Exscientia PLC (EXAI) 2022 Q4 法說會逐字稿

Hello, everyone. My name is Chris, and I'll be your conference operator today. At this time, I'd like to welcome everyone to Exscientia's business update call for the full year ended 2022. (Operator Instructions)

大家好。我叫克里斯，今天我將擔任你們的會議接線員。此時，我想歡迎大家參加 Exscientia 截至 2022 年全年的業務更新電話會議。（操作員說明）

At this time, I'd like to introduce Sara Sherman, Vice President of Investor Relations. Sara, you may begin.

在這個時候，我想介紹投資者關係副總裁 Sara Sherman。薩拉，你可以開始了。

Thank you, operator. A press release and our 20-F were issued this morning with our full year 2022 financial results and business update. These documents can be found on our website at www.investor.exscientia.ai, along with the presentation for today's webcast.

謝謝你，運營商。今天上午發布了一份新聞稿和我們的 20-F，其中包含我們 2022 年全年的財務業績和業務更新。這些文件可以在我們的網站 www.investor.exscientia.ai 上找到，連同今天的網絡廣播演示文稿。

Before we begin, I'd like to remind you that we may make forward-looking statements on our call. These may include statements about our projected growth, revenue, business models, preclinical and clinical results and business performance. Actual results may differ materially from those indicated by these statements. Unless required by law, Exscientia does not undertake any obligation to update these statements regarding the future or to confirm these statements in relation to actual results.

在我們開始之前，我想提醒您，我們可能會在電話會議上做出前瞻性陳述。這些可能包括關於我們的預期增長、收入、商業模式、臨床前和臨床結果以及業務績效的陳述。實際結果可能與這些陳述所表明的結果存在重大差異。除非法律要求，否則 Exscientia 不承擔更新這些關於未來的聲明或確認這些與實際結果相關的聲明的義務。

On today's call, I'm joined by Andrew Hopkins, Chief Executive Officer; and Ben Taylor, CFO and Chief Strategy Officer; Dave Hallett, Chief Scientific Officer; Garry Pairaudeau, Chief Technology Officer; and Mike Krams, Chief Quantitative Medicine Officer, will also be available for the Q&A session.

在今天的電話會議上，首席執行官安德魯·霍普金斯 (Andrew Hopkins) 也加入了我的行列；首席財務官兼首席戰略官 Ben Taylor；首席科學官 Dave Hallett； Garry Pairaudeau，首席技術官；首席定量醫學官 Mike Krams 也將出席問答環節。

And with that, I will now turn the call over to Andrew.

有了這個，我現在將把電話轉給安德魯。

Thank you, Sara. 2022 was another transformational year of Exscientia. We continue to validate our AI-driven precision medicine platform and strengthen our business. Exscientia's goal is to fundamentally transform the way our industry designs and develops drugs. We believe our unique pairing of excellent science with advanced computational experimental capabilities at every step of the R&D process differentiates our patient-first precision medicine approach.

謝謝你，薩拉。 2022 年是 Exscientia 的又一個轉型年。我們繼續驗證我們的人工智能驅動的精準醫療平台並加強我們的業務。 Exscientia 的目標是從根本上改變我們行業設計和開發藥物的方式。我們相信，我們在研發過程的每一步都將卓越的科學與先進的計算實驗能力獨特地結合在一起，這使我們以患者為先的精準醫療方法與眾不同。

Our approach of model-driven adaptive learning as an overarching technological principle enables us to innovate from discovery and into development. To that end, our remarkable progress to date is a testament to the strength for our company. We are well capitalized with $611 million in cash at the end of the year. This provides us with several years runway to advance our near-term programs, deepening our pipeline, whilst also investing for long-term growth.

我們將模型驅動的自適應學習方法作為一項總體技術原則，使我們能夠從發現到發展進行創新。為此，我們迄今為止取得的顯著進步證明了我們公司的實力。截至年底，我們擁有 6.11 億美元的現金，資本充足。這為我們提供了數年的時間來推進我們的近期計劃，深化我們的管道，同時也為長期增長進行投資。

To that end, we marked several significant milestones throughout the year across our internal and partner programs, which we will provide more insight on today. We will also highlight data that illustrates how we're working on designing better drugs of a right patient by combining precision engineering with personalized medicine.

為此，我們在全年的內部和合作夥伴計劃中標記了幾個重要的里程碑，我們將在今天提供更多見解。我們還將突出顯示我們如何通過將精密工程與個性化醫療相結合來為合適的患者設計更好的藥物的數據。

At a high level, last year was significant for the trajectory of our business. We started here by signing a collaboration with Sanofi for up to 15 targets, and ended the year showcasing the value of a multimodal gene signature data for immuno-oncology patient selection at ESMO IO.

從總體上看，去年對我們的業務發展軌跡意義重大。我們首先與賽諾菲簽署了多達 15 個目標的合作協議，並於年底在 ESMO IO 上展示了多模態基因特徵數據對免疫腫瘤患者選擇的價值。

Importantly, we've advanced our pipeline. We highlight five programs across oncology and immunology and inflammation, either in clinical stage or IND-enabling studies. We have presented important data from our design and translational platforms across these programs, and we are pleased we can now share these targets and how we combined precision design with personalized medicine.

重要的是，我們已經推進了我們的管道。我們重點介紹了五個跨腫瘤學、免疫學和炎症的項目，無論是在臨床階段還是在 IND 支持研究中。我們已經在這些項目中展示了來自我們的設計和轉化平台的重要數據，我們很高興現在可以分享這些目標以及我們如何將精密設計與個性化醫療相結合。

For our A2a candidate, EXS21546, or 546, last year, we reported top line healthy volunteer data in June. The data confirmed our target product profile design includes impotency, high receptor selectivity and expected low drain exposure, with no CNS adverse events reported. This data provided support to move into our patient trial.

對於我們去年的 A2a 候選人 EXS21546 或 546，我們在 6 月份報告了頂級健康志願者數據。數據證實，我們的目標產品概況設計包括陽痿、高受體選擇性和預期的低引流暴露，沒有報告中樞神經系統不良事件。這些數據為進入我們的患者試驗提供了支持。

Late last year, we also received CTA approval to initiate our Phase I/II trial. The IGNITE trial will examine the safety, pharmacokinetics, pharmacodynamics and efficacy of 546 when used in combination with anti-PD-1 therapy in relapsed/refractory Renal Cell Carcinoma and non-small cell lung cancer.

去年年底，我們還獲得了 CTA 的批准，可以啟動我們的 I/II 期試驗。 IGNITE 試驗將檢查 546 與抗 PD-1 療法聯合用於治療復發/難治性腎細胞癌和非小細胞肺癌時的安全性、藥代動力學、藥效學和療效。

During the trial, we will be observationally validating our patient selection biomarker, aimed at enriching patients more likely to respond to 546 discovered preclinically. The trial will enroll up to 110 patients, and we continue to expect the first patient to be dosed in the first half of this year.

在試驗期間，我們將通過觀察驗證我們的患者選擇生物標誌物，旨在豐富患者更有可能對臨床前發現的 546 種藥物做出反應。該試驗將招募多達 110 名患者，我們繼續預計第一名患者將在今年上半年接受給藥。

A vital component of our A2a program is a robust biomarker strategy, as we believe the key to a successful A2a inhibitor is enriching for the right patients with high identity in the tumor microenvironment. We presented relevant data at ESMO Immuno-encology Annual Congress in December, identifying a novel patient selection, multi-gene transcript signature, the adenosine burden score or ABS. The biomarker was to score preclinically used now patient tissue platform and multi-omics data set integration from complex disease-relevant model systems.

我們的 A2a 計劃的一個重要組成部分是強大的生物標誌物策略，因為我們認為成功的 A2a 抑製劑的關鍵是豐富腫瘤微環境中具有高身份的正確患者。我們在 12 月的 ESMO 免疫生態學年會上展示了相關數據，確定了新的患者選擇、多基因轉錄特徵、腺苷負荷評分或 ABS。生物標誌物是對臨床前使用的現在患者組織平台和來自複雜疾病相關模型系統的多組學數據集集成進行評分。

The IGNITE trial will evaluate this gene signature to identify patients most likely to respond to 546. We look forward to presenting additional data on biological validation of the ABS and our 546 program at the upcoming AACR meeting next month in Orlando.

IGNITE 試驗將評估該基因特徵，以確定最有可能對 546 產生反應的患者。我們期待在下個月即將於奧蘭多舉行的 AACR 會議上提供有關 ABS 和我們 546 計劃的生物學驗證的更多數據。

With our CDK7 inhibitor, GTAEXS617, developed in partnership with GTAPerion, we remain on track to enroll the first patient in our planned Phase I/II study in the first half of this year. This program also showcased what truly makes Exscientia drug unique, precision design aiming to transform patient benefit and patient selection strategies.

憑藉我們與 GTAPerion 合作開發的 CDK7 抑製劑 GTAEXS617，我們有望在今年上半年將第一名患者納入我們計劃的 I/II 期研究。該計劃還展示了真正使 Exscientia 藥物獨一無二的精確設計，旨在改變患者利益和患者選擇策略。

We highlighted some of this patient selection data at the ENA Congress in October to maximize understanding of the effect of '617 using primary patient material. For the first time, we showed how we integrate machine learning, data from primary human tumor samples and multi-omic sequencing capabilities to predict tumor efficacy of '617.

我們在 10 月份的 ENA 大會上強調了一些患者選擇數據，以最大限度地了解 '617 使用主要患者材料的影響。我們首次展示了我們如何整合機器學習、來自原發性人類腫瘤樣本的數據和多組學測序能力來預測 '617 的腫瘤療效。

Using our deep learning AI and high content imaging platform, we've previously confirmed '617 activity in primary human samples. Data presented at AACR led us to generally define two groups of patient samples, effectively high and low responder groups when focusing on ovarian cancer. We believe that leveraging this information will enable us to identify responders and nonresponders to '617 across tumor types. This is a key component of how we designed our Phase I/II study. We look forward to sharing more detail on the tumor types we'll be investigating shortly.

使用我們的深度學習 AI 和高內涵成像平台，我們之前已經確認了主要人類樣本中的 '617 活動。在 AACR 上提供的數據使我們大致定義了兩組患者樣本，即在關注卵巢癌時有效的高反應組和低反應組。我們相信，利用這些信息將使我們能夠識別各種腫瘤類型對 '617 的反應者和無反應者。這是我們設計 I/II 期研究的關鍵組成部分。我們期待分享更多關於我們即將調查的腫瘤類型的細節。

With both our CDK7 and A2a programs, we can now begin to see the hallmark of what an Exscientia drug looks like. AI and machine learning is applied not just in the process of how we design the drug, but also how we identify the right patients for that drug.

通過我們的 CDK7 和 A2a 程序，我們現在可以開始看到 Exscientia 藥物的特徵。人工智能和機器學習不僅應用於我們設計藥物的過程，還應用於我們如何為該藥物確定合適的患者。

Exscientia invented the first AI design drug to ever enter the clinic. Since then, we have made significant advancements in our technology and AI capabilities. We have developed a comprehensive physics-based platform, encompassing molecular dynamics and quantum mechanics, which is combined with our AI generative and active learning capabilities. We have also significantly progressed our engineering and data platforms, enabling scalability and robustness.

Exscientia 發明了第一個進入臨床的 AI 設計藥物。從那時起，我們在技術和人工智能能力方面取得了重大進步。我們開發了一個全面的基於物理學的平台，涵蓋分子動力學和量子力學，並結合了我們的 AI 生成和主動學習能力。我們還顯著改進了我們的工程和數據平台，實現了可擴展性和穩健性。

As you may have seen, over the past several weeks, we have highlighted three new targets that are progressing. EXS4318, our clinical-stage PKC feature compound that was in-licensed by BMS. EXS74539, our LSD1 inhibitor, and EXS73565, our MALT1 protease inhibitor. These embody what Exscientia can do in terms of AI generator molecular design where we truly lead the field.

您可能已經看到，在過去幾周里，我們強調了三個正在取得進展的新目標。 EXS4318，我們的臨床階段 PKC 特徵化合物，已獲得 BMS 的許可。我們的 LSD1 抑製劑 EXS74539 和我們的 MALT1 蛋白酶抑製劑 EXS73565。這些體現了 Exscientia 在 AI 生成器分子設計方面的真正領先地位。

These molecules are great examples of how our drug centers using our AI can solve complex problems such as kinase selectivity in the case of PKC-theta; brain penetration, coupled with reversibility in the case of LSD1; and Allosteric inhibition in the case of MALT1.

這些分子很好地說明了我們的藥物中心如何使用我們的 AI 解決複雜問題，例如 PKC-theta 中的激酶選擇性；大腦滲透，加上 LSD1 的可逆性；和變構抑制在 MALT1 的情況下。

I'll now spend a few minutes on each of these important programs, showing you how we design these compounds and what we have seen to date. In February of this year, Bristol Myers Squibb initiated a first-in-human study of EXS4318, a potential first-in-class selective PKC-theta inhibitor. BMS will oversee clinical and commercial development and Exscientia is eligible for milestone payments. And if approved, tiered royalties on the net product sales.

我現在將花幾分鐘時間介紹這些重要的程序中的每一個，向您展示我們如何設計這些化合物以及迄今為止我們所看到的。今年 2 月，百時美施貴寶 (Bristol Myers Squibb) 啟動了 EXS4318 的首次人體研究，這是一種潛在的一流選擇性 PKC-theta 抑製劑。 BMS 將監督臨床和商業開發，Exscientia 有資格獲得里程碑付款。如果獲得批准，則按產品淨銷售額收取特許權使用費。

PKC-theta is an attractive immune modulating target, which plays a critical role in the control of T cell function and is a key driver of several highly common autoimmune diseases, but has proved challenging to dose. The target product profile was particularly challenging due to the need to balance sustain, high levels of target inhibition to drive efficacy with low daily dosing in-humans. PKC-theta is structurally similar to several related kinases, makes it difficult to achieve high levels of selectivity required to avoid off-target effects.

PKC-theta 是一個有吸引力的免疫調節靶點，它在控制 T 細胞功能中起著關鍵作用，並且是幾種非常常見的自身免疫性疾病的關鍵驅動因素，但已證明劑量具有挑戰性。由於需要平衡維持、高水平的目標抑制以提高療效和人體每日低劑量，因此目標產品概況特別具有挑戰性。 PKC-theta 在結構上與幾種相關激酶相似，因此很難達到避免脫靶效應所需的高水平選擇性。

Our team of experts, leveraging our AI design platform, delivered a balanced candidate with potent on-target activity, while maintaining high selectivity and a favorable therapeutic index as demonstrated in the IND-enabling studies.

我們的專家團隊利用我們的 AI 設計平台，提供了具有強大靶向活性的平衡候選藥物，同時保持了高選擇性和有利的治療指數，如 IND 支持研究所示。

As you can see here, previous molecules have failed that were challenged to design a candidate with required potency as well as selectivity against ever closely related kinases. We believe our well-balanced molecule meets required properties to potentially provide benefit in patients. These molecules are first immunology and inflammation candidate to enter into a clinic.

正如您在這裡看到的，以前的分子都失敗了，這些分子在設計具有所需效力和對密切相關激酶的選擇性的候選物時遇到了挑戰。我們相信我們均衡的分子滿足所需的特性，可能為患者帶來益處。這些分子是第一個進入臨床的免疫學和炎症候選分子。

This is a significant milestone, illustrating Exscientia's strength, efficiency and flexibility to precision design high-quality therapeutic candidates. Last week, we shared an update on our next-generation LSD1 and MALT1 inhibitors. I'll highlight a few details, but I encourage everyone to visit our website and watch the video, which detail these candidates forever.

這是一個重要的里程碑，說明了 Exscientia 在精確設計高質量治療候選藥物方面的實力、效率和靈活性。上週，我們分享了下一代 LSD1 和 MALT1 抑製劑的更新。我會強調一些細節，但我鼓勵大家訪問我們的網站並觀看視頻，其中永遠詳細介紹了這些候選人。

539 is a differentiated lysine demethylase 1, or LSD1 inhibitor, precision designed to improve patient benefit and solve challenging design objectives. It promises strong potential in both hematology and oncology. To date, other LSD1 inhibitors in development elsewhere have failed to achieve the combination of appropriate pharmacokinetics, good brain penetrance and reversible mechanism of action. Our candidate has been designed to achieve suitable CNS penetration to target brain metastases common in certain cancer subtypes.

539 是一種差異化的賴氨酸脫甲基酶 1 或 LSD1 抑製劑，旨在提高患者獲益並解決具有挑戰性的設計目標。它有望在血液學和腫瘤學領域發揮巨大潛力。迄今為止，其他地方正在開發的其他 LSD1 抑製劑未能實現適當的藥代動力學、良好的腦外顯率和可逆作用機制的組合。我們的候選藥物旨在實現適當的 CNS 滲透，以靶向某些癌症亞型中常見的腦轉移。

In vivo studies have shown favorable activity also in small cell lung cancer xenograft models, with dose-dependent inhibition of tumor growth. In vivo studies have also shown a favorable absorption, distribution, metabolism and excretion profile with shorter predicted human half-life and some LSD1 inhibitors currently in clinical trials. We believe this may benefit on-target tox management, allowing for platelets to recover following dosing, given the reversible nature of '539.

體內研究表明，在小細胞肺癌異種移植模型中也具有良好的活性，對腫瘤生長具有劑量依賴性抑製作用。體內研究還顯示出良好的吸收、分佈、代謝和排泄特徵，預測的人體半衰期更短，一些 LSD1 抑製劑目前正在臨床試驗中。考慮到 '539 的可逆性，我們認為這可能有利於靶向毒性管理，允許血小板在給藥後恢復。

We believe the exquisite control of LSD1 inhibition and with superior management of platelets will be a critical differentiator for '539 in the clinic, particularly in combination with the standard of care that often has negative effects on platelets. The flexibility to genuinely explore intermittent dosing regimens in the clinic and thus, maximize our therapeutic window is another reason we believe that 539 is differentiated from other compounds in development.

我們相信，對 LSD1 抑制的精確控制和對血小板的卓越管理將成為臨床上 '539 的一個關鍵差異化因素，特別是與通常對血小板產生負面影響的護理標準相結合。在臨床上真正探索間歇給藥方案並因此最大化我們的治療窗口的靈活性是我們認為 539 與其他開發中的化合物不同的另一個原因。

Here, you can see the properties of 539 against two other LSD1 candidates, specifically looking at factors such as CNS penetration, mechanism of action and predicted, as in the case of 539, or published clinical dosing regimens. As you can see, only 539 achieves a unique combination of a reversible mechanism, suitable CNS penetration to target brain metastases and the predicted human half-life aligned with once daily dosing.

在這裡，您可以看到 539 與其他兩個 LSD1 候選藥物的特性，特別是 CNS 滲透、作用機制和預測等因素，如 539 的情況，或已公佈的臨床給藥方案。如您所見，只有 539 實現了可逆機制、針對腦轉移的適當 CNS 滲透以及與每日一次給藥相一致的預測人體半衰期的獨特組合。

Our molecule also met a long list of other criteria, such as selectivity against related enzymes, high bioavailability in preclinical species, and in vivo efficacy in relevant models of SCLC, a potential indication where '539 may have benefit.

我們的分子還滿足一長串其他標準，例如對相關酶的選擇性、臨床前物種的高生物利用度以及相關 SCLC 模型的體內療效，這是 '539 可能受益的潛在跡象。

Importantly, we were able to use AI to find this highly differentiated molecule with its specific target product profile, ultimately exploring new chemical space. Using our 3D mapping algorithms, we identify targetable features of each region of a protein. We then used our free degenerative AI design algorithms to produce prioritized populations and molecules, meeting specific optimization criteria.

重要的是，我們能夠使用人工智能找到這種具有特定目標產品特徵的高度分化分子，最終探索新的化學空間。使用我們的 3D 映射算法，我們可以識別蛋白質每個區域的可靶向特徵。然後，我們使用免費的退化 AI 設計算法來生成優先種群和分子，以滿足特定的優化標準。

Machine learning models efficiently scored the compound of CNS penetrants alongside optimizing multiple parameters, including potency and admin properties. By then applying active learning methods, we were able to select the most information-rich molecules to make and test at each design cycle, usually around 10 to 20 compounds. This allowed us to find novel molecules outside the established domain of applicability that were counterintuitive, which enabled us to find a new starting point for design and covering this chemotype ultimately led to '539.

機器學習模型有效地對 CNS 滲透劑的化合物進行評分，同時優化多個參數，包括效力和管理屬性。通過應用主動學習方法，我們能夠在每個設計週期選擇信息最豐富的分子來製造和測試，通常是大約 10 到 20 種化合物。這使我們能夠在既定的適用範圍之外找到違反直覺的新分子，這使我們能夠找到新的設計起點並涵蓋這種化學類型，最終導致了 '539。

The result was that we were able to create molecules which achieved a target product profile that no competitor molecule have exhibited. We believe '539 has the potential to become the first potent, selective, reversible and brain penetrant LSD1 inhibitor to meet significant unmet need in a range of oncological and hematological indications.

結果是我們能夠創造出達到目標產品特徵的分子，這是競爭對手分子所沒有的。我們相信 '539 有潛力成為第一個有效的、選擇性的、可逆的和腦滲透性 LSD1 抑製劑，以滿足一系列腫瘤學和血液學適應症中未滿足的重大需求。

We look forward to highlighting the precision design of this compound as well as the latest in vivo data at the AACR next month.

我們期待著在下個月的 AACR 上重點介紹這種化合物的精密設計以及最新的體內數據。

I'll now highlight another candidate we've recently unveiled, our MALT1 inhibitor, EXS73565, or '565. MALT1 or mucosa-associated lymphoid tissue lymphoma translocation protein 1, is an important protease target with potential applications in hematology. It aims to inhibit the uncontrolled proliferation of malignant T and B cells in hematological cancers.

我現在將重點介紹我們最近公佈的另一個候選藥物，即我們的 MALT1 抑製劑 EXS73565 或 '565。 MALT1 或粘膜相關淋巴組織淋巴瘤易位蛋白 1 是一種重要的蛋白酶靶標，在血液學中具有潛在應用。它旨在抑制血液癌症中惡性 T 細胞和 B 細胞的不受控制的增殖。

Exscientia's AI-driven precision design approach was able to optimize the safety profile of agents targeting MALT1, was also generating potency and selectivity. When considering an optimal target product profile, the team took into account the likely use of a MALT1 inhibitor in combination Fabry such as BTK inhibitors. Therefore, in addition to potency, selectivity in a balanced set of properties, we were mindful of potential drug-drug interactions.

Exscientia 的人工智能驅動的精密設計方法能夠優化針對 MALT1 的藥物的安全性，同時也產生了效力和選擇性。在考慮最佳目標產品概況時，該團隊考慮了可能將 MALT1 抑製劑與 Fabry 抑製劑（例如 BTK 抑製劑）結合使用。因此，除了在一系列平衡特性中的效力和選擇性外，我們還注意到潛在的藥物相互作用。

In these two charts here, you can see that in vivo studies of '565 have shown antitumor activity in most models and favorable pharmacokinetics both as monotherapy and in combination with Ibrutinib. Our toxicology studies have also shown an acceptable therapeutic index, with the ability to maintain high levels of potency, selectivity and safety benchmarks, whilst avoiding meaningful inhibition of UGT1A1, which can lead to excessive levels of bilirubin and is a known cause of drug-drug interactions.

在這裡的這兩張圖表中，您可以看到 '565 的體內研究顯示在大多數模型中具有抗腫瘤活性，並且無論是作為單一療法還是與 Ibrutinib 聯合使用，都顯示出良好的藥代動力學。我們的毒理學研究還顯示了可接受的治療指數，能夠保持高水平的效力、選擇性和安全性基準，同時避免對 UGT1A1 進行有意義的抑制，這可能導致膽紅素水平過高，並且是藥物-藥物相互作用的已知原因相互作用。

This chart here compares '565 directly with published and patented MALT1 scaffolds from various groups. '565 compares very favorably across all parameters, examining importancy, cellular activity and drug-like properties. '565 has very little activity at UGT1A1 and is highly differentiated in this respect. We would predict that many of the other compounds will likely inhibit UGT1A1 to a meaningful degree and thus present challenges in clinical development.

此處的圖表將 '565 直接與來自不同團體的已發布和獲得專利的 MALT1 支架進行了比較。 '565 在所有參數上的比較都非常有利，檢查重要性、細胞活性和藥物樣特性。 '565 在 UGT1A1 上的活動很少，並且在這方面高度分化。我們預測許多其他化合物可能會在一定程度上抑制 UGT1A1，從而對臨床開發提出挑戰。

It's important to note, in designing this compound, it was the first time that we merged molecular dynamics with AI at Exscientia. Molecular dynamics, a physics-based method, is just one of the tools that we have in our tech stack today. In fact, molecular dynamic simulations provided additional insights into critical binding interactions within the allosteric site.

值得注意的是，在設計這種化合物時，這是我們第一次在 Exscientia 將分子動力學與人工智能相結合。分子動力學是一種基於物理學的方法，它只是我們當今技術堆棧中擁有的工具之一。事實上，分子動力學模擬為變構位點內的關鍵結合相互作用提供了額外的見解。

Using Hotspot analysis allowed us to understand the allosteric binding pocket, highlighting key interactions needed for design. Molecular dynamics then enabled us to understand the dynamic motion of the binding pocket and developed a design strategy to improve potency and broader properties of our compounds.

使用熱點分析使我們能夠了解變構結合口袋，突出設計所需的關鍵交互。然後，分子動力學使我們能夠了解結合口袋的動態運動，並製定了一種設計策略來提高化合物的效力和更廣泛的特性。

Using data and knowledge of other allosteric MALT1 inhibitors, our generative design algorithm, Gambit, was used to evolve novel molecules. This resulted in a suite of promising compounds. We believe that '565 can be developed to meet a significant medical need that exists today, through potent and selective MALT1 protease inhibition, with the potential for a meaningful safety differentiation.

利用其他變構 MALT1 抑製劑的數據和知識，我們的生成設計算法 Gambit 用於進化新分子。這導致了一系列有前途的化合物。我們相信，通過有效和選擇性的 MALT1 蛋白酶抑制，可以開發出 '565 來滿足當今存在的重要醫療需求，並有可能實現有意義的安全差異化。

In summary, these compounds demonstrate the potential of the Exscientia platform to efficiently deliver precision design compounds that may provide substantial benefit to patients. Better design, we believe, improves the probability of success of reaching patients.

總之，這些化合物展示了 Exscientia 平台有效提供精密設計化合物的潛力，這些化合物可能為患者帶來實質性益處。我們相信，更好的設計可以提高成功接觸患者的可能性。

And while the average industry time line to discover a development candidate takes around 4.5 years, and synthesizing between 2,500 to 5,000 compounds, it is remarkable that these two candidates were designed in 15 to 20 months, respectively. And from synthesizing, 344 and 414 precision design compounds. These stats underscore how our AI-driven approach is not only differentiated in terms of precision design, but also faster and more efficient than conventional methods.

雖然發現開發候選化合物的平均行業時間線大約需要 4.5 年，合成 2,500 到 5,000 種化合物，但值得注意的是，這兩個候選化合物的設計時間分別為 15 到 20 個月。並從合成、344 和 414 精密設計化合物。這些統計數據強調了我們的 AI 驅動方法不僅在精密設計方面與眾不同，而且比傳統方法更快、更高效。

IND-enabling studies are underway for both these inhibitors, and we expect to provide an update on clinical development plans leveraging Exscientia's personalized medicine platform in the second half of 2023. These compounds have potential broad application in oncology and hematology.

這兩種抑製劑的 IND 支持研究正在進行中，我們預計將在 2023 年下半年利用 Exscientia 的個性化醫療平台提供最新的臨床開發計劃。這些化合物在腫瘤學和血液學中具有潛在的廣泛應用。

Overall, we are thrilled with our recent advancements and look forward to sharing more details on our progress.

總的來說，我們對我們最近的進展感到興奮，並期待分享更多關於我們進展的細節。

I'll hand over now to Ben to walk through our financials.

我現在將移交給本，讓他了解我們的財務狀況。

Thanks, Andrew. I'll now take a minute to close with highlights from our financial results. Full results are detailed in our press release in 20-F. I'll review the results in U.S. dollars using the December 31, 2022, constant currency rate of $1.2077 to the pound.

謝謝，安德魯。我現在花一點時間來結束我們財務業績的亮點。我們在 20-F 的新聞稿中詳細介紹了完整的結果。我將使用 2022 年 12 月 31 日 1.2077 美元兌英鎊的固定匯率以美元計算結果。

We ended the year with $611 million in cash, equivalents and bank deposits. We believe this provides us with several years of cash runway and the resources to continue investing in our growth. At the same time, we believe that the recent macroeconomic factors, including bank defaults, political trends and large pharma announcements will cause 2023 to be a year of economic conservatism in the biopharma industry. As a side note, Exscientia does not have any banking exposure to SVB or Credit Suisse.

年底，我們擁有 6.11 億美元的現金、等價物和銀行存款。我們相信這為我們提供了數年的現金跑道和繼續投資於我們增長的資源。同時，我們認為近期的宏觀經濟因素，包括銀行違約、政治趨勢和大型製藥公司公告，將導致 2023 年成為生物製藥行業經濟保守的一年。附帶說明一下，Exscientia 對 SVB 或瑞士信貸沒有任何銀行風險。

From a business model perspective, we are well positioned to respond to the current market environment. We have now repeatedly demonstrated that we can achieve better drug discovery outcomes faster and with less cost than traditional methods.

從商業模式的角度來看，我們有能力應對當前的市場環境。我們現在已經反复證明，與傳統方法相比，我們可以更快、成本更低地實現更好的藥物發現結果。

In order for the pharmaceutical industry to improve ROI in the face of growing price and competitive pressures, it needs the quality and efficiency that we bring. We also believe that our personalized medicine platform will help improve the probability of success in the clinic, which, in turn, will further improve return on investment.

為了讓製藥行業在面對不斷增長的價格和競爭壓力的情況下提高投資回報率，它需要我們帶來的質量和效率。我們還相信，我們的個性化醫療平台將有助於提高臨床成功的可能性，進而進一步提高投資回報率。

At Exscientia, our partners continue to invest substantial resources in our projects. Our existing partnerships alone could contribute several hundred million in milestones over the next 3 years. We expect a number of earlier milestones during 2023, with the majority of the milestones occurring in 2024 and 2025 as we achieve development candidate goals.

在 Exscientia，我們的合作夥伴繼續在我們的項目中投入大量資源。僅我們現有的合作夥伴關係就可以在未來 3 年內貢獻數億美元的里程碑。我們預計 2023 年會出現一些早期的里程碑，其中大部分里程碑發生在 2024 年和 2025 年，因為我們實現了發展候選目標。

We are also seeing an active interest in new business development and are reiterating our guidance of at least two deals this year. We have seen a focus on innovative technologies and specific pipeline candidates from potential pharma partners, and as a result, we have begun to adjust some of our operations to focus on areas that we believe will have the highest near-term impact and return.

我們也看到了對新業務發展的積極興趣，並重申了我們對今年至少兩筆交易的指導。我們已經看到潛在製藥合作夥伴對創新技術和特定管道候選人的關注，因此，我們已經開始調整我們的一些業務，以專注於我們認為近期影響和回報最高的領域。

In addition, we believe it is important to respond to the macroeconomic environment by keeping our own operations as efficient as possible. Over the last 6 months, we have reduced costs with several of our CRO relationships and believe there is additional room for improvement without a loss of quality.

此外，我們認為通過盡可能保持自身運營效率來應對宏觀經濟環境非常重要。在過去的 6 個月裡，我們已經降低了與我們的幾個 CRO 關係的成本，並且相信在不損失質量的情況下還有更多的改進空間。

In addition, we are evaluating multiple ways to apply technology or streamline our internal operations in order to drive greater efficiency. We estimate the combination of these efforts will save tens of millions of dollars in operating costs over the course of 2023.

此外，我們正在評估多種應用技術或簡化內部運營的方法，以提高效率。我們估計這些努力的結合將在 2023 年期間節省數千萬美元的運營成本。

I also wanted to be clear that our guidance of several years cash runway allows us to take all four of our disclosed later-stage internal programs, including A2a, CDK7, LSD1 and MALT1, through initial proof-of-concept clinical trials, if and when the clinical evidence and strategic business rationale support that decision.

我還想明確指出，我們對幾年現金跑道的指導使我們能夠通過初步的概念驗證臨床試驗，採用我們披露的所有四個後期內部項目，包括 A2a、CDK7、LSD1 和 MALT1，如果和當臨床證據和戰略商業理由支持該決定時。

With that, I will turn the call back over to Andrew.

有了這個，我會把電話轉回給安德魯。

Thank you, Ben. Today, we'll walk you through several examples of how we are working to produce better drugs faster by innovating in both discovery and in development. We believe that our differentiated approach and our advancements this year further validates our end-to-end platform and distinguish our company as leaders in the field of AI-based drug discovery. As you can see, we have another important year ahead to best position us for the future.

謝謝你，本。今天，我們將通過幾個例子向您介紹我們如何通過發現和開發方面的創新來更快地生產更好的藥物。我們相信，我們今年的差異化方法和進步進一步驗證了我們的端到端平台，並使我們公司成為基於 AI 的藥物發現領域的領導者。如您所見，我們還有重要的一年來為未來做好準備。

With that, we'll open up the call for questions and answers.

有了這個，我們將打開問題和答案的電話。

(Operator Instructions) The first question is from Vikram Purohit with Morgan Stanley.

（操作員說明）第一個問題來自摩根士丹利的 Vikram Purohit。

Two from our side. First, for '539 and '565. Your slides mentioned that the molecules were developed in I believe, 15 to 20 months versus a much longer industry average development time line. And I was wondering if you could just walk us through which components of early stage development you believe your platform helped to cut time lines for the most?

我們這邊的兩個。首先，對於 '539 和 '565。你的幻燈片提到，我相信這些分子是在 15 到 20 個月內開發的，而行業平均開發時間線要長得多。我想知道您是否可以向我們介紹您認為您的平台最有助於縮短時間線的早期開發的哪些組成部分？

And then secondly, on the topic of partnerships and business development. I mean going forward, what would you be looking for in your next set of partnerships? What kind of capabilities would be most additive to seek out?

其次，關於合作夥伴關係和業務發展的話題。我的意思是，展望未來，您會在下一組合作夥伴關係中尋找什麼？什麼樣的能力最適合尋找？

And conversely, what also do you think you could be bringing your partners with the next set of partnerships that you weren't able to with the earlier set of partnerships?

反過來，您認為您還可以通過下一組合作夥伴關係為您的合作夥伴帶來什麼，而您在早期的一組合作夥伴關係中無法做到這一點？

Vikram good to speak to you again. This is Andrew. Vikram, actually for that first question, I want to introduce Garry Pairaudeau, CTO, actually, because I think Garry's unique background of being a drug hunter and a technologist actually will highlight and understand where actually Exscientia's platform really brings value to the drug discovery and design process.

Vikram 很高興再次與您交談。這是安德魯。 Vikram，實際上對於第一個問題，我想介紹首席技術官 Garry Pairaudeau，實際上，因為我認為 Garry 作為藥物獵人和技術專家的獨特背景實際上將突出並理解 Exscientia 平台真正為藥物發現帶來價值的地方和設計過程。

Sure. Thanks, Andrew, and thanks, Vikram. So the time lines we put out the time from starting the project with a hit molecule to identifying the candidate molecule, so that's the molecule we would take forward into development.

當然。謝謝，安德魯，謝謝，維克拉姆。因此，我們制定了從使用命中分子開始項目到確定候選分子的時間線，這就是我們將推進開發的分子。

Typically, industry average times are around about 4 years for that period. The reason why our platform is so much more effective is because we're harnessing the full power of using artificial intelligence, using multiparameter optimization and using generative design to explore chemical space much more widely.

通常，該時期的行業平均時間約為 4 年。我們的平台之所以如此有效，是因為我們正在充分利用人工智能、使用多參數優化和使用生成式設計來更廣泛地探索化學空間。

What that means in a nutshell is every optimization cycle, we're exploring more possibilities and we're effectively taking larger jumps at each step, which is what's allowing us to cut the time down so dramatically. And we've seen this across all of our programs.

簡而言之，這意味著每個優化週期，我們正在探索更多的可能性，並且我們在每一步都有效地進行了更大的跳躍，這使我們能夠如此顯著地縮短時間。我們在所有項目中都看到了這一點。

Excellent. Thanks, Garry. And Dave, do you want to add a bit more about a broader set of capabilities we have now?

出色的。謝謝，加里。戴夫，你想補充一點關於我們現在擁有的更廣泛的能力嗎？

Yes. Thank you, Andrew. I think it's important to realize that Exscientia operates at that interface between kind of experiment and artificial intelligence. And I think it's the components of each that when they're brought together that actually make a significant kind of contribution to above time line.

是的。謝謝你，安德魯。我認為重要的是要認識到 Exscientia 在實驗和人工智能之間的接口上運行。而且我認為，當它們組合在一起時，每個組件實際上對上述時間線做出了重大貢獻。

So we -- it's very much in our interest to actually generate high-quality data that can actually be then utilized in the machine learning kind of environment. And so that explains why we've created and continue to grow our experimental footprint. But it is ultimately kind of placing experts with the right tools they need and with the right technology, and that's kind of why you see the acceleration of the time lines.

所以我們 - 實際生成高質量的數據非常符合我們的興趣，這些數據實際上可以在機器學習類型的環境中使用。因此，這就解釋了為什麼我們已經創建並繼續擴大我們的實驗足跡。但它最終是為專家提供他們需要的正確工具和正確的技術，這就是你看到時間線加速的原因。

Vikram, I'll take your second part of the question as well around partnerships. I think what's exciting about Exscientia development, particularly over the past couple of years, is how our end-to-end platform has really expanded. We've gone upstream, thinking about now how we think about target selection, particularly incorporating patient tissue, patient [drovive] approaches in target selection and combine that then with data science approaches and deep learning approaches that really think about how to integrate the wealth of external knowledge into these experiments.

維克拉姆，我將圍繞夥伴關係回答問題的第二部分。我認為 Exscientia 的發展令人興奮，尤其是在過去幾年，我們的端到端平台是如何真正擴展的。我們已經逆流而上，現在思考我們如何考慮目標選擇，特別是將患者組織、患者 [驅動] 方法納入目標選擇，然後將其與真正考慮如何整合財富的數據科學方法和深度學習方法相結合外部知識融入這些實驗。

And going all the way downstream now to thinking about how we design precision medicine biomarkers for patient selection using a whole range of machine and approaches to multimodal-omics, you can see that with the Denise burden score and the work we do in our CDK7 and expect to see more of that coming forward each year.

現在一直向下游走，思考我們如何使用一整套機器和多模式組學方法為患者選擇設計精準醫學生物標誌物，你可以看到 Denise 負擔評分和我們在 CDK7 和期望每年都能看到更多這樣的事情發生。

We're starting to see now of actually the hallmark of Exscientia is one way we combine both precision design with personalized medicine going forward. It's not just a process of how we design the drug, but also how we think about embodying that kind of technology into the kind of labels we're also thinking about.

我們現在開始看到 Exscientia 的標誌實際上是我們將精密設計與未來的個性化醫學相結合的一種方式。這不僅僅是我們如何設計藥物的過程，還有我們如何考慮將這種技術體現到我們也在考慮的標籤中。

But that means saying we now have a much broader offering. And I think actually, as we think about the developments and advances now, we're thinking about in clinical development and precision medicine, I think we're in a very strong position actually to offer a broad range of solutions to the pharmaceutical industry who are themselves face a number of challenges right now.

但這意味著我們現在有更廣泛的產品。我認為實際上，當我們考慮現在的發展和進步時，我們正在考慮臨床開發和精準醫學，我認為我們實際上處於非常有利的地位，可以為製藥行業提供廣泛的解決方案他們自己現在面臨著許多挑戰。

So we are very excited right now, with a lot of discussions we have in which regard how we think about applying precision medicine with partners, how we think about applying actually the model-informed model-driven adaptive learning processes that actually we've also created in discovery, how they also now apply in development in the design of our trials. So we're really excited actually.

因此，我們現在非常興奮，我們進行了很多討論，討論了我們如何考慮與合作夥伴一起應用精準醫學，我們如何考慮實際應用模型通知模型驅動的自適應學習過程，實際上我們也已經在發現中創造，它們現在如何應用於我們試驗設計的開發中。所以我們真的很興奮。

As Exscientia grows, I think we're in a very strong position actually to continue to develop and strengthen the offering of solutions we can bring to our pharma partners.

隨著 Exscientia 的發展，我認為我們實際上處於非常有利的地位，可以繼續開發和加強我們可以為我們的製藥合作夥伴提供的解決方案。

The next question is from Michael Ryskin with Bank of America.

下一個問題來自美國銀行的 Michael Ryskin。

This is Wolf on for Mike. So starting off the announcement of '539 and '565 are obviously quite exciting. Just wondering how to think about the incremental spend associated with these and other IND-enabling programs given the continued refinement and scale of your platform, and kind of building off of Vikram's question.

這是邁克的沃爾夫。所以開始宣布'539 和'565 顯然是相當令人興奮的。只是想知道如何考慮與這些和其他 IND 支持計劃相關的增量支出，考慮到您平台的持續改進和規模，以及某種程度上建立 Vikram 的問題。

And then as a follow-up, how are you thinking about your current capacity for parallel IND-enabling studies? What do you see as the primary limiting factor to the number of studies that you can have ongoing, once is it just a headcount thing or there technical issues as well?

然後作為後續行動，您如何看待您目前進行平行 IND 支持研究的能力？您認為可以進行的研究數量的主要限制因素是什麼，是人數問題還是技術問題？

Excellent. Good to speak to you again, Wolf. I'm going to introduce Ben Taylor actually to answer this question.

出色的。很高興再次和你說話，Wolf。我要介紹 Ben Taylor 實際上是為了回答這個問題。

Wolf, Nice to talk to you again. So a couple of things on just thinking about our budget and going ahead and operating expenses. So as we think about 2022 versus 2023, 2022 was really the year of scaling and putting a lot of the infrastructure in place that we would need to be able to execute on a broader pipeline, both in the discovery phase as well as in development.

狼，很高興再次與你交談。所以有幾件事只是考慮我們的預算，繼續進行和運營費用。因此，當我們考慮 2022 年與 2023 年時，2022 年實際上是擴展和部署大量基礎設施的一年，我們需要能夠在更廣泛的管道上執行這些基礎設施，無論是在發現階段還是在開發階段。

So when we look ahead at 2023, even though we are initiating a number of clinical trials, we actually don't see that scaling of cost continuing and would expect 2023 to be much more level with what we saw in the fourth quarter.

因此，當我們展望 2023 年時，儘管我們正在啟動一些臨床試驗，但我們實際上並沒有看到成本的持續增長，並且預計 2023 年將與我們在第四季度看到的情況持平。

So I think we've actually achieved a lot of that scale and infrastructure to be able to execute. And I think that goes into your question of how we can handle clinical programs moving forward. The actual additional expense internally that we would need to do that is not substantial.

所以我認為我們實際上已經實現了很多能夠執行的規模和基礎設施。我認為這涉及到您關於我們如何處理向前推進的臨床項目的問題。我們需要這樣做的內部實際額外費用並不大。

I think what we would look at is as those programs continue to get into later-stage development, that's where you really see the scaling in the expense. And so I think both on the discovery and the development side, we're at a pretty good place right now.

我認為我們會看到的是，隨著這些程序繼續進入後期開發階段，這才是你真正看到費用增加的地方。因此，我認為無論是在發現方面還是在開發方面，我們現在都處於一個非常好的位置。

I also mentioned we are finding a number of good efficiencies with our CRO relationships. That's been a real change for us as well because we're now of a scale in doing enough projects where we can actually get economies of scale out of our CRO relationships. We can push that pricing dialogue without losing quality. And so that's something that has been very powerful for us recently, and I think you'll see that impact in 2023.

我還提到我們正在通過我們的 CRO 關係找到許多良好的效率。這對我們來說也是一個真正的變化，因為我們現在已經有足夠的規模來做足夠多的項目，我們實際上可以從我們的 CRO 關係中獲得規模經濟。我們可以在不降低質量的情況下推動定價對話。所以這是最近對我們非常強大的事情，我認為你會在 2023 年看到這種影響。

The next question is from Peter Lawson with Barclays.

下一個問題來自巴克萊銀行的彼得勞森。

I guess a question for Ben, just on the back of your comment about the potential area of conservativeness around pharma. And just how does that help or hinder collaborations? Kind of what's your analysis around that?

我想問 Ben 一個問題，就在你對圍繞製藥業的潛在保守領域的評論之後。這究竟是如何幫助或阻礙合作的？你對此有何分析？

Yes. So to be clear, we still see a lot of interest out of pharma partners. I think what we've seen is a bit of change in the focus of the pharma partners. So back in 2020, a lot of the dialogue was around, how can I scale my pipeline? How can I do the really large pipeline deals?

是的。所以需要明確的是，我們仍然看到製藥合作夥伴有很多興趣。我認為我們看到的是製藥合作夥伴的關注點發生了一些變化。所以回到 2020 年，很多對話都圍繞著我如何擴展我的管道？我怎樣才能做真正的大型管道交易？

I think what we're seeing in this sort of environment is a real focus on specific technologies and specific identified programs. So from our perspective, we can actually handle either. And in fact, sometimes these specific partnerships can be more profitable for us than the broad pipeline deals because there's less infrastructure required to execute on them.

我認為我們在這種環境中看到的是對特定技術和特定程序的真正關注。所以從我們的角度來看，我們實際上可以處理任何一個。事實上，有時這些特定的合作夥伴關係對我們來說比廣泛的管道交易更有利可圖，因為執行它們所需的基礎設施更少。

I think also we are in a different position than we were two years ago because we've advanced a number of programs and technologies and platforms that we didn't have then. And we've seen a lot of the pharma partners have interest in those later-stage programs as well.

我認為我們現在的處境也與兩年前不同，因為我們已經推進了許多當時沒有的程序、技術和平台。我們已經看到很多製藥合作夥伴也對這些後期項目感興趣。

So I think with this economically conservative environment, the fact that we're still seeing a lot of interest out of pharma partners. And hopefully, this is an economic cycle. So if we're seeing this level of interest right now, we feel pretty good if the economic cycle improved.

所以我認為在這種經濟保守的環境下，我們仍然看到製藥合作夥伴有很多興趣。希望這是一個經濟周期。因此，如果我們現在看到這種程度的興趣，如果經濟周期有所改善，我們會感覺很好。

Got you. And then just a question on timing for the data. I know both of your adenosine and CDK7 patients kind of in trials enrolled the first patients in the first half. Just your expectations for timing around those data sets?

明白了然後只是關於數據時間的問題。我知道你的腺苷和 CDK7 患者都在試驗中招募了上半年的第一批患者。只是您對圍繞這些數據集進行計時的期望？

Thanks, Peter. First I'm going to introduce Mike Krams, who leads our development efforts. Mike?

謝謝，彼得。首先，我要介紹領導我們開發工作的 Mike Krams。麥克風？

Thank you for the question. First of all, we are using model-informed drug development, simulation guided clinical trial design and experiments where we accrue in real-time all the data and look at the data at all times. However, the time at which we will actually announce major findings, but probably coincide with the movement from the dose escalation phase to the dose expansion phase in the Phase I/II trials.

感謝你的提問。首先，我們正在使用基於模型的藥物開發、模擬指導的臨床試驗設計和實驗，我們實時收集所有數據並隨時查看數據。然而，我們實際宣布主要發現的時間可能與 I/II 期試驗從劑量遞增階段到劑量擴展階段的移動相吻合。

We haven't given guidance as to the exact timing of that. However, it will be similar to any of the Phase I/II trials. That's running in this field. But importantly, the trials that we're running are based on model-informed approaches where we accrue and analyze the data at all times.

我們還沒有給出具體時間的指導。但是，它將類似於任何 I/II 期試驗。那就是在這個領域運行。但重要的是，我們正在進行的試驗基於模型通知方法，我們始終在其中收集和分析數據。

Got you. And is -- could we expect data in second half? Or is that too tighter time line?

明白了而且是 - 我們可以期待下半年的數據嗎？還是時間線太緊了？

We haven't given guidance on the exact timing. But I would think that the second half of '23 is particularly early given that the first patients will come in the first half. You can just go through the time.

我們還沒有給出具體時間的指導。但我認為 23 年下半年特別早，因為第一批患者將在上半年到來。你可以穿越時間。

(Operator Instructions) The next question is from Chris Shibutani with Goldman Sachs.

（操作員說明）下一個問題來自高盛的 Chris Shibutani。

This is Roger on for Chris. So you noted that you plan on moving towards antibiotics as the company pivots towards using action learning techniques to develop on biologics. Just wanted to kind of understand since that's such an area that's challenging from both development and economics. What are the variables that make you believe this kind of investment going forward is worthwhile? Is it the plethora of data that kind of feeds into the closed loop of model? Lower competitive dynamics? Just kind of want to understand the rationale there.

這是克里斯的羅傑。因此，您指出，隨著公司轉向使用行動學習技術開發生物製劑，您計劃轉向抗生素。只是想了解一下，因為這是一個對發展和經濟都具有挑戰性的領域。是什麼變量讓您相信這種投資在未來是值得的？是不是大量的數據進入了模型的閉環？較低的競爭動力？只是有點想了解那裡的基本原理。

And we have a relatively small effort in antivirals and pandemic preparedness. We have no plans at all to move into antibiotics as a field right now. We have a great collaboration in antivirals with the Gates Foundation. That right now is focused on small molecules, and we move forward. That's led by Professor Ian Goodfellow of the University of Cambridge.

我們在抗病毒藥物和大流行病防範方面的努力相對較小。我們現在根本沒有進入抗生素領域的計劃。我們與蓋茨基金會在抗病毒藥物方面有很好的合作。現在專注於小分子，我們繼續前進。這是由劍橋大學的 Ian Goodfellow 教授領導的。

But an important [Alvi] bought up actually is Exscientia's development of a biologics platform. We are, as we announced last year, developing e-biologics design engine. That currently, we are testing a proof of concept as we speak. We're also building out a new automated biologics lab actually to really speed up sort of a make and test cycle or generation of data.

但實際上收購的一個重要 [Alvi] 是 Exscientia 開發的生物製劑平台。正如我們去年宣布的那樣，我們正在開發電子生物設計引擎。目前，我們正在測試概念驗證。我們還在建設一個新的自動化生物實驗室，實際上是為了真正加快某種製造和測試週期或數據的生成。

So one of the key areas that we see here actually is the ability actually to generate high-quality data to drive machine learning models. And I'll give you an example of that. We currently have a collaboration with Oxford University, where we're looking to generate a lot of paired sequence data. We believe actually we can create some of the large databases in the world and understanding the observable human antibody space.

因此，我們在這裡看到的關鍵領域之一實際上是能夠實際生成高質量數據來驅動機器學習模型。我會給你舉個例子。我們目前與牛津大學合作，我們正在尋求生成大量配對序列數據。我們相信實際上我們可以創建世界上的一些大型數據庫並了解可觀察到的人類抗體空間。

And that actually can give us sort of the priors and defined in our models. So when evolving and designing molecules and by AI, we can then design into where human antibody space actually is. We're incredibly excited by that actually. It's led by Professor Charlotte Deane, who works here at Exscientia, also holds a Chair in Oxford University.

這實際上可以給我們一些先驗知識並在我們的模型中定義。因此，在通過人工智能進化和設計分子時，我們可以設計到人類抗體空間的實際位置。實際上，我們對此感到非常興奮。它由在 Exscientia 工作的夏洛特·迪恩教授領導，他還在牛津大學擔任教席。

And later this year, we look forward to bringing to you sort of more news and information about how our biologics platform is developing. But importantly, I think we have a key advantage here as well. We've already shown that our patient-centric precision medicine platform works equally well for antibodies as it does with small molecules. So we there can also think about downstream, how we can start to think about applying precision medicine also to biologics and bringing of those two fields together. And I think that's going to be a unique set of attributes actually in that field.

今年晚些時候，我們期待為您帶來更多關於我們的生物製劑平台如何發展的新聞和信息。但重要的是，我認為我們在這方面也有關鍵優勢。我們已經證明，我們以患者為中心的精準醫學平台對抗體和小分子同樣有效。所以我們也可以考慮下游，我們如何開始考慮將精準醫學也應用於生物製品並將這兩個領域結合在一起。我認為這將成為該領域中的一組獨特屬性。

There are no further questions at this time. I'll turn it over to Andrew Hopkins for any closing remarks.

目前沒有其他問題。我將把它交給安德魯霍普金斯做任何結束語。

Thank you, operator, and thank you to everyone for the call today and for your continued support of Exscientia.

謝謝接線員，也感謝大家今天的來電和對 Exscientia 的持續支持。

Over coming months and into 2024, we look forward to advancing multiple programs going forward, bringing new molecules into the clinic, unveiling incredibly important new projects and programs and building up our clinical development innovations to bring truly personalized medicine to patients.

在未來幾個月和 2024 年，我們期待推進多個項目向前發展，將新分子帶入臨床，推出非常重要的新項目和項目，並建立我們的臨床開發創新，為患者帶來真正個性化的醫療。

I want to thank you again for joining us today, and have a good day. Thank you, all.

我想再次感謝你今天加入我們，祝你有美好的一天。謝謝你們。

Ladies and gentlemen, this concludes today's conference call. Thank you for participating. You may now disconnect.

女士們，先生們，今天的電話會議到此結束。感謝您的參與。您現在可以斷開連接。