verena additions

3 files changed, 289 insertions, 107 deletions

diff --git a/bibliography.bib b/bibliography.bib
index 7d2775d..45c5852 100644
--- a/bibliography.bib
+++ b/bibliography.bib
@@ -1,3 +1,116 @@
+@article{Rubiolo1992,
+  author = {Rubiolo, P. and Pieters, L. and Calomme, M. and Bicchi, C. and Vlietinck, A. and Vanden Berghe, D.},
+  year = 1992,
+  title = {Mutagenicity of pyrrolizidine alkaloids in the Salmonella typhimurium/mammalian microsome system},
+  journal = {Mutation research},
+  number = 281, 
+  pages = {143–147}
+}
+
+@article{Chen2010,
+  author = {Chen, T. and Mei, N. and Fu, P.P.},
+  year = 2010,
+  title = {Genotoxicity of pyrrolizidine alkaloids},
+  journal = {J. Appl. Toxicol.},
+  numbr = 30,
+  pages = {183-96}
+}
+
+@article{Li2013,
+  authors = {Li YH, Kan WL, Li N, Lin G},
+  year = 2013,
+  title = {Assessment of pyrrolizidine alkaloid-induced toxicity in an in vitro screening model},
+  journal = {J. Ethnopharmacol.},
+  number = 150,
+  pages = {560-7}
+}
+
+@article{Xia2013,
+  authors = {Xia, Q. and Zhao, Y. and Von Tungeln, L.S. and Doerge, D.R. and Lin, G. and et al.},
+  year = 2013,
+  title = {Pyrrolizidine alkaloid-derived DNA adducts as a common biological biomarker of pyrrolizidine alkaloid-induced tumorigenicity},
+  journal = {Chem Res. Toxicol.},
+  number = 26,
+  pages = {1384-96}
+}
+
+@article{Fu2004,
+  authors = {Fu, P.P. and Xia, Q. and, Lin, G. and Chou, M.W.},
+  year = 2004,
+  title = {Pyrrolizidine alkaloids--genotoxicity, metabolism enzymes, metabolic activation, and mechanisms},
+  journal = {Drug Metab. Rev.},
+  number = 36,
+  pages = {1-55}
+}
+
+@article{Louisse2019,
+  title = {Determination of genotoxic potencies of pyrrolizidine alkaloids in HepaRG cells using the γH2AX assay},
+  journal = {Food and Chemical Toxicology},
+  volume = {131},
+  pages = {110532},
+  year = {2019},
+  issn = {0278-6915},
+  doi = {https://doi.org/10.1016/j.fct.2019.05.040},
+  url = {https://www.sciencedirect.com/science/article/pii/S0278691519303072},
+  author = {Jochem Louisse and Deborah Rijkers and Geert Stoopen and Wendy Jansen Holleboom and Mona Delagrange and Elise Molthof and Patrick P.J. Mulder and Ron L.A.P. Hoogenboom and Marc Audebert and Ad A.C.M. Peijnenburg},
+  keywords = {Pyrrolizidine alkaloids (PAs), HepaRG, Genotoxicity, γH2AX assay, Relative potency factor (RPF)},
+  abstract = {Pyrrolizidine alkaloids (PAs) are secondary metabolites from plants that have been found in substantial amounts in herbal supplements, infusions and teas. Several PAs cause cancer in animal bioassays, mediated via a genotoxic mode of action, but for the majority of the PAs, carcinogenicity data are lacking. It is assumed in the risk assessment that all PAs have the same potency as riddelliine, which is considered to be one of the most potent carcinogenic PAs in rats. This may overestimate the risks, since many PAs are expected to have lower potencies. In this study we determined the concentration-dependent genotoxicity of 37 PAs representing different chemical classes using the γH2AX in cell western assay in HepaRG human liver cells. Based on these in vitro data, PAs were grouped into different potency classes. The group with the highest potency consists particularly of open diester PAs and cyclic diester PAs (including riddelliine). The group of the least potent or non-active PAs includes the monoester PAs, non-esterified necine bases, PA N-oxides, and the unsaturated PA trachelanthamine. This study reveals differences in in vitro genotoxic potencies of PAs, supporting that the assumption that all PAs have a similar potency as riddelliine is rather conservative.}
+}
+
+@article{Allemang2018,
+  title = {Relative potency of fifteen pyrrolizidine alkaloids to induce DNA damage as measured by micronucleus induction in HepaRG human liver cells},
+  journal = {Food and Chemical Toxicology},
+  volume = {121},
+  pages = {72-81},
+  year = {2018},
+  issn = {0278-6915},
+  doi = {https://doi.org/10.1016/j.fct.2018.08.003},
+  url = {https://www.sciencedirect.com/science/article/pii/S027869151830512X},
+  author = {Ashley Allemang and Catherine Mahony and Cathy Lester and Stefan Pfuhler},
+  keywords = {Pyrrolizidine alkaloids, HepaRG, Genetic toxicology, Micronucleus test, Relative potency factor, Risk assessment},
+  abstract = {Plant-based 1,2-unsaturated Pyrrolizidine Alkaloids (PAs) can be found as contaminants in foods like teas, herbs and honey. PAs are responsible for liver genotoxicity/carcinogenicity following metabolic activation, making them a relevant concern for safety assessment. Current regulatory risk assessments take a precautionary approach and assume all PAs are as potent as the known most potent representatives: lasiocarpine and riddelliine. Our study investigated whether genotoxicity potency differed as a consequence of structural differences, assessing micronuclei in vitro in HepaRG cells which express metabolising enzymes at levels similar to primary human hepatocytes. Benchmark Dose (BMD) analysis was used to calculate the critical effect dose for 15 PAs representing 6 structural classes. When BMD confidence intervals were used to rank PAs, lasiocarpine was the most potent PA and plotted distinctly from all other PAs examined. PA-N-oxides were least potent, notably less potent than their corresponding parent PA's. The observed genotoxic potency compared favorably with existing in vitro data when metabolic competency was considered. Although further consideration of biokinetics will be needed to develop a robust understanding of relative potencies for a realistic risk assessment of PA mixtures, these data facilitate understanding of their genotoxic potencies and affirm that not all PAs are created equal.}
+}
+@article{Hadi2021,
+  title = {Genotoxicity of selected pyrrolizidine alkaloids in human hepatoma cell lines HepG2 and Huh6},
+  journal = {Mutation Research/Genetic Toxicology and Environmental Mutagenesis},
+  volume = {861-862},
+  pages = {503305},
+  year = {2021},
+  issn = {1383-5718},
+  doi = {https://doi.org/10.1016/j.mrgentox.2020.503305},
+  url = {https://www.sciencedirect.com/science/article/pii/S1383571820301765},
+  author = {Naji Said Aboud Hadi and Ezgi Eyluel Bankoglu and Lea Schott and Eva Leopoldsberger and Vanessa Ramge and Olaf Kelber and Hartwig Sievers and Helga Stopper},
+  keywords = {Pyrrolizidine alkaloids, Genomic damage, Micronuclei, Crosslink comet assay, HepG2 cells, Huh6 cells},
+  abstract = {Introduction
+Pyrrolizidine alkaloids (PAs) are found in many plant species as secondary metabolites which affect humans via contaminated food sources, herbal medicines and dietary supplements. Hundreds of compounds belonging to PAs have been identified. PAs undergo hepatic metabolism, after which they can induce hepatotoxicity and carcinogenicity. Many aspects of their mechanism of carcinogenicity are still unclear and it is important for human risk assessment to investigate this class of compounds further.
+Material and methods
+Human hepatoma cells HepG2 were used to investigate the genotoxicity of different chemical structural classes of PAs, namely europine, lycopsamine, retrorsine, riddelliine, seneciphylline, echimidine and lasiocarpine, in the cytokinesis-block micronucleus (CBMN) assay. The different ester type PAs europine, seneciphylline, and lasiocarpine were also tested in human hepatoma Huh6 cells. Six different PAs were investigated in a crosslink comet assay in HepG2 cells.
+Results
+The maximal increase of micronucleus formation was for all PAs in the range of 1.64–2.0 fold. The lowest concentrations at which significant induction of micronuclei were found were 3.2 μM for lasiocarpine and riddelliine, 32 μM for retrorsine and echimidine, and 100 μM for seneciphylline, europine and lycopsamine. Significant induction of micronuclei by lasiocarpine, seneciphylline, and europine were achieved in Huh6 cells at similar concentrations. Reduced tail formation after hydrogen peroxide treatment was found in the crosslink comet assay for all diester type PAs, while an equimolar concentration of the monoesters europine and lycopsamine did not significantly reduce DNA migration.
+Conclusion
+The widely available human hepatoma cell lines HepG2 and Huh6 were suitable for the assessment of PA-induced genotoxicity. Selected PAs confirmed previously published potency rankings in the micronucleus assay. In HepG2 cells, the crosslinking activity was related to the ester type, which is a first report of PA mediated effects in the comet assay.}
+}
+
+@InCollection{Hartmann1995,
+  author = {Hartmann, T. and Witte, L.},
+  year = 1995,
+  title = {Chemistry, Biology and Chemoecology of the Pyrrolizidine Alkaloids},
+  booktitle = {Alkaloids: Chemical and Biological Perspectives},
+  editor = {S.W. Pelletier}, 
+  pages = {155-233},
+  publisher = {Pergamon},
+  address = {London, New York}
+}
+
+@article{Langel2011,
+  author = {Langel, D. and Ober, D. and Pelser P.B.},
+  year = 2011,
+  title = {The evolution of pyrrolizidine alkaloid biosynthesis and diversity in the Senecioneae},
+  jounrnal = {Phytochemistry Reviews},
+  number = 10,
+  pages = {3-74}
+}
+
 @article{Weininger1989,
   author = {David Weininger and Arthur Weininger and Joseph L. Weininger},
   title = {SMILES. 2. Algorithm for generation of unique SMILES notation},
diff --git a/mutagenicity.md b/mutagenicity.md
index 5a01ee9..3911799 100644
--- a/mutagenicity.md
+++ b/mutagenicity.md
@@ -53,69 +53,12 @@ accuracies of all investigated models ranged from 80-85% which is comparable
 with the interlaboratory variability of the *Salmonella* mutagenicity assay.
 Pyrrolizidine alkaloid predictions showed a clear distinction between chemical
 groups, where Otonecines had the highest proportion of positive mutagenicity
-predictions and Monoester the lowest.
+predictions and Monoesters the lowest.
 
 Introduction
 ============
 
 **TODO**: rationale for investigation
-
-<!---
-Pyrrolizidine alkaloids (PAs) are secondary plant ingredients found in
-many plant species as protection against predators [Hartmann & Witte
-1995](#_ENREF_59)[Langel et al. 2011](#_ENREF_76)(; ). PAs are ester
-alkaloids, which are composed of a necine base (two fused five-membered
-rings joined by a nitrogen atom) and one or two necic acid (carboxylic
-ester arms). The necine base can have different structures and thereby
-divides PAs into several structural groups, e.g. otonecine, platynecine,
-and retronecine. The structural groups of the necic acid are macrocyclic
-diester, open-ring diester and monoester [Langel et al.
-2011](#_ENREF_76)().
-
-PA are mainly metabolised in the liver, which is at the same time the
-main target organ of toxicity [Bull & Dick 1959](#_ENREF_17)[Bull et al.
-1958](#_ENREF_18)[Butler et al. 1970](#_ENREF_20)[DeLeve et al.
-1996](#_ENREF_33)[Jago 1971](#_ENREF_65)[Li et al.
-2011](#_ENREF_78)[Neumann et al. 2015](#_ENREF_99)(; ; ; ; ; ; ). There
-are three principal metabolic pathways for 1,2-unsaturated PAs [Chen et
-al. 2010](#_ENREF_26)(): (i) Detoxification by hydrolysis: the ester
-bond on positions C7 and C9 are hydrolysed by non-specific esterases to
-release necine base and necic acid, which are then subjected to further
-phase II-conjugation and excretion. (ii) Detoxification by *N*-oxidation
-of the necine base (only possible for retronecine-type PAs): the
-nitrogen is oxidised to form a PA *N*-oxides, which can be conjugated by
-phase II enzymes e.g. glutathione and then excreted. PA *N*-oxides can
-be converted back into the corresponding parent PA [Wang et al.
-2005](#_ENREF_134)(). (iii) Metabolic activation or toxification: PAs
-are metabolic activated/ toxified by oxidation (for retronecine-type
-PAs) or oxidative *N*-demethylation (for otonecine-type PAs [Lin
-1998](#_ENREF_82)()). This pathway is mainly catalysed by cytochrome
-P450 isoforms CYP2B and 3A [Ruan et al. 2014b](#_ENREF_115)(), and
-results in the formation of dehydropyrrolizidines (DHP, also known as
-pyrrolic ester or reactive pyrroles). DHPs are highly reactive and cause
-damage in the cells where they are formed, usually hepatocytes. However,
-they can also pass from the hepatocytes into the adjacent sinusoids and
-damage the endothelial lining cells [Gao et al. 2015](#_ENREF_48)()
-predominantly by reaction with protein, lipids and DNA. There is even
-evidence, that conjugation of DHP to glutathione, which would generally
-be considered a detoxification step, could result in reactive
-metabolites, which might also lead to DNA adduct formation [Xia et al.
-2015](#_ENREF_138)(). Due to the ability to form DNA adducts, DNA
-crosslinks and DNA breaks 1,2-unsaturated PAs are generally considered
-genotoxic and carcinogenic [Chen et al. 2010](#_ENREF_26)[EFSA
-2011](#_ENREF_36)[Fu et al. 2004](#_ENREF_45)[Li et al.
-2011](#_ENREF_78)[Takanashi et al. 1980](#_ENREF_126)[Yan et al.
-2008](#_ENREF_140)[Zhao et al. 2012](#_ENREF_148)(; ; ; ; ; ; ). Still,
-there is no evidence yet that PAs are carcinogenic in humans [ANZFA
-2001](#_ENREF_4)[EMA 2016](#_ENREF_39)(; ). One general limitation of
-studies with PAs is the number of different PAs investigated. Around 30
-PAs are currently commercially available, therefore all studies focus on
-these PAs. This is also true for *in vitro* and *in vivo* tests on
-mutagenicity and genotoxicity. To gain a wider perspective, in this
-study over 600 different PAs were assessed on their mutagenic potential
-using four different machine learning techniques.
---->
-
 <!---
 
 Mutagenicity datasets
@@ -123,9 +66,30 @@ Algorithms
 descriptors
 define abbreviations
 pyrrolizidine 
+large dataset -> comparison of algorithms and descriptors
+reliable experimental outcome
 --->
 
-The main objectives of this study were
+As case study we decided to apply these mutagenicity models to {{pa.nr}}
+Pyrrolizidines alkaloids (PAs) in order to highlight potentials and problems
+with the applicability of mutagenicity models for compounds with very limited
+experimental data.
+
+Pyrrolizidine alkaloids (PAs) are characteristic metabolites of some plant
+families, mainly: *Asteraceae*, *Boraginaceae*, *Fabaceae* and *Orchidaceae*
+(@Hartmann1995, @Langel2011) and form a powerful defence mechanism against
+herbivores. PAs are heterocyclic ester alkaloids composed of a necine base (two
+fused five-membered rings joined by a single nitrogen atom) and a necic acid
+(one or two carboxylic ester arms), occurring principally in two forms,
+tertiary base PAs and PA N-oxides. Several *in vitro* studies have shown the
+mutagenic potential of PAs, which seems highly dependent on structure of necine
+base and necic acid (@Hadi2021; @Allemang2018, @Louisse2019). However, due to
+limited availability of pure substances, only a limited number of PAs have been
+investigated with regards to their structure-specific mutagenicity. To overcome
+this bottleneck, the prediction of structure-specific mutagenic potential of
+PAs with different machine learning models could provide further inside in the mechanisms.
+
+Summing up the main objectives of this study were
 
   - to generate a new mutagenicity training dataset, by combining the most comprehensive public datasets
   - to compare the performance of MolPrint2D (*MP2D*) fingerprints with Chemistry Development Kit (*CDK*) descriptors
@@ -503,43 +467,6 @@ investigated models can be downloaded from
 A visual representation of all PA predictions can be found at
 <https://git.in-silico.ch/mutagenicity-paper/tree/pyrrolizidine-alkaloids/pa-predictions.pdf>.
 
-<!--
-@tbl:pa-mp2d and @tbl:pa-cdk summarise the outcome of pyrrolizidine alkaloid predictions from all models with MolPrint2D and CDK descriptors.
-
-| Model  | mutagenic | non-mutagenic | Nr. predictions |
-|-------:|-----------|---------------|-----------------|
-| lazar-all | {{pa.mp2d_lazar_all.mut_perc}}% ({{pa.mp2d_lazar_all.mut}}) | {{pa.mp2d_lazar_all.non_mut_perc}}% ({{pa.mp2d_lazar_all.non_mut}}) | {{pa.mp2d_lazar_all.n_perc}}% ({{pa.mp2d_lazar_all.n}}) |
-| lazar-HC | {{pa.mp2d_lazar_high_confidence.mut_perc}}% ({{pa.mp2d_lazar_high_confidence.mut}}) | {{pa.mp2d_lazar_high_confidence.non_mut_perc}}% ({{pa.mp2d_lazar_high_confidence.non_mut}}) | {{pa.mp2d_lazar_high_confidence.n_perc}}% ({{pa.mp2d_lazar_high_confidence.n}}) |
-| RF | {{pa.mp2d_rf.mut_perc}}% ({{pa.mp2d_rf.mut}}) | {{pa.mp2d_rf.non_mut_perc}}% ({{pa.mp2d_rf.non_mut}}) | {{pa.mp2d_rf.n_perc}}% ({{pa.mp2d_rf.n}}) |
-| LR-sgd | {{pa.mp2d_lr.mut_perc}}% ({{pa.mp2d_lr.mut}}) | {{pa.mp2d_lr.non_mut_perc}}% ({{pa.mp2d_lr.non_mut}}) | {{pa.mp2d_lr.n_perc}}% ({{pa.mp2d_lr.n}}) |
-| LR-scikit | {{pa.mp2d_lr2.mut_perc}}% ({{pa.mp2d_lr2.mut}}) | {{pa.mp2d_lr2.non_mut_perc}}% ({{pa.mp2d_lr2.non_mut}}) | {{pa.mp2d_lr2.n_perc}}% ({{pa.mp2d_lr2.n}}) |
-| NN | {{pa.mp2d_nn.mut_perc}}% ({{pa.mp2d_nn.mut}}) | {{pa.mp2d_nn.non_mut_perc}}% ({{pa.mp2d_nn.non_mut}}) | {{pa.mp2d_nn.n_perc}}% ({{pa.mp2d_nn.n}}) |
-| SVM | {{pa.mp2d_svm.mut_perc}}% ({{pa.mp2d_svm.mut}}) | {{pa.mp2d_svm.non_mut_perc}}% ({{pa.mp2d_svm.non_mut}}) | {{pa.mp2d_svm.n_perc}}% ({{pa.mp2d_svm.n}}) |
-
-: Summary of MolPrint2D pyrrolizidine alkaloid predictions {#tbl:pa-mp2d}
-
-| Model  | mutagenic | non-mutagenic | Nr. predictions |
-|-------:|-----------|---------------|-----------------|
-| lazar-all | {{pa.cdk_lazar_all.mut_perc}}% ({{pa.cdk_lazar_all.mut}}) | {{pa.cdk_lazar_all.non_mut_perc}}% ({{pa.cdk_lazar_all.non_mut}}) | {{pa.cdk_lazar_all.n_perc}}% ({{pa.cdk_lazar_all.n}}) |
-| lazar-HC | {{pa.cdk_lazar_high_confidence.mut_perc}}% ({{pa.cdk_lazar_high_confidence.mut}}) | {{pa.cdk_lazar_high_confidence.non_mut_perc}}% ({{pa.cdk_lazar_high_confidence.non_mut}}) | {{pa.cdk_lazar_high_confidence.n_perc}}% ({{pa.cdk_lazar_high_confidence.n}}) |
-| RF | {{pa.cdk_rf.mut_perc}}% ({{pa.cdk_rf.mut}}) | {{pa.cdk_rf.non_mut_perc}}% ({{pa.cdk_rf.non_mut}}) | {{pa.cdk_rf.n_perc}}% ({{pa.cdk_rf.n}}) |
-| LR-sgd | {{pa.cdk_lr.mut_perc}}% ({{pa.cdk_lr.mut}}) | {{pa.cdk_lr.non_mut_perc}}% ({{pa.cdk_lr.non_mut}}) | {{pa.cdk_lr.n_perc}}% ({{pa.cdk_lr.n}}) |
-| LR-scikit | {{pa.cdk_lr2.mut_perc}}% ({{pa.cdk_lr2.mut}}) | {{pa.cdk_lr2.non_mut_perc}}% ({{pa.cdk_lr2.non_mut}}) | {{pa.cdk_lr2.n_perc}}% ({{pa.cdk_lr2.n}}) |
-| NN | {{pa.cdk_nn.mut_perc}}% ({{pa.cdk_nn.mut}}) | {{pa.cdk_nn.non_mut_perc}}% ({{pa.cdk_nn.non_mut}}) | {{pa.cdk_nn.n_perc}}% ({{pa.cdk_nn.n}}) |
-| SVM | {{pa.cdk_svm.mut_perc}}% ({{pa.cdk_svm.mut}}) | {{pa.cdk_svm.non_mut_perc}}% ({{pa.cdk_svm.non_mut}}) | {{pa.cdk_svm.n_perc}}% ({{pa.cdk_svm.n}}) |
-
-: Summary of CDK pyrrolizidine alkaloid predictions {#tbl:pa-cdk}
--->
-
-@fig:pa-groups displays the proportion of positive mutagenicity predictions
-from all models for the different pyrrolizidine alkaloid groups. Tensorflow
-models predicted all {{pa.n}} pyrrolizidine alkaloids, `lazar` MP2D models
-predicted {{pa.mp2d_lazar_all.n}} compounds
-({{pa.mp2d_lazar_high_confidence.n}} with high confidence) and `lazar` CDK
-models {{pa.cdk_lazar_all.n}} compounds ({{pa.cdk_lazar_high_confidence.n}}
-with high confidence).
-
-![Summary of pyrrolizidine alkaloid predictions](figures/pa-groups.png){#fig:pa-groups}
 
 <!--
 ![Summary of Diester predictions](figures/Diester.png){#fig:die}
@@ -617,6 +544,65 @@ mutagenicity predictions in the context of training data. t-SNE visualisations o
 ![t-SNE visualisation of CDK support vector machine predictions](figures/tsne-cdk-svm-classifications.png){#fig:tsne-cdk-svm}
 -->
 
+@tbl:pa-summary summarises the outcome of pyrrolizidine alkaloid predictions from all models with MolPrint2D and CDK descriptors.
+
+
+| Model  | MP2D Mutagenic | Nr. predictions | CDK Mutagenic | Nr. predictions |
+|-------:|----------------|-----------------|---------------|-----------------|
+| lazar-all | {{pa.mp2d_lazar_all.mut_perc}}% ({{pa.mp2d_lazar_all.mut}}) | {{pa.mp2d_lazar_all.n_perc}}% ({{pa.mp2d_lazar_all.n}}) | {{pa.cdk_lazar_all.mut_perc}}% ({{pa.cdk_lazar_all.mut}}) | {{pa.cdk_lazar_all.n_perc}}% ({{pa.cdk_lazar_all.n}}) |
+| lazar-HC | {{pa.mp2d_lazar_high_confidence.mut_perc}}% ({{pa.mp2d_lazar_high_confidence.mut}}) | {{pa.mp2d_lazar_high_confidence.n_perc}}% ({{pa.mp2d_lazar_high_confidence.n}}) | {{pa.cdk_lazar_high_confidence.mut_perc}}% ({{pa.cdk_lazar_high_confidence.mut}}) | {{pa.cdk_lazar_high_confidence.n_perc}}% ({{pa.cdk_lazar_high_confidence.n}}) |
+| RF | {{pa.mp2d_rf.mut_perc}}% ({{pa.mp2d_rf.mut}}) | {{pa.mp2d_rf.n_perc}}% ({{pa.mp2d_rf.n}}) | {{pa.cdk_rf.mut_perc}}% ({{pa.cdk_rf.mut}}) | {{pa.cdk_rf.n_perc}}% ({{pa.cdk_rf.n}}) |
+| LR-sgd | {{pa.mp2d_lr.mut_perc}}% ({{pa.mp2d_lr.mut}}) | {{pa.mp2d_lr.n_perc}}% ({{pa.mp2d_lr.n}}) | {{pa.cdk_lr.mut_perc}}% ({{pa.cdk_lr.mut}}) | {{pa.cdk_lr.n_perc}}% ({{pa.cdk_lr.n}}) |
+| LR-scikit | {{pa.mp2d_lr2.mut_perc}}% ({{pa.mp2d_lr2.mut}}) | {{pa.mp2d_lr2.n_perc}}% ({{pa.mp2d_lr2.n}}) | {{pa.cdk_lr2.mut_perc}}% ({{pa.cdk_lr2.mut}}) | {{pa.cdk_lr2.n_perc}}% ({{pa.cdk_lr2.n}}) |
+| NN | {{pa.mp2d_nn.mut_perc}}% ({{pa.mp2d_nn.mut}}) | {{pa.mp2d_nn.n_perc}}% ({{pa.mp2d_nn.n}}) | {{pa.cdk_nn.mut_perc}}% ({{pa.cdk_nn.mut}}) | {{pa.cdk_nn.n_perc}}% ({{pa.cdk_nn.n}}) |
+| SVM | {{pa.mp2d_svm.mut_perc}}% ({{pa.mp2d_svm.mut}}) | {{pa.mp2d_svm.n_perc}}% ({{pa.mp2d_svm.n}}) | {{pa.cdk_svm.mut_perc}}% ({{pa.cdk_svm.mut}}) | {{pa.cdk_svm.n_perc}}% ({{pa.cdk_svm.n}}) |
+
+: Summary of pyrrolizidine alkaloid predictions {#tbl:pa-summary}
+
+@fig:pa-groups displays the proportion of positive mutagenicity predictions
+from all models for the different pyrrolizidine alkaloid groups. Tensorflow
+models predicted all {{pa.n}} pyrrolizidine alkaloids, `lazar` MP2D models
+predicted {{pa.mp2d_lazar_all.n}} compounds
+({{pa.mp2d_lazar_high_confidence.n}} with high confidence) and `lazar` CDK
+models {{pa.cdk_lazar_all.n}} compounds ({{pa.cdk_lazar_high_confidence.n}}
+with high confidence).
+
+![Summary of pyrrolizidine alkaloid predictions](figures/pa-groups.png){#fig:pa-groups}
+
+For the lazar-HC model, only
+{{pa.mp2d_lazar_high_confidence.n_perc}}/{{pa.cdk_lazar_high_confidence.n_perc}}%
+of the PA dataset were within the stricter similarity thresholds of 0.5/0.9
+(MP2D/CDK). Reduction of the similarity threshold to 0.2/0.5 in the lazar-all
+model increased the amount of predictable PAs to
+{{pa.mp2d_lazar_all.n_perc}}/{{pa.cdk_lazar_all.n_perc}}%. As the other ML
+models do not consider applicability domains, all PAs were predicted. 
+
+Although most of the models show similar accuracies, sensitivities and
+specificities in crossvalidation experiments some of the models (MPD-RF, CDK-RF
+and CDK-SVM) predict a lower number of mutagens
+({{pa.cdk_rf.mut_perc}}-{{pa.mp2d_rf.mut_perc}}%) than the majority of the
+models ({{pa.mp2d_svm.mut_perc}}-{{pa.mp2d_lazar_high_confidence.mut_perc}}%,
+@tbl:pa-summary, @fig:pa-groups). 
+
+Over all models, the mean value of mutagenic predicted PAs was highest for
+Otonecines ({{pa.groups.Otonecine.mut_perc}}%, 
+{{pa.groups.Otonecine.mut}}/{{pa.groups.Otonecine.n_pred}}),
+followed by Macrocyclic diesters ({{pa.groups.Macrocyclic_diester.mut_perc}}%, {{pa.groups.Macrocyclic_diester.mut}}/{{pa.groups.Macrocyclic_diester.n_pred}}),
+Dehydropyrrolizidine ({{pa.groups.Dehydropyrrolizidine.mut_perc}}%, {{pa.groups.Dehydropyrrolizidine.mut}}/{{pa.groups.Dehydropyrrolizidine.n_pred}}),
+Tertiary PAs ({{pa.groups.Tertiary_PA.mut_perc}}%, {{pa.groups.Tertiary_PA.mut}}/{{pa.groups.Tertiary_PA.n_pred}}) and
+Retronecines ({{pa.groups.Retronecine.mut_perc}}%, {{pa.groups.Retronecine.mut}}/{{pa.groups.Retronecine.n_pred}}).
+
+When excluding the aforementioned three deviating models,
+the rank order stays the same, but the percentage of mutagenic PAs is higher.
+
+The following rank order for mutagenic probability can be deduced from the results of all models taken together: 
+
+Necine base: 				Platynecine < Retronecine << Otonecine
+
+Necic acid: 				Monoester < Diester << Macrocyclic diester
+
+Modification of necine base:		N-oxide  < Tertiary PA < Dehydropyrrolizidine
+
 Discussion
 ==========
 
@@ -716,8 +702,10 @@ CDK descriptors contain in contrast in every case matrices with
 Pyrrolizidine alkaloid mutagenicity predictions
 -----------------------------------------------
 
-@fig:pa-groups shows a clear differentiation between the different
-pyrrolizidine alkaloid groups. The largest proportion of mutagenic predictions
+### Algorithms and descriptors
+
+<!--
+The largest proportion of mutagenic predictions
 was observed for Otonecines {{pa.groups.Otonecine.mut_perc}}%
 ({{pa.groups.Otonecine.mut}}/{{pa.groups.Otonecine.n_pred}}), the lowest for
 Monoesters {{pa.groups.Monoester.mut_perc}}%
@@ -733,9 +721,12 @@ models ({{pa.mp2d_svm.mut_perc}}-{{pa.mp2d_lazar_high_confidence.mut_perc}}%
 (@fig:pa-groups). lazar-CDK on the other hand
 predicts the largest number of mutagens for all groups with exception of
 Otonecines.
+-->
 
-These differences between predictions from different algorithms and descriptors
-were not expected based on crossvalidation results.
+@fig:pa-groups shows a clear differentiation between the different
+pyrrolizidine alkaloid groups.
+Nevertheless differences between predictions from different algorithms and descriptors
+(@tbl:pa-summary) were not expected based on crossvalidation results.
 
 In order to investigate, if any of the investigated models show systematic
 errors in the  vicinity of pyrrolizidine-alkaloids we have performed a
@@ -743,12 +734,72 @@ detailled t-SNE analysis of all models (see @fig:tsne-mp2d-rf and
 @fig:tsne-cdk-lazar-all for two examples, all visualisations can be found at
 <https://git.in-silico.ch/mutagenicity-paper/figures>.
 
-Nevertheless none of the models showed obvious deviations from their expected
+None of the models showed obvious deviations from their expected
 behaviour, so the reason for the disagreement between some of the models
-remains unclear at the moment.  It is however perfectly possible that some
+remains unclear at the moment.  It is however possible that some
 systematic errors are covered up by converting high dimensional spaces to two
 coordinates and are thus invisible in t-SNE visualisations.
 
+### Necic acid
+
+The rank order of the necic acid is comparable in all models. PAs from the
+monoester type had the lowest genotoxic potential, followed by PAs from the
+open-ring diester type. PAs with macrocyclic diesters had the highest genotoxic
+potential. The result fits well with current state of knowledge: in general,
+PAs, which have a macrocyclic diesters as necic acid, are considered to be more toxic
+than those with an open-ring diester or monoester (@EFSA2011, @Fu2004,
+Ruan2014b). This was also confirmed by more recent studies, confirming that
+macrocyclic- and open-diesters are more genotoxic *in vitro* than monoesters
+(@Hadi2021; @Allemang2018, @Louisse2019). 
+
+### Necine base
+
+In the rank order of necine base PAs, platynecine is the least mutagenic, followed
+by retronecine, and otonecine. Saturated PAs of the platynecine-type are
+generally accepted to be less or non-toxic and have been shown in *in vitro*
+experiments to form no DNA-adducts (@Xia2013). In literature,
+otonecine-type PAs were shown to be more toxic than those of the
+retronecine-type (@Li2013). 
+
+### Modifications of necine base
+
+The group-specific results reflect the expected relationship between the
+groups: the low mutagenic potential of N-oxides and the high potential of
+Dehydropyrrolizidines (DHP) (@Chen2010). 
+
+Dehydropyrrolizidines are regarded as the toxic principle in the metabolism of
+PAs, and known to produce protein- and DNA-adducts (@Chen2010). None of the
+models did not meet this expectation and predicted the majority of DHP as
+non-mutagenic. However, the following issues need to be considered. On the one
+hand, all DHP were outside of the stricter applicability domain of MP2D lazar.
+This indicates that they are structurally very different than the training data
+and might be out of the applicability domain of all models based on this
+training set. In addition, DHP has two unsaturated double bounds in its necine
+base, making it highly reactive. DHP and other comparable molecules have a very
+short lifespan, and usually cannot be used in *in vitro* experiments. 
+
+<!--
+Furthermore, the probabilities for this substance groups needs to be considered, and not only the consolidated prediction. In the LAZAR model, all DHPs had probabilities for both outcomes (genotoxic and not genotoxic) mainly below 30%. Additionally, the probabilities for both outcomes were close together, often within 10% of each other. The fact that for both outcomes, the probabilities were low and close together, indicates a lower confidence in the prediction of the model for DHPs. 
+-->
+
+PA N-oxides are easily conjugated for extraction, they are generally considered
+as detoxification products, which are *in vivo* quickly renally eliminated
+(@Chen2010).
+
+Overall the low number of positive mutagenicity predictions was unexpected.
+PAs are generally considered to be genotoxic, and the mode of action is also known.
+Therefore, the fact that some models predict the majority of PAs as not
+mutagenic seems contradictory. To understand this result, the experimental
+basis of the training dataset has to be considered. The 
+training dataset is based on the *Salmonella typhimurium* mutagenicity bioassay (Ames test). There are some
+studies, which show mutagenicity of PAs in the Ames test (@Chen2010).
+Also, @Rubiolo1992 examined several different PAs and several
+different extracts of PA-containing plants in the AMES test. They found that
+the Ames test was indeed able to detect mutagenicity of PAs, but in general,
+appeared to have a low sensitivity. The pre-incubation phase for metabolic
+activation of PAs by microsomal enzymes was the sensitivity-limiting step. This
+could very well mean that the low sensitivity of the Ames test for PAs is also reflected in the investigated models.
+
 <!--
 non-conflicting CIDs
 43040
@@ -798,8 +849,6 @@ R RF and SVM models favor very strongly non-mutagenic predictions (only {{pa.r.r
 
 It is interesting to note, that different implementations of the same algorithm show little accordance in their prediction (see e.g R-RF vs. Tensorflow-RF and LR-sgd vs. LR-scikit in Table 4 and @tbl:pa-summary).
 
-**TODO** **Verena, Philipp** habt ihr eine Erklaerung dafuer?
-
 @fig:tsne-mp2d and @fig:tsne-padel show the t-SNE of training data and pyrrolizidine alkaloids. In @fig:tsne-mp2d the PAs are located closely together at the outer border of the training set. In @fig:tsne-padel they are less clearly separated and spread over the space occupied by the training examples.
 
 This is probably the reason why CDK models predicted all instances and the MP2D model only {{pa.lazar.mp2d.all.n}} PAs. Predicting a large number of instances is however not the ultimate goal, we need accurate predictions and an unambiguous estimation of the applicability domain. With CDK descriptors *all* PAs are within the applicability domain of the training data, which is unlikely despite the size of the training set. MolPrint2D descriptors provide a clearer separation, which is also reflected in a better separation between high and low confidence predictions in `lazar` MP2D predictions as compared to `lazar` CDK predictions. Crossvalidation results with substantially higher accuracies for MP2D models than for CDK models also support this argument.
@@ -812,11 +861,31 @@ From a practical point we still have to face the question, how to choose model p
 Conclusions
 ===========
 
-A new public *Salmonella* mutagenicity training dataset with 8309 compounds was
-created and used it to train `lazar` and Tensorflow models with MolPrint2D
-and CDK descriptors.
+A new public *Salmonella* mutagenicity training dataset with {{cv.n}}
+experimental results was created and used to train `lazar` and Tensorflow
+models with MolPrint2D and CDK descriptors. All investigated algorithm and
+descriptor combinations showed accuracies comparable to the interlaboratory
+variability of the Ames test.
+
+Pyrrolizidine alkaloid predictions showed a clear separation between different
+classes of PAs which were generally in accordance with the current
+toxicological knowledge about these compounds.  Some of the models showed
+however a substantially lower number of mutagenicity predictions, despite
+similar crossvalidation results and we were unable to identify the reasons for
+this discrepancy within this investigation.
+
+Thus the practical question how to choose model predictions in the absence of
+experimental data remains open. Tensorflow predictions do not include
+applicability domain estimations and the rationales for predictions cannot be
+traced by toxicologists.  Transparent models like `lazar` may have an advantage
+in this context, because they present rationales for predictions (similar
+compounds with experimental data) which can be accepted or rejected by
+toxicologists and provide validated applicability domain estimations. 
 
 <!---
+in a form that is understandable and criticiseable by toxicologists without a machine learning background.
+
+is available (we found two PAs in the training data, but this number is too low, to draw any general conclusions). Based on crossvalidation results and the arguments in favor of MolPrint2D descriptors we would put the highest trust in `lazar` MolPrint2D predictions, especially in high-confidence predictions. `lazar` predictions have a accuracy comparable to experimental variability (@Helma2018) for compounds within the applicability domain. But they should not be trusted blindly. For practical purposes it is important to study the rationales (i.e. neighbors and their experimental activities) for each prediction of relevance. A freely accessible GUI for this purpose has been implemented at https://lazar.in-silico.ch.
 The best performance was obtained with `lazar` models
 using MolPrint2D descriptors, with prediction accuracies
 ({{cv.lazar-high-confidence.acc_perc}}%) comparable to the interlaboratory variability
diff --git a/mutagenicity.pdf b/mutagenicity.pdf
index 1b98269..5a333b1 100644
--- a/mutagenicity.pdf
+++ b/mutagenicity.pdf