DOME: recommendations for supervised machine learning validation in biology

Walsh, Ian; Fishman, Dmytro; Garcia-Gasulla, Darío; Titma, Tiina; Pollastri, Gianluca; Harrow, Jennifer; Psomopoulos, Fotis; Tosatto, Silvio

doi:10.1038/s41592-021-01205-4

Cited by 139 publications

(147 citation statements)

References 45 publications

Supporting

Mentioning

127

Contrasting

Order By: Relevance

“…It is straightforward to develop ML algorithms incorrectly, resulting in models that do not perform accurately on new data. A complete set of community-wide recommendations that aim to establish requirements for ML validation in biology was published recently by Walsh et al 59 The recommendations are split into four core areas of ML: data, optimization, the model, and evaluation of the final model. Topics relevant to QbD ML modeling include splitting datasets correctly, avoiding overfitting when optimizing, and how to evaluate the performance of the ML algorithm using appropriate metrics.…”

Section: The Art Of Developing a Successful ML Model To Advance Qbdmentioning

confidence: 99%

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Walsh

Myint

Nguyen-Khuong

et al. 2022

mAbs

Self Cite

View full text Add to dashboard Cite

Ensuring consistent high yields and product quality are key challenges in biomanufacturing. Even minor deviations in critical process parameters (CPPs) such as media and feed compositions can significantly affect product critical quality attributes (CQAs). To identify CPPs and their interdependencies with product yield and CQAs, design of experiments, and multivariate statistical approaches are typically used in industry. Although these models can predict the effect of CPPs on product yield, there is room to improve CQA prediction performance by capturing the complex relationships in high-dimensional data. In this regard, machine learning (ML) approaches offer immense potential in handling non-linear datasets and thus are able to identify new CPPs that could effectively predict the CQAs. ML techniques can also be synergized with mechanistic models as a ‘hybrid ML’ or ‘white box ML’ to identify how CPPs affect the product yield and quality mechanistically, thus enabling rational design and control of the bioprocess. In this review, we describe the role of statistical modeling in Quality by Design (QbD) for biomanufacturing, and provide a generic outline on how relevant ML can be used to meaningfully analyze bioprocessing datasets. We then offer our perspectives on how relevant use of ML can accelerate the implementation of systematic QbD within the biopharma 4.0 paradigm.

show abstract

Section: The Art Of Developing a Successful ML Model To Advance Qbdmentioning

confidence: 99%

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Walsh

Myint

Nguyen-Khuong

et al. 2022

mAbs

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning has been recently combined with GSMMs, expanding the potential of both approaches [140] . An inherent difficulty of machine learning is that this approach requires relatively large amounts of data to parameterize the algorithm and estimate its performance [141] , thus reducing the applicability of machine learning in this field.…”

Section: Other Approaches For Community Modelingmentioning

confidence: 99%

Modeling approaches for probing cross-feeding interactions in the human gut microbiome

Saa

Urrutia

Silva-Andrade

et al. 2022

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Microbial communities perform emergent activities that are essentially different from those carried by their individual members. The gut microbiome and its metabolites have a significant impact on the host, contributing to homeostasis or disease. Food molecules shape this community, being fermented through cross-feeding interactions of metabolites such as lactate, acetate, and amino acids, or products derived from macromolecule degradation. Mathematical and experimental approaches have been applied to understand and predict the interactions between microorganisms in complex communities such as the gut microbiota. Rational and mechanistic understanding of microbial interactions is essential to exploit their metabolic activities and identify keystone taxa and metabolites. The latter could be used in turn to modulate or replicate the metabolic behavior of the community in different contexts. This review aims to highlight recent experimental and modeling approaches for studying cross-feeding interactions within the gut microbiome. We focus on short-chain fatty acid production and fiber fermentation, which are fundamental processes in human health and disease. Special attention is paid to modeling approaches, particularly kinetic and genome-scale stoichiometric models of metabolism, to integrate experimental data under different diet and health conditions. Finally, we discuss limitations and challenges for the broad application of these modeling approaches and their experimental verification for improving our understanding of the mechanisms of microbial interactions.

show abstract

“…For the processing of HRI, the point-based PSRI index was adapted as described in [27] and transformed to the Hyperspectral image PSRI (HPSRI) as follows:…”

Section: Reflectance Indices Calculationmentioning

confidence: 99%

“…Extracting information from HRIs that is not just pertinent to the plant phenotyping but also readily interpretable is of a special concern. Currently, machine learning-based methods of advanced image analysis as well as other mathematical tools are becoming widespread [25][26][27][28][29][30]. Although quite efficient in many cases, these methods normally do not take physiologically relevant information as an input.…”

Section: Introductionmentioning

confidence: 99%

Enrichment of the Information Extracted From Hyperspectral Reflectance Images for Noninvasive Phenotyping

Solovchenko¹,

Shurygin²,

Кузин³

et al. 2021

Preprint

View full text Add to dashboard Cite

Hyperspectral reflectance imaging is an emerging method for rapid non-invasive quantitative screening of plant traits. This method is essential for high-throughput phenotyping and hence for accelerated breeding of crop plants as well as for precision agriculture practices. However, extraction of sensible information from reflectance images is hindered by the complexity of plant optical properties, especially when they are measured in the field. We propose using reflectance indices (Plant Senescence Reflectance Index, PSRI; Anthocyanin Reflectance Index, ARI; and spectral deconvolution) previously developed for remote sensing of vegetation and point-based reflectometers to infer the spatially resolved information on plant development and biochemical composition using ripening apple fruit as the model. Specifically, the proposed approach enables capturing data on distribution of chlorophylls and primary carotenoids as well as secondary carotenoids (both linked with fruit ripening and leaf senescence during plant development) as well as the information on spatial distribution of anthocyanins (known as stress pigments) over the plant surface. We argue that the proposed approach would enrich the phenotype assessments made on the base of reflectance image analysis with valuable information on plant physiological condition, stress acclimation state, and the progression of the plant development.

show abstract

DOME: recommendations for supervised machine learning validation in biology

Cited by 139 publications

References 45 publications

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Harnessing the potential of machine learning for advancing “Quality by Design” in biomanufacturing

Modeling approaches for probing cross-feeding interactions in the human gut microbiome

Enrichment of the Information Extracted From Hyperspectral Reflectance Images for Noninvasive Phenotyping

Contact Info

Product

Resources

About