Combining Data-Driven and Structure-Based Approaches in Designing Dual PARP1-BRD4 Inhibitors for Breast Cancer Treatment.

Poly(ADP-ribose) polymerase 1 (PARP1) inhibitors have revolutionized the treatment of many cancers with DNA-repairing deficiencies via synthetic lethality. Advocated by the polypharmacology concept, recent evidence discovered that a significantly synergistic effect in increasing the death of cancer cells was observed by simultaneously perturbating the enzymatic activities of bromodomain-containing protein 4 (BRD4) and PARP1. Here, we developed a novel cheminformatics approach combined with a structure-based method aiming to facilitate the design of dual PARP1-BRD4 inhibitors. Instead of linking pharmacophores, the developed approach first identified merged pharmacophores (a pool of amide-containing ring systems), from which phenanthridin-6(5H)-one was further prioritized. Based on this starting point, several small molecules were rationally designed, among which HF4 exhibited low micromolar inhibitory activity against BRD4 and PARP1, particularly exhibiting strong inhibition of BRD4 BD1 with an IC50 value of 204 nM. Furthermore, it demonstrated potent antiproliferative effects against breast cancer gene-deficient and proficient breast cancer cell lines by arresting cell cycle progression and impeding DNA damage repair. Collectively, our systematic efforts to design lead-like molecules have the potential to open doors for the exploration of dual PARP1-BRD4 inhibitors as a promising avenue for breast cancer treatment. Furthermore, the developed approach can be extended to systematically design inhibitors targeting PARP1 and other related targets.

AlphaFold accelerated discovery of psychotropic agonists targeting the trace amine-associated receptor 1.

Artificial intelligence is revolutionizing protein structure prediction, providing unprecedented opportunities for drug design. To assess the potential impact on ligand discovery, we compared virtual screens using protein structures generated by the AlphaFold machine learning method and traditional homology modeling. More than 16 million compounds were docked to models of the trace amine-associated receptor 1 (TAAR1), a G protein-coupled receptor of unknown structure and target for treating neuropsychiatric disorders. Sets of 30 and 32 highly ranked compounds from the AlphaFold and homology model screens, respectively, were experimentally evaluated. Of these, 25 were TAAR1 agonists with potencies ranging from 12 to 0.03 µM. The AlphaFold screen yielded a more than twofold higher hit rate (60%) than the homology model and discovered the most potent agonists. A TAAR1 agonist with a promising selectivity profile and drug-like properties showed physiological and antipsychotic-like effects in wild-type but not in TAAR1 knockout mice. These results demonstrate that AlphaFold structures can accelerate drug discovery.

2-Aryladenine Derivatives as a Potent Scaffold for Adenosine Receptor Antagonists: The 6-Morpholino Derivatives.

A set of 2-aryl-9-H or methyl-6-morpholinopurine derivatives were synthesized and assayed through radioligand binding tests at human A1, A2A, A2B, and A3 adenosine receptor subtypes. Eleven purines showed potent antagonism at A1, A3, dual A1/A2A, A1/A2B, or A1/A3 adenosine receptors. Additionally, three compounds showed high affinity without selectivity for any specific adenosine receptor. The structure-activity relationships were made for this group of new compounds. The 9-methylpurine derivatives were generally less potent but more selective, and the 9H-purine derivatives were more potent but less selective. These compounds can be an important source of new biochemical tools and/or pharmacological drugs.

PD-1 blockade plus COX inhibitors in dMMR metastatic colorectal cancer: Clinical, genomic, and immunologic analyses from the PCOX trial.

BACKGROUND: Approximately 20% of patients with DNA mismatch repair deficiency (dMMR) metastatic colorectal cancer do not respond to anti-programmed death-1 (PD-1) ligand therapy, and baseline biomarkers of response are lacking. METHODS: We conducted a phase 2 study to evaluate the efficacy of cyclooxygenase (COX) inhibitors in combination with anti-PD-1 therapy in patients with dMMR metastatic colorectal cancer. The primary endpoint was objective response rate. The secondary endpoints included progression-free survival (PFS), overall survival (OS), disease control rate, duration of response, and safety. FINDINGS: A total of 30 patients were enrolled, and the objective response rate was 73.3%, meeting the predefined endpoint of 68%. The median PFS and median OS were not reached at a median follow-up period of 50.8 months. Disease control was achieved in 28 patients (93.3%). The median duration of response was not reached. The combination was well tolerated. Multiomics analysis revealed that the antigen processing and presentation pathway was positively associated with treatment response and PFS. Higher TAPBP expression was predictive of better PFS (log-rank p = 0.003), and this prognostic significance was confirmed in an immunotherapy validation cohort. CONCLUSIONS: Thus, COX inhibitors combined with PD-1 blockade may be effective and safe treatment options for patients with dMMR metastatic colorectal cancer, and TAPBP may serve as a biomarker for immune checkpoint inhibitor therapy (this study was registered at ClinicalTrials.gov: NCT03638297). FUNDING: Funded by the National Natural Science Foundation of China (81974369) and the program of Guangdong Provincial Clinical Research Center for Digestive Diseases (2020B1111170004).

Targeting urinary calcium oxalate crystallization with inulin-type AOFOS from Aspidopterys obcordata Hemsl. for the management of rat urolithiasis.

ETHNOPHARMACOLOGICAL RELEVANCE: Calcium oxalate crystals play a key role in the development and recurrence of kidney stones (also known as urolithiasis); thus, inhibiting the formation of these crystals is a central focus of urolithiasis prevention and treatment. Previously, we reported the noteworthy in vitro inhibitory effects of Aspidopterys obcordata fructo oligosaccharide (AOFOS), an active polysaccharide of the traditional Dai medicine Aspidopterys obcordata Hemsl. (commonly known as Hei Gai Guan), on the growth of calcium oxalate crystals. AIM OF THE STUDY: To investigated the effectiveness and mechanism of AOFOS in treating kidney stones. MATERIALS AND METHODS: A kidney stones rats model was developed, followed by examining AOFOS transport dynamics and effectiveness in live rats. Additionally, a correlation between the polysaccharide and calcium oxalate crystals was studied by combining crystallization experiments with density functional theory calculations. RESULTS: The results showed that the polysaccharide was transported to the urinary system. Furthermore, their accumulation was inhibited by controlling their crystallization and modulating calcium ion and oxalate properties in the urine. Consequently, this approach helped effectively prevent kidney stone formation in the rats. CONCLUSIONS: The present study emphasized the role of the polysaccharide AOFOS in modulating crystal properties and controlling crystal growth, providing valuable insights into their potential therapeutic use in managing kidney stone formation.

Neoadjuvant Chemotherapy With Oxaliplatin and Fluoropyrimidine Versus Upfront Surgery for Locally Advanced Colon Cancer: The Randomized, Phase III OPTICAL Trial.

PURPOSE: The role of neoadjuvant chemotherapy (NAC) in colon cancer remains unclear. This trial investigated whether 3 months of modified infusional fluorouracil, leucovorin, and oxaliplatin (mFOLFOX6) or capecitabine and oxaliplatin (CAPOX) as NAC could improve outcomes in patients with locally advanced colon cancer versus upfront surgery. PATIENTS AND METHODS: OPTICAL was a randomized, phase III trial in patients with clinically staged locally advanced colon cancer (T3 with extramural spread into the mesocolic fat ≥5 mm or T4). Patients were randomly assigned 1:1 to receive six preoperative cycles of mFOLFOX6 or four cycles of CAPOX, followed by surgery and adjuvant chemotherapy (NAC group), or immediate surgery and the physician's choice of adjuvant chemotherapy (upfront surgery group). The primary end point was 3-year disease-free survival (DFS) assessed in the modified intention-to-treat (mITT) population. RESULTS: Between January 2016 and April 2021, of the 752 patients enrolled, 744 patients were included in the mITT analysis (371 in the NAC group; 373 in the upfront surgery group). At a median follow-up of 48.0 months (IQR, 46.0-50.1), 3-year DFS rates were 82.1% in the NAC group and 77.5% in the upfront surgery group (stratified hazard ratio [HR], 0.74 [95% CI, 0.54 to 1.03]). The R0 resection was achieved in 98% of patients who underwent surgery in both groups. Compared with upfront surgery, NAC resulted in a 7% pathologic complete response rate (pCR), significantly lower rates of advanced tumor staging (pT3-4: 77% v 94%), lymph node metastasis (pN1-2: 31% v 46%), and potentially improved overall survival (stratified HR, 0.44 [95% CI, 0.25 to 0.77]). CONCLUSION: NAC with mFOLFOX6 or CAPOX did not show a significant DFS benefit. However, this neoadjuvant approach was safe, resulted in substantial pathologic downstaging, and appears to be a viable therapeutic option for locally advanced colon cancer.

Identification of differential biological activity and synergy between the PARP inhibitor rucaparib and its major metabolite.

The (poly)pharmacology of drug metabolites is seldom comprehensively characterized in drug discovery. However, some drug metabolites can reach high plasma concentrations and display in vivo activity. Here, we use computational and experimental methods to comprehensively characterize the kinase polypharmacology of M324, the major metabolite of the PARP1 inhibitor rucaparib. We demonstrate that M324 displays unique PLK2 inhibition at clinical concentrations. This kinase activity could have implications for the efficacy and safety of rucaparib and therefore warrants further clinical investigation. Importantly, we identify synergy between the drug and the metabolite in prostate cancer models and a complete reduction of α-synuclein accumulation in Parkinson's disease models. These activities could be harnessed in the clinic or open new drug discovery opportunities. The study reported here highlights the importance of characterizing the activity of drug metabolites to comprehensively understand drug response in the clinic and exploit our current drug arsenal in precision medicine.

Targeting the NAT10/NPM1 axis abrogates PD-L1 expression and improves the response to immune checkpoint blockade therapy.

BACKGROUND: PD-1/PD-L1 play a crucial role as immune checkpoint inhibitors in various types of cancer. Although our previous study revealed that NPM1 was a novel transcriptional regulator of PD-L1 and stimulated the transcription of PD-L1, the underlying regulatory mechanism remains incompletely characterized. METHODS: Various human cancer cell lines were used to validate the role of NPM1 in regulating the transcription of PD-L1. The acetyltransferase NAT10 was identified as a facilitator of NPM1 acetylation by coimmunoprecipitation and mass spectrometry. The potential application of combined NAT10 inhibitor and anti-CTLA4 treatment was evaluated by an animal model. RESULTS: We demonstrated that NPM1 enhanced the transcription of PD-L1 in various types of cancer, and the acetylation of NPM1 played a vital role in this process. In particular, NAT10 facilitated the acetylation of NPM1, leading to enhanced transcription and increased expression of PD-L1. Moreover, our findings demonstrated that Remodelin, a compound that inhibits NAT10, effectively reduced NPM1 acetylation, leading to a subsequent decrease in PD-L1 expression. In vivo experiments indicated that Remodelin combined with anti-CTLA-4 therapy had a superior therapeutic effect compared with either treatment alone. Ultimately, we verified that the expression of NAT10 exhibited a positive correlation with the expression of PD-L1 in various types of tumors, serving as an indicator of unfavorable prognosis. CONCLUSION: This study suggests that the NAT10/NPM1 axis is a promising therapeutic target in malignant tumors.

Biomarkers of Pathologic Complete Response to Neoadjuvant Immunotherapy in Mismatch Repair-Deficient Colorectal Cancer.

PURPOSE: Immune checkpoint inhibitors (ICI) have become the standard of care for patients with mismatch repair-deficient/microsatellite instability-high (dMMR/MSI-H) colorectal cancer. However, biomarkers of response to ICI are still lacking. EXPERIMENTAL DESIGN: Forty-two patients with dMMR colorectal cancer treated with neoadjuvant PD-1 blockade were prospectively enrolled. To identify biomarkers of pathologic complete response (pCR) to neoadjuvant therapy, we analyzed genomic and transcriptomic profiles based on next-generation sequencing, and immune cell density based on multiplex immunofluorescence (mIF) staining. An integrated analysis of single-cell RNA sequencing from our previous study and GSE178341, as well as mIF was performed to further explore the significance of the tumor microenvironment (TME) on pCR response. RESULTS: The tumor mutation burden of both tumor tissue and plasma blood samples was comparable between the pCR and non-pCR groups, while HLA-DQA1 and HLA-DQB1 were significantly overexpressed in the pCR group. Gene signature enrichment analysis showed that pathways including T-cell receptor pathway, antigen presentation pathway were significantly enriched in the pCR group. In addition, higher pre-existing CD8+ T-cell density was associated with pCR response (767.47 per.mm2 vs. 326.64 per.mm2, P = 0.013 Wilcoxon test). Further integrated analysis showed that CD8+ T cells with low PD-1 expression (PD-1lo CD8+ T cells) expressing high levels of TRGC2, CD160, and KLRB1 and low levels of proliferated and exhausted genes were significantly associated with pCR response. CONCLUSIONS: Immune-associated transcriptomic features, particularly CD8+ T cells were associated with pCR response to ICI in dMMR colorectal cancer. Heterogeneity of TME within dMMR colorectal cancer may help to discriminate patients with complete response to neoadjuvant ICI.

Discovery and biological evaluation of novel dual PTP1B and ACP1 inhibitors for the treatment of insulin resistance.

In this study, a virtual screening pipeline comprising ligand-based and structure-based approaches was established and applied for the identification of dual PTP1B and ACP1 inhibitors. As a result, a series of benzoic acid derivatives was discovered, and compound H3 and S6 demonstrated PTP1B and ACP1 inhibitory activity, with IC50 values of 3.5 and 8.2 µM for PTP1B, and 2.5 and 5.2 µM for ACP1, respectively. Molecular dynamics simulations illustrated that H3 interacted with critical residues in the active site, such as Cys215 and Arg221 for PTP1B, and Cys17 and Arg18 for ACP1. Enzymatic kinetic research indicated that identified inhibitors competitively inhibited PTP1B and ACP1. Additionally, cellular assays demonstrated that H3 and S6 effectively increased glucose uptake in insulin-resistant HepG2 cells while displaying very limited cytotoxicity at their effective concentrations. In summary, H3 and S6 represent novel dual-target inhibitors for PTP1B and ACP1, warranting further investigation as potential agents for the treatment of diabetes.

Capecitabine maintenance therapy in metastatic colorectal cancer patients with no evidence of disease: CAMCO trial.

Background: In patients with metastatic colorectal cancer (mCRC) exhibiting no evidence of disease (NED), this study assessed the efficacy and safety of capecitabine maintenance therapy. Methods: The single-arm, phase II CAMCO trial enrolled mCRC-NED patients after first-line treatment, administering oral capecitabine maintenance for 1 year. Results: A total of 93 patients were enrolled. The primary end point, 3-year disease-free survival, yielded a rate of 51.6% (95% CI: 41.3-62.0%). Secondary end points included a 3-year overall survival rate of 83.9% (95% CI: 76.3-91.5%). Grade 3 adverse events (AE) were observed in seven patients (7.5%). Predominantly grade 1 and 2, the most common AE was hand-foot syndrome. Conclusion: In mCRC-NED patients, capecitabine maintenance demonstrated a manageable 3-year disease-free survival rate of 51.6%, accompanied by manageable AEs. Clinical Trial Registration: NCT01880658 (ClinicalTrials.gov).

A machine learning and live-cell imaging tool kit uncovers small molecules induced phospholipidosis.

Drug-induced phospholipidosis (DIPL), characterized by excessive accumulation of phospholipids in lysosomes, can lead to clinical adverse effects. It may also alter phenotypic responses in functional studies using chemical probes. Therefore, robust methods are needed to predict and quantify phospholipidosis (PL) early in drug discovery and in chemical probe characterization. Here, we present a versatile high-content live-cell imaging approach, which was used to evaluate a chemogenomic and a lysosomal modulation library. We trained and evaluated several machine learning models using the most comprehensive set of publicly available compounds and interpreted the best model using SHapley Additive exPlanations (SHAP). Analysis of high-quality chemical probes extracted from the Chemical Probes Portal using our algorithm revealed that closely related molecules, such as chemical probes and their matched negative controls can differ in their ability to induce PL, highlighting the importance of identifying PL for robust target validation in chemical biology.

China special issue on gastrointestinal tumors-Radiological features of pathological complete response in mismatch repair deficient colorectal cancer after neoadjuvant PD-1 blockade: A post hoc analysis of the PICC phase II trial.

Neoadjuvant programmed cell death protein 1 (PD-1) blockade exhibits promising efficacy in patients with mismatch repair deficient (dMMR) colorectal cancer (CRC). However, discrepancies between radiological and histological findings have been reported in the PICC phase II trial (NCT03926338). Therefore, we strived to discern radiological features associated with pathological complete response (pCR) based on computed tomography (CT) images. Data were obtained from the PICC trial that included 36 tumors from 34 locally advanced dMMR CRC patients, who received neoadjuvant PD-1 blockade for 3 months. Among the 36 tumors, 28 (77.8%) tumors achieved pCR. There were no statistically significant differences in tumor longitudinal diameter, the percentage change in tumor longitudinal diameter from baseline, primary tumor sidedness, clinical stage, extramural venous invasion status, intratumoral calcification, peritumoral fat infiltration, intestinal fistula and tumor necrosis between the pCR and non-pCR tumors. Otherwise, tumors with pCR had smaller posttreatment tumor maximum thickness (median: 10 mm vs 13 mm, P = .004) and higher percentage decrease in tumor maximum thickness from baseline (52.9% vs 21.6%, P = .005) compared to non-pCR tumors. Additionally, a higher proportion of the absence of vascular sign (P = .003, odds ratio [OR] = 25.870 [95% CI, 1.357-493.110]), nodular sign (P < .001, OR = 189.000 [95% CI, 10.464-3413.803]) and extramural enhancement sign (P = .003, OR = 21.667 [2.848-164.830]) was observed in tumors with pCR. In conclusion, these CT-defined radiological features may have the potential to serve as valuable tools for clinicians in identifying patients who have achieved pCR after neoadjuvant PD-1 blockade, particularly in individuals who are willing to adopt a watch-and-wait strategy.

Genome-Wide Identification and Expression Analysis of the VILLIN Gene Family in Soybean.

The VILLIN (VLN) protein is an important regulator of the actin cytoskeleton, which orchestrates many developmental processes and participates in various biotic and abiotic responses in plants. Although the VLN gene family and their potential functions have been analyzed in several plants, knowledge of VLN genes in soybeans and legumes remains rather limited. In this study, a total of 35 VLNs were characterized from soybean and five related legumes. Combining with the VLN sequences from other nine land plants, we categorized the VLN gene family into three groups according to phylogenetic relationships. Further detailed analysis of the soybean VLNs indicated that the ten GmVLNs were distributed on 10 of the 20 chromosomes, and their gene structures and protein motifs showed high group specificities. The expression pattern analysis suggested that most GmVLNs are widely expressed in various tissues, but three members have a very high level in seeds. Moreover, we observed that the cis-elements enriched in the promoters of GmVLNs are mainly related to abiotic stresses, hormone signals, and developmental processes. The largest number of cis-elements were associated with light responses, and two GmVLNs, GmVLN5a, and GmVLN5b were significantly increased under the long light condition. This study not only provides some basic information about the VLN gene family but also provides a good reference for further characterizing the diverse functions of VLN genes in soybeans.

Remodeling of the immune and stromal cell compartment by PD-1 blockade in mismatch repair-deficient colorectal cancer.

Immune checkpoint inhibitor (ICI) therapy can induce complete responses in mismatch repair-deficient and microsatellite instability-high (d-MMR/MSI-H) colorectal cancers (CRCs). However, the underlying mechanism for pathological complete response (pCR) to immunotherapy has not been completely understood. We utilize single-cell RNA sequencing (scRNA-seq) to investigate the dynamics of immune and stromal cells in 19 patients with d-MMR/MSI-H CRC who received neoadjuvant PD-1 blockade. We found that in tumors with pCR, there is a concerted decrease in CD8+ Trm-mitotic, CD4+ Tregs, proinflammatory IL1B+ Mono and CCL2+ Fibroblast following treatment, while the proportions of CD8+ Tem, CD4+ Th, CD20+ B, and HLA-DRA+ Endothelial cells increase. Proinflammatory features in the tumor microenvironment mediate the persistence of residual tumors by modulating CD8+ T cells and other response-associated immune cell populations. Our study provides valuable resources and biological insights into the mechanism of successful ICI therapy and potential targets for improving treatment efficacy.

A comparison of traditional plant knowledge between Daman people and Tibetans in Gyirong River Valley, Tibet, China.

BACKGROUND: By comparing the differences in plant use between various cultures or regions, we can gain a better understanding of traditional knowledge of plant use among different groups, which may lead to a more objective understanding. Even though the Tibetan and Daman people live in the same ecosystem in Gyirong town, China, their cultural backgrounds and livelihoods differ. Therefore, the objective of this study is to document the traditional knowledge of plant use among the Daman people and compare it with the local Tibetan knowledge of plant use. By doing so, we aim to explore the relationship between plant selection and use and the cultural backgrounds of different groups. METHODS: During fieldwork, ethnobotanical data were collected using various methods including free listings, key informant interviews, and semi-structured interviews. To quantify the importance of plant species in the Daman people's culture, the culture importance index, informant consensus factor index, and The Index of Agreement on Species consensus (IASc) were used. In addition, we cited previous ethnobotanical survey data from the Tibetan in Gyirong. To more comprehensively compare the differences in plant use between the Daman and Tibetan, this study constructed a knowledge network to compare the knowledge differences between the two groups. RESULTS: In this study, traditional knowledge was collected from 32 Daman informants, resulting in a total of 68 species belonging to 39 families mentioned by Daman people and 111 species mentioned by Tibetans. Of these, 58 plants were used by both populations. The plants were classified into 3 categories and 28 subcategories, with 22 identical classes in both groups. The majority of use categories showed a high degree of sharing in both groups, and the Tibetan people had more plant use categories than the Daman people. Five plants with IASc value > 0.5 were identified in both groups: Rhododendron anthopogon D. Don, Artemisia japonica Thunb., Juniperus indica Bertol., Gastrodia elata Blume, and Rheum australe D. Don. The analysis of the knowledge network revealed a 66% overlap between the knowledge of the Daman and the knowledge of the Tibetans. Additionally, the plant knowledge of Tibetan people was found to be richer and more complex than that of the Daman people. However, the Daman people possess 30 unique knowledge items. CONCLUSIONS: From the perspective of plant use, the history of the Daman people's discrete migration on the border between China and Nepal allows them to retain their own knowledge of plant use. The status quo of joining Chinese nationality and settling in Gyirong town allows them to gradually integrate into the local Tibetan society. In summary, despite living in the same ecosystem and biodiversity background, the plant utilization of the Daman people and Tibetans still shows significant differences, which are due to their different cultural backgrounds and social status.

Neoadjuvant versus adjuvant imatinib in primary localized gastrointestinal stromal tumor.

Background: The effect of neoadjuvant therapy (NAT) with imatinib versus upfront resection (UR) followed by adjuvant therapy (AT) with imatinib on the outcomes of gastrointestinal stromal tumors (GIST) is unknown. Methods: This is a retrospective study at a high-volume center. All the patients with primary localized GIST were identified in a hospital database from 2007 to 2021. The endpoints included local recurrence-free survival (LRFS), distance recurrence-free survival (DRFS), and overall survival (OS). Cox regression was used to perform multivariate survival analyses. The sensitivity analysis was conducted with the inverse probability of treatment weighting (IPTW) method. Results: A total of 211 patients were included (Group A: UR + AT, n=140; Group B: NAT + resection + AT, n=71). In the entire cohort, 5-year DRFS, LRFS, and OS were 85.6%, 90.7%, and 92.5%, respectively. In the multivariate analysis, better DRFS was linked to NAT, tumor size of 5 cm, and AT. Sixteen patients (11.4%) in Group A and 1 (1.4%) in Group B had distant recurrences after AT discontinuation. The sensitivity analysis by IPTW provided approximately similar results. An interaction effect was observed between NAT and tumor location on DRFS. In non-gastric GISTs, NAT was associated with better DRFS [hazard ratio =0.131, 95% confidence interval (CI): 0.017-0.989, P=0.049], which was not the case in gastric GIST (P=0.08). NAT was not independently associated with LRFS or OS. Conclusions: When compared to UR + AT, NAT + resection + AT may reduce the risk of distant recurrence in localized GIST and may be especially beneficial for patients with non-gastric GISTs.

CT-based deep learning model for the prediction of DNA mismatch repair deficient colorectal cancer: a diagnostic study.

BACKGROUND: Stratification of DNA mismatch repair (MMR) status in patients with colorectal cancer (CRC) enables individual clinical treatment decision making. The present study aimed to develop and validate a deep learning (DL) model based on the pre-treatment CT images for predicting MMR status in CRC. METHODS: 1812 eligible participants (training cohort: n = 1124; internal validation cohort: n = 482; external validation cohort: n = 206) with CRC were enrolled from two institutions. All pretherapeutic CT images from three dimensions were trained by the ResNet101, then integrated by Gaussian process regression (GPR) to develop a full-automatic DL model for MMR status prediction. The predictive performance of the DL model was evaluated using the area under the receiver operating characteristic curve (AUC) and then tested in the internal and external validation cohorts. Additionally, the participants from institution 1 were sub-grouped by various clinical factors for subgroup analysis, then the predictive performance of the DL model for identifying MMR status between participants in different groups were compared. RESULTS: The full-automatic DL model was established in the training cohort to stratify the MMR status, which presented promising discriminative ability with the AUCs of 0.986 (95% CI 0.971-1.000) in the internal validation cohort and 0.915 (95% CI 0.870-0.960) in the external validation cohort. In addition, the subgroup analysis based on the thickness of CT images, clinical T and N stages, gender, the longest diameter, and the location of tumors revealed that the DL model showed similar satisfying prediction performance. CONCLUSIONS: The DL model may potentially serve as a noninvasive tool to facilitate the pre-treatment individualized prediction of MMR status in patients with CRC, which could promote the personalized clinical-making decision.

canSAR: update to the cancer translational research and drug discovery knowledgebase.

canSAR (https://cansar.ai) is the largest public cancer drug discovery and translational research knowledgebase. Now hosted in its new home at MD Anderson Cancer Center, canSAR integrates billions of experimental measurements from across molecular profiling, pharmacology, chemistry, structural and systems biology. Moreover, canSAR applies a unique suite of machine learning algorithms designed to inform drug discovery. Here, we describe the latest updates to the knowledgebase, including a focus on significant novel data. These include canSAR's ligandability assessment of AlphaFold; mapping of fragment-based screening data; and new chemical bioactivity data for novel targets. We also describe enhancements to the data and interface.