Error from NUTS estimation

2 messages 2 people Latest: Oct 27, 2025

Error from NUTS estimation

From: Mark Sale Date: October 09, 2025 technical
Dear Colleagues I'm getting an error from NONMEM (7.5.1) when I try to run estimation using NUTS with multiple problems, with a really trivial model (one compartment, 1 and 2 parameters estimated for the two problems) The error is: At line 83 of file Fortran runtime error: Attempting to allocate already allocated variable 'nuts_iparts3' Runs fine with single problem and with 2 problems, runs fine with METH=COND, METH=BAYES or METH=IMPMAP Seems to crash starting problem #2 The control file is below. Running Window 11, Gfortran Also, if I'm FIXing a parameter (THETA(2) in problem 1), does it make sense to have a prior variance? NMTRAN doesn't complain, and it gives reasonable results. $PROB BASE $INPUT AMT EVID OBNUM ID TIME DV COV1 $DATA Model_dev1.csv IGNORE=@ $SUBS ADVAN1 $ABBR DERIV2=NO $PK V = 1 BASECL = THETA(1) CLFCOV = THETA(2) MU_1 = BASECL*(COV1/100)**CLFCOV CL=DEXP(MU_1+ETA(1)) K = CL/V $ERROR IPRED = F IOBS = IPRED *EXP(ERR(1)) Y=IOBS $THETA (-0.356) ; THETA(1) CLEARANCE (0 FIX) ; THETA(2) CLEARANCE~COV1 $THETAP (-0.356, FIX) (0, FIX) $THETAPV BLOCK(2) FIX VALUES(2,0) $OMEGA (0.1) ;; ETA(1) CL $OMEGAP ;; OMEGA PRIOR (0.135 FIX) $OMEGAPD ;; OMEGA PRIOR DF (5 FIX) $SIGMA (0.05) ;; EPS(1) $SIGMAP ;; SIGMA PRIOR (0.24 FIX) $SIGMAPD FIX ;; SIGMA PRIOR DF 5 FIX $EST METH=NUTS INTER CTYPE=0 $PROB FULL $INPUT AMT EVID OBNUM ID TIME DV COV1 $DATA Model_dev1.csv IGNORE=@ REWIND $THETA (-0.356) ; THETA(1) CLEARANCE (-0.2877) ; THETA(2) CLEARANCE~COV1 $THETAP (-0.356, FIX) (-0.2877, FIX) $THETAPV BLOCK(2) FIX VALUES(2,0) $OMEGA (0.1) ;; ETA(1) CL $OMEGAP ;; OMEGA PRIOR (0.135 FIX) $OMEGAPD ;; OMEGA PRIOR DF (5 FIX) $SIGMA (0.05) ;; EPS(1) $SIGMAP ;; SIGMA PRIOR (0.24 FIX) $SIGMAPD FIX ;; SIGMA PRIOR DF 5 FIX $EST METH=NUTS INTER CTYPE=0 An ideas? Thanks Mark Sale M.D. Vice President Integrated Drug Development [email protected] Remote-Forestville CA Office Hours 9 AM - 5 PM Eastern Time +1 302-516-1684 www.certara.com [Certara Logo] This message (including any attachments) may contain confidential, proprietary, privileged and/or private information. The information is intended to be for the use of the individual or entity designated above. If you are not the intended recipient of this message, please notify the sender immediately, and delete the message and any attachments. Any disclosure, reproduction, distribution or other use of this message or any attachments by an individual or entity other than the intended recipient is prohibited.

RE: Error from NUTS estimation

From: Robert Bauer Date: October 27, 2025 technical
Hello Mark and other nmusers: After some investigation, I determined there is a bug in NONMEM 7.6.0, present since NONMEM 7.5.0, in which not all NUTS arrays re de-allocated after the first $PROB is completed, resulting in the allocation error when loading the second $PROB. The work-around is to isolate each $PROB in a separate control stream file, and execute them sequentially, whenever $EST METHOD=NUTS is used. Robert J. Bauer, Ph.D. Senior Director Pharmacometrics R&D ICON Early Phase 731 Arbor way, suite 100 Blue Bell, PA 19422 Office: (215) 616-6428 Mobile: (925) 286-0769 [email protected]<mailto:[email protected]> http://www.iconplc.com/
Quoted reply history
From: [email protected] <[email protected]> On Behalf Of Mark Sale Sent: Thursday, October 9, 2025 2:58 PM To: Nmusers <[email protected]> Subject: [EXTERNAL] [NMusers] Error from NUTS estimation Dear Colleagues I'm getting an error from NONMEM (7.5.1) when I try to run estimation using NUTS with multiple problems, with a really trivial model (one compartment, 1 and 2 parameters estimated for the two problems) The error is: At line 83 of file Fortran runtime error: Attempting to allocate already allocated variable 'nuts_iparts3' Runs fine with single problem and with 2 problems, runs fine with METH=COND, METH=BAYES or METH=IMPMAP Seems to crash starting problem #2 The control file is below. Running Window 11, Gfortran Also, if I'm FIXing a parameter (THETA(2) in problem 1), does it make sense to have a prior variance? NMTRAN doesn't complain, and it gives reasonable results. $PROB BASE $INPUT AMT EVID OBNUM ID TIME DV COV1 $DATA Model_dev1.csv IGNORE=@ $SUBS ADVAN1 $ABBR DERIV2=NO $PK V = 1 BASECL = THETA(1) CLFCOV = THETA(2) MU_1 = BASECL*(COV1/100)**CLFCOV CL=DEXP(MU_1+ETA(1)) K = CL/V $ERROR IPRED = F IOBS = IPRED *EXP(ERR(1)) Y=IOBS $THETA (-0.356) ; THETA(1) CLEARANCE (0 FIX) ; THETA(2) CLEARANCE~COV1 $THETAP (-0.356, FIX) (0, FIX) $THETAPV BLOCK(2) FIX VALUES(2,0) $OMEGA (0.1) ;; ETA(1) CL $OMEGAP ;; OMEGA PRIOR (0.135 FIX) $OMEGAPD ;; OMEGA PRIOR DF (5 FIX) $SIGMA (0.05) ;; EPS(1) $SIGMAP ;; SIGMA PRIOR (0.24 FIX) $SIGMAPD FIX ;; SIGMA PRIOR DF 5 FIX $EST METH=NUTS INTER CTYPE=0 $PROB FULL $INPUT AMT EVID OBNUM ID TIME DV COV1 $DATA Model_dev1.csv IGNORE=@ REWIND $THETA (-0.356) ; THETA(1) CLEARANCE (-0.2877) ; THETA(2) CLEARANCE~COV1 $THETAP (-0.356, FIX) (-0.2877, FIX) $THETAPV BLOCK(2) FIX VALUES(2,0) $OMEGA (0.1) ;; ETA(1) CL $OMEGAP ;; OMEGA PRIOR (0.135 FIX) $OMEGAPD ;; OMEGA PRIOR DF (5 FIX) $SIGMA (0.05) ;; EPS(1) $SIGMAP ;; SIGMA PRIOR (0.24 FIX) $SIGMAPD FIX ;; SIGMA PRIOR DF 5 FIX $EST METH=NUTS INTER CTYPE=0 An ideas? Thanks Mark Sale M.D. Vice President Integrated Drug Development [email protected]<mailto:[email protected]> Remote-Forestville CA Office Hours 9 AM - 5 PM Eastern Time +1 302-516-1684 http://www.certara.com [Certara Logo] This message (including any attachments) may contain confidential, proprietary, privileged and/or private information. The information is intended to be for the use of the individual or entity designated above. If you are not the intended recipient of this message, please notify the sender immediately, and delete the message and any attachments. Any disclosure, reproduction, distribution or other use of this message or any attachments by an individual or entity other than the intended recipient is prohibited.