Latest news with #PDE
Yahoo
27-05-2025
- Health
- Yahoo
Pattern Computer Announces Hepatocellular Carcinoma Pattern Identification and Model Creation Study
Study leveraged Pattern Discovery Engine™ to construct highly accurate model to predict whether or not a given cell is cancerous Identified nine genes that are crucial for prediction and may have other uses in diagnostics and/or therapeutics Highlights use of the Pattern Discovery Engine as a hypothesis discovery tool REDMOND, Wash., May 27, 2025 (GLOBE NEWSWIRE) -- Pattern Computer®, Inc. ('Pattern' or 'the Company'), the global leader in Pattern Discovery, today announced the submission for peer review of a study titled "Explainable Molecular Stratification and Co-regulation Pattern Identification in Hepatocellular Carcinoma Single Cell Transcriptomics Data." In this study the Company's Pattern Discovery Engine ™ (PDE), a suite of proprietary algorithms, was used to analyze a liver cancer dataset, build predictive models to differentiate Hepatocellular carcinoma (HCC) from normal liver tissues, and uncover differences in gene regulation between the cancer and non-cancer samples. The PDE constructed a highly accurate model (97% accuracy) to predict whether or not a given cell is cancerous. The Company noted that the PDE identified a small set of nine genes with fundamentally different regulatory structure in cancer cells versus normal, which is of importance as it. highlights the use of the PDE as a hypothesis discovery tool. Mark Anderson, Pattern Chair and CEO, commented, 'While the inner workings are proprietary, the hypotheses it delivers are every bit as explicit and understandable, or more so, as hypotheses generated by human intuition – which, of course, is often a black box we like to label 'inspiration' or 'insight.' This project demonstrates a new paradigm for scientific discovery: instead of beginning with a hypothesis, we begin with data – and discover hypotheses for testing, exploration, and yes, inspiration. We don't aim to replace human intuition, but to augment it with the power to discover patterns in data that yield hypotheses about patterns in the world at large.' The PDE suite of algorithms enables the summarization of relationships in ultra-high-dimensional datasets in simple, human-readable, symbolic equations. It can discover previously unknown patterns within large datasets, without making prior assumptions, performing feature engineering, or pruning data. These algorithms use the patterns they uncovered to build explainable predictive models – which constitute novel hypotheses. Liver cancer remains the third leading cause of cancer deaths, amounting to 7.8% of all cancer deaths. HCC is the major form of primary liver cancer, accounting for over 90% of the cases, with 5-year survival rate of only 18%. Given its asymptomatic nature in the early stages, most HCC patients are diagnosed at advanced stages and face poor prognosis with limited treatment options. Consequently, individual strategies based on identifying early potential prognostic biomarkers and novel therapeutic targets are urgently needed. These efforts can ultimately lead to more efficient and reliable diagnoses, personalized treatment strategies, and improved patient outcomes. From the publication: In this study, we utilized Pattern Computer, Inc.'s Pattern Discovery Engine ™ (PDE) to establish a robust analytical framework for single-cell gene expression data, specifically targeting hepatocellular carcinoma. While the workings of the engine are proprietary, the end result is composed of sets of equations that are interpretable and human-readable – and hence constitute testable hypotheses. Our analysis identified a panel of nine signature genes that consistently distinguish cancerous from healthy tissues across diverse cell types. Next, these signature genes were used to construct an XAI model with over 97% balanced accuracy in predicting cancer status at the single-cell level. Beyond predictive power, this model offers a symbolic predictive equation, providing interpretable insights into the regulatory relationships among the genes. Finally, we generated a directed gene-to-gene regulatory network, uncovering substantial disruptions in co-regulation within cancerous cells compared to the tightly coordinated regulatory dynamics observed in healthy cells. This regulatory shift underscores the molecular dysregulation underlying hepatocellular carcinoma. These findings extend beyond classification accuracy, shedding light on the disrupted regulatory landscapes of cancer cells. By linking gene expression patterns to functional insights, our approach highlights therapeutic targets and biomarkers, paving the way for intervention strategies in this challenging disease. Mr. Anderson added, 'Explainable Artificial Intelligence (XAI) is revolutionizing biological research by enabling precise discoveries with unmatched transparency and interpretability. Our commitment to pioneering solutions in the fight against cancer is unwavering, with each innovative milestone achieved bringing the Company closer to our overarching mission of improving outcomes for individuals affected by cancer. Leveraging our AI-enabled Pattern Discovery Engine, we have achieved significant progress in expanding the Company's industry-leading oncology pipeline against the top five cancers worldwide.' Mr. Anderson concluded, 'Pattern's advanced computational approaches push the boundaries of cancer treatment, and we are confident in our ability to make more such discoveries across various types of challenging cancers. As we work towards transforming cancer treatment paradigms, we are looking to partner with firms to bring our cancer drug discoveries and diagnostic advances against the world's top five cancers into clinical trials.' About PatternPattern Computer, Inc. uses its Pattern Discovery Engine™ to solve the most important and intractable problems in business and medicine. These proprietary mathematical techniques in advanced AI can find complex patterns in very-high-order data that have eluded detection by much larger systems. As the Company applies its computational platform to the challenging fields of drug discovery and diagnostics, it is also making major Pattern Discoveries for partners in other sectors, including extended biotech, materials science, aerospace manufacturing quality control, veterinary medicine, air traffic operations, and energy services. See CONTACT: Laura Guerrant-Oiye (808) 960-2642 – laura@ The foregoing contains statements about Pattern Computer's future that are not statements of historical fact. These statements are 'forward looking statements' for purposes of applicable securities laws and are based on current information and/or management's good faith belief as to future events. The words 'believe,' 'expect,' 'anticipate,' 'project,' 'should,' 'could,' 'will,' and similar expressions signify forward-looking statements. Forward-looking statements should not be read as a guarantee of future performance. By their nature, forward-looking statements involve inherent risk and uncertainties, which change over time, and actual performance could differ materially from that anticipated by any forward-looking statements. Pattern Computer undertakes no obligation to update or revise any forward-looking statement. Copyright © 2025 Pattern Computer Inc. All Rights Reserved. Pattern Computer, Inc., Pattern Discovery Engine, PatternBio, TrueXAI, and ProSpectral are trademarks of Pattern Computer Inc. or its subsidiaries. Other trademarks may be trademarks of their respective owners.
Yahoo
19-05-2025
- Business
- Yahoo
Pattern Computer Brings Autonomous Risk and Confidence Tools to XAI
• Next-generation risk-aware XAI for mission-critical applications • Advances trust and transparency in high-stakes decision making REDMOND, Wash., May 19, 2025 (GLOBE NEWSWIRE) -- Pattern Computer®, Inc. ('Pattern' or 'the Company'), the global leader in Pattern Discovery, today announced the addition of RC/XAI™ (Risk and Confidence Explainable AI), to its Pattern Discovery Engine™ (PDE). The immediate effect of this technical achievement will be to bring known and demonstrated confidence and risk values to decisions for customers using the company's new PatternDE™ online platform. Users in industries such as equity market trading are expected to be among the first to benefit from this unique capacity, adding new assurance on a per – trade basis. This release introduces advanced risk-aware model convergence, conformal prediction, and enhanced explainability, setting a new standard for trustworthy AI in mission-critical sectors such as finance, medical diagnostics, and industrial process optimization. These new features derive from additions to the Iceland™ PDE component. Innovative Features in Iceland/SR™ 3.0 Version 3.0 incorporates several groundbreaking enhancements, including the Janus-Delphi Loss Framework™, risk-aware and instance-level metrics, and a refined conformal gating regime. Key features include: Janus-Delphi Loss Framework – A new evolution of the Janus Loss system, integrating per-instance scalable overconfidence penalties and localized risk-sensitive metrics. This approach enhances posterior probability estimation, ensuring models are finely calibrated to their operating context. The Janus-Delphi framework supports critical domain requirements for informed-consent by decision makers relying on the models' predictions, including per-instance certainty scores and real-time risk stratification. Risk-Aware and Risk-Transparent Model Generation – Iceland/SR 3.0 introduces risk-aware symbolic regression, allowing models to self-calibrate through dynamically adjusted confidence metrics. Moreover, the symbolic models (mathematical equations interpretable directly) explicitly self-optimize during training to maximize the risk-surface they expose for analysis, allowing end-users informed consent when deciding whether or not to base decisions on their predictions. This transparency not only facilitates high-confidence predictions while minimizing overfitting, but also supports compliance with emerging regulatory frameworks such as the SEC's proposed AI risk management rules, the EU's AI Act, and other global standards aimed at increasing accountability in automated decision-making. Abstention Metrics for Risk and Confidence – Newly added abstention gating mechanisms provide instance-level coverage, decision gating scores, and confidence intervals, enabling precise quantification of model risk, lost opportunity expectations when gates are trusted, and predicted abstention rates in real-world deployments. This allows users to make data-driven decisions with quantifiable confidence. Information-Theoretic and Conformity Metrics – Expanded support for information-theoretic measures to optimize model complexity and interpretability, ensuring each prediction is grounded in academic and industry standard, statistically rigorous post hoc evaluation and selection for best generalization on as-yet-unseen data. Redefining Explainability in AI With its highly optimized multi-threaded architecture and robust symbolic inference capabilities, RC/XAI represents a significant move forward for organizations seeking both cutting-edge performance and transparent model behavior. Mark R. Anderson, Pattern Founding Chair and CEO, commented, "What started as comparatively simple equations-as-predictors in our earlier Gilford Island™ system has become a full decision-support trust architecture in Iceland/SR™. Explainable AI has reached a new frontier: one where it holds itself accountable. This is not merely about understanding a model's decision path but about calibrating it with enough precision to allow for truly informed consent in high-stakes environments. These are models that don't just tell you how they arrive at a decision, but also how self-confident they are in each specific instance. This is a breakthrough in a new mathematics of 'trust-aware AI.' Pattern has developed the new technology in conjunction with well-known Wall Street firms. Anderson added, "With this new technology, we're delivering more than just mathematical models—we're setting a new benchmark for transparency and trust in explainable AI. This isn't just about better algorithms, it's about empowering organizations to make informed decisions that answer to their risk tolerance policies. Our mission has always been to discover previously unavailable patterns in data, and with RC/XAI and this new version of PatternDE, we're now giving our customers and partners the clarity they need to act with confidence in even the most complex, high-stakes environments.' Availability Iceland/SR 3.0 and RC/XAI are now available in Pattern's PatternDE™ platform. About PatternPattern Computer, Inc. uses its Pattern Discovery Engine™ to solve the most important and intractable problems in business and medicine. These proprietary mathematical techniques in advanced AI can find complex patterns in very high-dimensional data that have eluded detection by much larger systems. As the Company applies its computational platform to the challenging fields of drug discovery and diagnostics, it is also making major Pattern Discoveries for partners in other sectors, including extended biotech, materials science, aerospace manufacturing quality control, veterinary medicine, air traffic operations, energy services, finance, market trading and more. See CONTACT: Laura Guerrant-Oiye (808) 960-2642 – laura@ The foregoing contains statements about Pattern Computer's future that are not statements of historical fact. These statements are 'forward looking statements' for purposes of applicable securities laws and are based on current information and/or management's good faith belief as to future events. The words 'believe,' 'expect,' 'anticipate,' 'project,' 'should,' 'could,' 'will,' and similar expressions signify forward-looking statements. Forward-looking statements should not be read as a guarantee of future performance. By their nature, forward-looking statements involve inherent risk and uncertainties, which change over time, and actual performance could differ materially from that anticipated by any forward-looking statements. Pattern Computer undertakes no obligation to update or revise any forward-looking statement. Copyright © 2025 Pattern Computer Inc. All Rights Reserved. Pattern Computer, Inc., Pattern Discovery Engine, PatternBio, TrueXAI, and ProSpectral are trademarks of Pattern Computer Inc. or its subsidiaries. Other trademarks may be trademarks of their respective in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Yahoo
01-05-2025
- Business
- Yahoo
Area vocational schools receive state funding to boost offerings
Three area schools were awarded PAsmart Advancing Grants for Career and Technical Education Wednesday by the Pennsylvania Department of Education. Admiral Peary Area Vocational Technical School got $450,000, with Greater Johnstown Career & Technology Center earning $75,000 and Windber Area School District being awarded $75,000. These grants will be used to expand access to computer science and STEM (science, technology, engineering and mathematics) education. 'At PDE, we are committed to supporting innovative education and workforce development projects that ensure today's students are prepared with the skills they'll need to succeed in the jobs of tomorrow,' Pennsylvania Department of Education acting Secretary Carrie Rowe said in a release. 'I'm proud of Pennsylvania's commitment to career and technical education, which equips students with skills, credentials and hands-on experiences they need to excel in high-demand fields like STEM and computer science.' Rowe added that the funding reflects the state's continued commitment to 'providing every learner in Pennsylvania with the tools to build a successful future.' The area schools were three of 55 organizations across the commonwealth to receive a combined $10.35 million through these grants. According to PDE, institutions that received $400,000 or $450,000, such as Admiral Peary, have innovative projects planned to expand access to career and technical education for STEM and computer science curriculum. The $75,000 grants are geared toward supporting collaboration between schools and local or regional CTE providers, PDE said. The smaller amount may also be used to help communities design and plan local or regional approaches to expanding career education in computer science and STEM.
Yahoo
13-03-2025
- Politics
- Yahoo
Trump must ditch Biden-era memo pushing 'racially discriminatory' discipline, says parents group
FIRST ON FOX: Grassroots parental rights advocacy group Parents Defending Education (PDE) is urging the Trump administration to reverse "unconstitutional" Biden-era policies that penalize schools for racial disparities in discipline, as outlined in a Dear Colleague letter issued by the Department of Justice (DOJ) and Department of Education (DOE) in 2023. The Biden-era document pushes schools "to adopt racially discriminatory discipline policies" or face the loss of federal funding, according to PDE. "Despite clear Supreme Court precedent holding that disparate impact alone cannot support a Title VI violation, the School Discipline Letter states that racial disparities in school discipline outcomes are prima facie evidence of racial discrimination, even when a school's disciplinary code is race neutral," the group wrote to the Department of Education Secretary Linda McMahon on Thursday morning. "Moreover, the letter threatens school districts with the loss of federal funds if they do not adjust their procedures to eliminate such disparities." Biden's DOJ and the Department of Education's Office for Civil Rights released the guide in 2023 for schools to address racial discrimination in K-12 student discipline. Ohio College 'Illegally Forcing Students' To Share Bathrooms With Opposite Sex: Watchdog "Discrimination in school discipline can have devastating long-term consequences on students and their future opportunities," then-Assistant Attorney General Kristen Clarke of the Justice Department's Civil Rights Division said in a DOJ release. Read On The Fox News App "The Justice Department Civil Rights Division uses our federal civil rights laws to protect students from discriminatory discipline, including discrimination in suspensions and expulsions, law enforcement referrals and school-based arrests. The investigations that we describe demonstrate how students may experience discrimination based on multiple facets of their identities and reflect our joint commitment to fully protect all students." In the letter, the DOE and DOJ agencies wrote that their agencies engaged in "decades of enforcement activity" demonstrating "that discrimination based on race, color, and national origin in student discipline was, and continues to be, a significant concern." "Discrimination in student discipline forecloses opportunities for students, pushing them out of the classroom and diverting them from a path to success in school and beyond. Significant disparities by race – beginning as early as preschool – have persisted in the application of student discipline in schools," the Dear Colleague letter reads. "While racial disparities in student discipline alone do not violate the law, ensuring compliance with Federal nondiscrimination obligations can involve examining the underlying causes of such disparities." Trans Inmate In Prison For Killing Baby Must Get Gender Surgery At 'Earliest Opportunity': Judge PDE spokesperson Erika Sanzi told Fox News Digital it's "hard to believe" that the previous administration "thought it was noble, let alone legal, to instruct schools to adopt racially discriminatory discipline policies in order to eliminate racial disparities in their discipline data then threaten them with loss of funds if they didn't fall in line." At the time of the guide's release, the agencies completed investigations into 14 school districts across 10 states, including Alabama, Arizona, California and others. The investigations focused on whether the schools were unfairly disciplining Black, Latino and Native American students. Concerns included the use of suspensions, expulsions, school-based arrests and other actions the administration deemed discriminatory. "Not surprisingly, districts got skittish about suspending too many students from certain racial groups for chronically disruptive and even violent behavior, and schools descended into chaos," Sanzi said. "It's long overdue that we rescind this letter … it shouldn't be controversial to state unequivocally that school policies must be race neutral." OHIO TRANSGENDER BATHROOM LAW TAKES EFFECT AS TOP PROPONENT CALLS IT 'VICTORY FOR SAFETY & COMMON SENSE' The DOE, which President Donald Trump hopes to fully dismantle, has reversed course on much of the previous administration's "woke" and DEI-related policies during his first three months in office. It also launched an investigation this week into 60 universities due to allegations of antisemitism and violence against Jewish students since the Oct. 7, 2023, Hamas terrorist attacks on Israel. Fox News Digital has reached out to the Department of Justice and the Department of Education for article source: Trump must ditch Biden-era memo pushing 'racially discriminatory' discipline, says parents group
Fox News
13-03-2025
- Politics
- Fox News
Trump must ditch Biden-era memo pushing 'racially discriminatory' discipline, says parents group
FIRST ON FOX: Grassroots parental rights advocacy group Parents Defending Education (PDE) is urging the Trump administration to reverse "unconstitutional" Biden-era policies that penalize schools for racial disparities in discipline, as outlined in a Dear Colleague letter issued by the Department of Justice (DOJ) and Department of Education (DOE) in 2023. The Biden-era document pushes schools "to adopt racially discriminatory discipline policies" or face the loss of federal funding, according to PDE. "Despite clear Supreme Court precedent holding that disparate impact alone cannot support a Title VI violation, the School Discipline Letter states that racial disparities in school discipline outcomes are prima facie evidence of racial discrimination, even when a school's disciplinary code is race neutral," the group wrote to the Department of Education Secretary Linda McMahon on Thursday morning. "Moreover, the letter threatens school districts with the loss of federal funds if they do not adjust their procedures to eliminate such disparities." Biden's DOJ and the Department of Education's Office for Civil Rights released the guide in 2023 for schools to address racial discrimination in K-12 student discipline. "Discrimination in school discipline can have devastating long-term consequences on students and their future opportunities," then-Assistant Attorney General Kristen Clarke of the Justice Department's Civil Rights Division said in a DOJ release. "The Justice Department Civil Rights Division uses our federal civil rights laws to protect students from discriminatory discipline, including discrimination in suspensions and expulsions, law enforcement referrals and school-based arrests. The investigations that we describe demonstrate how students may experience discrimination based on multiple facets of their identities and reflect our joint commitment to fully protect all students." In the letter, the DOE and DOJ agencies wrote that their agencies engaged in "decades of enforcement activity" demonstrating "that discrimination based on race, color, and national origin in student discipline was, and continues to be, a significant concern." "Not surprisingly, districts got skittish about suspending too many students from certain racial groups for chronically disruptive and even violent behavior, and schools descended into chaos. … [I]t shouldn't be controversial to state unequivocally that school policies must be race neutral." "Discrimination in student discipline forecloses opportunities for students, pushing them out of the classroom and diverting them from a path to success in school and beyond. Significant disparities by race – beginning as early as preschool – have persisted in the application of student discipline in schools," the Dear Colleague letter reads. "While racial disparities in student discipline alone do not violate the law, ensuring compliance with Federal nondiscrimination obligations can involve examining the underlying causes of such disparities." PDE spokesperson Erika Sanzi told Fox News Digital it's "hard to believe" that the previous administration "thought it was noble, let alone legal, to instruct schools to adopt racially discriminatory discipline policies in order to eliminate racial disparities in their discipline data then threaten them with loss of funds if they didn't fall in line." At the time of the guide's release, the agencies completed investigations into 14 school districts across 10 states, including Alabama, Arizona, California and others. The investigations focused on whether the schools were unfairly disciplining Black, Latino and Native American students. Concerns included the use of suspensions, expulsions, school-based arrests and other actions the administration deemed discriminatory. "Not surprisingly, districts got skittish about suspending too many students from certain racial groups for chronically disruptive and even violent behavior, and schools descended into chaos," Sanzi said. "It's long overdue that we rescind this letter … it shouldn't be controversial to state unequivocally that school policies must be race neutral." The DOE, which President Donald Trump hopes to fully dismantle, has reversed course on much of the previous administration's "woke" and DEI-related policies during his first three months in office. It also launched an investigation this week into 60 universities due to allegations of antisemitism and violence against Jewish students since the Oct. 7, 2023, Hamas terrorist attacks on Israel. Fox News Digital has reached out to the Department of Justice and the Department of Education for comment.
