---
title: 論文紹介：Transfer learning in DeepLC
tags: 
author: [Shunichi Ito](https://docswell.com/user/shunichi1100921)
site: [Docswell](https://www.docswell.com/)
thumbnail: https://bcdn.docswell.com/page/K74WWY2YE1.jpg?width=480
description: Transfer learning in DeepLC improves LC retention time prediction across substantially different modifications and setups.    Bouwmeester, R., Nameni, A., Declercq, A., Devreese, R., Velghe, K., Gorshkov, V., Penanes, P. A., Kjeldsen, F., Rompais, M., Carapito, C., Gabriels, R., & Martens, L. (2026).  Nature communications, 17(1), 2601. 10 Feb. 2026, https://doi.org/10.1038/s41467-026-68981-5  DeepLCで、転移学習を適応したほうがCalibrationという従来手法よりよかったという論文です。 手法としてはただ転移学習を適応しただけなので、手法とその結果には大きな新規性はないように思いますが、DeepLCの未知PTMsへの適応範囲の広さが転移学習においても強みとして残るという点でAcceptされたものと思います。 DeepLCではPTMsを原子組成としてEncodeしCNNで学習しており、未知のPTMも原子組成を用いて予測可能なことから、RT予測のゴールドスタンダードとなっています。 しかしながら、100以上のペプチドがあるなら転移学習のほうがよいという筆者の主張は少し過剰であると考えており、実際にはLCのセットアップが逆相（RPLC）の場合はほとんどの場合でキャリブレーションで十分だと思います。
published: May 09, 26
canonical: https://docswell.com/s/shunichi1100921/ZQ2M47-paper_transfer_learning_in_deeplc
---
# Page. 1

![Page Image](https://bcdn.docswell.com/page/K74WWY2YE1.jpg)

Nature Co mmunications
|
17 : 2601 (2026)
Transfer learning in DeepLC
improves LC retention time prediction across
substantially different modifications and setups
Bouwmeester R., Nameni A., Declercq A. et al., Martens L.
K ey messa ge
One pre-trained DeepLC, fine-tuned by transfer learning, adapts to almost any LC setup or PTM — with
far less data than training from scratch.
E-Journal | 2026-04-27 | Shunichi Ito


# Page. 2

![Page Image](https://bcdn.docswell.com/page/LJ1YY6MNEG.jpg)

INTRODUCT ION
1/ 5
DeepLC predicts retention time from peptide sequence
DeepLC: learns Peptides / Retention Time relationship
Peptide ID confidence
Peptide sequence /
Modifications
(e.g. AGK[ac]PEPTIDER)
DeepLC
Retention Time (RT)
Identification validation
(Deep Learning Model)
DIA spectral library
The problem
• RT shifts with: pH · stationary phase · pressure · temperature
• Models don't transfer between labs / setups
• New post-translational modifications (PTMs) break existing models
Bouwmeester et al., Nat. Commun. 17:2601 (2026) | EJ 2026-04-27 Shunichi Ito


# Page. 3

![Page Image](https://bcdn.docswell.com/page/GJWGGWDM72.jpg)

APPROAC H
2/5
Three ways to adapt DeepLC to a new LC setup
DeepLC can be adapted to new data in three different ways:
(A) Calibration
(B) New model
(C) Transfer learning
traditional approach
train from scratch
fine-tune
Pre-trained DeepLC
DeepLC with RANDOM parameters
Pre-trained DeepLC
(FROZEN – no update)
(No Peptide / RT knowledge)
(still trainable)
Fit GAM / spline
Train fully on NEW data
Transfer Learning on NEW data
simple curve fit on output
Train from scratch
Fine tune prior knowledge
Adjusts OUTPUT only
Setup-specific model
Adjusts MODEL itself
Cannot handle large setup changes
Needs lots of training data
Best of both worlds
Bouwmeester et al., Nat. Commun. 17:2601 (2026) | EJ 2026-04-27 Shunichi Ito


# Page. 4

![Page Image](https://bcdn.docswell.com/page/4EZLL5GM73.jpg)

RESULTS
①
3/ 5
Standard datasets: transfer learning nearly always wins
Learning curves across 3 PRIDE datasets (Fig. 1 d–f)
Take-home
< 100 peptides
1k – 10k peptides
473 / 474 datasets
Calibration is fine
Transfer learning wins by 1–2.5 %
RMAE
Transfer learning ≥ from-scratch
Bouwmeester et al., Nat. Commun. 17:2601 (2026) | EJ 2026-04-27 Shunichi Ito


# Page. 5

![Page Image](https://bcdn.docswell.com/page/Y76WW9Y57V.jpg)

RESULTS
②
4/5
Extreme cases: calibration breaks, transfer learning holds
Case A · TMPP (+572 Da modification)
Case B · Basic (high-pH) LC
Calibration (10-fold CV)
New Model (10-fold CV)
Transfer Learning (10-fold CV)
Calibration (10-fold CV)
New Model (10-fold CV)
Transfer Learning (10-fold CV)
𝑅 = 0.821
𝑅 = 0.974
𝑅 = 𝟎. 𝟗𝟗𝟒
𝑅 = 𝟎. 𝟔𝟎𝟏
𝑅 = 0.946
𝑅 = 𝟎. 𝟗𝟕𝟎
Transfer learning adapts even when pre-training assumptions no longer hold.
Bouwmeester et al., Nat. Commun. 17:2601 (2026) | EJ 2026-04-27 Shunichi Ito


# Page. 6

![Page Image](https://bcdn.docswell.com/page/G75MMNGG74.jpg)

RESULTS ③
·
CONCL USION
Unseen PTMs: transfer learning beats training from scratch & take-home
Unseen PTMs (Fig. 5)
CO NC LU SIO N
One pre-trained model,
many LC realities.
Beats calibration on new LC conditions
Beats from-scratch with far less data
Generalizes to unseen PTMs (13 / 14)
Prac tic al r ecipe
<100 shared peptides → calibration. Otherwise → fine-tune DeepLC.
13 / 14 PTMs: transfer learning beats training from scratch.
Bouwmeester et al., Nat. Commun. 17:2601 (2026) | EJ 2026-04-27 Shunichi Ito
5/5