CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model

Xinke Zhan; Tiantao Liu; Pratiti Bhadra; Yu An Huang; Zhuhong You; Shirley W.I. Siu

doi:10.1007/978-981-95-0030-7_19

CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model

Xinke Zhan
, Tiantao Liu
, Pratiti Bhadra
, Yu An Huang
, Zhuhong You
, Shirley W.I. Siu

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Anticancer peptides (ACPs), which are able to specifically target and kill cancer cells, are promising cancer therapeutics. However, it requires significant time and cost to identify ACPs through biological experiments. To facilitate the ACP screening process, we propose the ACP prediction method CALM-AcPEP, a deep learning framework based on the ACmix module, Evolutionary Scale Modeling 2 (ESM2) and cross-attention. The ACmix module combines a convolution neural network and self-attention to recognize the original sequence representation, while the pre-trained ESM2 efficiently captures the evolutionary information of the peptide sequence. Then, the relationship between the original sequence and the evolutionary information is learned by the cross-attention mechanism, strengthening the representation of ACPs. The results of our study show that our proposed method is promising for the prediction of ACPs.

Original language	English
Title of host publication	Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings
Editors	De-Shuang Huang, Chuanlei Zhang, Qinhu Zhang, Yijie Pan
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	221-230
Number of pages	10
ISBN (Print)	9789819500291
DOIs	https://doi.org/10.1007/978-981-95-0030-7_19
State	Published - 2025
Event	21st International Conference on Intelligent Computing, ICIC 2025 - Ningbo, China Duration: 26 Jul 2025 → 29 Jul 2025

Publication series

Name	Lecture Notes in Computer Science
Volume	15867 LNBI
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	21st International Conference on Intelligent Computing, ICIC 2025
Country/Territory	China
City	Ningbo
Period	26/07/25 → 29/07/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

ACmix
ESM2
anticancer peptides
cross attention
deep learning

Access to Document

10.1007/978-981-95-0030-7_19

Cite this

Zhan, X., Liu, T., Bhadra, P., Huang, Y. A., You, Z., & Siu, S. W. I. (2025). CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model. In D.-S. Huang, C. Zhang, Q. Zhang, & Y. Pan (Eds.), Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings (pp. 221-230). (Lecture Notes in Computer Science; Vol. 15867 LNBI). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-0030-7_19

Zhan, Xinke ; Liu, Tiantao ; Bhadra, Pratiti et al. / CALM-AcPEP : Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model. Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings. editor / De-Shuang Huang ; Chuanlei Zhang ; Qinhu Zhang ; Yijie Pan. Springer Science and Business Media Deutschland GmbH, 2025. pp. 221-230 (Lecture Notes in Computer Science).

@inproceedings{186dabf16a4d4b058158652e2cb122e0,

title = "CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model",

abstract = "Anticancer peptides (ACPs), which are able to specifically target and kill cancer cells, are promising cancer therapeutics. However, it requires significant time and cost to identify ACPs through biological experiments. To facilitate the ACP screening process, we propose the ACP prediction method CALM-AcPEP, a deep learning framework based on the ACmix module, Evolutionary Scale Modeling 2 (ESM2) and cross-attention. The ACmix module combines a convolution neural network and self-attention to recognize the original sequence representation, while the pre-trained ESM2 efficiently captures the evolutionary information of the peptide sequence. Then, the relationship between the original sequence and the evolutionary information is learned by the cross-attention mechanism, strengthening the representation of ACPs. The results of our study show that our proposed method is promising for the prediction of ACPs.",

keywords = "ACmix, ESM2, anticancer peptides, cross attention, deep learning",

author = "Xinke Zhan and Tiantao Liu and Pratiti Bhadra and Huang, \{Yu An\} and Zhuhong You and Siu, \{Shirley W.I.\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 21st International Conference on Intelligent Computing, ICIC 2025 ; Conference date: 26-07-2025 Through 29-07-2025",

year = "2025",

doi = "10.1007/978-981-95-0030-7\_19",

language = "英语",

isbn = "9789819500291",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "221--230",

editor = "De-Shuang Huang and Chuanlei Zhang and Qinhu Zhang and Yijie Pan",

booktitle = "Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings",

}

Zhan, X, Liu, T, Bhadra, P, Huang, YA, You, Z & Siu, SWI 2025, CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model. in D-S Huang, C Zhang, Q Zhang & Y Pan (eds), Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings. Lecture Notes in Computer Science, vol. 15867 LNBI, Springer Science and Business Media Deutschland GmbH, pp. 221-230, 21st International Conference on Intelligent Computing, ICIC 2025, Ningbo, China, 26/07/25. https://doi.org/10.1007/978-981-95-0030-7_19

CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model. / Zhan, Xinke; Liu, Tiantao; Bhadra, Pratiti et al.
Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings. ed. / De-Shuang Huang; Chuanlei Zhang; Qinhu Zhang; Yijie Pan. Springer Science and Business Media Deutschland GmbH, 2025. p. 221-230 (Lecture Notes in Computer Science; Vol. 15867 LNBI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - CALM-AcPEP

T2 - 21st International Conference on Intelligent Computing, ICIC 2025

AU - Zhan, Xinke

AU - Liu, Tiantao

AU - Bhadra, Pratiti

AU - Huang, Yu An

AU - You, Zhuhong

AU - Siu, Shirley W.I.

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025

Y1 - 2025

N2 - Anticancer peptides (ACPs), which are able to specifically target and kill cancer cells, are promising cancer therapeutics. However, it requires significant time and cost to identify ACPs through biological experiments. To facilitate the ACP screening process, we propose the ACP prediction method CALM-AcPEP, a deep learning framework based on the ACmix module, Evolutionary Scale Modeling 2 (ESM2) and cross-attention. The ACmix module combines a convolution neural network and self-attention to recognize the original sequence representation, while the pre-trained ESM2 efficiently captures the evolutionary information of the peptide sequence. Then, the relationship between the original sequence and the evolutionary information is learned by the cross-attention mechanism, strengthening the representation of ACPs. The results of our study show that our proposed method is promising for the prediction of ACPs.

AB - Anticancer peptides (ACPs), which are able to specifically target and kill cancer cells, are promising cancer therapeutics. However, it requires significant time and cost to identify ACPs through biological experiments. To facilitate the ACP screening process, we propose the ACP prediction method CALM-AcPEP, a deep learning framework based on the ACmix module, Evolutionary Scale Modeling 2 (ESM2) and cross-attention. The ACmix module combines a convolution neural network and self-attention to recognize the original sequence representation, while the pre-trained ESM2 efficiently captures the evolutionary information of the peptide sequence. Then, the relationship between the original sequence and the evolutionary information is learned by the cross-attention mechanism, strengthening the representation of ACPs. The results of our study show that our proposed method is promising for the prediction of ACPs.

KW - ACmix

KW - ESM2

KW - anticancer peptides

KW - cross attention

KW - deep learning

UR - https://www.scopus.com/pages/publications/105012425549

U2 - 10.1007/978-981-95-0030-7_19

DO - 10.1007/978-981-95-0030-7_19

M3 - 会议稿件

AN - SCOPUS:105012425549

SN - 9789819500291

T3 - Lecture Notes in Computer Science

SP - 221

EP - 230

BT - Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings

A2 - Huang, De-Shuang

A2 - Zhang, Chuanlei

A2 - Zhang, Qinhu

A2 - Pan, Yijie

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 26 July 2025 through 29 July 2025

ER -

Zhan X, Liu T, Bhadra P, Huang YA, You Z, Siu SWI. CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model. In Huang DS, Zhang C, Zhang Q, Pan Y, editors, Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2025. p. 221-230. (Lecture Notes in Computer Science). doi: 10.1007/978-981-95-0030-7_19

CALM-AcPEP: Predicting Anticancer Peptides Using Cross-Attention and Pre-Trained Language Model

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this