Back

Sequence charge decoration organizes salt response regimes in intrinsically disordered proteins: an interpretable machine-learning

Aryal, M.

2026-06-04 biophysics
10.64898/2026.06.01.729380 bioRxiv
Show abstract

The conformational ensembles of intrinsically disordered proteins (IDPs) respond sensitively to ionic strength, with the direction and magnitude of response varying widely across sequence classes from polyelectrolyte contraction to polyampholyte swelling. Recent sequence-conditioned models provide rapid access to full ensembles or ensemble-averaged properties at specified solution conditions, but do not directly identify which low-dimensional polymer physics descriptors organize salt response behavior. Here, we construct a 511-sequence library spanning controlled{kappa} -variants, NCPR series, IDRome-stratified natural IDRs, and low-FCR IDRome sequences, and perform 2,555 CALVADOS-2 simulations across five monovalent salt concentrations (50 mM to 500 mM). For each sequence, we extract the salt-response slope, dRg/d[salt], and assign one of four regimes: polyelectrolyte contraction, polyampholyte swelling, non-monotonic response, or salt-insensitive behavior. Using eight theory-motivated sequence descriptors, we find that sequence charge decoration weighted by chain length, SCD xN, is the dominant coordinate organizing salt response, accounting for [~]40% of total SHAP attribution and exceeding the next feature by more than twice. Ridge regression explains substantial in-distribution variance (R2 = 0.83 under random cross-validation), whereas gradient-boosted trees improve in-distribution performance (R2 = 0.97) and retain predictive power under the more stringent leave-one-subset-out validation test (R2 = 0.60), indicating that salt response contains transferable but nonlinear sequence-encoded structure. Regime classification robustly recovers the direction of salt response, with no polyelectrolyte-polyampholyte confusion, whereas non-monotonic and salt-insensitive sequences remain harder to distinguish from static sequence features alone. Together, these results establish SCD xN as a compact, interpretable organizing coordinate for CALVADOS-2-derived IDP salt response and provide a polymer-physics, feature-level complement to ensemble-level generative models.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Journal of Chemical Theory and Computation
140 papers in training set
Top 0.1%
18.5%
2
Journal of Chemical Information and Modeling
238 papers in training set
Top 0.7%
7.3%
3
Proceedings of the National Academy of Sciences
2444 papers in training set
Top 6%
6.7%
4
Biophysical Journal
631 papers in training set
Top 1%
6.7%
5
Protein Science
246 papers in training set
Top 0.7%
5.5%
6
Communications Chemistry
48 papers in training set
Top 0.1%
4.0%
7
JACS Au
43 papers in training set
Top 0.1%
3.4%
50% of probability mass above
8
eLife
5828 papers in training set
Top 33%
3.3%
9
Nature Communications
5641 papers in training set
Top 35%
3.3%
10
Chemical Science
73 papers in training set
Top 0.4%
3.2%
11
The Journal of Physical Chemistry Letters
63 papers in training set
Top 0.2%
3.2%
12
The Journal of Physical Chemistry B
167 papers in training set
Top 0.7%
2.8%
13
PRX Life
42 papers in training set
Top 0.3%
2.8%
14
PLOS Computational Biology
1863 papers in training set
Top 12%
2.4%
15
Nature Chemistry
42 papers in training set
Top 0.4%
2.4%
16
Journal of Molecular Biology
232 papers in training set
Top 1%
2.1%
17
Briefings in Bioinformatics
354 papers in training set
Top 5%
1.7%
18
Journal of the American Chemical Society
217 papers in training set
Top 2%
1.4%
19
Advanced Science
286 papers in training set
Top 7%
1.1%
20
Biomacromolecules
29 papers in training set
Top 0.4%
1.1%
21
Scientific Reports
3612 papers in training set
Top 69%
1.0%
22
Computational and Structural Biotechnology Journal
242 papers in training set
Top 6%
1.0%
23
PNAS Nexus
159 papers in training set
Top 3%
1.0%
24
Communications Biology
993 papers in training set
Top 30%
0.8%
25
The Journal of Chemical Physics
56 papers in training set
Top 0.5%
0.8%
26
PLOS ONE
5266 papers in training set
Top 64%
0.6%
27
Biochemistry
148 papers in training set
Top 3%
0.6%
28
Science Advances
1243 papers in training set
Top 33%
0.6%
29
ACS Central Science
71 papers in training set
Top 2%
0.6%
30
Structure
193 papers in training set
Top 3%
0.6%