Search

Acute Promyelocytic Leukemia (APL) is a subtype of Acute Myeloid Leukemia (AML), classified by a translocation between chromosomes 15 and 17 [t(15;17)], that is notably distinguished clinically by a rapidly progressive and fatal course. Due to the acute nature of its presentation, prompt and accurate diagnosis is required to initiate appropriate therapy that can be curative. However, the gold standard genetic tests can take days to confirm a diagnosis and thus therapy is often initiated on high clinical suspicion based on both clinical presentation as well as direct visualization of the peripheral smear. While there are described cellular morphological features that distinguish APL, there is still considerable difficulty in diagnosing APL from direct visualization of a peripheral smear by a hematopathologist. We hypothesized that deep learning pattern recognition would have greater discriminatory power and consistency compared to humans to distinguish t(15;17) translocation positive APL from t(15;17) translocation negative AML. To best tackle the problem of diagnosing APL rapidly from a peripheral smear, study patients with APL and AML were identified via retrospective chart review from a list of confirmed FISH t(15;17)-positive (n = 34) and -negative (n = 72) patients presenting at The Johns Hopkins Hospital (JHH). Additional inclusion criteria included new disease diagnosis, no prior treatment, and availability of peripheral blood smear image uploaded to CellaVision. Patients were separated into a discovery cohort presenting prior to 1/2019 (APL, n = 22; AML, n=60) and a validation cohort presenting on or after 1/2019 (APL, n = 12; AML, n = 12). A multiple-instance deep learning model employing convolutional layers at the per-cell level (Figure 1A) was trained on the discovery cohort and then tested on the independent prospective validation cohort to assess generalizability of the model. When compared to 10 academic clinicians (denoted with red +) who consisted of leukemia-treating hematologists, oncologists, and hematopathologists, the deep learning model was equivalent or outperformed 9/10 readers (Figure 1B) with an AUC of 0.861. We further looked at the performance of using proportion of promyelocytes (per CellaVision classification) as a biomarker of APL which had an AUC of 0.611. Finally, we applied integrated gradients, a method by which to extract per-pixel importance to the classification probability to identify and understand the morphological features the model was learning and using to distinguish APL (Figure 1C). We noted that the appearance of the chromatin in the non-APL leukemias was more dispersed and focused at the edge of the cell whereas in APL, the chromatin was more condensed and focused at the center of the cell. These morphological features, taught to us by the model, have not been previously reported in the literature as being useful for distinguishing APL from non-APL. Our work presents a deep learning model capable of rapid and accurate diagnosis of APL from universally available peripheral smears. In addition, explainable artificial intelligence is provided for biological insights to facilitate clinical management and reveal morphological concepts previously unappreciated in APL. The deep learning framework we have delineated is applicable to any diagnostic pipeline that can leverage a peripheral blood smear, potentially allowing for efficient diagnosis and early treatment of disease. Figure 1. Disclosures Streiff: Bayer: Consultancy, Speakers Bureau; Dispersol: Consultancy; BristolMyersSquibb: Consultancy; Janssen: Consultancy, Research Funding; Pfizer: Consultancy, Speakers Bureau; Portola: Consultancy; Boehringer-Ingelheim: Research Funding; NHLBI: Research Funding; PCORI: Research Funding; NovoNordisk: Research Funding; Sanofi: Research Funding. Moliterno:Pharmessentia: Consultancy; MPNRF: Research Funding. DeZern:MEI: Consultancy; Abbvie: Consultancy; Astex: Research Funding; Celgene: Consultancy, Honoraria. Levis:Astellas: Honoraria, Research Funding; Menarini: Honoraria; Amgen: Honoraria; FujiFilm: Honoraria, Research Funding; Daiichi-Sankyo: Honoraria.

T. gondii is a major opportunistic pathogen chronically infecting nearly one third of the world's population. Due to the high infection and mortality rates in immunocompromised patients and newborns, the extent or magnitude of T. gondii pathogenesis is determined mainly by host-pathogen interactions. T. gondii utilizes specialized secretory proteins to modify host cellular factors and facilitate invasion and replication. This review provides update on the recent progress in this field of research with particular emphasis on the T. gondii secretory proteins and their role in invasion and pathogenesis.

MiRNAs and proteins play important roles in different stages of tumor development and serve as biomarkers for the early diagnosis of cancer. A new algorithm that combines machine learning algorithms and multilayer complex network analysis is hereby proposed to explore the potential diagnostic values of miRNAs and proteins. XGBoost and random forest algorithms were employed to exclude unrelated miRNAs and proteins, and the most significant candidates were retained for the further analysis. Given these candidates’ possible functional relationships to one other, a multilayer complex network was constructed to identify miRNAs and proteins that could serve as biomarkers for breast cancer. Proteins and miRNAs that are nodes in the network were subsequently categorized into two network layers considering their distinct functions. Maximal information coefficient (MIC) was applied to assess intralayer and interlayer connection. The betweenness centrality was used as the first measurement of the importance of the nodes within each single layer. To further characterize the interlayer interaction between miRNAs and proteins, the degree of the nodes was chosen as the second measurement to map their signalling pathways. By combining these two measurements into one score and comparing the difference of the same candidate between normal tissue and cancer tissue, this novel multilayer network analysis could be applied to successfully identify molecules associated with breast cancer.

MiRNAs and proteins play important roles in different stages of breast tumor development and serve as biomarkers for the early diagnosis of breast cancer. A new algorithm that combines machine learning algorithms and multilayer complex network analysis is hereby proposed to explore the potential diagnostic values of miRNAs and proteins. XGBoost and random forest algorithms were employed to screen the most important miRNAs and proteins. Maximal information coefficient was applied to assess intralayer and interlayer connection. A multilayer complex network was constructed to identify miRNAs and proteins that could serve as biomarkers for breast cancer. Proteins and miRNAs that are nodes in the network were subsequently categorized into two network layers considering their distinct functions. The betweenness centrality was used as the first measurement of the importance of the nodes within each single layer. The degree of the nodes was chosen as the second measurement to map their signalling pathways. By combining these two measurements into one score and comparing the difference of the same candidate between normal tissue and cancer tissue, this novel multilayer network analysis could be applied to successfully identify molecules associated with breast cancer.

Rhoptry protein 18 (ROP18) is a major determinant of strain-specific virulence in Toxoplasma gondii. The kinase activity of ROP18 is required for acute virulence, while the aspartate in the catalytic loop of ROP18 is considered essential for phosphoryl transfer. We showed that a single amino acid mutation at the catalytic aspartate residue (D409A mutation) significantly altered ROP18 kinase activity in vitro, and abolished ROP18-mediated ATF6β degradation. Furthermore, the investigated single amino acid mutation in ROP18 led to alternation of subcellular localization of ROP18 protein. Our findings demonstrate that a single amino acid mutation on the proton transport catalytic aspartic acid induced alternations associated with ROP18 protein.

Here, we show that spiroindolone, an effective treatment for plasmodia, is also active against Toxoplasma gondii tachyzoites. In vitro , spiroindolone NITD609 is cidal for tachyzoites (50% inhibitory concentration [IC 50 ], 1μM) and not toxic to human cells at ≥10μM. Two daily oral doses of 100 mg/kg of body weight reduced the parasite burden in mice by 90% ( P = 0.002), measured 3 days after the last dose. This inhibition of T. gondii tachyzoites in vitro and in vivo indicates that spiroindolone is a promising lead candidate for further medicine development.

Through our focused effort to discover new and effective agents against toxoplasmosis, a structure-based drug design approach was used to develop a series of potent inhibitors of the enoyl-acyl carrier protein (ACP) reductase (ENR) enzyme in Toxoplasma gondii (TgENR). Modifications to positions 5 and 4' of the well-known ENR inhibitor triclosan afforded a series of 29 new analogues. Among the resulting compounds, many showed high potency and improved physicochemical properties in comparison with the lead. The most potent compounds 16 a and 16 c have IC50 values of 250 nM against Toxoplasma gondii tachyzoites without apparent toxicity to the host cells. Their IC50 values against recombinant TgENR were found to be 43 and 26 nM, respectively. Additionally, 11 other analogues in this series had IC50 values ranging from 17 to 130 nM in the enzyme-based assay. With respect to their excellent in vitro activity as well as improved drug-like properties, the lead compounds 16 a and 16 c are deemed to be excellent starting points for the development of new medicines to effectively treat Toxoplasma gondii infections.

Triclosan is a potent inhibitor of Toxoplasma gondii enoyl reductase (TgENR), which is an essential enzyme for parasite survival. In view of triclosan's poor druggability, which limits its therapeutic use, a new set of B-ring modified analogs were designed to optimize its physico-chemical properties. These derivatives were synthesized and evaluated by in vitro assay and TgENR enzyme assay. Some analogs display improved solubility, permeability and a comparable MIC50 value to that of triclosan. Modeling of these inhibitors revealed the same overall binding mode with the enzyme as triclosan, but the B-ring modifications have additional interactions with the strongly conserved Asn130.

Toxoplasma gondii persistently infects over two billion people worldwide. It can cause substantial morbidity and mortality. Existing treatments have associated toxicities and hypersensitivity and do not eliminate encysted bradyzoites that recrudesce. New, improved medicines are needed. Transductive peptides carry small molecule cargos across multiple membranes to enter intracellular tachyzoites and encysted bradyzoites. They also carry cargos into retina when applied topically to eyes, and cross blood brain barrier when administered intravenously. Phosphorodiamidate morpholino oligomers (PMO) inhibit gene expression in a sequence-specific manner. Herein, effect of transductive peptide conjugated PMO (PPMO) on tachyzoite protein expression and replication in vitro and in vivo was studied. Initially, sequence-specific PPMO successfully reduced transfected T. gondii ’s fluorescence and luminescence. PPMO directed against T. gondii ’s dihydrofolate reductase (DHFR), an enzyme necessary for folate synthesis, limited tachyzoite replication. Rescue with exogenous folate demonstrated DHFR PPMO‘s specificity. PPMO directed against enoyl-ACP reductase (ENR), an enzyme of type II fatty acid synthesis that is structurally distinct in T. gondii from ENR in mammalian cells was investigated. PPMO directed against plant-like Apetela 2 (AP2) domain transcription factor XI-3 (AP2XI-3), not present in human cells, was characterized. ENR and AP2XI-3 PPMO each restricted intracellular parasite replication validating these molecular targets in tachyzoites. DHFR-specific PPMO administered to infected mice diminished parasite burden. Thus, these antisense oligomers are a versatile approach to validate T. gondii molecular targets, reduce essential T. gondii proteins in vitro and in vivo, and have potential for development as curative medicines.