Safety and efficacy analysis of neoadjuvant pertuzumab, trastuzumab and standard chemotherapy for HER2-positive early breast cancer: real-world data from NeoPowER study.

BACKGROUND: The addition of pertuzumab (P) to trastuzumab (H) and standard chemotherapy (CT) as neoadjuvant treatment (NaT) for patients with HER2 + breast cancer (BC), has shown to increase the pathological complete response (pCR) rate, without main safety concerns. The aim of NeoPowER trial is to evaluate safety and efficacy of P + H + CT in a real-world population. METHODS: We retrospectively reviewed the medical records of stage II-III, HER2 + BC patients treated with NaT: who received P + H + CT (neopower group) in 5 Emilia Romagna institutions were compared with an historical group who received H + CT (control group). The primary endpoint was the safety, secondary endpoints were pCR rate, DRFS and OS and their correlation to NaT and other potential variables. RESULTS: 260 patients were included, 48% received P + H + CT, of whom 44% was given anthraciclynes as part of CT, compared to 83% in the control group. The toxicity profile was similar, excluding diarrhea more frequent in the neopower group (20% vs. 9%). Three patients experienced significant reductions in left ventricular ejection fraction (LVEF), all receiving anthracyclines. The pCR rate was 46% (P + H + CT) and 40% (H + CT) (p = 0.39). The addition of P had statistically correlation with pCR only in the patients receiving anthra-free regimens (OR = 3.05,p = 0.047). Preoperative use of anthracyclines (OR = 1.81,p = 0.03) and duration of NaT (OR = 1.18,p = 0.02) were statistically related to pCR. 12/21 distant-relapse events and 14/17 deaths occurred in the control group. Patients who achieve pCR had a significant increase in DRFS (HR = 0.23,p = 0.009). CONCLUSIONS: Adding neoadjuvant P to H and CT is safe. With the exception of diarrhea, rate of adverse events of grade > 2 did not differ between the two groups. P did not increase the cardiotoxicity when added to H + CT, nevertheless in our population all cardiac events occurred in patients who received anthracycline-containing regimens. Not statistically significant, higher pCR rate is achievable in patients receiving neoadjuvant P + H + CT. The study did not show a statistically significant correlation between the addition of P and long-term outcomes.

Node-degree aware edge sampling mitigates inflated classification performance in biomedical random walk-based graph representation learning.

Motivation: Graph representation learning is a family of related approaches that learn low-dimensional vector representations of nodes and other graph elements called embeddings. Embeddings approximate characteristics of the graph and can be used for a variety of machine-learning tasks such as novel edge prediction. For many biomedical applications, partial knowledge exists about positive edges that represent relationships between pairs of entities, but little to no knowledge is available about negative edges that represent the explicit lack of a relationship between two nodes. For this reason, classification procedures are forced to assume that the vast majority of unlabeled edges are negative. Existing approaches to sampling negative edges for training and evaluating classifiers do so by uniformly sampling pairs of nodes. Results: We show here that this sampling strategy typically leads to sets of positive and negative examples with imbalanced node degree distributions. Using representative heterogeneous biomedical knowledge graph and random walk-based graph machine learning, we show that this strategy substantially impacts classification performance. If users of graph machine-learning models apply the models to prioritize examples that are drawn from approximately the same distribution as the positive examples are, then performance of models as estimated in the validation phase may be artificially inflated. We present a degree-aware node sampling approach that mitigates this effect and is simple to implement. Availability and implementation: Our code and data are publicly available at https://github.com/monarch-initiative/negativeExampleSelection.

An open source knowledge graph ecosystem for the life sciences.

Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoint resources and abstraction algorithms), and benchmarks (e.g., prebuilt KGs). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 different large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability.

GRAPE for fast and scalable graph processing and random-walk-based embedding.

Graph representation learning methods opened new avenues for addressing complex, real-world problems represented by graphs. However, many graphs used in these applications comprise millions of nodes and billions of edges and are beyond the capabilities of current methods and software implementations. We present GRAPE (Graph Representation Learning, Prediction and Evaluation), a software resource for graph processing and embedding that is able to scale with big graphs by using specialized and smart data structures, algorithms, and a fast parallel implementation of random-walk-based methods. Compared with state-of-the-art software resources, GRAPE shows an improvement of orders of magnitude in empirical space and time complexity, as well as competitive edge- and node-label prediction performance. GRAPE comprises approximately 1.7 million well-documented lines of Python and Rust code and provides 69 node-embedding methods, 25 inference models, a collection of efficient graph-processing utilities, and over 80,000 graphs from the literature and other sources. Standardized interfaces allow a seamless integration of third-party libraries, while ready-to-use and modular pipelines permit an easy-to-use evaluation of graph-representation-learning methods, therefore also positioning GRAPE as a software resource that performs a fair comparison between methods and libraries for graph processing and embedding.