A typical business vision in healthcare is to bring innovative treatments to patients with unmet-needs faster. Augmenting human expertise can ensure that only candidates and clinical programs with the highest likelihood of success are pursued – saving time, resources, and reducing costs.
We’ve created a suite of products to accelerate innovation by addressing high-value questions for stakeholders in portfolio strategy, R&D, therapeutic programs, business development and licensing, M&A, clinical operations, and competitive/business intelligence
The AlphaMeld® suite of products impacts the entire process of drug discovery and development ensuring
- Emerging technologies and targets can be identified
- Only candidates with the most robust connections between target-drug-disease are prioritized with the highest translational potential
- Prioritization of a clinical pipeline based on probability of success and failure
- Parked assets are leveraged into new disease indications or evaluated as potential combination therapies
- Optimal investment allocation for internal programs for portfolio strategy
- The competitive landscape is monitored so that all opportunities and threats are recognized
- Patient recruitment and sites for clinical trials are optimized for the disease indication
In the drug development process, standard estimates for overall probability of clinical success remains low at about 10%. Deploying a machine-based artificial smart approach to digest diverse datasets and amplify patterns of successful clinical innovation is key to enabling the intelligent allocation of investment and making high-value portfolio decisions via internal development initiatives or strategic acquisition or in-licensing of external assets.
SUITS OF PRODUCTS
Use Case 1
Strategic portfolio augmentation with high-value clinical assets that have a high likelihood of success
Large Pharma spin-out
Licensing and M&A Group
RxMeldTM identified a landscape of 50 disease indications in non-malignant blood disorders with an association of more than 300 drugs, taking into account over 2 million data points. RxMeld’s machine learning algorithms amplified the signals of success for clinical innovation in each disease indication’s drug pipeline. The asset landscape was narrowed down to 67 drugs that were amenable to human expert intervention. The iterative process resulted in the identification of 10 highly actionable assets with a probability of clinical success greater than 80%. We successfully concluded the collaboration rapidly building scale and efficiency to augment human expertise.
Use Case 2
Building efficiency and focus on the business development due diligence process through AI-powered automation. The existing process involved deep human intervention and time-consuming processes for evaluating thousands of in-licensing opportunities to identify assets for more in-depth analysis.
For every opportunity received by the Pharma collaborator, RxMeldTMprovided a competitive snapshot for each asset, its probability of clinical success, and a comparative list of alternative assets (if any) in the same disease indication. This AI-powered evaluation allowed the search and evaluation teams to focus and prioritize organizational resources for conducting in-depth analysis on high-value assets.
Use Case 1
To identify the next breakthrough innovations for novel targets/mechanisms of action and technologies to transform fibrosis management and treatment. Early innovation is a noise-ridden space with data inundation from basic to applied research yielding more than 5,000 published papers a day. Evaluation of cross-industry technologies and possible adaptability to healthcare is also imperative in identifying relevant signals of innovation. This presents a unique challenge for human experts to manage and leverage effectively. An AI- and ML-based approach can rapidly identify patterns of innovation and amplify human expertise to ensure that signals of innovation are not lost in translation.
Top 10 Large Pharma
R&D and Discovery teams
EIMeldTM identified associations between targets and pathways relevant to fibrosis. Machine learning algorithms amplified the targets with established functional evidence and novelty. EIMeldTM triangulated these signals with
associated KOL support, innovation hubs, grants, patent activity, and deal activity. This resulted in the identification of novel targets for further evaluation through academic collaborations.
Use Case 1
The high drug development attrition rate occurs for many reasons, including unanticipated pharmacology and unknown biology. Scientific discovery requires an understanding of the relationships between disease pathways and potential drug targets. Mapping these relationships is often a manual effort drawing upon various data sources, limiting the possibilities that scientists can explore. Once a hypothesis about a new target or relationship is formulated, manual data curation and review are often required to validate a new theory.
Top 10 Pharma
R&D, Discovery teams
TargetMeldTM provided exhaustive measures to comprehensively make meaningful connections between targets, pharmacology, and disease pathophysiologies to increase the probability of clinical success. Based on the quality and quantity of evidence, TargetMeldTM rapidly shortlisted clinical, pre-clinical, and in-vivo targets and, through manual curation, identified actionable target product profiles.
Use Case 1
As organizations strive to remain pioneers in their respective fields, a thorough understanding of the commercial, clinical, and financial landscape is key to continued success. Competitive benchmarking should allow for an objective analysis of actionable intelligence about competitor objectives, strategies, capabilities, and emerging innovation. It can also provide a clear understanding of an unmet need and opportunity for growth. CIMeldTM enables AI- and ML-driven signal triangulation to identify threats and opportunities based on disease indication, clinical phase, gene, and target. CIMeldTM is tailored to fit the needs of an organization to help decision-makers keep a finger on the pulse of significant breakthroughs, developments, and events in a market of interest. With a multitude of moving parts, AI-driven signal triangulation of structured and unstructured data sources ensures that no stone is left unturned when looking to execute on high-value investment strategies.
Top 10 Pharma
Licensing and M&A
CIMeldTM provided critical competitive information for portfolio strategy, taking into account commercial, clinical, and financial insights, and was able to identify multiple opportunities and threats. It also provided a first-mover advantage in identifying opportunities for in-licensing as well as M&A.
The high failure rate of clinical trials has a significant impact on providing much-needed treatments to patients with an unmet need. As a result, drug development costs remain high, and compounds are more likely to demonstrate a lack of efficacy for reasons beyond just the mechanism of action. Patient enrollment and protocol adherence, as well as competition among sites to enroll eligible subjects also contribute to failure rates. The massive accumulation of data and other associated information remains cumbersome to manage and may also contain nuggets of valuable data that are impossible to extract, given the finite resources available for any given trial. CliniMeldTM utilizes AI’s transformative power to enhance the clinical trial planning process and operational execution.
Biopharmaceutical companies, CROs, project managers, and clinical development teams