Deep learning in wastewater treatment: a critical review.

Modeling wastewater processes supports tasks such as process prediction, soft sensing, data analysis and computer assisted design of wastewater systems. Wastewater treatment processes are large, complex processes, with multiple controlling mechanisms, a high degree of disturbance variability and non-linear (generally stable) behavior with multiple internal recycle loops. Semi-mechanistic biochemical models currently dominate research and application, with data-driven deep learning models emerging as an alternative and supplementary approach. But these modeling approaches have grown in separate communities of research and practice, and so there is limited appreciation of the strengths, weaknesses, contrasts and similarities between the methods. This review addresses that gap by providing a detailed guide to deep learning methods and their application to wastewater process modeling. The review is aimed at wastewater modeling experts who are familiar with established mechanistic modeling approach, and are curious about the opportunities and challenges afforded by deep learning methods. We conclude with a discussion and needs analysis on the value of different ways of modeling wastewater processes and open research problems.

Testing for homologous recombination repair or homologous recombination deficiency for poly (ADP-ribose) polymerase inhibitors: A current perspective.

Poly (ADP-ribose) polymerase inhibitors (PARPis) have demonstrated clinical activity in patients with BRCA1 and/or BRCA2 mutated breast, ovarian, prostate, and pancreatic cancers. Notably, BRCA mutations are associated with defects in the homologous recombination repair (HRR) pathway. This homologous recombination deficiency (HRD) phenotype can also be observed as genomic instability in tumour cells. Accordingly, PARPi sensitivity has been observed in various tumours with HRD, independent of BRCA mutations. Currently, four PARPis are approved by regulatory agencies for the treatment of cancer across multiple tumour types. Most indications are specific to tumours with a confirmed BRCA mutation, mutations in other HRR-related genes, HRD evidenced by genomic instability, or evidence of platinum sensitivity. Regulatory agencies have also approved companion and complementary diagnostics to facilitate patient selection for each PARPi indication. This review aims to summarise the biological basis, clinical validation, and clinical relevance of the available diagnostic methods and assays to assess HRD.

Homologous Recombination Deficiency: Concepts, Definitions, and Assays.

BACKGROUND: Homologous recombination deficiency (HRD) is a phenotype that is characterized by the inability of a cell to effectively repair DNA double-strand breaks using the homologous recombination repair (HRR) pathway. Loss-of-function genes involved in this pathway can sensitize tumors to poly(adenosine diphosphate [ADP]-ribose) polymerase (PARP) inhibitors and platinum-based chemotherapy, which target the destruction of cancer cells by working in concert with HRD through synthetic lethality. However, to identify patients with these tumors, it is vital to understand how to best measure homologous repair (HR) status and to characterize the level of alignment in these measurements across different diagnostic platforms. A key current challenge is that there is no standardized method to define, measure, and report HR status using diagnostics in the clinical setting. METHODS: Friends of Cancer Research convened a consortium of project partners from key healthcare sectors to address concerns about the lack of consistency in the way HRD is defined and methods for measuring HR status. RESULTS: This publication provides findings from the group's discussions that identified opportunities to align the definition of HRD and the parameters that contribute to the determination of HR status. The consortium proposed recommendations and best practices to benefit the broader cancer community. CONCLUSION: Overall, this publication provides additional perspectives for scientist, physician, laboratory, and patient communities to contextualize the definition of HRD and various platforms that are used to measure HRD in tumors.

Characterization of FGFR1 Locus in sqNSCLC Reveals a Broad and Heterogeneous Amplicon.

FGFR1 amplification occurs in ~20% of sqNSCLC and trials with FGFR inhibitors have selected FGFR1 amplified patients by FISH. Lung cancer cell lines were profiled for sensitivity to AZD4547, a potent, selective inhibitor of FGFRs 1-3. Sensitivity to FGFR inhibition was associated with but not wholly predicted by increased FGFR1 gene copy number. Additional biomarker assays evaluating expression of FGFRs and correlation between amplification and expression in clinical tissues are therefore warranted. We validated nanoString for mRNA expression analysis of 194 genes, including FGFRs, from clinical tumour tissue. In a panel of sqNSCLC tumours 14.4% (13/90) were FGFR1 amplified by FISH. Although mean FGFR1 expression was significantly higher in amplified samples, there was significant overlap in the range of expression levels between the amplified and non-amplified cohorts with several non-amplified samples expressing FGFR1 to levels equivalent to amplified samples. Statistical analysis revealed increased expression of FGFR1 neighboring genes on the 8p12 amplicon (BAG4, LSM1 and WHSC1L1) in FGFR1 amplified tumours, suggesting a broad rather than focal amplicon and raises the potential for codependencies. High resolution aCGH analysis of pre-clinical and clinical samples supported the presence of a broad and heterogeneous amplicon around the FGFR1 locus. In conclusion, the range of FGFR1 expression levels in both FGFR1 amplified and non-amplified NSCLC tissues, together with the breadth and intra-patient heterogeneity of the 8p amplicon highlights the need for gene expression analysis of clinical samples to inform the understanding of determinants of response to FGFR inhibitors. In this respect the nanoString platform provides an attractive option for RNA analysis of FFPE clinical samples.

The impact of germline mutations on targeted therapy.

Targeted therapies provide clinical benefit and improved therapeutic index. They have a growing prominence in patient management and focus in drug development. Their development is fuelled by our deepening knowledge of complex disease phenotypes and the need for improvement in new therapeutic efficacy. Extrapolation of the biological discovery through to new therapy targeting the causal biological variants to drive clinical gain is challenging. Here, we review the impact of germline mutations on targeted therapies. Historically, germline changes have contributed most to our understanding of disease mechanisms, drug metabolism and exposure, the latter of which has enabled safer positioning of therapies, such as clopidogrel and irinotecan. Similarly, prescreening for germline variants can avoid potentially fatal hypersensitivity reactions with abacavir. However, germline mutations continue to emerge as a central player in targeting therapeutics; ivacaftor drives partial restoration of mucus secretion in cystic fibrosis patients harbouring specific mutations, and treatment with olaparib exploits germline mutations in BRCA genes to drive synthetic lethality as an anti-cancer mechanism. Central is definition of the causal link, association or contribution to the biological variance - and that we believe it is drugable for therapeutic gain. The demand for better therapies to treat modern diseases provides the appetite for continued investigation of the biological variance associated with germline mutations, inevitably leading to increased impact on the development of targeted therapeutics.

Subtypes of primary colorectal tumors correlate with response to targeted treatment in colorectal cell lines.

BACKGROUND: Colorectal cancer (CRC) is a heterogeneous and biologically poorly understood disease. To tailor CRC treatment, it is essential to first model this heterogeneity by defining subtypes of patients with homogeneous biological and clinical characteristics and second match these subtypes to cell lines for which extensive pharmacological data is available, thus linking targeted therapies to patients most likely to respond to treatment. METHODS: We applied a new unsupervised, iterative approach to stratify CRC tumor samples into subtypes based on genome-wide mRNA expression data. By applying this stratification to several CRC cell line panels and integrating pharmacological response data, we generated hypotheses regarding the targeted treatment of different subtypes. RESULTS: In agreement with earlier studies, the two dominant CRC subtypes are highly correlated with a gene expression signature of epithelial-mesenchymal-transition (EMT). Notably, further dividing these two subtypes using iNMF (iterative Non-negative Matrix Factorization) revealed five subtypes that exhibit activation of specific signaling pathways, and show significant differences in clinical and molecular characteristics. Importantly, we were able to validate the stratification on independent, published datasets comprising over 1600 samples. Application of this stratification to four CRC cell line panels comprising 74 different cell lines, showed that the tumor subtypes are well represented in available CRC cell line panels. Pharmacological response data for targeted inhibitors of SRC, WNT, GSK3b, aurora kinase, PI3 kinase, and mTOR, showed significant differences in sensitivity across cell lines assigned to different subtypes. Importantly, some of these differences in sensitivity were in concordance with high expression of the targets or activation of the corresponding pathways in primary tumor samples of the same subtype. CONCLUSIONS: The stratification presented here is robust, captures important features of CRC, and offers valuable insight into functional differences between CRC subtypes. By matching the identified subtypes to cell line panels that have been pharmacologically characterized, it opens up new possibilities for the development and application of targeted therapies for defined CRC patient sub-populations.

Automatic extraction of angiogenesis bioprocess from text.

MOTIVATION: Understanding key biological processes (bioprocesses) and their relationships with constituent biological entities and pharmaceutical agents is crucial for drug design and discovery. One way to harvest such information is searching the literature. However, bioprocesses are difficult to capture because they may occur in text in a variety of textual expressions. Moreover, a bioprocess is often composed of a series of bioevents, where a bioevent denotes changes to one or a group of cells involved in the bioprocess. Such bioevents are often used to refer to bioprocesses in text, which current techniques, relying solely on specialized lexicons, struggle to find. RESULTS: This article presents a range of methods for finding bioprocess terms and events. To facilitate the study, we built a gold standard corpus in which terms and events related to angiogenesis, a key biological process of the growth of new blood vessels, were annotated. Statistics of the annotated corpus revealed that over 36% of the text expressions that referred to angiogenesis appeared as events. The proposed methods respectively employed domain-specific vocabularies, a manually annotated corpus and unstructured domain-specific documents. Evaluation results showed that, while a supervised machine-learning model yielded the best precision, recall and F1 scores, the other methods achieved reasonable performance and less cost to develop. AVAILABILITY: The angiogenesis vocabularies, gold standard corpus, annotation guidelines and software described in this article are available at http://text0.mib.man.ac.uk/~mbassxw2/angiogenesis/ CONTACT: xinglong.wang@gmail.com.

Identification of common predictive markers of in vitro response to the Mek inhibitor selumetinib (AZD6244; ARRY-142886) in human breast cancer and non-small cell lung cancer cell lines.

Selumetinib (AZD6244; ARRY-142886) is a tight-binding, uncompetitive inhibitor of mitogen-activated protein kinase kinases (MEK) 1 and 2 currently in clinical development. We evaluated the effects of selumetinib in 31 human breast cancer cell lines and 43 human non-small cell lung cancer (NSCLC) cell lines to identify characteristics correlating with in vitro sensitivity to MEK inhibition. IC(50) <1 micromol/L (considered sensitive) was seen in 5 of 31 breast cancer cell lines and 15 of 43 NSCLC cell lines, with a correlation between sensitivity and raf mutations in breast cancer cell lines (P = 0.022) and ras mutations in NSCLC cell lines (P = 0.045). Evaluation of 27 of the NSCLC cell lines with Western blots showed no clear association between MEK and phosphoinositide 3-kinase pathway activation and sensitivity to MEK inhibition. Baseline gene expression profiles were generated for each cell line using Agilent gene expression arrays to identify additional predictive markers. Genes associated with differential sensitivity to selumetinib were seen in both histologies, including a small number of genes in which differential expression was common to both histologies. In total, these results suggest that clinical trials of selumetinib in breast cancer and NSCLC might select patients whose tumors harbor raf and ras mutations, respectively.

Transcriptional pathway signatures predict MEK addiction and response to selumetinib (AZD6244).

Selumetinib (AZD6244, ARRY-142886) is a selective, non-ATP-competitive inhibitor of mitogen-activated protein/extracellular signal-regulated kinase kinase (MEK)-1/2. The range of antitumor activity seen preclinically and in patients highlights the importance of identifying determinants of response to this drug. In large tumor cell panels of diverse lineage, we show that MEK inhibitor response does not have an absolute correlation with mutational or phospho-protein markers of BRAF/MEK, RAS, or phosphoinositide 3-kinase (PI3K) activity. We aimed to enhance predictivity by measuring pathway output through coregulated gene networks displaying differential mRNA expression exclusive to resistant cell subsets and correlated to mutational or dynamic pathway activity. We discovered an 18-gene signature enabling measurement of MEK functional output independent of tumor genotype. Where the MEK pathway is activated but the cells remain resistant to selumetinib, we identified a 13-gene signature that implicates the existence of compensatory signaling from RAS effectors other than PI3K. The ability of these signatures to stratify samples according to functional activation of MEK and/or selumetinib sensitivity was shown in multiple independent melanoma, colon, breast, and lung tumor cell lines and in xenograft models. Furthermore, we were able to measure these signatures in fixed archival melanoma tumor samples using a single RT-qPCR-based test and found intergene correlations and associations with genetic markers of pathway activity to be preserved. These signatures offer useful tools for the study of MEK biology and clinical application of MEK inhibitors, and the novel approaches taken may benefit other targeted therapies.

Identification of biomarkers in human head and neck tumor cell lines that predict for in vitro sensitivity to gefitinib.

Potential biomarkers were identified for in vitro sensitivity to the epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor gefitinib in head and neck cancer. Gefitinib sensitivity was determined in cell lines, followed by transcript profiling coupled with a novel pathway analysis approach. Eleven cell lines were highly sensitive to gefitinib (inhibitor concentration required to give 50% growth inhibition [GI(50)] < 1 microM), three had intermediate sensitivity (GI(50) 1-7 microM), and six were resistant (GI(50) > 7 microM); an exploratory principal component analysis revealed a separation between the genomic profiles of sensitive and resistant cell lines. Subsequently, a hypothesis-driven analysis of Affymetrix data (Affymetrix, Inc., Santa Clara, CA, USA) revealed higher mRNA levels for E-cadherin (CDH1); transforming growth factor, alpha (TGF-alpha); amphiregulin (AREG); FLJ22662; EGFR; p21-activated kinase 6 (PAK6); glutathione S-transferase Pi (GSTP1); and ATP-binding cassette, subfamily C, member 5 (ABCC5) in sensitive versus resistant cell lines. A hypothesis-free analysis identified 46 gene transcripts that were strongly differentiated, seven of which had a known association with EGFR and head and neck cancer (human EGF receptor 3 [HER3], TGF-alpha, CDH1, EGFR, keratin 16 [KRT16], fibroblast growth factor 2 [FGF2], and cortactin [CTTN]). Polymerase chain reaction (PCR) and enzyme-linked immunoabsorbant assay analysis confirmed Affymetrix data, and EGFR gene mutation, amplification, and genomic gain correlated strongly with gefitinib sensitivity. We identified biomarkers that predict for in vitro responsiveness to gefitinib, seven of which have known association with EGFR and head and neck cancer. These in vitro predictive biomarkers may have potential utility in the clinic and warrant further investigation.