2021
DOI: 10.1016/j.csbj.2021.05.038
|View full text |Cite
|
Sign up to set email alerts
|

A comparative study of multiple instance learning methods for cancer detection using T-cell receptor sequences

Abstract: Graphical abstract

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
39
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 21 publications
(39 citation statements)
references
References 54 publications
0
39
0
Order By: Relevance
“…The multiple instance learning standard assumption meets the biological assumptions that responders (“positive bags”) must harbor at least one true neoantigen (“positive instance”) while non-responders (“negative bags”) harbor only neoantigen candidates that cannot trigger anti-tumoral activity (“negative instances”) 17 . The MILES (Multiple-Instance Learning via Embedded Instance Selection) 34 algorithm was chosen as the algorithm of choice in this study as it performed well in a previous benchmarking study related to cancer detection based on TCR sequences 18 .…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…The multiple instance learning standard assumption meets the biological assumptions that responders (“positive bags”) must harbor at least one true neoantigen (“positive instance”) while non-responders (“negative bags”) harbor only neoantigen candidates that cannot trigger anti-tumoral activity (“negative instances”) 17 . The MILES (Multiple-Instance Learning via Embedded Instance Selection) 34 algorithm was chosen as the algorithm of choice in this study as it performed well in a previous benchmarking study related to cancer detection based on TCR sequences 18 .…”
Section: Resultsmentioning
confidence: 99%
“…The MILES (Multiple-Instance Learning via Embedded Instance Selection) 34 algorithm was chosen as the algorithm of choice in this study as it performed well in a previous benchmarking study related to cancer detection based on TCR sequences 18 .…”
Section: Neoantigen Candidate Profiles Are Heterogeneous In Cancer Pa...mentioning
confidence: 99%
See 1 more Smart Citation
“…Finally, bag-based approaches use distance functions that capture the similarity between patients as input for modified ML models. Weber et al ( 2019 ) and Nowicka et al ( 2019 ) proposed mapping-based approaches on single-cell data, whereas Cheplygina et al ( 2014 ) and Xiong et al ( 2021 ) compared both instance-based and bag-models on imaging data and next-generation sequencing data, respectively.…”
Section: Challenges In Computational Analysismentioning
confidence: 99%
“…In MIL, an object, called a bag, contains a set of instances. MIL was introduced in [3] to solve the problem of drug activity prediction, but many other studies have already applied this approach successfully, such as image classification [4], cancer detection via images or sequences [5,6], text categorization [7], speaker recognition [8] and web mining [9]. Amongst the characteristics of problems that are fit to be solved by MIL approaches are those in week supervision scenarios that do not work well with standard machine learning pipelines [10].…”
Section: Introductionmentioning
confidence: 99%