News
March 29th, 2017
The CASMI 2016 Cat 2+3 paper is out! Jan 20th, 2017
Organisation of CASMI 2017 is underway, stay tuned! Dec 4th, 2016
The MS1 peak lists for Category 2+3 have been added for completeness. May 6th, 2016
The winners and full results are available. April 25th, 2016
The solutions are public now. April 18th, 2016
The contest is closed now, the results are fantastic and will be opened soon! April 9th, 2016
All teams who submit before the deadline April 11th will be allowed to update the submission until Friday 15th. February 12th, 2016
New categories 2 and 3 and data for automatic methods released. 10 new challenges in category 1. January 25th, 2016
E. Schymanski and S. Neumann joined the organising team, additional contest data coming soon. January 11th, 2016
New CASMI 2016 raw data files are available.
March 29th, 2017
The CASMI 2016 Cat 2+3 paper is out! Jan 20th, 2017
Organisation of CASMI 2017 is underway, stay tuned! Dec 4th, 2016
The MS1 peak lists for Category 2+3 have been added for completeness. May 6th, 2016
The winners and full results are available. April 25th, 2016
The solutions are public now. April 18th, 2016
The contest is closed now, the results are fantastic and will be opened soon! April 9th, 2016
All teams who submit before the deadline April 11th will be allowed to update the submission until Friday 15th. February 12th, 2016
New categories 2 and 3 and data for automatic methods released. 10 new challenges in category 1. January 25th, 2016
E. Schymanski and S. Neumann joined the organising team, additional contest data coming soon. January 11th, 2016
New CASMI 2016 raw data files are available.
Results in Category 2
Summary of Challenge wins
Vaniya | Duehrkop | Verdegem | Allen | Brouard | |
---|---|---|---|---|---|
Gold | 70 | 82 | 44 | 63 | 86 |
Silver | 26 | 21 | 53 | 71 | 50 |
Bronze | 35 | 11 | 65 | 40 | 31 |
Gold (neg) | 33 | 0 | 24 | 26 | 20 |
Gold (pos) | 37 | 82 | 20 | 37 | 66 |
Summary statistics per participant
Mean rank | Median rank | Top | Top3 | Top10 | Mean RRP | Median RRP | |
---|---|---|---|---|---|---|---|
Vaniya | 19.75 | 3.0 | 46 | 79 | 101 | 0.804 | 0.922 |
Duehrkop | 25.17 | 1.0 | 70 | 90 | 100 | 0.945 | 1.000 |
Verdegem | 70.79 | 9.8 | 24 | 59 | 105 | 0.880 | 0.972 |
Allen | 47.98 | 6.0 | 39 | 77 | 123 | 0.906 | 0.987 |
Brouard | 127.34 | 5.2 | 62 | 93 | 118 | 0.874 | 0.988 |
Summary of Rank by Challenge and Participant
For each challenge, the rank of the winner(s) is highlighted in bold. If the submission did not contain the correct candidate this is denoted as "-". If someone did not participate in a challenge, nothing is shown. The tables are sortable if you click into the column header. This summary is also available as CSV download.Vaniya | Duehrkop | Verdegem | Allen | Brouard | |
---|---|---|---|---|---|
challenge-001 | 29.5 | 353.0 | 27.5 | 21.5 | |
challenge-002 | - | 5.0 | 5.0 | 5.5 | |
challenge-003 | 7.5 | 27.0 | 7.0 | 4.5 | |
challenge-004 | 21.5 | 8.5 | 8.0 | 7.0 | |
challenge-005 | 2.0 | 3.5 | 112.0 | 383.0 | |
challenge-006 | 40.5 | 86.0 | 63.0 | 75.0 | |
challenge-007 | 2.0 | 4.0 | 3.0 | 266.0 | |
challenge-008 | 1.5 | 2.5 | 2.0 | 2.0 | |
challenge-009 | - | 1.0 | 1.0 | 55.0 | |
challenge-010 | 4.5 | 3.5 | 6.0 | 7.0 | |
challenge-011 | 1.0 | 14.5 | 8.0 | 3753.0 | |
challenge-012 | 15.0 | 28.5 | 47.5 | 2530.0 | |
challenge-013 | 1.0 | 1.0 | 40.0 | ||
challenge-014 | - | 35.5 | 19.5 | 22.0 | |
challenge-015 | 3.0 | 73.0 | 146.0 | 39.0 | |
challenge-016 | 101.0 | 1.5 | 2.0 | 72.0 | |
challenge-017 | - | 95.5 | 82.0 | 58.0 | |
challenge-018 | 1.0 | 3.0 | 1.0 | 1.0 | |
challenge-019 | - | 21.5 | 3.0 | 341.0 | |
challenge-020 | 71.0 | 10.5 | 70.0 | 1.0 | |
challenge-021 | - | 2.0 | 32.0 | 1217.0 | |
challenge-022 | 4.5 | 8.0 | 4.5 | 1.0 | |
challenge-023 | 2.0 | 6.0 | 7.5 | 917.0 | |
challenge-024 | 2.5 | 70.5 | 27.0 | 183.0 | |
challenge-025 | 8.5 | 5.0 | 7.0 | 65.0 | |
challenge-026 | 2.5 | 75.5 | 1.5 | 1.0 | |
challenge-027 | - | 109.5 | 81.5 | 31.0 | |
challenge-028 | 26.5 | 14.0 | 14.0 | 1.0 | |
challenge-029 | 4.0 | 3.5 | 9.0 | 3.0 | |
challenge-030 | 19.0 | 139.5 | 2.0 | 81.0 | |
challenge-031 | - | 9.5 | 6.5 | 3.0 | |
challenge-032 | 68.5 | 3.0 | 42.0 | 78.0 | |
challenge-033 | - | 6.0 | 49.5 | 1.0 | |
challenge-034 | 1.0 | 1.5 | 1.0 | 6.0 | |
challenge-035 | 23.5 | 14.5 | 12.5 | 5.0 | |
challenge-036 | 8.0 | 1.0 | 1170.5 | 972.0 | |
challenge-037 | 6.5 | 6.5 | 64.0 | 68.0 | |
challenge-038 | 3.5 | 2.5 | 3.5 | 29.0 | |
challenge-039 | - | 240.5 | 205.0 | 8.0 | |
challenge-040 | - | 6.5 | 33.5 | 39.0 | |
challenge-041 | 1.0 | 139.0 | 424.0 | 1.0 | |
challenge-042 | 6.5 | 5.0 | 6.5 | 1.0 | |
challenge-043 | - | 188.5 | 12.0 | 20.0 | |
challenge-044 | 2.5 | 1.5 | 3.0 | 19.0 | |
challenge-045 | - | 74.5 | 14.0 | 16.0 | |
challenge-046 | 1.5 | 62.0 | 29.0 | 44.0 | |
challenge-047 | 1.0 | 3.5 | 136.0 | 216.0 | |
challenge-048 | 2.0 | 2.0 | 3.0 | 5.0 | |
challenge-049 | 12.5 | 13.5 | 11.5 | 129.0 | |
challenge-050 | - | 3.5 | 3.0 | 234.0 | |
challenge-051 | 1.0 | 79.0 | 159.5 | 36.0 | |
challenge-052 | - | 48.5 | 103.5 | 160.0 | |
challenge-053 | 1.0 | 61.0 | 308.5 | 2014.0 | |
challenge-054 | 3.0 | 50.0 | 17.0 | 17.0 | |
challenge-055 | 1.0 | 11.5 | 4.0 | 21.0 | |
challenge-056 | - | 84.0 | 5.0 | 14.0 | |
challenge-057 | 22.5 | 1.5 | 1.0 | 81.0 | |
challenge-058 | 1.0 | 1.0 | 11.0 | 5.5 | |
challenge-059 | - | 2.0 | 2.0 | 4.0 | |
challenge-060 | 3.0 | 44.5 | 69.0 | 95.0 | |
challenge-061 | 2.0 | 21.0 | 319.0 | ||
challenge-062 | 1.0 | 66.5 | 76.0 | 605.0 | |
challenge-063 | 1.0 | 1.0 | 1.0 | 20.0 | |
challenge-064 | 2.0 | 3.0 | 23.0 | 12.0 | |
challenge-065 | - | 3.5 | 3.5 | 134.0 | |
challenge-066 | 17.0 | 23.5 | 4.5 | 14.0 | |
challenge-067 | - | 17.0 | 1.0 | 5.0 | |
challenge-068 | 2.0 | 1.5 | 1.0 | 3.0 | |
challenge-069 | 5.0 | 84.5 | 21.5 | 101.0 | |
challenge-070 | - | 3.0 | 2.5 | 367.0 | |
challenge-071 | 2.0 | 3.0 | 3.0 | 2.0 | |
challenge-072 | 1.0 | 1.0 | 70.0 | ||
challenge-073 | 1.0 | 1.0 | 1.0 | 1.0 | |
challenge-074 | 1.0 | 1.0 | 1.0 | 90.0 | |
challenge-075 | 4.5 | 9.0 | 4.0 | 3.0 | |
challenge-076 | 1.5 | 17.0 | 4.0 | 57.0 | |
challenge-077 | 4.5 | 39.0 | 63.0 | 36.0 | |
challenge-078 | 16.0 | 7.0 | 112.0 | ||
challenge-079 | 1.0 | 7.5 | 1.0 | 6.0 | |
challenge-080 | 1.5 | 2.0 | 28.0 | ||
challenge-081 | 4.0 | 5.5 | 8.5 | 6.0 | |
challenge-082 | 17.0 | 1.0 | 4.0 | 1.0 | 1.0 |
challenge-083 | 147.0 | 3.0 | 3.5 | 16.0 | 33.0 |
challenge-084 | 11.0 | 14.0 | 48.0 | 17.0 | 63.0 |
challenge-085 | 49.0 | 1.0 | 53.0 | 89.0 | 16.0 |
challenge-086 | 76.5 | 1.0 | 53.0 | 72.0 | 1.0 |
challenge-087 | 34.5 | 10.0 | 87.0 | 35.5 | 1.0 |
challenge-088 | 41.0 | 1.0 | 50.0 | 65.0 | 1.0 |
challenge-089 | 131.5 | 1.0 | 28.0 | 68.0 | 1.0 |
challenge-090 | 12.5 | 3.0 | 12.5 | 38.5 | 6.0 |
challenge-091 | 10.0 | 11.0 | 89.5 | 6.5 | 1.0 |
challenge-092 | - | 1.0 | 629.0 | 2.0 | 1.0 |
challenge-093 | 79.0 | 1.0 | 13.5 | 22.0 | 26.0 |
challenge-094 | - | 81.0 | 1.0 | 1.0 | 85.0 |
challenge-095 | 106.0 | 1.0 | 4.0 | 1.0 | 76.0 |
challenge-096 | 2.5 | 1.0 | 2.0 | 2.0 | 1.0 |
challenge-097 | 1.0 | 11.0 | 32.0 | 257.5 | 71.0 |
challenge-098 | 1.0 | 1.5 | 48.0 | 2.5 | 1.5 |
challenge-099 | 1.0 | 1.0 | 138.5 | 15.0 | 1.0 |
challenge-100 | - | 1.0 | 8.5 | 15.5 | 1.0 |
challenge-101 | 9.0 | 5.0 | 14.0 | 2.0 | 4.0 |
challenge-102 | 184.0 | 22.0 | 116.0 | 212.0 | 31.0 |
challenge-103 | 238.5 | 1.0 | 158.0 | 5.0 | 1.0 |
challenge-104 | 4.0 | 1.0 | 7.0 | 6.0 | 1.0 |
challenge-105 | 1.0 | 1.5 | 7.5 | 3.5 | 128.5 |
challenge-106 | 7.0 | 1.0 | 1.0 | 3.0 | |
challenge-107 | 44.5 | 2.0 | 41.5 | 2.0 | 2.0 |
challenge-108 | 27.0 | 1.0 | 1.0 | 2.0 | 1.0 |
challenge-109 | 3.0 | 1.5 | 9.0 | 3.0 | 1.5 |
challenge-110 | 1.0 | 1.0 | 1281.0 | 124.5 | 1.0 |
challenge-111 | 1.0 | 1.0 | 1.0 | 2.0 | 1.0 |
challenge-112 | - | 2.0 | 2.0 | 6.0 | 4.0 |
challenge-113 | 35.5 | 1.0 | 3.5 | 35.0 | 1.0 |
challenge-114 | 11.0 | 1.0 | 9.0 | 20.0 | 1.0 |
challenge-115 | 1.0 | 1.0 | 5.5 | 3.0 | 1.0 |
challenge-116 | 49.5 | 2.0 | 31.0 | 1.5 | 2.0 |
challenge-117 | 1.0 | 1.0 | 1.5 | 40.0 | 1.0 |
challenge-118 | - | 1.0 | 11.0 | 5.0 | 3.0 |
challenge-119 | - | 94.0 | 134.5 | 125.0 | 131.0 |
challenge-120 | 77.0 | 66.0 | 614.0 | 9.0 | |
challenge-121 | 46.0 | 34.0 | 3.0 | 6.0 | 136.0 |
challenge-122 | 2.5 | 1.0 | 4.0 | 12.0 | 46.0 |
challenge-123 | 1.5 | 1.0 | 1.5 | 1.0 | 1.0 |
challenge-124 | 3.0 | 1.0 | 6.5 | 2.0 | 1.0 |
challenge-125 | 117.0 | 24.0 | 156.0 | 123.5 | 4.0 |
challenge-126 | 9.0 | 195.0 | 87.0 | 18.0 | 2.0 |
challenge-127 | 21.0 | 4.0 | 43.0 | 65.0 | 1.0 |
challenge-128 | 20.0 | 1.0 | 66.0 | 6.0 | 1.0 |
challenge-129 | 139.0 | 3.0 | 13.5 | 6.0 | 2.0 |
challenge-130 | 1.0 | 1.0 | 6.5 | 52.5 | 1.0 |
challenge-131 | 151.5 | 966.0 | 64.0 | 39.5 | 990.0 |
challenge-132 | 1.0 | 1.0 | 3.5 | 1.0 | 1.0 |
challenge-133 | 1.0 | 1.0 | 1.0 | 1.0 | |
challenge-134 | 6.5 | 4.0 | 2.5 | 3.0 | 30.0 |
challenge-135 | - | 17.0 | 31.0 | 1.0 | 3.0 |
challenge-136 | 15.5 | 9.0 | 3.5 | 3.0 | 2.0 |
challenge-137 | 1.0 | 1.0 | 2.0 | 177.5 | 1.0 |
challenge-138 | 1.0 | 1.0 | 1.0 | 1.0 | 15.0 |
challenge-139 | 1.0 | 1.0 | 1.0 | 1.0 | 66.0 |
challenge-140 | - | 1.0 | 8.5 | 6.0 | 1.0 |
challenge-141 | - | 1.0 | 14.0 | 186.0 | 2.0 |
challenge-142 | 1.0 | 1.0 | 65.0 | 2.0 | 2.0 |
challenge-143 | 1.0 | 1.0 | 525.0 | 13.0 | 1.0 |
challenge-144 | 1.5 | 1.0 | 144.0 | 88.0 | 230.0 |
challenge-145 | 1.0 | 1.0 | 15.0 | 1.0 | 3.0 |
challenge-146 | - | 1.0 | 3.0 | 2.0 | 77.0 |
challenge-147 | - | 2.0 | 3.5 | 4.0 | 1.0 |
challenge-148 | 1.0 | 1.0 | 3.0 | 2.0 | 1.0 |
challenge-149 | 1.0 | 6.0 | 2.5 | 5.0 | 96.0 |
challenge-150 | 1.0 | 1.0 | 2.0 | 3.0 | 1.0 |
challenge-151 | 1.0 | 1.5 | 25.5 | 40.0 | 1.5 |
challenge-152 | - | 1.0 | 265.0 | 173.0 | 2075.0 |
challenge-153 | - | 1.0 | 9.0 | 2.0 | 1.0 |
challenge-154 | - | 11.0 | 12.0 | 3.0 | 54.0 |
challenge-155 | 9.0 | 1.0 | 252.0 | 27.0 | 1.0 |
challenge-156 | - | 1.0 | 1.0 | 1.0 | 1.0 |
challenge-157 | 36.0 | 268.0 | 8.5 | 143.5 | 32.0 |
challenge-158 | 2.0 | 1.0 | 1.0 | 1.0 | 1.0 |
challenge-159 | 2.0 | 506.0 | 16.0 | 2.0 | 61.0 |
challenge-160 | 33.0 | 1.0 | 68.0 | 121.0 | 2.0 |
challenge-161 | - | 1.0 | 193.0 | 21.0 | 1.0 |
challenge-162 | 12.0 | 11.0 | 208.0 | 53.0 | 14.0 |
challenge-163 | 6.0 | 55.0 | 227.0 | 135.0 | 26.0 |
challenge-164 | 2.0 | 1.0 | 1.0 | 1.0 | 1.0 |
challenge-165 | 1.0 | 1.0 | 168.0 | 29.0 | 1.0 |
challenge-166 | - | 1.0 | 102.0 | 72.5 | 1.0 |
challenge-167 | - | 1.0 | 205.0 | 1.0 | 3.0 |
challenge-168 | 13.5 | 2.0 | 335.5 | 120.0 | 3.0 |
challenge-169 | 1.0 | 3.0 | 1.0 | 1.0 | 3.0 |
challenge-170 | - | 3.0 | 33.0 | 4.5 | 1.0 |
challenge-171 | 2.0 | 7.0 | 8.5 | 24.0 | 7.0 |
challenge-172 | 11.0 | 1.0 | 186.0 | 64.0 | 1.0 |
challenge-173 | 40.0 | 1.0 | 20.5 | 88.0 | 4.0 |
challenge-174 | - | 3.0 | 244.0 | 10.0 | 2.0 |
challenge-175 | 15.5 | 44.0 | 136.0 | 5.5 | 8.0 |
challenge-176 | 1.0 | 1.0 | 1.5 | 1.0 | 1.0 |
challenge-177 | 1.0 | 1.0 | 28.0 | 213.5 | 24.0 |
challenge-178 | 72.5 | 1.0 | 1809.5 | 615.5 | 3101.0 |
challenge-179 | 3.0 | 20.0 | 22.5 | 1.0 | 14.0 |
challenge-180 | 19.5 | 44.0 | 186.5 | 4.5 | 6.0 |
challenge-181 | 1.0 | 41.0 | 7.0 | 6.0 | 11.0 |
challenge-182 | - | 1.5 | 2.0 | 9.0 | 1.0 |
challenge-183 | 6.0 | 33.0 | 217.0 | 9.0 | 40.0 |
challenge-184 | 1.0 | 1.0 | 270.0 | 32.0 | 1.0 |
challenge-185 | - | 1.0 | 11.5 | 4.0 | 1.0 |
challenge-186 | 1.0 | 1.0 | 2.0 | 1.0 | 3.0 |
challenge-187 | 1.0 | 1.0 | 1.0 | 1.0 | 23.0 |
challenge-188 | 2.0 | 1.0 | 81.0 | 1.0 | 1.0 |
challenge-189 | - | - | 1.0 | 10.0 | 682.0 |
challenge-190 | 1.0 | 1.0 | 3.0 | 2.0 | 1.0 |
challenge-191 | - | 2.0 | 103.5 | 4.0 | 2.0 |
challenge-192 | 1.0 | 1.0 | 5.5 | 1.0 | 1.0 |
challenge-193 | 3.0 | 3.0 | 6.0 | 1.0 | 2.0 |
challenge-194 | 1.5 | 1.0 | 2.5 | 3.0 | 3.0 |
challenge-195 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
challenge-196 | 4.5 | 297.0 | 3.5 | 3.0 | 300.0 |
challenge-197 | - | 34.0 | 845.5 | 13.5 | 8.0 |
challenge-198 | 1.5 | 1.0 | 9.5 | 6.0 | 4.0 |
challenge-199 | 94.5 | 9.0 | 280.5 | 1.0 | 131.0 |
challenge-200 | - | 56.0 | 21.5 | 7.0 | 73.0 |
challenge-201 | - | 1.0 | 2.5 | 2.5 | 1.0 |
challenge-202 | - | 1.0 | 505.0 | 1090.0 | 758.0 |
challenge-203 | 1.0 | 1.0 | 1.0 | 1.0 | |
challenge-204 | - | 6.0 | 233.5 | 6.5 | 5.0 |
challenge-205 | 2.0 | 1.0 | 10.0 | 10.0 | 3.0 |
challenge-206 | 1.0 | 2.0 | 1.0 | 1.0 | 1.0 |
challenge-207 | 88.0 | 25.0 | 146.0 | 39.0 | 25.0 |
challenge-208 | 2.0 | 1.5 | 2.0 | 2.0 | 1.5 |
Participant information and abstracts
Participant: Vaniya Authors: Vaniya, Arpana [1], Stephanie N. Samra [1], Sajjan S. Mehta [1], Diego Pedrosa [1], Hiroshi Tsugawa [2], and Oliver Fiehn [1] Affiliations: [1] Genome Center, University of California, Davis [2] RIKEN Center for Sustainable Resource Science (CSRS), Wako, Japan ParticipantID: avaniya003 Category: Category 2 Automatic methods: Yes Abstract: MS-FINDER developed by H.Tsugawa et al. was used as an in silico software for unknown compound identification in Category 2. MS-FINDER version 1.62 was used. MS/MS spectra were uploaded to MS-FINDER in msp format. Precursor m/z, ion mode, mass accuracy of instrument, and precursor type were used as metadata. Each candidate file was converted to a structure database file which can be read by MS-FINDER. Each file was saved in the software folder in order for it to be called by MS-FINDER. This file was changed after each calculation in order to match the challenge data. A search of the challenge msp against the challenge candidate list was performed on the top 500 candidates. Up to 500 top candidates structures were exported as a text file from MS-FINDER. Final scores and SMILES were reported for submission to CASMI 2016. Multiple candidates were submitted for each challenge.
Participant: Duehrkop Authors: Dührkop, Kai (1) and Shen, Huibin (2) and Meusel, Marvin (1) and Rousu, Juho (2) and Böcker, Sebastian (1) Affiliations: (1) Chair of Bioinformatics, Friedrich-Schiller University, Jena (2) Department of Computer Science, Aalto University ParticipantID: csifingerid Category: category2 Automatic pipeline: yes Spectral libraries: yes (for training) Abstract We processed the peaklists in MGF format using a command line version of CSI:FingerId 1.0.1. Fragmentation trees were computed with Sirius 3.1.4 using the Q-TOF instrument settings. We computed trees for all candidate formulas in the given structure candidate list. Only the top scoring trees were selected for further processing: Trees with a score smaller than 80% of the score of the optimal tree were discarded. Each of these trees was processed with CSI:FingerId as described in [1]. We predicted for each tree a molecular fingerprint (with platt probability estimates) and compared them against the fingerprints of all structure candidates with the same molecular formula. The resulting hits were merged together in one list and were sorted by score. A constant value of 10000 was added to all scores to make them positive (as stated in the CASMI rules). Ties of compounds with same score (and sometimes also with same 2D structure) were ordered randomly. The machine learning method was trained on 7352 spectra (4564 compounds) downloaded from GNPS [2] and Massbank [3]. As our training dataset contains only spectra in positive ion mode (there are too few spectra with negative ion mode in GNPS), we ommited all challenges with negative ion mode; As long as there are not enough public available reference spectra measured in negative ion mode our method will be only able to process positive ion mode spectra. We observed for 67 challenges that the top scoring structure candidate was a compound which is also contained in our training set. If we evaluate our method on spectra from compounds we have already trained on we usually reach a performance comparable to spectral library search. To avoid an overestimation of the performance of our method, we removed all of these top scoring candidates from our training set and retrained our classifiers. To compensate the removed spectra, we added the training spectra that are provided by CASMI. The submission with the ParticipantID csifingerid_leaveout contains the search results of these newly trained classifiers. [1] Kai Dührkop, Huibin Shen, Marvin Meusel, Juho Rousu and Sebastian Böcker Searching molecular structure databases with tandem mass spectra using CSI:FingerID. Proc Natl Acad Sci U S A, 112(41):12580-12585, 2015. [2] https://gnps.ucsd.edu [3] Horai H, et al. MassBank: a public repository for sharing mass spectral data for life sciences. J Mass Spectrom 45(7):703–714, 2010.
Participant: Verdegem Authors: Verdegem, Dries and Ghesquière, Bart Affiliation: Vesalius Research Center, VIB/KULeuven, Leuven, Belgium ParticipantID: dverdegem Category: category2 Automatic method: yes Abstract For all assignments, we used the MAGMa+ software [1]. MAGMa+ uses MAGMa [2] under the hood. It runs MAGMa twice with two different, fine-tuned parameters of which the values depend on the ionization mode. MAGMa+ then determines the molecular class of the top ranked metabolites returned by both MAGMa runs. This latent molecular class is determined by a trained two-class random forest classifier. Depending on the most prevelant molecular class, one of both MAGMa outcomes (the one from the run with the parameters corresponding to the most prevelant class) is returned to the user. As structure database, the possible solution list provided in the contest was used. We did not perform any prefiltering. [1] Verdegem, Dries, et al. "Improved metabolite identification with MIDAS and MAGMa through MS/MS spectral dataset-driven parameter optimization." accepted for publication in Metabolomics [2] Ridder, Lars, et al. "Substructure‐based annotation of high‐resolution multistage MSn spectral trees." Rapid Communications in Mass Spectrometry 26.20 (2012): 2461-2471.
Participant: Allen Authors: Felicity Allen, Tanvir Sajed, Russ Greiner, David Wishart Affiliations: Department of Computing Science University of Alberta, Canada ParticipantID: FelicityAllenCFMOrig Category: category2 Automatic pipeline: yes Spectral libraries: no Abstract We processed the list of molecules and provided candidates using cfm-id. The original CFM positive and negative models were used, which were trained on data from the Metlin database. Mass tolerances of 10ppm were used and the Jaccard score was applied for spectral comparisons. The input spectrum was repeated for the low, medium and high energies.
Participant: Brouard Authors: Céline Brouard(1,2), Huibin Shen(1,2), Kai Dührkop(3), Sebastian Böcker(3) and Juho Rousu(1,2) Affiliations: (1) Department of Computer Science, Aalto University, Espoo, Finland (2) Helsinki Institute for Information Technology, Espoo, Finland (3) Chair for Bioinformatics, Friedrich-Schiller University, Jena, Germany ParticipantID: IOKRAlignf Category: category2 Automatic pipeline: yes Spectral libraries: no Abstract We used a recent machine learning approach, called Input Output Kernel Regression, for predicting the candidate scores. In this method, the similarities between the MS/MS spectra and the molecular similarities are encoded using two kernel functions. In input, we computed different kernels based on MS/MS spectra and on fragmentation trees. In output we built a gaussian kernel based on molecular fingerprints. We used approximately 6000 molecular fingerprints from OpenBabel. We combined the different input kernels using the Alignf algorithm, which searches to maximize the alignment between the combined kernel the output kernel. We trained separate models for the MS/MS spectra in positive mode and the MS/MS spectra in negative mode. We considered additional MS/MS spectra from GNPS and MassBank for training the models.