LIVIA — Prediction Analysis

Interaction Analysis Summary

↓ Download CSV

Click a row to switch models. This updates all visualizations and the script below.

Rank/Model	Pair	iLIS	iLIA	iLISA	ipSAE	actifpTM	ipTM	LIS	cLIS	LIR (i/j)	cLIR (i/j)

iLIS: ≥0.551 (1% FPR) ≥0.339 (5% FPR) ≥0.223 (10% FPR) <0.223 (below threshold)

iLIS (average): ≥0.303 (1% FPR) ≥0.120 (5% FPR) ≥0.073 (10% FPR) <0.073 (below threshold)

Thresholds based on large-scale Y2H reference sets in yeast, fly, and human predicted using ColabFold. See Kim et al., 2026, for iLIS benchmark details. Different platforms may require different thresholds.

Score Matrix

Lower-left: iLIS (Oranges). Upper-right: iLIA (Greens). Diagonal: self.

Predicted Aligned Error (PAE) Maps

0Predicted Aligned Error (Å)30

Local Interaction Score (LIS) Maps (PAE ≤ 12 Å)

0Local Interaction Score (LIS)1

contact Local Interaction Score (cLIS) Maps (PAE ≤ 12 Å & Cβ ≤ 8 Å)

0contact Local Interaction Score (cLIS)1

Sequence Viewer

Light background = LIR (PAE ≤ 12 Å). Dark background with white text = cLIR (PAE ≤ 12 Å & Cβ ≤ 8 Å). Each chain uses its own color.

Linear Contact Map

Lines connect cLIR residue pairs within Cβ distance in the 3D structure. Color gradient from chain A to chain B.

Circular Contact Map

Arcs represent chains. Lines connect cLIR residue pairs in physical contact across all chain pairs.

Selected Model

All Models Combined

3D Structure Viewer

Interactive 3D preview powered by Mol* (Sehnal et al. 2021). LIR regions shown as cartoons; cLIR residues highlighted. Drag to rotate, scroll to zoom.

Visualization Script

Local Interaction Residue (LIR) Display

Fill gaps ≤ residues | Min segment ≥ residues

Gap filling bridges short breaks for continuous cartoon. Min segment removes isolated LIR fragments shorter than the threshold.

Show complete structure (display all residues instead of LIR only) Gray non-LIR (color non-interacting residues gray) Cutoffs

PAE cutoff (Å):

Cβ cutoff (Å):

Presets — gradient (LIR light, cLIR dark)

Teal / Coral

Blue / Orange

Purple / Gold

Slate / Rose

Indigo / Tangerine

Green / Red

Presets — high contrast (all 4 colors distinct)

Cyan / Navy / Peach / Crimson

Sky / Indigo / Salmon / Red

Lime / Forest / Gold / Maroon

Mint / DarkTeal / Apricot / Burnt

Orchid / Purple / Yellow / Fire

Blue / Navy / Sage / Ember

Presets — solid

Teal / Coral

Blue / Orange

Purple / Gold

Steel / Wheat

Cornflower / Tomato

Presets — coloring modes

pLDDT

bychain

bypolymer

Color Scheme

Chain A (Protein 1)

LIR

#80CBC4

cLIR

#00897B

Chain B (Protein 2)

LIR

#FFAB91

cLIR

#E64A19

↓ Download .cxc ↓ Download structure ↓ Download All Chains .cxc

Place the script and structure files in the same folder, then open the script in ChimeraX or PyMOL. "All Chains" shows every chain with LIR regions, colored by chain.

Per-Residue Intra-chain LIS & pLDDT

Per-residue metrics for each chain across all models. Selected model as solid line; other models as light traces; average as dashed line.

How to Use (Full guide)

Quick Start

Run a prediction on any supported platform
Download/export the results
Drop the files above — the platform is auto-detected
Click Process to calculate AFM-LIS metrics
Click a chain pair in the table to generate a ChimeraX script
Download the script (.cxc or .pml) and structure file, place in the same folder

Platform-Specific Tips

AlphaFold3: Drop the zip from AlphaFold Server directly
ColabFold: Upload the output folder or select individual _unrelaxed_rank_*.pdb and _scores_rank_*.json files
Boltz-1/2: Upload output folder containing .cif, confidence_*.json, and pae_*.npz files
Chai-1: Upload output folder with pred.model_idx_*.cif and scores files
OpenFold: Upload .cif with *_full_data*.json files
Generic: Any .cif/.pdb with a PAE JSON file (predicted_aligned_error field)

AFM-LIS Metrics (Kim et al. 2024; Kim et al. 2026)

iLIS	integrated LIS — √(LIS × cLIS)
iLIA	integrated LIA — √(LIA × cLIA), geometric mean of interface area counts
iLISA	integrated LISA — iLIS × iLIA, overall binding strength
LIS	Local Interaction Score — normalized PAE confidence (0–1)
cLIS	contact-filtered LIS — restricted to direct contacts
LIR	Local Interaction Residues (PAE ≤ 12 Å)
cLIR	contact-filtered LIR (PAE ≤ 12 Å & Cβ ≤ 8 Å)

Confidence Metrics (from prediction platform)

ipTM	interface predicted TM-score — global interface confidence from the prediction model
ipSAE	interaction prediction Score from Aligned Errors (Dunbrack, 2025)
actifpTM	actual interface pTM (Varga et al., 2025)

PAE (Predicted Aligned Error) measures how confidently the model predicts the relative position of two residues — lower values indicate higher confidence.