Dear nmusers,
I have a compound with nonlinear CL. I tried to run the nonlinear model but
got error message as following, could someone point out what could be the
error in my control file or my data?
Best regards,
Yuhong
0PROGRAM TERMINATED BY OBJ
ERROR IN CELS WITH INDIVIDUAL 1 ID= 1.00000000000000E+00
SUM OF "SQUARED" WEIGHTED INDIVIDUAL RESIDUALS IS INFINITE
MESSAGE ISSUED FROM ESTIMATION STEP
AT INITIAL OBJ. FUNCTION EVALUATION
My control file is
$INPUT ID STUD STYP DOSE AMT EVID MDV TIME DV HEIG WT BMI AGE SEX RACE
$DATA ../data/M_PK.NM.csv IGNORE=#
$SUBROUTINE ADVAN6 TRANS1 TOL=3
$MODEL NCOMP=3
COMP=(DEPOT DEFDOSE)
COMP=(CENT DEFOBS)
COMP=(PERIPH)
$PK
ALAG1 = THETA(1)
KA = THETA(2)
V2 = THETA(3)
Q = THETA(4)
V3 = THETA(5)
TVM = THETA(6)
KM = THETA(7)
;####################################################################
; Define IIV parameters
;ZLAG = ETA(1)
;ZKA = ETA(2)
;ZV2 = ETA(3)
;ZQ3 = ETA(4)
;ZV3 = ETA(5)
ZVM = ETA(1)
;ZKM = ETA(3)
;########################################################################
; NONMEM PK Parameter Definitions
VM = TVM*EXP(ZVM)
;KM = TKM*EXP(ZKM)
;V2 = TV2*EXP(ZV2)
;Q = TQ3*EXP(ZQ3)
;V3 = TV3*EXP(ZV3)
;KA = TKA*EXP(ZKA)
;ALAG1 = TLAG*EXP(ZLAG)
S2 = V2/1000
;###########################################################################
$DES
; PK Model
CP = A(2)/S2
DADT(1) = - KA*A(1)
DADT(2) = KA*A(1) - Q/V2*A(2) + Q/V3*A(3) - CP*VM/(KM+CP)
DADT(3) = Q/V2*A(2) - Q/V3*A(3)
;###########################################################################
$ERROR
Y = F + F*EPS(1)+EPS(2)
IPRE = F
;##########################################################################
; SECONDARY PARAMETERS
;##########################################################################
$THETA
(0,1) ; ALAG1 [hr]
(0,4) ; KA [1/hr]
(0,4) ; V2 [L]
(0,0.1) ; Q3 [L/hr]
(0,10) ; V3 [L]
(0,100) ; VM [ng/mL/hr]
(0,10) ; KM [ng/mL]
$OMEGA
;0.5 ; ZLAG
;0 FIX ; ZKA
;0 FIX ; ZV2
;0 FIX ; ZQ3
;0 FIX ; ZV3
0.5 ; ZVM
;0.5 ; ZKM
$SIGMA
0.02 ; Proportional
0 FIX ; Additive [ug/mL]
$EST PRINT=20 MAXEVAL=9999 POSTHOC NOABORT METHOD=1 POSTHOC INTER
MSF=MSFO.msf
$COV MATRIX=S PRINT=E
$TABLE ID TIME IPRE EVID MDV AMT DV ALAG1 VM KM V2 V3 Q KA ZVM
STUD DOSE AGE WT BMI SEX RACE NOPRINT ONEHEADER FILE=nmout.tab
NONLINEAR PK MODEL ERROR
Yuhong, You likely have a predicted value of 0 at some point (maybe a predose sample?). With a predicted value of 0, the proportional error variance will be 0, and you have the additive error variance fixed to 0. So, the total error variance will be zero. Since the "weight" for the sum of squares is the error variance, and this appears in the denominator of the calculation of the sum of weighted squared deviations, you're getting an infinite sum of squares. You might consider not fixing the additive error variance to 0. Mark Mark Sale MD President, Next Level Solutions, LLC www.NextLevelSolns.com 919-846-9185 A carbon-neutral company See our real time solar energy production at: http://enlighten.enphaseenergy.com/public/systems/aSDz2458
Quoted reply history
-------- Original Message --------
Subject: [NMusers] NONLINEAR PK MODEL ERROR
From: Yuhong Chen < [email protected] >
Date: Mon, February 13, 2012 4:20 pm
To: [email protected]
Dear nmusers, I have a compound with nonlinear CL. I tried to run the nonlinear model but got error message as following, could someone point out what could be the error in my control file or my data? Best regards, Yuhong 0PROGRAM TERMINATED BY OBJ ERROR IN CELS WITH INDIVIDUAL 1 ID= 1.00000000000000E+00 SUM OF "SQUARED" WEIGHTED INDIVIDUAL RESIDUALS IS INFINITE MESSAGE ISSUED FROM ESTIMATION STEP AT INITIAL OBJ. FUNCTION EVALUATION My control file is $INPUT ID STUD STYP DOSE AMT EVID MDV TIME DV HEIG WT BMI AGE SEX RACE $DATA ../data/M_PK.NM.csv IGNORE=# $SUBROUTINE ADVAN6 TRANS1 TOL=3 $MODEL NCOMP=3 COMP=(DEPOT DEFDOSE) COMP=(CENT DEFOBS) COMP=(PERIPH) $PK ALAG1 = THETA(1) KA = THETA(2) V2 = THETA(3) Q = THETA(4) V3 = THETA(5) TVM = THETA(6) KM = THETA(7) ;#################################################################### ; Define IIV parameters ;ZLAG = ETA(1) ;ZKA = ETA(2) ;ZV2 = ETA(3) ;ZQ3 = ETA(4) ;ZV3 = ETA(5) ZVM = ETA(1) ;ZKM = ETA(3) ;######################################################################## ; NONMEM PK Parameter Definitions VM = TVM*EXP(ZVM) ;KM = TKM*EXP(ZKM) ;V2 = TV2*EXP(ZV2) ;Q = TQ3*EXP(ZQ3) ;V3 = TV3*EXP(ZV3) ;KA = TKA*EXP(ZKA) ;ALAG1 = TLAG*EXP(ZLAG) S2 = V2/1000 ;########################################################################### $DES ; PK Model CP = A(2)/S2 DADT(1) = - KA*A(1) DADT(2) = KA*A(1) - Q/V2*A(2) + Q/V3*A(3) - CP*VM/(KM+CP) DADT(3) = Q/V2*A(2) - Q/V3*A(3) ;########################################################################### $ERROR Y = F + F*EPS(1)+EPS(2) IPRE = F ;########################################################################## ; SECONDARY PARAMETERS ;########################################################################## $THETA (0,1) ; ALAG1 [hr] (0,4) ; KA [1/hr] (0,4) ; V2 [L] (0,0.1) ; Q3 [L/hr] (0,10) ; V3 [L] (0,100) ; VM [ng/mL/hr] (0,10) ; KM [ng/mL] $OMEGA ;0.5 ; ZLAG ;0 FIX ; ZKA ;0 FIX ; ZV2 ;0 FIX ; ZQ3 ;0 FIX ; ZV3 0.5 ; ZVM ;0.5 ; ZKM $SIGMA 0.02 ; Proportional 0 FIX ; Additive [ug/mL] $EST PRINT=20 MAXEVAL=9999 POSTHOC NOABORT METHOD=1 POSTHOC INTER MSF=MSFO.msf $COV MATRIX=S PRINT=E $TABLE ID TIME IPRE EVID MDV AMT DV ALAG1 VM KM V2 V3 Q KA ZVM STUD DOSE AGE WT BMI SEX RACE NOPRINT ONEHEADER FILE=nmout.tab
Yuhong,
Usually this error points out to zero variance of the residual error. In this case, you have proportional error model. If prediction is zero (or close to zero) at some point, you may get it. I would try to estimate (rather than fix to zero) the additive part of the error model. One possible explanation is ALAG1 use: if the first observation is before ALAG1 time, you will get zero prediction (and this error)
Thanks
Leonid
--------------------------------------
Leonid Gibiansky, Ph.D.
President, QuantPharm LLC
web: www.quantpharm.com
e-mail: LGibiansky at quantpharm.com
tel: (301) 767 5566
Quoted reply history
On 2/13/2012 4:20 PM, Yuhong Chen wrote:
> Dear nmusers,
> I have a compound with nonlinear CL. I tried to run the nonlinear model
> but got error message as following, could someone point out what could
> be the error in my control file or my data?
> Best regards,
> Yuhong
>
> 0PROGRAM TERMINATED BY OBJ
>
> ERROR IN CELS WITH INDIVIDUAL 1 ID= 1.00000000000000E+00
>
> SUM OF "SQUARED" WEIGHTED INDIVIDUAL RESIDUALS IS INFINITE
>
> MESSAGE ISSUED FROM ESTIMATION STEP
>
> AT INITIAL OBJ. FUNCTION EVALUATION
>
> My control file is
>
> $INPUT ID STUD STYP DOSE AMT EVID MDV TIME DV HEIG WT BMI AGE SEX RACE
>
> $DATA ../data/M_PK.NM.csv IGNORE=#
>
> $SUBROUTINE ADVAN6 TRANS1 TOL=3
> $MODEL NCOMP=3
> COMP=(DEPOT DEFDOSE)
> COMP=(CENT DEFOBS)
> COMP=(PERIPH)
>
> $PK
> ALAG1 = THETA(1)
> KA = THETA(2)
> V2 = THETA(3)
> Q = THETA(4)
> V3 = THETA(5)
> TVM = THETA(6)
> KM = THETA(7)
>
> ;####################################################################
> ; Define IIV parameters
>
> ;ZLAG = ETA(1)
> ;ZKA = ETA(2)
> ;ZV2 = ETA(3)
> ;ZQ3 = ETA(4)
> ;ZV3 = ETA(5)
> ZVM = ETA(1)
> ;ZKM = ETA(3)
>
> ;########################################################################
> ; NONMEM PK Parameter Definitions
>
> VM = TVM*EXP(ZVM)
> ;KM = TKM*EXP(ZKM)
> ;V2 = TV2*EXP(ZV2)
> ;Q = TQ3*EXP(ZQ3)
> ;V3 = TV3*EXP(ZV3)
> ;KA = TKA*EXP(ZKA)
> ;ALAG1 = TLAG*EXP(ZLAG)
>
> S2 = V2/1000
>
> ;###########################################################################
> $DES
> ; PK Model
> CP = A(2)/S2
> DADT(1) = - KA*A(1)
> DADT(2) = KA*A(1) - Q/V2*A(2) + Q/V3*A(3) - CP*VM/(KM+CP)
> DADT(3) = Q/V2*A(2) - Q/V3*A(3)
>
> ;###########################################################################
> $ERROR
> Y = F + F*EPS(1)+EPS(2)
> IPRE = F
>
> ;##########################################################################
> ; SECONDARY PARAMETERS
>
> ;##########################################################################
> $THETA
> (0,1) ; ALAG1 [hr]
> (0,4) ; KA [1/hr]
> (0,4) ; V2 [L]
> (0,0.1) ; Q3 [L/hr]
> (0,10) ; V3 [L]
> (0,100) ; VM [ng/mL/hr]
> (0,10) ; KM [ng/mL]
>
> $OMEGA
> ;0.5 ; ZLAG
> ;0 FIX ; ZKA
> ;0 FIX ; ZV2
> ;0 FIX ; ZQ3
> ;0 FIX ; ZV3
> 0.5 ; ZVM
> ;0.5 ; ZKM
>
> $SIGMA
> 0.02 ; Proportional
> 0 FIX ; Additive [ug/mL]
>
> $EST PRINT=20 MAXEVAL=9999 POSTHOC NOABORT METHOD=1 POSTHOC INTER
> MSF=MSFO.msf
> $COV MATRIX=S PRINT=E
>
> $TABLE ID TIME IPRE EVID MDV AMT DV ALAG1 VM KM V2 V3 Q KA ZVM
> STUD DOSE AGE WT BMI SEX RACE NOPRINT ONEHEADER FILE=nmout.tab
Thanks a lot for the suggestions, it is working now.
Yuhong
Quoted reply history
On Mon, Feb 13, 2012 at 5:00 PM, Leonid Gibiansky <[email protected]
> wrote:
> Yuhong,
> Usually this error points out to zero variance of the residual error. In
> this case, you have proportional error model. If prediction is zero (or
> close to zero) at some point, you may get it. I would try to estimate
> (rather than fix to zero) the additive part of the error model. One
> possible explanation is ALAG1 use: if the first observation is before ALAG1
> time, you will get zero prediction (and this error)
> Thanks
> Leonid
>
>
> ------------------------------**--------
> Leonid Gibiansky, Ph.D.
> President, QuantPharm LLC
> web: www.quantpharm.com
> e-mail: LGibiansky at quantpharm.com
> tel: (301) 767 5566
>
>
>
>
> On 2/13/2012 4:20 PM, Yuhong Chen wrote:
>
>> Dear nmusers,
>> I have a compound with nonlinear CL. I tried to run the nonlinear model
>> but got error message as following, could someone point out what could
>> be the error in my control file or my data?
>> Best regards,
>> Yuhong
>>
>> 0PROGRAM TERMINATED BY OBJ
>>
>> ERROR IN CELS WITH INDIVIDUAL 1 ID= 1.00000000000000E+00
>>
>> SUM OF "SQUARED" WEIGHTED INDIVIDUAL RESIDUALS IS INFINITE
>>
>> MESSAGE ISSUED FROM ESTIMATION STEP
>>
>> AT INITIAL OBJ. FUNCTION EVALUATION
>>
>> My control file is
>>
>> $INPUT ID STUD STYP DOSE AMT EVID MDV TIME DV HEIG WT BMI AGE SEX RACE
>>
>> $DATA ../data/M_PK.NM.csv IGNORE=#
>>
>> $SUBROUTINE ADVAN6 TRANS1 TOL=3
>> $MODEL NCOMP=3
>> COMP=(DEPOT DEFDOSE)
>> COMP=(CENT DEFOBS)
>> COMP=(PERIPH)
>>
>> $PK
>> ALAG1 = THETA(1)
>> KA = THETA(2)
>> V2 = THETA(3)
>> Q = THETA(4)
>> V3 = THETA(5)
>> TVM = THETA(6)
>> KM = THETA(7)
>>
>> ;#############################**##############################**#########
>> ; Define IIV parameters
>>
>> ;ZLAG = ETA(1)
>> ;ZKA = ETA(2)
>> ;ZV2 = ETA(3)
>> ;ZQ3 = ETA(4)
>> ;ZV3 = ETA(5)
>> ZVM = ETA(1)
>> ;ZKM = ETA(3)
>>
>> ;#############################**##############################**
>> #############
>> ; NONMEM PK Parameter Definitions
>>
>> VM = TVM*EXP(ZVM)
>> ;KM = TKM*EXP(ZKM)
>> ;V2 = TV2*EXP(ZV2)
>> ;Q = TQ3*EXP(ZQ3)
>> ;V3 = TV3*EXP(ZV3)
>> ;KA = TKA*EXP(ZKA)
>> ;ALAG1 = TLAG*EXP(ZLAG)
>>
>> S2 = V2/1000
>>
>>
>> ;#############################**##############################**
>> ################
>> $DES
>> ; PK Model
>> CP = A(2)/S2
>> DADT(1) = - KA*A(1)
>> DADT(2) = KA*A(1) - Q/V2*A(2) + Q/V3*A(3) - CP*VM/(KM+CP)
>> DADT(3) = Q/V2*A(2) - Q/V3*A(3)
>>
>> ;#############################**##############################**
>> ################
>> $ERROR
>> Y = F + F*EPS(1)+EPS(2)
>> IPRE = F
>>
>> ;#############################**##############################**
>> ###############
>> ; SECONDARY PARAMETERS
>>
>>
>> ;#############################**##############################**
>> ###############
>> $THETA
>> (0,1) ; ALAG1 [hr]
>> (0,4) ; KA [1/hr]
>> (0,4) ; V2 [L]
>> (0,0.1) ; Q3 [L/hr]
>> (0,10) ; V3 [L]
>> (0,100) ; VM [ng/mL/hr]
>> (0,10) ; KM [ng/mL]
>>
>> $OMEGA
>> ;0.5 ; ZLAG
>> ;0 FIX ; ZKA
>> ;0 FIX ; ZV2
>> ;0 FIX ; ZQ3
>> ;0 FIX ; ZV3
>> 0.5 ; ZVM
>> ;0.5 ; ZKM
>>
>> $SIGMA
>> 0.02 ; Proportional
>> 0 FIX ; Additive [ug/mL]
>>
>> $EST PRINT=20 MAXEVAL=9999 POSTHOC NOABORT METHOD=1 POSTHOC INTER
>> MSF=MSFO.msf
>> $COV MATRIX=S PRINT=E
>>
>> $TABLE ID TIME IPRE EVID MDV AMT DV ALAG1 VM KM V2 V3 Q KA ZVM
>> STUD DOSE AGE WT BMI SEX RACE NOPRINT ONEHEADER FILE=nmout.tab
>>
>>
>>