Machine learning predicts immunoglobulin light chain toxicity through somatic mutations
Abstract In systemic light chain amyloidosis (AL), pathogenic monoclonal immunoglobulin light chains (LCs) form toxic aggregates and amyloid fibrils in target organs. Prompt diagnosis is crucial to avoid permanent organ damage. However, delays in diagnosis are common, with a consequent poor patient’s prognosis, as symptoms usually appear only after strong organ involvement. Here, we present LICTOR, a machine learning approach predicting LC toxicity in AL, based on the distribution of somatic mutations acquired during clonal selection. LICTOR achieved a specificity and a sensitivity of 0.82 and 0.76, respectively, with an area under the receiver operating characteristic curve (AUC) of 0.87. Tested on an independent set of 12 LCs sequences with known clinical phenotypes, LICTOR achieved a prediction accuracy of 83%. Furthermore, we were able to abolish the toxic phenotype of an LC by in silico reverting two germline-specific somatic mutations identified by LICTOR and by experimentally assessing the loss of in vivo toxicity in a Caenorhabditis elegans model. Therefore, LICTOR represents a promising strategy for AL diagnosis and reducing high mortality rates in AL..
| Medienart: |
|
|---|
Preprint| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
bioRxiv.org - (2021) vom: 13. Jan. Zur Gesamtaufnahme - year:2021 |
|---|
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Garofalo, Maura [VerfasserIn] |
|---|
| Links: |
Volltext [kostenfrei] |
|---|
| doi: |
10.1101/849901 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
XBI000771104 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | XBI000771104 | ||
| 003 | DE-627 | ||
| 005 | 20230429091501.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 200313s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1101/849901 |2 doi | |
| 035 | |a (DE-627)XBI000771104 | ||
| 035 | |a (DE-599)biorXiv10.1101/849901 | ||
| 035 | |a (biorXiv)10.1101/849901 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | |a 570 |q DE-84 | |
| 100 | 1 | |a Garofalo, Maura |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Machine learning predicts immunoglobulin light chain toxicity through somatic mutations |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Abstract In systemic light chain amyloidosis (AL), pathogenic monoclonal immunoglobulin light chains (LCs) form toxic aggregates and amyloid fibrils in target organs. Prompt diagnosis is crucial to avoid permanent organ damage. However, delays in diagnosis are common, with a consequent poor patient’s prognosis, as symptoms usually appear only after strong organ involvement. Here, we present LICTOR, a machine learning approach predicting LC toxicity in AL, based on the distribution of somatic mutations acquired during clonal selection. LICTOR achieved a specificity and a sensitivity of 0.82 and 0.76, respectively, with an area under the receiver operating characteristic curve (AUC) of 0.87. Tested on an independent set of 12 LCs sequences with known clinical phenotypes, LICTOR achieved a prediction accuracy of 83%. Furthermore, we were able to abolish the toxic phenotype of an LC by in silico reverting two germline-specific somatic mutations identified by LICTOR and by experimentally assessing the loss of in vivo toxicity in a Caenorhabditis elegans model. Therefore, LICTOR represents a promising strategy for AL diagnosis and reducing high mortality rates in AL. | ||
| 700 | 1 | |a Piccoli, Luca |e verfasserin |4 aut | |
| 700 | 1 | |a Romeo, Margherita |e verfasserin |4 aut | |
| 700 | 1 | |a Barzago, Maria Monica |e verfasserin |4 aut | |
| 700 | 1 | |a Ravasio, Sara |e verfasserin |4 aut | |
| 700 | 1 | |a Foglierini, Mathilde |e verfasserin |4 aut | |
| 700 | 1 | |a Matkovic, Milos |e verfasserin |4 aut | |
| 700 | 1 | |a Sgrignani, Jacopo |e verfasserin |4 aut | |
| 700 | 1 | |a De Gasparo, Raoul |e verfasserin |4 aut | |
| 700 | 1 | |a Prunotto, Marco |e verfasserin |4 aut | |
| 700 | 1 | |a Varani, Luca |e verfasserin |4 aut | |
| 700 | 1 | |a Diomede, Luisa |e verfasserin |4 aut | |
| 700 | 1 | |a Michielin, Olivier |e verfasserin |4 aut | |
| 700 | 1 | |a Lanzavecchia, Antonio |e verfasserin |4 aut | |
| 700 | 1 | |a Cavalli, Andrea |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t bioRxiv.org |g (2021) vom: 13. Jan. |
| 773 | 1 | 8 | |g year:2021 |g day:13 |g month:01 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1101/849901 |z kostenfrei |3 Volltext |
| 912 | |a GBV_XBI | ||
| 912 | |a SSG-OLC-PHA | ||
| 951 | |a AR | ||
| 952 | |j 2021 |b 13 |c 01 | ||
| 953 | |2 045F |a 570 | ||