Direct Evaluation of Treatment Response in Brain Metastatic Disease with Deep Neuroevolution.

Cancer centers have an urgent and unmet clinical and research need for AI that can guide patient management. A core component of advancing cancer treatment research is assessing response to therapy. Doing so by hand, for example, as per RECIST or RANO criteria, is tedious and time-consuming, and can miss important tumor response information. Most notably, the prevalent response criteria often exclude lesions, the non-target lesions, altogether. We wish to assess change in a holistic fashion that includes all lesions, obtaining simple, informative, and automated assessments of tumor progression or regression. Because genetic sub-types of cancer can be fairly specific and patient enrollment in therapy trials is often limited in number and accrual rate, we wish to make response assessments with small training sets. Deep neuroevolution (DNE) is a novel radiology artificial intelligence (AI) optimization approach that performs well on small training sets. Here, we use a DNE parameter search to optimize a convolutional neural network (CNN) that predicts progression versus regression of metastatic brain disease. We analyzed 50 pairs of MRI contrast-enhanced images as our training set. Half of these pairs, separated in time, qualified as disease progression, while the other 25 image pairs constituted regression. We trained the parameters of a CNN via "mutations" that consisted of random CNN weight adjustments and evaluated mutation "fitness" as summed training set accuracy. We then incorporated the best mutations into the next generation's CNN, repeating this process for approximately 50,000 generations. We applied the CNNs to our training set, as well as a separate testing set with the same class balance of 25 progression and 25 regression cases. DNE achieved monotonic convergence to 100% training set accuracy. DNE also converged monotonically to 100% testing set accuracy. We have thus shown that DNE can accurately classify brain metastatic disease progression versus regression. Future work will extend the input from 2D image slices to full 3D volumes, and include the category of "no change." We believe that an approach such as ours can ultimately provide a useful and informative complement to RANO/RECIST assessment and volumetric AI analysis.

The effect of surgery on radiation necrosis in irradiated brain metastases: extent of resection and long-term clinical and radiographic outcomes.

OBJECTIVE: Radiation therapy is a cornerstone of brain metastasis (BrM) management but carries the risk of radiation necrosis (RN), which can require resection for palliation or diagnosis. We sought to determine the relationship between extent of resection (EOR) of pathologically-confirmed RN and postoperative radiographic and symptomatic outcomes. METHODS: A single-center retrospective review was performed at an NCI-designated Comprehensive Cancer Center to identify all surgically-resected, previously-irradiated necrotic BrM without admixed recurrent malignancy from 2003 to 2018. Clinical, pathologic and radiographic parameters were collected. Volumetric analysis determined EOR and longitudinally evaluated perilesional T2-FLAIR signal preoperatively, postoperatively, and at 3-, 6-, 12-, and 24-months postoperatively when available. Rates of time to 50% T2-FLAIR reduction was calculated using cumulative incidence in the competing risks setting with last follow-up and death as competing events. The Spearman method was used to calculate correlation coefficients, and continuous variables for T2-FLAIR signal change, including EOR, were compared across groups. RESULTS: Forty-six patients were included. Most underwent prior stereotactic radiosurgery with or without whole-brain irradiation (N = 42, 91%). Twenty-seven operations resulted in gross-total resection (59%; GTR). For the full cohort, T2-FLAIR edema decreased by a mean of 78% by 6 months postoperatively that was durable to last follow-up (p < 0.05). EOR correlated with edema reduction at last follow-up, with significantly greater T2-FLAIR reduction with GTR versus subtotal resection (p < 0.05). Among surviving patients, a significant proportion were able to decrease their steroid use: steroid-dependency decreased from 54% preoperatively to 15% at 12 months postoperatively (p = 0.001). CONCLUSIONS: RN resection conferred both durable T2-FLAIR reduction, which correlated with EOR; and reduced steroid dependency.

Method Development and Application of an Accelerated Solution Stability Screen for Drug Discovery.

An important aspect to understand about an experimental molecule in drug discovery is its stability in solution. A compound that degrades might be eliciting its apparent effect via a degradation product, so it is important to understand the solution stability profile of a compound early on in the drug discovery process. Improvements and application of a streamlined, higher-throughput method for testing solution stability to support drug discovery are described. Mass spectrometry detection has been incorporated into the screen to allow for the identification of degradation products. The amount of compound needed for the assay has been significantly reduced using 10 mM DMSO solutions instead of solid material. The buffers used in the screen provide the stability-pH profile of compounds with additional variations to assess liabilities under oxidizing and reducing conditions. In this article, we discuss the method development, screen validation, guidelines for result interpretation, and results for a set of marketed drugs to illustrate the application of the screen.

Designing of advanced smart medical stocking using stress-memory polymeric filaments for pressure control and massaging.

Compression treatment for the patients with chronic disorders such as venous ulcers and varicose veins needs the proper and adequate level of pressure sustainability. This has been a great challenge for health practitioners and stocking manufacturers even till today. There is an imperious need of any research, where internal compression pressure can be controlled or readjusted externally. In line with this, for the first time this study is focused mainly to design and optimize the smart stocking structure by integrating the stress-memory polymeric filament as a main load bearing element. Six different structures were employed to prepare the stocking fabric tubes. All the structures were investigated for pressure analysis and studied the effect of physical parameters such as temperature, strain, and leg radius. It is possible to control the level of massage effect by varying the stocking structures. An empirical relationship is derived, which provides the knowledge for how to control the stocking pressure with structural modifications like never done before. The effect of massage function on blood flow velocity in the popliteal vein on lower limb was objectively measured by Doppler ultrasound scanning. This study also sheds the insight of stocking structural modification for pressure control and provide the benchmark for achieving the efficient compression. This advanced stress-memory polymeric filaments based multifunctional compression stocking provides static pressure, massage effect, and easy size fitting in a more controlled manner for smart compression therapy.

Methionine sulfoximine supplementation enhances productivity in GS-CHOK1SV cell lines through glutathione biosynthesis.

In Lonza Biologics' GS Gene Expression System™, recombinant protein-producing GS-CHOK1SV cell lines are generated by transfection with an expression vector encoding both GS and the protein product genes followed by selection in MSX and glutamine-free medium. MSX is required to inhibit endogenous CHOK1SV GS, and in effect create a glutamine auxotrophy in the host that can be complemented by the expression vector encoded GS in selected cell lines. However, MSX is not a specific inhibitor of GS as it also inhibits the activity of GCL (a key enzyme in the glutathione biosynthesis pathway) to a similar extent. Glutathione species (GSH and GSSG) have been shown to provide both oxidizing and reducing equivalents to ER-resident oxidoreductases, raising the possibility that selection for transfectants with increased GCL expression could result in the isolation of GS-CHOKISV cell lines with improved capacity for recombinant protein production. In this study we have begun to address the relationship between MSX supplementation, the amount of intracellular GCL subunit and mAb production from a panel of GS-CHOK1SV cell lines. We then evaluated the influence of reduced GCL activity on batch culture of an industrially relevant mAb-producing GS-CHOK1SV cell line. To the best of our knowledge, this paper describes for the first time the change in expression of GCL subunits and recombinant mAb production in these cell lines with the degree of MSX supplementation in routine subculture. Our data also shows that partial inhibition of GCL activity in medium containing 75 µM MSX increases mAb productivity, and its more specific inhibitor BSO used at a concentration of 80 µM in medium increases the specific rate of mAb production eight-fold and the concentration in harvest medium by two-fold. These findings support a link between the inhibition of glutathione biosynthesis and recombinant protein production in industrially relevant systems and provide a process-driven method for increasing mAb productivity from GS-CHOK1SV cell lines. © 2016 American Institute of Chemical Engineers Biotechnol. Prog., 33:17-25, 2017.

The discovery of potent and long-acting oral factor Xa inhibitors with tetrahydroisoquinoline and benzazepine P4 motifs.

The discovery and evaluation of potent and long-acting oral sulfonamidopyrrolidin-2-one factor Xa inhibitors with tetrahydroisoquinoline and benzazepine P4 motifs are described. Unexpected selectivity issues versus tissue plasminogen activator in the former series were addressed in the later, delivering a robust candidate for progression towards clinical studies.

New thiopyrazolo[3,4-d]pyrimidine derivatives as anti-mycobacterial agents.

The multiple parallel synthesis of a series of N,S-bis-alkylated thiopyrazolo[3,4-d]pyrimidines, based on sequential S- then N-alkylation, is reported. These compounds showed significant anti-mycobacterial activity (MICs down to 2mug/ml) and their potential as significant drug-like leads is substantiated through cytotoxicity evaluation and in silico profiling.