packet_len_plus_2 = zena_packet.packet_len + 2;
// two extra bytes for deliberately wrong FCS
fwrite (&packet_len_plus_2, sizeof(int), 1, stdout);
fwrite (&packet_len_plus_2, sizeof(int), 1, stdout);
zena_packet.packet[zena_packet.packet_len] = 0;
zena_packet.packet[zena_packet.packet_len+1] = 0;
fwrite (zena_packet.packet, 1, packet_len_plus_2, stdout);
}
fflush(stdout);
break;
} // end switch
} // end main loop
// Release USB interface and close USB connection.
// This code never reached at the moment -- need to implement signal handler for this.
// However I've noticed no resource leaks. Process kill seems to take care of this.
libusb_close (zena);
libusb_exit(NULL);
debug (1, "Normal exit");
return EXIT_SUCCESS;
}
int main(int argc, char *argv[])
{
struct sqlConnection *conn, *conn2;
char query2[256];
struct sqlResult *sr2;
char **row2;
char cond_str[255];
char *proteinDatabaseName; /* example: sp031112 */
char *protDbName; /* example: proteins031112 */
char emptyStr[1] = {""};
FILE *o2;
char *accession;
char *aaSeq;
char *chp;
int i, j, len;
int cCnt;
char *answer, *answer2;
double hydroSum;
char *protDisplayId;
int aaResCnt[30];
double aaResCntDouble[30];
char aaAlphabet[30];
int aaResFound;
int totalResCnt;
int molWtCnt;
double molWt[100000];
int pIcnt;
double pI[100000];
double aa_hydro[256];
int icnt, jExon, pcnt, ipcnt = 0;
double aaLenDouble[100000];
double avgHydro[100000];
double cCountDouble[100000];
double exonCountDouble[100000];
double interProCountDouble[100000];
char *taxon;
char *database;
char *exonCnt;
int interProCount;
char *kgId;
if (argc != 5) usage();
strcpy(aaAlphabet, "WCMHYNFIDQKRTVPGEASLXZB");
/* Ala: 1.800 Arg: -4.500 Asn: -3.500 Asp: -3.500 Cys: 2.500 Gln: -3.500 */
aa_hydro['A'] = 1.800;
aa_hydro['R'] = -4.500;
aa_hydro['N'] = -3.500;
aa_hydro['D'] = -3.500;
aa_hydro['C'] = 2.500;
aa_hydro['Q'] = -3.500;
/* Glu: -3.500 Gly: -0.400 His: -3.200 Ile: 4.500 Leu: 3.800 Lys: -3.900 */
aa_hydro['E'] = -3.500;
aa_hydro['G'] = -0.400;
aa_hydro['H'] = -3.200;
aa_hydro['I'] = 4.500;
aa_hydro['L'] = 3.800;
aa_hydro['K'] = -3.900;
/* Met: 1.900 Phe: 2.800 Pro: -1.600 Ser: -0.800 Thr: -0.700 Trp: -0.900 */
aa_hydro['M'] = 1.900;
aa_hydro['F'] = 2.800;
aa_hydro['P'] = -1.600;
aa_hydro['S'] = -0.800;
aa_hydro['T'] = -0.700;
aa_hydro['W'] = -0.900;
/* Tyr: -1.300 Val: 4.200 Asx: -3.500 Glx: -3.500 Xaa: -0.490 */
aa_hydro['Y'] = -1.300;
aa_hydro['V'] = 4.200;
proteinDatabaseName = argv[1];
protDbName = argv[2];
taxon = argv[3];
database = argv[4];
o2 = mustOpen("pepResDist.tab", "w");
conn = hAllocConn(database);
conn2 = hAllocConn(database);
for (j=0; j<23; j++)
{
aaResCnt[j] = 0;
}
icnt = jExon = pcnt = 0;
pIcnt = 0;
molWtCnt = 0;
sqlSafef(query2, sizeof(query2), "select acc from %s.accToTaxon where taxon=%s;", proteinDatabaseName, taxon);
sr2 = sqlMustGetResult(conn2, query2);
row2 = sqlNextRow(sr2);
while (row2 != NULL)
{
accession = row2[0];
sqlSafefFrag(cond_str, sizeof(cond_str), "acc='%s'", accession);
protDisplayId = sqlGetField(proteinDatabaseName, "displayId", "val", cond_str);
sqlSafefFrag(cond_str, sizeof(cond_str), "proteinID='%s'", protDisplayId);
answer = sqlGetField(database, "knownGene", "name", cond_str);
/* count InterPro domains */
if (answer != NULL)
{
sqlSafefFrag(cond_str, sizeof(cond_str), "accession='%s'", accession);
answer2 = sqlGetField(protDbName, "swInterPro", "count(*)", cond_str);
if (answer2 != NULL)
{
interProCount = interProCount + atoi(answer2);
interProCountDouble[ipcnt] = (double)(atoi(answer2));
ipcnt++;
}
else
{
printf("%s is not in InterPro DB.\n", accession);fflush(stdout);
}
}
/* count exons, using coding exons from kgProtMap2 (KG-III) table */
sqlSafefFrag(cond_str, sizeof(cond_str), "spID='%s'", accession);
kgId = sqlGetField(database, "kgXref", "kgID", cond_str);
sqlSafefFrag(cond_str, sizeof(cond_str), "qName='%s'", kgId);
answer2 = sqlGetField(database, "kgProtMap2", "blockCount", cond_str);
if (answer2 != NULL)
{
exonCnt = strdup(answer2);
if (atoi(exonCnt) == 0)
{
errAbort("%s %s has 0 block count\n", accession, protDisplayId);
}
exonCountDouble[jExon] = (double)(atoi(exonCnt));
jExon++;
}
else
{
exonCnt = emptyStr;
}
/* process Mol Wt */
sqlSafefFrag(cond_str, sizeof(cond_str), "accession='%s'", accession);
answer2 = sqlGetField(database, "pepMwAa", "molWeight", cond_str);
if (answer2 != NULL)
{
molWt[molWtCnt] = (double)(atof(answer2));
molWtCnt++;
}
/* process pI */
sqlSafefFrag(cond_str, sizeof(cond_str), "accession='%s'", accession);
answer2 = sqlGetField(database, "pepPi", "pI", cond_str);
if (answer2 != NULL)
{
pI[pIcnt] = (double)(atof(answer2));
pIcnt++;
}
sqlSafefFrag(cond_str, sizeof(cond_str), "acc='%s'", accession);
aaSeq = sqlGetField(proteinDatabaseName, "protein", "val", cond_str);
if (aaSeq == NULL)
{
errAbort("%s does not have protein sequence data in %s, aborting ...\n", accession,
proteinDatabaseName);
}
len = strlen(aaSeq);
chp = aaSeq;
for (i=0; i<len; i++)
{
aaResFound = 0;
for (j=0; j<23; j++)
{
if (*chp == aaAlphabet[j])
{
aaResFound = 1;
aaResCnt[j] ++;
}
}
if (!aaResFound)
{
warn("%c %d not a valid AA residue in %s:\n%s", *chp, *chp, accession, aaSeq);
}
chp++;
}
/* calculate hydrophobicity */
chp = aaSeq;
cCnt = 0;
hydroSum = 0;
for (i=0; i<len; i++)
{
hydroSum = hydroSum + aa_hydro[(int)(*chp)];
/* count Cysteines */
if ((*chp == 'C') || (*chp == 'c'))
{
cCnt ++;
}
chp++;
}
aaLenDouble[icnt] = len;
cCountDouble[icnt] = (double)cCnt;
avgHydro[icnt] = hydroSum/(double)len;
icnt++;
row2 = sqlNextRow(sr2);
}
totalResCnt = 0;
for (i=0; i<23; i++)
{
totalResCnt = totalResCnt + aaResCnt[i];
}
/* write out residue count distribution */
for (i=0; i<20; i++)
{
aaResCntDouble[i] = ((double)aaResCnt[i])/((double)totalResCnt);
fprintf(o2, "%d\t%f\n", i+1, (float)aaResCntDouble[i]);
}
fprintf(o2, "%d\t%f\n", i+1, 0.0);
carefulClose(&o2);
/* calculate and write out various distributions */
calDist(molWt, molWtCnt, 21, 0.0, 10000.0,"pepMolWtDist.tab");
calDist(pI, pIcnt, 61, 3.0, 0.2, "pepPiDist.tab");
calDist(avgHydro, icnt, 41, -2.0, 0.1, "pepHydroDist.tab");
calDist(cCountDouble, icnt, 51, 0.0, 1.0, "pepCCntDist.tab");
calDist(exonCountDouble, jExon, 31, 0.0, 1.0, "pepExonCntDist.tab");
calDist(interProCountDouble, ipcnt, 16, 0.0, 1.0, "pepIPCntDist.tab");
sqlFreeResult(&sr2);
hFreeConn(&conn);
hFreeConn(&conn2);
return(0);
}