KEMP-PIP: A Feature-Fusion Based Approach for Pro-inflammatory Peptide Prediction

Soumik Deb Niloy; Md. Fahmid-Ul-Alam Juboraj; Swakkhar Shatabda

q-bio.QMFeb 22, 2026

KEMP-PIP: A Feature-Fusion Based Approach for Pro-inflammatory Peptide Prediction

Authors: Soumik Deb Niloy, Md. Fahmid-Ul-Alam Juboraj, Swakkhar Shatabda

Organizations: Department of Computer Science and Engineering, BRAC University, Dhaka 1212, Bangladesh

Abstract

Pro-inflammatory peptides (PIPs) play critical roles in immune signaling and inflammation but are difficult to identify experimentally due to costly and time-consuming assays. To address this challenge, we present KEMP-PIP, a hybrid machine learning framework that integrates deep protein embeddings with handcrafted descriptors for robust PIP prediction. Our approach combines contextual embeddings from pretrained ESM protein language models with multi-scale k-mer frequencies, physicochemical descriptors, and modlAMP sequence features. Feature pruning and class-weighted logistic regression manage high dimensionality and class imbalance, while ensemble averaging with an optimized decision threshold enhances the sensitivity--specificity balance. Through systematic ablation studies, we demonstrate that integrating complementary feature sets consistently improves predictive performance. On the standard benchmark dataset, KEMP-PIP achieves an MCC of 0.505, accuracy of 0.752, and AUC of 0.762, outperforming ProIn-fuse, MultiFeatVotPIP, and StackPIP. Relative to StackPIP, these results represent improvements of 9.5% in MCC and 4.8% in both accuracy and AUC. The KEMP-PIP web server is freely available at https://nilsparrow1920-kemp-pip.hf.space/ and the full implementation at https://github.com/S18-Niloy/KEMP-PIP.

Figures & tables

PIP (train)	n-PIP (train)	PIP (test)	n-PIP (test)
1,245	1,627	171	171

Table 1: Dataset composition after preprocessing and redundancy reduction. PIP: pro-inflammatory; n-PIP: non-pro-inflammatory.

Figure 1: Architecture of the KEMP-PIP framework. Four feature streams are fused into two hybrid models whose predictions are ensemble-averaged with a tuned threshold.

Feature Type	Description	Original Dim.	Pruned Dim.
Multi-scale k-mer	Normalized frequencies, $k\in\{2,3,4\}$	168,400	35,358
Physicochemical	Hydrophobicity, charge, cleavage densities	11	11
ModlAMP	Global sequence descriptors	10	10
ESM embeddings	CLS token, ESM2-T6-8M	320	320
Model C (fused)	k-mer + ModlAMP + ESM	168,730	35,688
Model D (fused)	Physicochemical + ModlAMP + ESM	341	341

Table 2: Feature descriptor summary. Pruning applies only to k-mer features via zero-variance filtering; all other features are retained in full.

Individual feature sets
Feature Combination	Dim.	Validation			Test
Feature Combination	Dim.	MCC	AUC	ACC	MCC	AUC	ACC
k-mer	35,358	0.2391	0.6868	0.6319	0.3351	0.7592	0.6608
Physicochemical	11	0.0879	0.6360	0.5035	0.1451	0.6438	0.5643
ESM	320	0.1797	0.6009	0.5660	0.2026	0.6577	0.5994
modlAMP	10	0.1658	0.6432	0.5382	0.1461	0.6538	0.5643

Table 3: Feature ablation study. Best values per column in bold .

Feature Set	XGBoost			RF			SVM			MLP
Feature Set	MCC	AUC	ACC	MCC	AUC	ACC	MCC	AUC	ACC	MCC	AUC	ACC
k	0.2761	0.6973	0.6374	0.2458	0.7325	0.6228	$-$ 0.0524	0.3909	0.4825	0.3107	0.7575	0.6491
p	0.1530	0.6202	0.5760	0.1588	0.6487	0.5789	0.1230	0.5990	0.5614	0.0946	0.6266	0.5468
m	0.3275	0.7093	0.6637	0.2807	0.7061	0.6404	0.2515	0.6464	0.6257	0.2111	0.6706	0.6023
e	0.1463	0.6141	0.5731	0.1859	0.6239	0.5906	0.2132	0.6433	0.6053	0.2281	0.6417	0.6140
k+p	0.3047	0.7244	0.6520	0.2411	0.7033	0.6199	$-$ 0.0432	0.3931	0.4854	0.2414	0.7222	0.5994

Table 4: Feature ablation across four classifiers on the independent test set. Best MCC per row in bold . Abbreviations: k = k-mer, p = physicochemical, m = modlAMP, e = ESM.

Ensemble	$\boldsymbol{\alpha}$	$\boldsymbol{t}$	ACC	AUC	MCC	F1	SN	SP
A $\oplus$ B	0.10	0.10	0.7339	0.7787	0.4738	0.7534	0.8129	0.6550
A $\oplus$ C	0.00	0.17	0.7251	0.7834	0.4508	0.7314	0.7485	0.7018
A $\oplus$ D	0.60	0.37	0.7456	0.7585	0.4922	0.7372	0.7135	0.7778
A $\oplus$ E	0.00	0.18	0.7281	0.7876	0.4565	0.7335	0.7485	0.7076
B $\oplus$ C	0.55	0.11	0.7368	0.7820	0.4784	0.7541	0.8070	0.6667
B $\oplus$ D	0.95	0.10	0.7398	0.7750	0.4912	0.7652	0.8480	0.6316

Table 5: Performance of pairwise ensembles with optimized

\alpha

and threshold

t

. Best value per column in bold .

\oplus

denotes ensemble averaging.

Panel of Figure 3 — Figure 3: ROC curves for ensemble combinations (a)–(j).

Method	SN	SP	ACC	AUC	MCC
ProIn-fuse	0.502	0.736	0.619	0.704	0.246
MultiFeatVotPIP	0.521	0.790	0.655	0.686	0.322
StackPIP	0.628	0.731	0.704	0.714	0.410
KEMP-PIP	0.708	0.795	0.752	0.762	0.505

Table 6: Independent test-set comparison. Best scores in bold .

Figure 4: Web interface of the KEMP-PIP framework, supporting FASTA file upload, CSV upload, and manual sequence entry.

Molecular Property Prediction

Molecular property prediction estimates chemical, physical, and biological properties from molecular structure and context.

See all 202 papers

Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding
May 30, 2026Zaifei Yang, Samuel Ping-Man Choi, James KwokHierarchical Representation Learning Multimodal Embedding
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong. · Lee Shau Kee School of Business and Administration, The Hong Kong Metropolitan University, Ho Man Tin, Kowloon, Hong Kong.
PepBenchmark: A Standardized Benchmark for Peptide Machine Learning
Apr 12, 2026Jiahui Zhang, Rouyi Wang, Kuangqi Zhou +4Drug Discovery
Zhongguancun Academy · University of Science and Technology of China · Nankai University +1
An Integrated Deep-Learning Framework for Peptide-Protein Interaction Prediction and Target-Conditioned Peptide Generation with ConGA-PepPI and TC-PepGen
Apr 20, 2026Chupei Tang, Junxiao Kong, Moyu Tang +5Molecular Generation Conditional Generative Modeling
School of Mathematics and Statistics, Lanzhou University, 222 South Tianshui Road, Lanzhou 730000, Gansu, China · Cuiying Honors College, Lanzhou University, Lanzhou, Gansu, China · Shanghai Innovation Institute, Shanghai, China +1

May 30, 2026J/K move · Enter open · S save

Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding

Zaifei Yang, Samuel Ping-Man Choi, James Kwok

Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong. · Lee Shau Kee School of Business and Administration, The Hong Kong Metropolitan University, Ho Man Tin, Kowloon, Hong Kong.

Hierarchical Representation Learning Multimodal Embedding Protein-Protein Interaction Prediction Multimodal Fusion Protein Representation Learning Molecular Representation Learning

Open paper AskPDF arXiv

Protein-protein interactions (PPIs) are essential for many biological processes. However, existing PPI prediction approaches suffer from two major limitations: they overlook the hierarchical organization of proteins, particularly meso-scale motifs that critically regulate PPIs, and fail to effectively integrate sequence, structure, and function modalities. To address these limitations, we propose MMM-PPI, a Hierarchical Motif-based Multi-Modal protein Encoder for PPI Prediction that constructs PPI embeddings in a bottom-up multi-modal manner across three scales. At the micro-scale, we encode three modal residue features; at the meso-scale, a novel multimodal motif encoder aggregates residues into spatially-informed motif embeddings; at the macro-scale, a multimodal protein encoder integrates motifs into protein embeddings by jointly modeling motif importance and inter-modal correlations. The pre-trained encoder can be used off-the-shelf for large-scale PPI prediction. Extensive experiments on multiple PPI datasets show that MMM-PPI outperforms state-of-the-art multi-label PPI prediction models, particularly under challenging data partitions and limited data scenarios. Codes are in https://github.com/yzf-code/MMM-PPI.

Abstract

Molecular Property Prediction

Explore similar work

Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding

PepBenchmark: A Standardized Benchmark for Peptide Machine Learning

An Integrated Deep-Learning Framework for Peptide-Protein Interaction Prediction and Target-Conditioned Peptide Generation with ConGA-PepPI and TC-PepGen