Back

Structure-property machine learning models with predictive capabilities for glycans in food

Naravane, T.; Simmons, G.

2023-11-12 biochemistry
10.1101/2023.11.12.566488 bioRxiv
Show abstract

Structure-property predictive models for food aim to decipher the complex relation between the physical shape of a molecule and its physical properties and/or the functional role of the molecule in a product formulation. Our focus in this paper is the modeling of glycans (i.e., carbohydrates), which are not only abundant in food, but essential to both food production and, more importantly, human health. In our study, we use regression methods to generalize the relationships between the structure of starch (e.g., chain length and composition of protein and amylose) and a range of its properties (e.g., gelatinization temperature, time series viscosity data, gel consistency, and sensory texture) for 301 samples of rice. Our results indicate that the structure-composition data is a significantly better predictor of sensory mouthfeel than the physical properties, even though the latter is typically used in experimental research. This demonstrates the potential to harness several structure-property relationships and we provide strategies to accelerate further experiment-based research.

Matching journals

The top 16 journals account for 50% of the predicted probability mass.

1
Scientific Reports
○ 3612 papers in training set
Top 2%
13.2%
Similar papers in this journal
2
PLOS ONE
● 5266 papers in training set
Top 26%
5.7%
Similar papers in this journal
3
Analytical Chemistry
● 218 papers in training set
Top 0.6%
5.7%
Similar papers in this journal
4
Sensors
○ 43 papers in training set
Top 0.3%
3.4%
Similar papers in this journal
5
Protein Science
○ 246 papers in training set
Top 1%
3.4%
Similar papers in this journal
6
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 2%
2.8%
7
Food Chemistry
○ 13 papers in training set
Top 0.1%
2.5%
8
Journal of Proteome Research
● 234 papers in training set
Top 0.9%
2.5%
9
Biology Methods and Protocols
◐ 61 papers in training set
Top 0.8%
1.8%
10
PLOS Computational Biology
● 1863 papers in training set
Top 14%
1.8%
11
Current Protocols
○ 15 papers in training set
Top 0.2%
1.5%
12
The Journal of Chemical Physics
● 56 papers in training set
Top 0.4%
1.4%
13
GigaScience
◐ 212 papers in training set
Top 3%
1.4%
14
ACS Omega
● 105 papers in training set
Top 2%
1.4%
15
Analytical Biochemistry
○ 26 papers in training set
Top 0.3%
1.4%
16
Horticulture Research
◐ 47 papers in training set
Top 0.6%
1.2%
50% of probability mass above
17
Journal of the American Society for Mass Spectrometry
● 37 papers in training set
Top 0.4%
1.2%
18
Royal Society Open Science
● 214 papers in training set
Top 4%
1.2%
19
Methods
○ 34 papers in training set
Top 0.3%
1.2%
20
Food Research International
○ 11 papers in training set
Top 0.1%
1.2%
21
International Journal of Biological Macromolecules
○ 76 papers in training set
Top 1%
1.2%
22
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.2%
23
Peer Community Journal
● 281 papers in training set
Top 4%
1.2%
24
BioMed Research International
○ 28 papers in training set
Top 1%
1.1%
25
Yeast
○ 17 papers in training set
Top 0.2%
1.1%
26
ACS ES&T Water
● 20 papers in training set
Top 0.2%
1.1%
27
Acta Biomaterialia
○ 92 papers in training set
Top 0.9%
1.1%
28
mAbs
○ 32 papers in training set
Top 0.4%
1.1%
29
Journal of Open Source Software
● 25 papers in training set
Top 0.3%
1.0%
30
Communications Chemistry
○ 48 papers in training set
Top 1%
1.0%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.